From 25559c22cef879c5cf7119540bfe21fb379d29f3 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 9 Jul 2018 08:15:49 +0200 Subject: tee: add kernel internal client interface Adds a kernel internal TEE client interface to be used by other drivers. Reviewed-by: Sumit Garg Tested-by: Sumit Garg Tested-by: Zeng Tao Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a2b3dfcee0b5..6cfe05893a76 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -453,6 +453,79 @@ static inline int tee_shm_get_id(struct tee_shm *shm) */ struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); +/** + * tee_client_open_context() - Open a TEE context + * @start: if not NULL, continue search after this context + * @match: function to check TEE device + * @data: data for match function + * @vers: if not NULL, version data of TEE device of the context returned + * + * This function does an operation similar to open("/dev/teeX") in user space. + * A returned context must be released with tee_client_close_context(). + * + * Returns a TEE context of the first TEE device matched by the match() + * callback or an ERR_PTR. + */ +struct tee_context * +tee_client_open_context(struct tee_context *start, + int (*match)(struct tee_ioctl_version_data *, + const void *), + const void *data, struct tee_ioctl_version_data *vers); + +/** + * tee_client_close_context() - Close a TEE context + * @ctx: TEE context to close + * + * Note that all sessions previously opened with this context will be + * closed when this function is called. + */ +void tee_client_close_context(struct tee_context *ctx); + +/** + * tee_client_get_version() - Query version of TEE + * @ctx: TEE context to TEE to query + * @vers: Pointer to version data + */ +void tee_client_get_version(struct tee_context *ctx, + struct tee_ioctl_version_data *vers); + +/** + * tee_client_open_session() - Open a session to a Trusted Application + * @ctx: TEE context + * @arg: Open session arguments, see description of + * struct tee_ioctl_open_session_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. If @arg->ret + * is TEEC_SUCCESS the session identifier is available in @arg->session. + */ +int tee_client_open_session(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + +/** + * tee_client_close_session() - Close a session to a Trusted Application + * @ctx: TEE Context + * @session: Session id + * + * Return < 0 on error else 0, regardless the session will not be + * valid after this function has returned. + */ +int tee_client_close_session(struct tee_context *ctx, u32 session); + +/** + * tee_client_invoke_func() - Invoke a function in a Trusted Application + * @ctx: TEE Context + * @arg: Invoke arguments, see description of + * struct tee_ioctl_invoke_arg + * @param: Parameters passed to the Trusted Application + * + * Returns < 0 on error else see @arg->ret for result. + */ +int tee_client_invoke_func(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + static inline bool tee_param_is_memref(struct tee_param *param) { switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { -- cgit v1.2.3-71-gd317 From 1e6cb72399fd58b38a1c11055ef18fe01f535cda Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sat, 1 Sep 2018 10:41:11 +0300 Subject: fsnotify: add super block object type Add the infrastructure to attach a mark to a super_block struct and detach all attached marks when super block is destroyed. This is going to be used by fanotify backend to setup super block marks. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fdinfo.c | 5 +++++ fs/notify/fsnotify.c | 8 +++++++- fs/notify/fsnotify.h | 11 +++++++++++ fs/notify/mark.c | 4 ++++ fs/super.c | 2 +- include/linux/fs.h | 5 +++++ include/linux/fsnotify_backend.h | 17 ++++++++++++++--- 7 files changed, 47 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 86fcf5814279..25385e336ac7 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -131,6 +131,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n", mnt->mnt_id, mflags, mark->mask, mark->ignored_mask); + } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_SB) { + struct super_block *sb = fsnotify_conn_sb(mark->connector); + + seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n", + sb->s_dev, mflags, mark->mask, mark->ignored_mask); } } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index ababdbfab537..2971803d151c 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -48,7 +48,7 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt) * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ -void fsnotify_unmount_inodes(struct super_block *sb) +static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; @@ -98,6 +98,12 @@ void fsnotify_unmount_inodes(struct super_block *sb) iput(iput_inode); } +void fsnotify_sb_delete(struct super_block *sb) +{ + fsnotify_unmount_inodes(sb); + fsnotify_clear_marks_by_sb(sb); +} + /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index 7902653dd577..5a00121fb219 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -21,6 +21,12 @@ static inline struct mount *fsnotify_conn_mount( return container_of(conn->obj, struct mount, mnt_fsnotify_marks); } +static inline struct super_block *fsnotify_conn_sb( + struct fsnotify_mark_connector *conn) +{ + return container_of(conn->obj, struct super_block, s_fsnotify_marks); +} + /* destroy all events sitting in this groups notification queue */ extern void fsnotify_flush_notify(struct fsnotify_group *group); @@ -43,6 +49,11 @@ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks); } +/* run the list of all marks associated with sb and destroy them */ +static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) +{ + fsnotify_destroy_marks(&sb->s_fsnotify_marks); +} /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 59cdb27826de..b5172ccb2e60 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -115,6 +115,8 @@ static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; + else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) + return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } @@ -192,6 +194,8 @@ static struct inode *fsnotify_detach_connector_from_object( inode->i_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; + } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { + fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } rcu_assign_pointer(*(conn->obj), NULL); diff --git a/fs/super.c b/fs/super.c index f3a8c008e164..ca53a08497ed 100644 --- a/fs/super.c +++ b/fs/super.c @@ -442,7 +442,7 @@ void generic_shutdown_super(struct super_block *sb) sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; - fsnotify_unmount_inodes(sb); + fsnotify_sb_delete(sb); cgroup_writeback_umount(); evict_inodes(sb); diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..2c14801d0aa3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1464,6 +1464,11 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ + +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b8f4182f42f1..81b88fc9df31 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -206,12 +206,14 @@ struct fsnotify_group { enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, + FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; #define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) #define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) +#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) #define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) static inline bool fsnotify_valid_obj_type(unsigned int type) @@ -255,6 +257,7 @@ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) +FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_obj_type(type) \ for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) @@ -267,8 +270,8 @@ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* - * Inode / vfsmount point to this structure which tracks all marks attached to - * the inode / vfsmount. The reference to inode / vfsmount is held by this + * Inode/vfsmount/sb point to this structure which tracks all marks attached to + * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ @@ -335,6 +338,7 @@ extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int dat extern int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); +extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline int fsnotify_inode_watches_children(struct inode *inode) @@ -455,9 +459,13 @@ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *gr { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); } +/* run all the marks in a group, and clear all of the sn marks */ +static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) +{ + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); +} extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -extern void fsnotify_unmount_inodes(struct super_block *sb); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); @@ -484,6 +492,9 @@ static inline void __fsnotify_inode_delete(struct inode *inode) static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} +static inline void fsnotify_sb_delete(struct super_block *sb) +{} + static inline void fsnotify_update_flags(struct dentry *dentry) {} -- cgit v1.2.3-71-gd317 From 4d18975c78f2d5c91792356501cf369e67594241 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Sat, 1 Sep 2018 16:08:45 +0200 Subject: fbdev: add remove_conflicting_pci_framebuffers() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Almost all PCI drivers using remove_conflicting_framebuffers() wrap it with the same code. v2: add kerneldoc for DRM helper v3: propagate remove_conflicting_framebuffers() return value + move kerneldoc to where function is implemented Signed-off-by: Michał Mirosław Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/7db1c278276de420eb45a1b71d06b5eb6bbd49ef.1535810304.git.mirq-linux@rere.qmqm.pl --- drivers/video/fbdev/core/fbmem.c | 35 +++++++++++++++++++++++++++++++++++ include/drm/drm_fb_helper.h | 12 ++++++++++++ include/linux/fb.h | 2 ++ 3 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 6e9961b71442..5ffadc8e681d 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -34,6 +34,7 @@ #include #include #include +#include #include @@ -1830,6 +1831,40 @@ int remove_conflicting_framebuffers(struct apertures_struct *a, } EXPORT_SYMBOL(remove_conflicting_framebuffers); +/** + * remove_conflicting_pci_framebuffers - remove firmware-configured framebuffers for PCI devices + * @pdev: PCI device + * @resource_id: index of PCI BAR configuring framebuffer memory + * @name: requesting driver name + * + * This function removes framebuffer devices (eg. initialized by firmware) + * using memory range configured for @pdev's BAR @resource_id. + * + * The function assumes that PCI device with shadowed ROM drives a primary + * display and so kicks out vga16fb. + */ +int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, const char *name) +{ + struct apertures_struct *ap; + bool primary = false; + int err; + + ap = alloc_apertures(1); + if (!ap) + return -ENOMEM; + + ap->ranges[0].base = pci_resource_start(pdev, res_id); + ap->ranges[0].size = pci_resource_len(pdev, res_id); +#ifdef CONFIG_X86 + primary = pdev->resource[PCI_ROM_RESOURCE].flags & + IORESOURCE_ROM_SHADOW; +#endif + err = remove_conflicting_framebuffers(ap, name, primary); + kfree(ap); + return err; +} +EXPORT_SYMBOL(remove_conflicting_pci_framebuffers); + /** * register_framebuffer - registers a frame buffer device * @fb_info: frame buffer info structure diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index 5db08c8f1d25..8b6ab3200a2c 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -615,4 +615,16 @@ drm_fb_helper_remove_conflicting_framebuffers(struct apertures_struct *a, #endif } +static inline int +drm_fb_helper_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, + int resource_id, + const char *name) +{ +#if IS_REACHABLE(CONFIG_FB) + return remove_conflicting_pci_framebuffers(pdev, resource_id, name); +#else + return 0; +#endif +} + #endif diff --git a/include/linux/fb.h b/include/linux/fb.h index 3e7e75383d32..3cd375dafd0e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -632,6 +632,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); extern int unlink_framebuffer(struct fb_info *fb_info); +extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, int res_id, + const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); -- cgit v1.2.3-71-gd317 From afaef01c001537fa97a25092d7f54d764dc7d8c1 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:16:58 +0300 Subject: x86/entry: Add STACKLEAK erasing the kernel stack at the end of syscalls The STACKLEAK feature (initially developed by PaX Team) has the following benefits: 1. Reduces the information that can be revealed through kernel stack leak bugs. The idea of erasing the thread stack at the end of syscalls is similar to CONFIG_PAGE_POISONING and memzero_explicit() in kernel crypto, which all comply with FDP_RIP.2 (Full Residual Information Protection) of the Common Criteria standard. 2. Blocks some uninitialized stack variable attacks (e.g. CVE-2017-17712, CVE-2010-2963). That kind of bugs should be killed by improving C compilers in future, which might take a long time. This commit introduces the code filling the used part of the kernel stack with a poison value before returning to userspace. Full STACKLEAK feature also contains the gcc plugin which comes in a separate commit. The STACKLEAK feature is ported from grsecurity/PaX. More information at: https://grsecurity.net/ https://pax.grsecurity.net/ This code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on our understanding of the code. Changes or omissions from the original code are ours and don't reflect the original grsecurity/PaX code. Performance impact: Hardware: Intel Core i7-4770, 16 GB RAM Test #1: building the Linux kernel on a single core 0.91% slowdown Test #2: hackbench -s 4096 -l 2000 -g 15 -f 25 -P 4.2% slowdown So the STACKLEAK description in Kconfig includes: "The tradeoff is the performance impact: on a single CPU system kernel compilation sees a 1% slowdown, other systems and workloads may vary and you are advised to test this feature on your expected workload before deploying it". Signed-off-by: Alexander Popov Acked-by: Thomas Gleixner Reviewed-by: Dave Hansen Acked-by: Ingo Molnar Signed-off-by: Kees Cook --- Documentation/x86/x86_64/mm.txt | 2 ++ arch/Kconfig | 7 +++++ arch/x86/Kconfig | 1 + arch/x86/entry/calling.h | 14 +++++++++ arch/x86/entry/entry_32.S | 7 +++++ arch/x86/entry/entry_64.S | 3 ++ arch/x86/entry/entry_64_compat.S | 5 ++++ include/linux/sched.h | 4 +++ include/linux/stackleak.h | 26 +++++++++++++++++ kernel/Makefile | 4 +++ kernel/fork.c | 3 ++ kernel/stackleak.c | 62 ++++++++++++++++++++++++++++++++++++++++ scripts/gcc-plugins/Kconfig | 19 ++++++++++++ 13 files changed, 157 insertions(+) create mode 100644 include/linux/stackleak.h create mode 100644 kernel/stackleak.c (limited to 'include/linux') diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 5432a96d31ff..600bc2afa27d 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -24,6 +24,7 @@ ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space [fixmap start] - ffffffffff5fffff kernel-internal fixmap range ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole +STACKLEAK_POISON value in this last hole: ffffffffffff4111 Virtual memory map with 5 level page tables: @@ -50,6 +51,7 @@ ffffffffa0000000 - fffffffffeffffff (1520 MB) module mapping space [fixmap start] - ffffffffff5fffff kernel-internal fixmap range ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole +STACKLEAK_POISON value in this last hole: ffffffffffff4111 Architecture defines a 64-bit virtual address. Implementations can support less. Currently supported are 48- and 57-bit virtual addresses. Bits 63 diff --git a/arch/Kconfig b/arch/Kconfig index 6801123932a5..ee79ff56faab 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -419,6 +419,13 @@ config SECCOMP_FILTER See Documentation/userspace-api/seccomp_filter.rst for details. +config HAVE_ARCH_STACKLEAK + bool + help + An architecture should select this if it has the code which + fills the used part of the kernel stack with the STACKLEAK_POISON + value before returning from system calls. + config HAVE_STACKPROTECTOR bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1a0be022f91d..662cb2cc9630 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -127,6 +127,7 @@ config X86 select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_THREAD_STRUCT_WHITELIST + select HAVE_ARCH_STACKLEAK select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 352e70cd33e8..20d0885b00fb 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -329,8 +329,22 @@ For 32-bit we have the following conventions - kernel is built with #endif +.macro STACKLEAK_ERASE_NOCLOBBER +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + PUSH_AND_CLEAR_REGS + call stackleak_erase + POP_REGS +#endif +.endm + #endif /* CONFIG_X86_64 */ +.macro STACKLEAK_ERASE +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + call stackleak_erase +#endif +.endm + /* * This does 'call enter_from_user_mode' unless we can avoid it based on * kernel config or using the static jump infrastructure. diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 2767c625a52c..dfb975b4c981 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -46,6 +46,8 @@ #include #include +#include "calling.h" + .section .entry.text, "ax" /* @@ -711,6 +713,7 @@ ENTRY(ret_from_fork) /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax call syscall_return_slowpath + STACKLEAK_ERASE jmp restore_all /* kernel thread */ @@ -885,6 +888,8 @@ ENTRY(entry_SYSENTER_32) ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + STACKLEAK_ERASE + /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ @@ -996,6 +1001,8 @@ ENTRY(entry_INT80_32) call do_int80_syscall_32 .Lsyscall_32_done: + STACKLEAK_ERASE + restore_all: TRACE_IRQS_IRET SWITCH_TO_ENTRY_STACK diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 957dfb693ecc..a5dd28093020 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -329,6 +329,8 @@ syscall_return_via_sysret: * We are on the trampoline stack. All regs except RDI are live. * We can do future final exit work right here. */ + STACKLEAK_ERASE_NOCLOBBER + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi popq %rdi @@ -688,6 +690,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) * We are on the trampoline stack. All regs except RDI are live. * We can do future final exit work right here. */ + STACKLEAK_ERASE_NOCLOBBER SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 7d0df78db727..8eaf8952c408 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -261,6 +261,11 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) /* Opportunistic SYSRET */ sysret32_from_system_call: + /* + * We are not going to return to userspace from the trampoline + * stack. So let's erase the thread stack right now. + */ + STACKLEAK_ERASE TRACE_IRQS_ON /* User mode traces as IRQs on. */ movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 977cb57d7bc9..c1a23acd24e7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1192,6 +1192,10 @@ struct task_struct { void *security; #endif +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + unsigned long lowest_stack; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h new file mode 100644 index 000000000000..628c2b947b89 --- /dev/null +++ b/include/linux/stackleak.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_STACKLEAK_H +#define _LINUX_STACKLEAK_H + +#include +#include + +/* + * Check that the poison value points to the unused hole in the + * virtual memory map for your platform. + */ +#define STACKLEAK_POISON -0xBEEF +#define STACKLEAK_SEARCH_DEPTH 128 + +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#include + +static inline void stackleak_task_init(struct task_struct *t) +{ + t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +} +#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ +static inline void stackleak_task_init(struct task_struct *t) { } +#endif + +#endif diff --git a/kernel/Makefile b/kernel/Makefile index 7a63d567fdb5..7343b3a9bff0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -117,6 +117,10 @@ obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o +KASAN_SANITIZE_stackleak.o := n +KCOV_INSTRUMENT_stackleak.o := n + $(obj)/configs.o: $(obj)/config_data.h targets += config_data.gz diff --git a/kernel/fork.c b/kernel/fork.c index d896e9ca38b0..47911e49c2b1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include @@ -1880,6 +1881,8 @@ static __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; + stackleak_task_init(p); + if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { diff --git a/kernel/stackleak.c b/kernel/stackleak.c new file mode 100644 index 000000000000..deba0d8992f9 --- /dev/null +++ b/kernel/stackleak.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code fills the used part of the kernel stack with a poison value + * before returning to userspace. It's part of the STACKLEAK feature + * ported from grsecurity/PaX. + * + * Author: Alexander Popov + * + * STACKLEAK reduces the information which kernel stack leak bugs can + * reveal and blocks some uninitialized stack variable attacks. + */ + +#include + +asmlinkage void stackleak_erase(void) +{ + /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ + unsigned long kstack_ptr = current->lowest_stack; + unsigned long boundary = (unsigned long)end_of_stack(current); + unsigned int poison_count = 0; + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + + /* Check that 'lowest_stack' value is sane */ + if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) + kstack_ptr = boundary; + + /* Search for the poison value in the kernel stack */ + while (kstack_ptr > boundary && poison_count <= depth) { + if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON) + poison_count++; + else + poison_count = 0; + + kstack_ptr -= sizeof(unsigned long); + } + + /* + * One 'long int' at the bottom of the thread stack is reserved and + * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y). + */ + if (kstack_ptr == boundary) + kstack_ptr += sizeof(unsigned long); + + /* + * Now write the poison value to the kernel stack. Start from + * 'kstack_ptr' and move up till the new 'boundary'. We assume that + * the stack pointer doesn't change when we write poison. + */ + if (on_thread_stack()) + boundary = current_stack_pointer; + else + boundary = current_top_of_stack(); + + while (kstack_ptr < boundary) { + *(unsigned long *)kstack_ptr = STACKLEAK_POISON; + kstack_ptr += sizeof(unsigned long); + } + + /* Reset the 'lowest_stack' value for the next syscall */ + current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; +} + diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index cb0c889e13aa..977b84e69787 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -139,4 +139,23 @@ config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE in structures. This reduces the performance hit of RANDSTRUCT at the cost of weakened randomization. +config GCC_PLUGIN_STACKLEAK + bool "Erase the kernel stack before returning from syscalls" + depends on GCC_PLUGINS + depends on HAVE_ARCH_STACKLEAK + help + This option makes the kernel erase the kernel stack before + returning from system calls. That reduces the information which + kernel stack leak bugs can reveal and blocks some uninitialized + stack variable attacks. + + The tradeoff is the performance impact: on a single CPU system kernel + compilation sees a 1% slowdown, other systems and workloads may vary + and you are advised to test this feature on your expected workload + before deploying it. + + This plugin was ported from grsecurity/PaX. More information at: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + endif -- cgit v1.2.3-71-gd317 From c8d126275a5fa59394fe17109bdb9812fed296b8 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:01 +0300 Subject: fs/proc: Show STACKLEAK metrics in the /proc file system Introduce CONFIG_STACKLEAK_METRICS providing STACKLEAK information about tasks via the /proc file system. In particular, /proc//stack_depth shows the maximum kernel stack consumption for the current and previous syscalls. Although this information is not precise, it can be useful for estimating the STACKLEAK performance impact for your workloads. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- fs/proc/base.c | 18 ++++++++++++++++++ include/linux/sched.h | 1 + include/linux/stackleak.h | 3 +++ kernel/stackleak.c | 4 ++++ scripts/gcc-plugins/Kconfig | 12 ++++++++++++ 5 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index ccf86f16d9f0..2a238d68610e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2891,6 +2891,21 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_STACKLEAK_METRICS +static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + unsigned long prev_depth = THREAD_SIZE - + (task->prev_lowest_stack & (THREAD_SIZE - 1)); + unsigned long depth = THREAD_SIZE - + (task->lowest_stack & (THREAD_SIZE - 1)); + + seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", + prev_depth, depth); + return 0; +} +#endif /* CONFIG_STACKLEAK_METRICS */ + /* * Thread groups */ @@ -2992,6 +3007,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_STACKLEAK_METRICS + ONE("stack_depth", S_IRUGO, proc_stack_depth), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a23acd24e7..ae9d10e14b82 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1194,6 +1194,7 @@ struct task_struct { #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; + unsigned long prev_lowest_stack; #endif /* diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 628c2b947b89..b911b973d328 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -18,6 +18,9 @@ static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +# ifdef CONFIG_STACKLEAK_METRICS + t->prev_lowest_stack = t->lowest_stack; +# endif } #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 628485db37ba..f66239572c89 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -41,6 +41,10 @@ asmlinkage void stackleak_erase(void) if (kstack_ptr == boundary) kstack_ptr += sizeof(unsigned long); +#ifdef CONFIG_STACKLEAK_METRICS + current->prev_lowest_stack = kstack_ptr; +#endif + /* * Now write the poison value to the kernel stack. Start from * 'kstack_ptr' and move up till the new 'boundary'. We assume that diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index c65fdd823591..b0a015ef5268 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -170,4 +170,16 @@ config STACKLEAK_TRACK_MIN_SIZE a stack frame size greater than or equal to this parameter. If unsure, leave the default value 100. +config STACKLEAK_METRICS + bool "Show STACKLEAK metrics in the /proc file system" + depends on GCC_PLUGIN_STACKLEAK + depends on PROC_FS + help + If this is set, STACKLEAK metrics for every task are available in + the /proc file system. In particular, /proc//stack_depth + shows the maximum kernel stack consumption for the current and + previous syscalls. Although this information is not precise, it + can be useful for estimating the STACKLEAK performance impact for + your workloads. + endif -- cgit v1.2.3-71-gd317 From 964c9dff0091893a9a74a88edf984c6da0b779f7 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:03 +0300 Subject: stackleak: Allow runtime disabling of kernel stack erasing Introduce CONFIG_STACKLEAK_RUNTIME_DISABLE option, which provides 'stack_erasing' sysctl. It can be used in runtime to control kernel stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- Documentation/sysctl/kernel.txt | 18 ++++++++++++++++++ include/linux/stackleak.h | 6 ++++++ kernel/stackleak.c | 38 ++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 15 ++++++++++++++- scripts/gcc-plugins/Kconfig | 8 ++++++++ 5 files changed, 84 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 37a679501ddc..1b8775298cf7 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -89,6 +89,7 @@ show up in /proc/sys/kernel: - shmmni - softlockup_all_cpu_backtrace - soft_watchdog +- stack_erasing - stop-a [ SPARC only ] - sysrq ==> Documentation/admin-guide/sysrq.rst - sysctl_writes_strict @@ -987,6 +988,23 @@ detect a hard lockup condition. ============================================================== +stack_erasing + +This parameter can be used to control kernel stack erasing at the end +of syscalls for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. + +That erasing reduces the information which kernel stack leak bugs +can reveal and blocks some uninitialized stack variable attacks. +The tradeoff is the performance impact: on a single CPU system kernel +compilation sees a 1% slowdown, other systems and workloads may vary. + + 0: kernel stack erasing is disabled, STACKLEAK_METRICS are not updated. + + 1: kernel stack erasing is enabled (default), it is performed before + returning to the userspace at the end of syscalls. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which can be diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index b911b973d328..3d5c3271a9a8 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -22,6 +22,12 @@ static inline void stackleak_task_init(struct task_struct *t) t->prev_lowest_stack = t->lowest_stack; # endif } + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/kernel/stackleak.c b/kernel/stackleak.c index f66239572c89..e42892926244 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -12,6 +12,41 @@ #include +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include +#include + +static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); + +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = 0; + int state = !static_branch_unlikely(&stack_erasing_bypass); + int prev_state = state; + + table->data = &state; + table->maxlen = sizeof(int); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + state = !!state; + if (ret || !write || state == prev_state) + return ret; + + if (state) + static_branch_disable(&stack_erasing_bypass); + else + static_branch_enable(&stack_erasing_bypass); + + pr_warn("stackleak: kernel stack erasing is %s\n", + state ? "enabled" : "disabled"); + return ret; +} + +#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) +#else +#define skip_erasing() false +#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ + asmlinkage void stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ @@ -20,6 +55,9 @@ asmlinkage void stackleak_erase(void) unsigned int poison_count = 0; const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + if (skip_erasing()) + return; + /* Check that 'lowest_stack' value is sane */ if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) kstack_ptr = boundary; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cc02050fd0c4..3ae223f7b5df 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -91,7 +91,9 @@ #ifdef CONFIG_CHR_DEV_SG #include #endif - +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include +#endif #ifdef CONFIG_LOCKUP_DETECTOR #include #endif @@ -1232,6 +1234,17 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#endif +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = &zero, + .extra2 = &one, + }, #endif { } }; diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index b0a015ef5268..0d5c799688f0 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -182,4 +182,12 @@ config STACKLEAK_METRICS can be useful for estimating the STACKLEAK performance impact for your workloads. +config STACKLEAK_RUNTIME_DISABLE + bool "Allow runtime disabling of kernel stack erasing" + depends on GCC_PLUGIN_STACKLEAK + help + This option provides 'stack_erasing' sysctl, which can be used in + runtime to control kernel stack erasing for kernels built with + CONFIG_GCC_PLUGIN_STACKLEAK. + endif -- cgit v1.2.3-71-gd317 From cc8a4ea182efac95ad4582053f8a51271fab734d Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:55 +0200 Subject: platform/chrome: Move mfd/cros_ec_lpc* includes to drivers/platform. The cros-ec-lpc driver lives in drivers/platform because is platform specific, however there are two includes (cros_ec_lpc_mec.h and cros_ec_lpc_reg.h) that lives in include/linux/mfd. These two includes are only used for the platform driver and are not really related to the MFD subsystem, so move the includes from include/linux/mfd to drivers/platform/chrome. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- drivers/platform/chrome/cros_ec_lpc.c | 3 +- drivers/platform/chrome/cros_ec_lpc_mec.c | 3 +- drivers/platform/chrome/cros_ec_lpc_mec.h | 90 +++++++++++++++++++++++++++++++ drivers/platform/chrome/cros_ec_lpc_reg.c | 3 +- drivers/platform/chrome/cros_ec_lpc_reg.h | 61 +++++++++++++++++++++ include/linux/mfd/cros_ec_lpc_mec.h | 90 ------------------------------- include/linux/mfd/cros_ec_lpc_reg.h | 61 --------------------- 7 files changed, 157 insertions(+), 154 deletions(-) create mode 100644 drivers/platform/chrome/cros_ec_lpc_mec.h create mode 100644 drivers/platform/chrome/cros_ec_lpc_reg.h delete mode 100644 include/linux/mfd/cros_ec_lpc_mec.h delete mode 100644 include/linux/mfd/cros_ec_lpc_reg.h (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index 31c8b8c49e45..7ec8789bf161 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -27,12 +27,13 @@ #include #include #include -#include #include #include #include #include +#include "cros_ec_lpc_reg.h" + #define DRV_NAME "cros_ec_lpcs" #define ACPI_DRV_NAME "GOOG0004" diff --git a/drivers/platform/chrome/cros_ec_lpc_mec.c b/drivers/platform/chrome/cros_ec_lpc_mec.c index 2eda2c2fc210..c4edfa83e493 100644 --- a/drivers/platform/chrome/cros_ec_lpc_mec.c +++ b/drivers/platform/chrome/cros_ec_lpc_mec.c @@ -24,10 +24,11 @@ #include #include #include -#include #include #include +#include "cros_ec_lpc_mec.h" + /* * This mutex must be held while accessing the EMI unit. We can't rely on the * EC mutex because memmap data may be accessed without it being held. diff --git a/drivers/platform/chrome/cros_ec_lpc_mec.h b/drivers/platform/chrome/cros_ec_lpc_mec.h new file mode 100644 index 000000000000..105068c0e919 --- /dev/null +++ b/drivers/platform/chrome/cros_ec_lpc_mec.h @@ -0,0 +1,90 @@ +/* + * cros_ec_lpc_mec - LPC variant I/O for Microchip EC + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __CROS_EC_LPC_MEC_H +#define __CROS_EC_LPC_MEC_H + +#include + +enum cros_ec_lpc_mec_emi_access_mode { + /* 8-bit access */ + ACCESS_TYPE_BYTE = 0x0, + /* 16-bit access */ + ACCESS_TYPE_WORD = 0x1, + /* 32-bit access */ + ACCESS_TYPE_LONG = 0x2, + /* + * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the + * EC data register to be incremented. + */ + ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, +}; + +enum cros_ec_lpc_mec_io_type { + MEC_IO_READ, + MEC_IO_WRITE, +}; + +/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ +#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 +#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) + +/* EMI registers are relative to base */ +#define MEC_EMI_BASE 0x800 +#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) +#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) +#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) +#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) +#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) +#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) +#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) +#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) + +/* + * cros_ec_lpc_mec_init + * + * Initialize MEC I/O. + */ +void cros_ec_lpc_mec_init(void); + +/* + * cros_ec_lpc_mec_destroy + * + * Cleanup MEC I/O. + */ +void cros_ec_lpc_mec_destroy(void); + +/** + * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port + * + * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request + * @offset: Base read / write address + * @length: Number of bytes to read / write + * @buf: Destination / source buffer + * + * @return 8-bit checksum of all bytes read / written + */ +u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, + unsigned int offset, unsigned int length, u8 *buf); + +#endif /* __CROS_EC_LPC_MEC_H */ diff --git a/drivers/platform/chrome/cros_ec_lpc_reg.c b/drivers/platform/chrome/cros_ec_lpc_reg.c index dcc7a3e30604..fc23d535c404 100644 --- a/drivers/platform/chrome/cros_ec_lpc_reg.c +++ b/drivers/platform/chrome/cros_ec_lpc_reg.c @@ -24,7 +24,8 @@ #include #include #include -#include + +#include "cros_ec_lpc_mec.h" static u8 lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest) { diff --git a/drivers/platform/chrome/cros_ec_lpc_reg.h b/drivers/platform/chrome/cros_ec_lpc_reg.h new file mode 100644 index 000000000000..1c12c38b306a --- /dev/null +++ b/drivers/platform/chrome/cros_ec_lpc_reg.h @@ -0,0 +1,61 @@ +/* + * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __CROS_EC_LPC_REG_H +#define __CROS_EC_LPC_REG_H + +/** + * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. + * Returns 8-bit checksum of all bytes read. + * + * @offset: Base read address + * @length: Number of bytes to read + * @dest: Destination buffer + */ +u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); + +/** + * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. + * Returns 8-bit checksum of all bytes written. + * + * @offset: Base write address + * @length: Number of bytes to write + * @msg: Write data buffer + */ +u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); + +/** + * cros_ec_lpc_reg_init + * + * Initialize register I/O. + */ +void cros_ec_lpc_reg_init(void); + +/** + * cros_ec_lpc_reg_destroy + * + * Cleanup reg I/O. + */ +void cros_ec_lpc_reg_destroy(void); + +#endif /* __CROS_EC_LPC_REG_H */ diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h deleted file mode 100644 index 176496ddc66c..000000000000 --- a/include/linux/mfd/cros_ec_lpc_mec.h +++ /dev/null @@ -1,90 +0,0 @@ -/* - * cros_ec_lpc_mec - LPC variant I/O for Microchip EC - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_MEC_H -#define __LINUX_MFD_CROS_EC_MEC_H - -#include - -enum cros_ec_lpc_mec_emi_access_mode { - /* 8-bit access */ - ACCESS_TYPE_BYTE = 0x0, - /* 16-bit access */ - ACCESS_TYPE_WORD = 0x1, - /* 32-bit access */ - ACCESS_TYPE_LONG = 0x2, - /* - * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the - * EC data register to be incremented. - */ - ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, -}; - -enum cros_ec_lpc_mec_io_type { - MEC_IO_READ, - MEC_IO_WRITE, -}; - -/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ -#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 -#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) - -/* EMI registers are relative to base */ -#define MEC_EMI_BASE 0x800 -#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) -#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) -#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) -#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) -#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) -#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) -#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) -#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) - -/* - * cros_ec_lpc_mec_init - * - * Initialize MEC I/O. - */ -void cros_ec_lpc_mec_init(void); - -/* - * cros_ec_lpc_mec_destroy - * - * Cleanup MEC I/O. - */ -void cros_ec_lpc_mec_destroy(void); - -/** - * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port - * - * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request - * @offset: Base read / write address - * @length: Number of bytes to read / write - * @buf: Destination / source buffer - * - * @return 8-bit checksum of all bytes read / written - */ -u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, - unsigned int offset, unsigned int length, u8 *buf); - -#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h deleted file mode 100644 index 5560bef63c2b..000000000000 --- a/include/linux/mfd/cros_ec_lpc_reg.h +++ /dev/null @@ -1,61 +0,0 @@ -/* - * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller - * - * Copyright (C) 2016 Google, Inc - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * This driver uses the Chrome OS EC byte-level message-based protocol for - * communicating the keyboard state (which keys are pressed) from a keyboard EC - * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, - * but everything else (including deghosting) is done here. The main - * motivation for this is to keep the EC firmware as simple as possible, since - * it cannot be easily upgraded and EC flash/IRAM space is relatively - * expensive. - */ - -#ifndef __LINUX_MFD_CROS_EC_REG_H -#define __LINUX_MFD_CROS_EC_REG_H - -/** - * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. - * Returns 8-bit checksum of all bytes read. - * - * @offset: Base read address - * @length: Number of bytes to read - * @dest: Destination buffer - */ -u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); - -/** - * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. - * Returns 8-bit checksum of all bytes written. - * - * @offset: Base write address - * @length: Number of bytes to write - * @msg: Write data buffer - */ -u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); - -/** - * cros_ec_lpc_reg_init - * - * Initialize register I/O. - */ -void cros_ec_lpc_reg_init(void); - -/** - * cros_ec_lpc_reg_destroy - * - * Cleanup reg I/O. - */ -void cros_ec_lpc_reg_destroy(void); - -#endif /* __LINUX_MFD_CROS_EC_REG_H */ -- cgit v1.2.3-71-gd317 From e2bbf91cad09118d7500f1fdaaa83d7741d30395 Mon Sep 17 00:00:00 2001 From: Enric Balletbo i Serra Date: Wed, 18 Jul 2018 18:09:56 +0200 Subject: mfd: cros_ec: Fix and improve kerneldoc comments. cros-ec includes inside the MFD subsystem, specially the file cros_ec_commands.h, has been modified several times and it has grown a lot, unfortunately, we didn't have care too much about the documentation. This patch tries to improve the documentation and also fixes all the issues reported by kerneldoc script. Signed-off-by: Enric Balletbo i Serra Signed-off-by: Benson Leung --- drivers/mfd/cros_ec_dev.h | 13 +- include/linux/mfd/cros_ec.h | 214 +++++++++++++------------ include/linux/mfd/cros_ec_commands.h | 295 ++++++++++++++++++++++------------- 3 files changed, 310 insertions(+), 212 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/cros_ec_dev.h b/drivers/mfd/cros_ec_dev.h index 45e9453608c5..978d836a0248 100644 --- a/drivers/mfd/cros_ec_dev.h +++ b/drivers/mfd/cros_ec_dev.h @@ -26,12 +26,13 @@ #define CROS_EC_DEV_VERSION "1.0.0" -/* - * @offset: within EC_LPC_ADDR_MEMMAP region - * @bytes: number of bytes to read. zero means "read a string" (including '\0') - * (at most only EC_MEMMAP_SIZE bytes can be read) - * @buffer: where to store the result - * ioctl returns the number of bytes read, negative on error +/** + * struct cros_ec_readmem - Struct used to read mapped memory. + * @offset: Within EC_LPC_ADDR_MEMMAP region. + * @bytes: Number of bytes to read. Zero means "read a string" (including '\0') + * At most only EC_MEMMAP_SIZE bytes can be read. + * @buffer: Where to store the result. The ioctl returns the number of bytes + * read or negative on error. */ struct cros_ec_readmem { uint32_t offset; diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 20949dde35cd..e44e3ec8a9c7 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -36,7 +36,7 @@ * I2C requires 1 additional byte for requests. * I2C requires 2 additional bytes for responses. * SPI requires up to 32 additional bytes for responses. - * */ + */ #define EC_PROTO_VERSION_UNKNOWN 0 #define EC_MAX_REQUEST_OVERHEAD 1 #define EC_MAX_RESPONSE_OVERHEAD 32 @@ -58,13 +58,14 @@ enum { EC_MAX_MSG_BYTES = 64 * 1024, }; -/* - * @version: Command version number (often 0) - * @command: Command to send (EC_CMD_...) - * @outsize: Outgoing length in bytes - * @insize: Max number of bytes to accept from EC - * @result: EC's response to the command (separate from communication failure) - * @data: Where to put the incoming data from EC and outgoing data to EC +/** + * struct cros_ec_command - Information about a ChromeOS EC command. + * @version: Command version number (often 0). + * @command: Command to send (EC_CMD_...). + * @outsize: Outgoing length in bytes. + * @insize: Max number of bytes to accept from the EC. + * @result: EC's response to the command (separate from communication failure). + * @data: Where to put the incoming data from EC and outgoing data to EC. */ struct cros_ec_command { uint32_t version; @@ -76,48 +77,55 @@ struct cros_ec_command { }; /** - * struct cros_ec_device - Information about a ChromeOS EC device - * - * @phys_name: name of physical comms layer (e.g. 'i2c-4') + * struct cros_ec_device - Information about a ChromeOS EC device. + * @phys_name: Name of physical comms layer (e.g. 'i2c-4'). * @dev: Device pointer for physical comms device - * @was_wake_device: true if this device was set to wake the system from - * sleep at the last suspend - * @cmd_readmem: direct read of the EC memory-mapped region, if supported - * @offset is within EC_LPC_ADDR_MEMMAP region. - * @bytes: number of bytes to read. zero means "read a string" (including - * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be read. - * Caller must ensure that the buffer is large enough for the result when - * reading a string. - * - * @priv: Private data - * @irq: Interrupt to use - * @id: Device id - * @din: input buffer (for data from EC) - * @dout: output buffer (for data to EC) - * \note - * These two buffers will always be dword-aligned and include enough - * space for up to 7 word-alignment bytes also, so we can ensure that - * the body of the message is always dword-aligned (64-bit). - * We use this alignment to keep ARM and x86 happy. Probably word - * alignment would be OK, there might be a small performance advantage - * to using dword. - * @din_size: size of din buffer to allocate (zero to use static din) - * @dout_size: size of dout buffer to allocate (zero to use static dout) - * @wake_enabled: true if this device can wake the system from sleep - * @suspended: true if this device had been suspended - * @cmd_xfer: send command to EC and get response - * Returns the number of bytes received if the communication succeeded, but - * that doesn't mean the EC was happy with the command. The caller - * should check msg.result for the EC's result code. - * @pkt_xfer: send packet to EC and get response - * @lock: one transaction at a time - * @mkbp_event_supported: true if this EC supports the MKBP event protocol. - * @event_notifier: interrupt event notifier for transport devices. - * @event_data: raw payload transferred with the MKBP event. - * @event_size: size in bytes of the event data. + * @was_wake_device: True if this device was set to wake the system from + * sleep at the last suspend. + * @cros_class: The class structure for this device. + * @cmd_readmem: Direct read of the EC memory-mapped region, if supported. + * @offset: Is within EC_LPC_ADDR_MEMMAP region. + * @bytes: Number of bytes to read. zero means "read a string" (including + * the trailing '\0'). At most only EC_MEMMAP_SIZE bytes can be + * read. Caller must ensure that the buffer is large enough for the + * result when reading a string. + * @max_request: Max size of message requested. + * @max_response: Max size of message response. + * @max_passthru: Max sice of passthru message. + * @proto_version: The protocol version used for this device. + * @priv: Private data. + * @irq: Interrupt to use. + * @id: Device id. + * @din: Input buffer (for data from EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @dout: Output buffer (for data to EC). This buffer will always be + * dword-aligned and include enough space for up to 7 word-alignment + * bytes also, so we can ensure that the body of the message is always + * dword-aligned (64-bit). We use this alignment to keep ARM and x86 + * happy. Probably word alignment would be OK, there might be a small + * performance advantage to using dword. + * @din_size: Size of din buffer to allocate (zero to use static din). + * @dout_size: Size of dout buffer to allocate (zero to use static dout). + * @wake_enabled: True if this device can wake the system from sleep. + * @suspended: True if this device had been suspended. + * @cmd_xfer: Send command to EC and get response. + * Returns the number of bytes received if the communication + * succeeded, but that doesn't mean the EC was happy with the + * command. The caller should check msg.result for the EC's result + * code. + * @pkt_xfer: Send packet to EC and get response. + * @lock: One transaction at a time. + * @mkbp_event_supported: True if this EC supports the MKBP event protocol. + * @event_notifier: Interrupt event notifier for transport devices. + * @event_data: Raw payload transferred with the MKBP event. + * @event_size: Size in bytes of the event data. + * @host_event_wake_mask: Mask of host events that cause wake from suspend. */ struct cros_ec_device { - /* These are used by other drivers that want to talk to the EC */ const char *phys_name; struct device *dev; @@ -153,20 +161,19 @@ struct cros_ec_device { }; /** - * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information - * + * struct cros_ec_sensor_platform - ChromeOS EC sensor platform information. * @sensor_num: Id of the sensor, as reported by the EC. */ struct cros_ec_sensor_platform { u8 sensor_num; }; -/* struct cros_ec_platform - ChromeOS EC platform information - * - * @ec_name: name of EC device (e.g. 'cros-ec', 'cros-pd', ...) - * used in /dev/ and sysfs. - * @cmd_offset: offset to apply for each command. Set when - * registering a devicde behind another one. +/** + * struct cros_ec_platform - ChromeOS EC platform information. + * @ec_name: Name of EC device (e.g. 'cros-ec', 'cros-pd', ...) + * used in /dev/ and sysfs. + * @cmd_offset: Offset to apply for each command. Set when + * registering a device behind another one. */ struct cros_ec_platform { const char *ec_name; @@ -175,16 +182,16 @@ struct cros_ec_platform { struct cros_ec_debugfs; -/* - * struct cros_ec_dev - ChromeOS EC device entry point - * - * @class_dev: Device structure used in sysfs - * @cdev: Character device structure in /dev - * @ec_dev: cros_ec_device structure to talk to the physical device - * @dev: pointer to the platform device - * @debug_info: cros_ec_debugfs structure for debugging information - * @has_kb_wake_angle: true if at least 2 accelerometer are connected to the EC. - * @cmd_offset: offset to apply for each command. +/** + * struct cros_ec_dev - ChromeOS EC device entry point. + * @class_dev: Device structure used in sysfs. + * @cdev: Character device structure in /dev. + * @ec_dev: cros_ec_device structure to talk to the physical device. + * @dev: Pointer to the platform device. + * @debug_info: cros_ec_debugfs structure for debugging information. + * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC. + * @cmd_offset: Offset to apply for each command. + * @features: Features supported by the EC. */ struct cros_ec_dev { struct device class_dev; @@ -200,124 +207,129 @@ struct cros_ec_dev { #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) /** - * cros_ec_suspend - Handle a suspend operation for the ChromeOS EC device + * cros_ec_suspend() - Handle a suspend operation for the ChromeOS EC device. + * @ec_dev: Device to suspend. * * This can be called by drivers to handle a suspend event. * - * ec_dev: Device to suspend - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_suspend(struct cros_ec_device *ec_dev); /** - * cros_ec_resume - Handle a resume operation for the ChromeOS EC device + * cros_ec_resume() - Handle a resume operation for the ChromeOS EC device. + * @ec_dev: Device to resume. * * This can be called by drivers to handle a resume event. * - * @ec_dev: Device to resume - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_resume(struct cros_ec_device *ec_dev); /** - * cros_ec_prepare_tx - Prepare an outgoing message in the output buffer + * cros_ec_prepare_tx() - Prepare an outgoing message in the output buffer. + * @ec_dev: Device to register. + * @msg: Message to write. * * This is intended to be used by all ChromeOS EC drivers, but at present * only SPI uses it. Once LPC uses the same protocol it can start using it. * I2C could use it now, with a refactor of the existing code. * - * @ec_dev: Device to register - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_prepare_tx(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_check_result - Check ec_msg->result + * cros_ec_check_result() - Check ec_msg->result. + * @ec_dev: EC device. + * @msg: Message to check. * * This is used by ChromeOS EC drivers to check the ec_msg->result for * errors and to warn about them. * - * @ec_dev: EC device - * @msg: Message to check + * Return: 0 on success or negative error code. */ int cros_ec_check_result(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * Call this to send a command to the ChromeOS EC. This should be used * instead of calling the EC's cmd_xfer() callback directly. * - * @ec_dev: EC device - * @msg: Message to write + * Return: 0 on success or negative error code. */ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_cmd_xfer_status - Send a command to the ChromeOS EC + * cros_ec_cmd_xfer_status() - Send a command to the ChromeOS EC. + * @ec_dev: EC device. + * @msg: Message to write. * * This function is identical to cros_ec_cmd_xfer, except it returns success * status only if both the command was transmitted successfully and the EC * replied with success status. It's not necessary to check msg->result when * using this function. * - * @ec_dev: EC device - * @msg: Message to write - * @return: Num. of bytes transferred on success, <0 on failure + * Return: The number of bytes transferred on success or negative error code. */ int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev, struct cros_ec_command *msg); /** - * cros_ec_remove - Remove a ChromeOS EC + * cros_ec_remove() - Remove a ChromeOS EC. + * @ec_dev: Device to register. * * Call this to deregister a ChromeOS EC, then clean up any private data. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_remove(struct cros_ec_device *ec_dev); /** - * cros_ec_register - Register a new ChromeOS EC, using the provided info + * cros_ec_register() - Register a new ChromeOS EC, using the provided info. + * @ec_dev: Device to register. * * Before calling this, allocate a pointer to a new device and then fill * in all the fields up to the --private-- marker. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_register(struct cros_ec_device *ec_dev); /** - * cros_ec_query_all - Query the protocol version supported by the ChromeOS EC + * cros_ec_query_all() - Query the protocol version supported by the + * ChromeOS EC. + * @ec_dev: Device to register. * - * @ec_dev: Device to register - * @return 0 if ok, -ve on error + * Return: 0 on success or negative error code. */ int cros_ec_query_all(struct cros_ec_device *ec_dev); /** - * cros_ec_get_next_event - Fetch next event from the ChromeOS EC - * - * @ec_dev: Device to fetch event from + * cros_ec_get_next_event() - Fetch next event from the ChromeOS EC. + * @ec_dev: Device to fetch event from. * @wake_event: Pointer to a bool set to true upon return if the event might be * treated as a wake event. Ignored if null. * - * Returns: 0 on success, Linux error number on failure + * Return: 0 on success or negative error code. */ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); /** - * cros_ec_get_host_event - Return a mask of event set by the EC. + * cros_ec_get_host_event() - Return a mask of event set by the ChromeOS EC. + * @ec_dev: Device to fetch event from. * - * When MKBP is supported, when the EC raises an interrupt, - * We collect the events raised and call the functions in the ec notifier. + * When MKBP is supported, when the EC raises an interrupt, we collect the + * events raised and call the functions in the ec notifier. This function + * is a helper to know which events are raised. * - * This function is a helper to know which events are raised. + * Return: 0 on success or negative error code. */ u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 6e1ab9bead28..88100bddf1ab 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -306,15 +306,18 @@ enum host_event_code { /* Host event mask */ #define EC_HOST_EVENT_MASK(event_code) (1UL << ((event_code) - 1)) -/* Arguments at EC_LPC_ADDR_HOST_ARGS */ +/** + * struct ec_lpc_host_args - Arguments at EC_LPC_ADDR_HOST_ARGS + * @flags: The host argument flags. + * @command_version: Command version. + * @data_size: The length of data. + * @checksum: Checksum; sum of command + flags + command_version + data_size + + * all params/response data bytes. + */ struct ec_lpc_host_args { uint8_t flags; uint8_t command_version; uint8_t data_size; - /* - * Checksum; sum of command + flags + command_version + data_size + - * all params/response data bytes. - */ uint8_t checksum; } __packed; @@ -468,54 +471,43 @@ struct ec_lpc_host_args { #define EC_HOST_REQUEST_VERSION 3 -/* Version 3 request from host */ +/** + * struct ec_host_request - Version 3 request from host. + * @struct_version: Should be 3. The EC will return EC_RES_INVALID_HEADER if it + * receives a header with a version it doesn't know how to + * parse. + * @checksum: Checksum of request and data; sum of all bytes including checksum + * should total to 0. + * @command: Command to send (EC_CMD_...) + * @command_version: Command version. + * @reserved: Unused byte in current protocol version; set to 0. + * @data_len: Length of data which follows this header. + */ struct ec_host_request { - /* Struct version (=3) - * - * EC will return EC_RES_INVALID_HEADER if it receives a header with a - * version it doesn't know how to parse. - */ uint8_t struct_version; - - /* - * Checksum of request and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Command code */ uint16_t command; - - /* Command version */ uint8_t command_version; - - /* Unused byte in current protocol version; set to 0 */ uint8_t reserved; - - /* Length of data which follows this header */ uint16_t data_len; } __packed; #define EC_HOST_RESPONSE_VERSION 3 -/* Version 3 response from EC */ +/** + * struct ec_host_response - Version 3 response from EC. + * @struct_version: Struct version (=3). + * @checksum: Checksum of response and data; sum of all bytes including + * checksum should total to 0. + * @result: EC's response to the command (separate from communication failure) + * @data_len: Length of data which follows this header. + * @reserved: Unused bytes in current protocol version; set to 0. + */ struct ec_host_response { - /* Struct version (=3) */ uint8_t struct_version; - - /* - * Checksum of response and data; sum of all bytes including checksum - * should total to 0. - */ uint8_t checksum; - - /* Result code (EC_RES_*) */ uint16_t result; - - /* Length of data which follows this header */ uint16_t data_len; - - /* Unused bytes in current protocol version; set to 0 */ uint16_t reserved; } __packed; @@ -540,6 +532,10 @@ struct ec_host_response { */ #define EC_CMD_PROTO_VERSION 0x00 +/** + * struct ec_response_proto_version - Response to the proto version command. + * @version: The protocol version. + */ struct ec_response_proto_version { uint32_t version; } __packed; @@ -550,12 +546,20 @@ struct ec_response_proto_version { */ #define EC_CMD_HELLO 0x01 +/** + * struct ec_params_hello - Parameters to the hello command. + * @in_data: Pass anything here. + */ struct ec_params_hello { - uint32_t in_data; /* Pass anything here */ + uint32_t in_data; } __packed; +/** + * struct ec_response_hello - Response to the hello command. + * @out_data: Output will be in_data + 0x01020304. + */ struct ec_response_hello { - uint32_t out_data; /* Output will be in_data + 0x01020304 */ + uint32_t out_data; } __packed; /* Get version number */ @@ -567,22 +571,37 @@ enum ec_current_image { EC_IMAGE_RW }; +/** + * struct ec_response_get_version - Response to the get version command. + * @version_string_ro: Null-terminated RO firmware version string. + * @version_string_rw: Null-terminated RW firmware version string. + * @reserved: Unused bytes; was previously RW-B firmware version string. + * @current_image: One of ec_current_image. + */ struct ec_response_get_version { - /* Null-terminated version strings for RO, RW */ char version_string_ro[32]; char version_string_rw[32]; - char reserved[32]; /* Was previously RW-B string */ - uint32_t current_image; /* One of ec_current_image */ + char reserved[32]; + uint32_t current_image; } __packed; /* Read test */ #define EC_CMD_READ_TEST 0x03 +/** + * struct ec_params_read_test - Parameters for the read test command. + * @offset: Starting value for read buffer. + * @size: Size to read in bytes. + */ struct ec_params_read_test { - uint32_t offset; /* Starting value for read buffer */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; +/** + * struct ec_response_read_test - Response to the read test command. + * @data: Data returned by the read test command. + */ struct ec_response_read_test { uint32_t data[32]; } __packed; @@ -597,18 +616,27 @@ struct ec_response_read_test { /* Get chip info */ #define EC_CMD_GET_CHIP_INFO 0x05 +/** + * struct ec_response_get_chip_info - Response to the get chip info command. + * @vendor: Null-terminated string for chip vendor. + * @name: Null-terminated string for chip name. + * @revision: Null-terminated string for chip mask version. + */ struct ec_response_get_chip_info { - /* Null-terminated strings */ char vendor[32]; char name[32]; - char revision[32]; /* Mask version */ + char revision[32]; } __packed; /* Get board HW version */ #define EC_CMD_GET_BOARD_VERSION 0x06 +/** + * struct ec_response_board_version - Response to the board version command. + * @board_version: A monotonously incrementing number. + */ struct ec_response_board_version { - uint16_t board_version; /* A monotonously incrementing number. */ + uint16_t board_version; } __packed; /* @@ -621,27 +649,42 @@ struct ec_response_board_version { */ #define EC_CMD_READ_MEMMAP 0x07 +/** + * struct ec_params_read_memmap - Parameters for the read memory map command. + * @offset: Offset in memmap (EC_MEMMAP_*). + * @size: Size to read in bytes. + */ struct ec_params_read_memmap { - uint8_t offset; /* Offset in memmap (EC_MEMMAP_*) */ - uint8_t size; /* Size to read in bytes */ + uint8_t offset; + uint8_t size; } __packed; /* Read versions supported for a command */ #define EC_CMD_GET_CMD_VERSIONS 0x08 +/** + * struct ec_params_get_cmd_versions - Parameters for the get command versions. + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions { - uint8_t cmd; /* Command to check */ + uint8_t cmd; } __packed; +/** + * struct ec_params_get_cmd_versions_v1 - Parameters for the get command + * versions (v1) + * @cmd: Command to check. + */ struct ec_params_get_cmd_versions_v1 { - uint16_t cmd; /* Command to check */ + uint16_t cmd; } __packed; +/** + * struct ec_response_get_cmd_version - Response to the get command versions. + * @version_mask: Mask of supported versions; use EC_VER_MASK() to compare with + * a desired version. + */ struct ec_response_get_cmd_versions { - /* - * Mask of supported versions; use EC_VER_MASK() to compare with a - * desired version. - */ uint32_t version_mask; } __packed; @@ -659,6 +702,11 @@ enum ec_comms_status { EC_COMMS_STATUS_PROCESSING = 1 << 0, /* Processing cmd */ }; +/** + * struct ec_response_get_comms_status - Response to the get comms status + * command. + * @flags: Mask of enum ec_comms_status. + */ struct ec_response_get_comms_status { uint32_t flags; /* Mask of enum ec_comms_status */ } __packed; @@ -685,19 +733,19 @@ struct ec_response_test_protocol { /* EC_RES_IN_PROGRESS may be returned if a command is slow */ #define EC_PROTOCOL_INFO_IN_PROGRESS_SUPPORTED (1 << 0) +/** + * struct ec_response_get_protocol_info - Response to the get protocol info. + * @protocol_versions: Bitmask of protocol versions supported (1 << n means + * version n). + * @max_request_packet_size: Maximum request packet size in bytes. + * @max_response_packet_size: Maximum response packet size in bytes. + * @flags: see EC_PROTOCOL_INFO_* + */ struct ec_response_get_protocol_info { /* Fields which exist if at least protocol version 3 supported */ - - /* Bitmask of protocol versions supported (1 << n means version n)*/ uint32_t protocol_versions; - - /* Maximum request packet size, in bytes */ uint16_t max_request_packet_size; - - /* Maximum response packet size, in bytes */ uint16_t max_response_packet_size; - - /* Flags; see EC_PROTOCOL_INFO_* */ uint32_t flags; } __packed; @@ -708,8 +756,10 @@ struct ec_response_get_protocol_info { /* The upper byte of .flags tells what to do (nothing means "get") */ #define EC_GSV_SET 0x80000000 -/* The lower three bytes of .flags identifies the parameter, if that has - meaning for an individual command. */ +/* + * The lower three bytes of .flags identifies the parameter, if that has + * meaning for an individual command. + */ #define EC_GSV_PARAM_MASK 0x00ffffff struct ec_params_get_set_value { @@ -810,6 +860,7 @@ enum ec_feature_code { #define EC_FEATURE_MASK_0(event_code) (1UL << (event_code % 32)) #define EC_FEATURE_MASK_1(event_code) (1UL << (event_code - 32)) + struct ec_response_get_features { uint32_t flags[2]; } __packed; @@ -820,24 +871,22 @@ struct ec_response_get_features { /* Get flash info */ #define EC_CMD_FLASH_INFO 0x10 -/* Version 0 returns these fields */ +/** + * struct ec_response_flash_info - Response to the flash info command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * + * Version 0 returns these fields. + */ struct ec_response_flash_info { - /* Usable flash size, in bytes */ uint32_t flash_size; - /* - * Write block size. Write offset and size must be a multiple - * of this. - */ uint32_t write_block_size; - /* - * Erase block size. Erase offset and size must be a multiple - * of this. - */ uint32_t erase_block_size; - /* - * Protection block size. Protection offset and size must be a - * multiple of this. - */ uint32_t protect_block_size; } __packed; @@ -845,7 +894,22 @@ struct ec_response_flash_info { /* EC flash erases bits to 0 instead of 1 */ #define EC_FLASH_INFO_ERASE_TO_0 (1 << 0) -/* +/** + * struct ec_response_flash_info_1 - Response to the flash info v1 command. + * @flash_size: Usable flash size in bytes. + * @write_block_size: Write block size. Write offset and size must be a + * multiple of this. + * @erase_block_size: Erase block size. Erase offset and size must be a + * multiple of this. + * @protect_block_size: Protection block size. Protection offset and size + * must be a multiple of this. + * @write_ideal_size: Ideal write size in bytes. Writes will be fastest if + * size is exactly this and offset is a multiple of this. + * For example, an EC may have a write buffer which can do + * half-page operations if data is aligned, and a slower + * word-at-a-time write mode. + * @flags: Flags; see EC_FLASH_INFO_* + * * Version 1 returns the same initial fields as version 0, with additional * fields following. * @@ -860,15 +924,7 @@ struct ec_response_flash_info_1 { uint32_t protect_block_size; /* Version 1 adds these fields: */ - /* - * Ideal write size in bytes. Writes will be fastest if size is - * exactly this and offset is a multiple of this. For example, an EC - * may have a write buffer which can do half-page operations if data is - * aligned, and a slower word-at-a-time write mode. - */ uint32_t write_ideal_size; - - /* Flags; see EC_FLASH_INFO_* */ uint32_t flags; } __packed; @@ -879,9 +935,14 @@ struct ec_response_flash_info_1 { */ #define EC_CMD_FLASH_READ 0x11 +/** + * struct ec_params_flash_read - Parameters for the flash read command. + * @offset: Byte offset to read. + * @size: Size to read in bytes. + */ struct ec_params_flash_read { - uint32_t offset; /* Byte offset to read */ - uint32_t size; /* Size to read in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* Write flash */ @@ -891,18 +952,28 @@ struct ec_params_flash_read { /* Version 0 of the flash command supported only 64 bytes of data */ #define EC_FLASH_WRITE_VER0_SIZE 64 +/** + * struct ec_params_flash_write - Parameters for the flash write command. + * @offset: Byte offset to write. + * @size: Size to write in bytes. + */ struct ec_params_flash_write { - uint32_t offset; /* Byte offset to write */ - uint32_t size; /* Size to write in bytes */ + uint32_t offset; + uint32_t size; /* Followed by data to write */ } __packed; /* Erase flash */ #define EC_CMD_FLASH_ERASE 0x13 +/** + * struct ec_params_flash_erase - Parameters for the flash erase command. + * @offset: Byte offset to erase. + * @size: Size to erase in bytes. + */ struct ec_params_flash_erase { - uint32_t offset; /* Byte offset to erase */ - uint32_t size; /* Size to erase in bytes */ + uint32_t offset; + uint32_t size; } __packed; /* @@ -941,21 +1012,28 @@ struct ec_params_flash_erase { /* Entile flash code protected when the EC boots */ #define EC_FLASH_PROTECT_ALL_AT_BOOT (1 << 6) +/** + * struct ec_params_flash_protect - Parameters for the flash protect command. + * @mask: Bits in flags to apply. + * @flags: New flags to apply. + */ struct ec_params_flash_protect { - uint32_t mask; /* Bits in flags to apply */ - uint32_t flags; /* New flags to apply */ + uint32_t mask; + uint32_t flags; } __packed; +/** + * struct ec_response_flash_protect - Response to the flash protect command. + * @flags: Current value of flash protect flags. + * @valid_flags: Flags which are valid on this platform. This allows the + * caller to distinguish between flags which aren't set vs. flags + * which can't be set on this platform. + * @writable_flags: Flags which can be changed given the current protection + * state. + */ struct ec_response_flash_protect { - /* Current value of flash protect flags */ uint32_t flags; - /* - * Flags which are valid on this platform. This allows the caller - * to distinguish between flags which aren't set vs. flags which can't - * be set on this platform. - */ uint32_t valid_flags; - /* Flags which can be changed given the current protection state */ uint32_t writable_flags; } __packed; @@ -982,8 +1060,13 @@ enum ec_flash_region { EC_FLASH_REGION_COUNT, }; +/** + * struct ec_params_flash_region_info - Parameters for the flash region info + * command. + * @region: Flash region; see EC_FLASH_REGION_* + */ struct ec_params_flash_region_info { - uint32_t region; /* enum ec_flash_region */ + uint32_t region; } __packed; struct ec_response_flash_region_info { @@ -1094,7 +1177,9 @@ struct rgb_s { }; #define LB_BATTERY_LEVELS 4 -/* List of tweakable parameters. NOTE: It's __packed so it can be sent in a + +/* + * List of tweakable parameters. NOTE: It's __packed so it can be sent in a * host command, but the alignment is the same regardless. Keep it that way. */ struct lightbar_params_v0 { -- cgit v1.2.3-71-gd317 From 1a63fe9a2b1f47af5b2b7436b41824b14999c17a Mon Sep 17 00:00:00 2001 From: Quentin Perret Date: Mon, 10 Sep 2018 17:28:10 +0100 Subject: firmware: arm_scmi: add a getter for power of performance states The SCMI protocol can be used to get power estimates from firmware corresponding to each performance state of a device. Although these power costs are already managed by the SCMI firmware driver, they are not exposed to any external subsystem yet. Fix this by adding a new get_power() interface to the exisiting perf_ops defined for the SCMI protocol. Signed-off-by: Quentin Perret Signed-off-by: Sudeep Holla --- drivers/firmware/arm_scmi/perf.c | 28 ++++++++++++++++++++++++++++ include/linux/scmi_protocol.h | 4 ++++ 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 87c99d296ecd..3c8ae7cc35de 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -427,6 +427,33 @@ static int scmi_dvfs_freq_get(const struct scmi_handle *handle, u32 domain, return ret; } +static int scmi_dvfs_est_power_get(const struct scmi_handle *handle, u32 domain, + unsigned long *freq, unsigned long *power) +{ + struct scmi_perf_info *pi = handle->perf_priv; + struct perf_dom_info *dom; + unsigned long opp_freq; + int idx, ret = -EINVAL; + struct scmi_opp *opp; + + dom = pi->dom_info + domain; + if (!dom) + return -EIO; + + for (opp = dom->opp, idx = 0; idx < dom->opp_count; idx++, opp++) { + opp_freq = opp->perf * dom->mult_factor; + if (opp_freq < *freq) + continue; + + *freq = opp_freq; + *power = opp->power; + ret = 0; + break; + } + + return ret; +} + static struct scmi_perf_ops perf_ops = { .limits_set = scmi_perf_limits_set, .limits_get = scmi_perf_limits_get, @@ -437,6 +464,7 @@ static struct scmi_perf_ops perf_ops = { .device_opps_add = scmi_dvfs_device_opps_add, .freq_set = scmi_dvfs_freq_set, .freq_get = scmi_dvfs_freq_get, + .est_power_get = scmi_dvfs_est_power_get, }; static int scmi_perf_protocol_init(struct scmi_handle *handle) diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index f4c9fc0fc755..3105055c00a7 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -91,6 +91,8 @@ struct scmi_clk_ops { * to sustained performance level mapping * @freq_get: gets the frequency for a given device using sustained frequency * to sustained performance level mapping + * @est_power_get: gets the estimated power cost for a given performance domain + * at a given frequency */ struct scmi_perf_ops { int (*limits_set)(const struct scmi_handle *handle, u32 domain, @@ -110,6 +112,8 @@ struct scmi_perf_ops { unsigned long rate, bool poll); int (*freq_get)(const struct scmi_handle *handle, u32 domain, unsigned long *rate, bool poll); + int (*est_power_get)(const struct scmi_handle *handle, u32 domain, + unsigned long *rate, unsigned long *power); }; /** -- cgit v1.2.3-71-gd317 From 04cfcc7ab358e331b32cabde1e853a125f3f8735 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:02 +0200 Subject: fbdev: Drop FBINFO_CAN_FORCE_OUTPUT flag This was only added for the drm's fbdev emulation support, so that it would try harder to show the Oops. Unfortunately this never really worked reliably, and in practice ended up pushing the real Oops off the screen due to plentyfull locking, sleep-while-atomic and other issues. So we removed all that support from the fbdev emulation a while back. Aside: We've also removed the kgdb support, for similar reasons. Since it's such a small patch I figured I don't split this up into the usual 3-phase removal. Acked-by: Bartlomiej Zolnierkiewicz Cc: Ben Skeggs Cc: Bartlomiej Zolnierkiewicz Cc: Greg Kroah-Hartman Cc: Hans de Goede Cc: Daniel Vetter Cc: Alexander Kapshuk Cc: Kees Cook Cc: Thierry Reding Cc: David Lechner Cc: nouveau@lists.freedesktop.org Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-1-daniel.vetter@ffwll.ch --- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 1 - drivers/staging/vboxvideo/vbox_fb.c | 3 +-- drivers/video/fbdev/core/fbcon.c | 1 - include/linux/fb.h | 4 ---- 4 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 844498c4267c..20a260887be3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -379,7 +379,6 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA | FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_IMAGEBLIT; - info->flags |= FBINFO_CAN_FORCE_OUTPUT; info->fbops = &nouveau_fbcon_sw_ops; info->fix.smem_start = fb->nvbo->bo.mem.bus.base + fb->nvbo->bo.mem.bus.offset; diff --git a/drivers/staging/vboxvideo/vbox_fb.c b/drivers/staging/vboxvideo/vbox_fb.c index 43c39eca4ae1..034f8ffa8f20 100644 --- a/drivers/staging/vboxvideo/vbox_fb.c +++ b/drivers/staging/vboxvideo/vbox_fb.c @@ -155,8 +155,7 @@ static int vboxfb_create(struct drm_fb_helper *helper, * The last flag forces a mode set on VT switches even if the kernel * does not think it is needed. */ - info->flags = FBINFO_DEFAULT | FBINFO_CAN_FORCE_OUTPUT | - FBINFO_MISC_ALWAYS_SETPAR; + info->flags = FBINFO_DEFAULT | FBINFO_MISC_ALWAYS_SETPAR; info->fbops = &vboxfb_ops; /* diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 75ebbbf0a1fb..9fd99681a7f2 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -1104,7 +1104,6 @@ static void fbcon_init(struct vc_data *vc, int init) if (p->userfont) charcnt = FNTCHARCNT(p->fontdata); - vc->vc_panic_force_write = !!(info->flags & FBINFO_CAN_FORCE_OUTPUT); vc->vc_can_do_color = (fb_get_color_depth(&info->var, &info->fix)!=1); vc->vc_complement_mask = vc->vc_can_do_color ? 0x7700 : 0x0800; if (charcnt == 256) { diff --git a/include/linux/fb.h b/include/linux/fb.h index 3cd375dafd0e..b1db5c5eb671 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -457,10 +457,6 @@ struct fb_tile_ops { */ #define FBINFO_BE_MATH 0x100000 -/* report to the VT layer that this fb driver can accept forced console - output like oopses */ -#define FBINFO_CAN_FORCE_OUTPUT 0x200000 - struct fb_info { atomic_t count; int node; -- cgit v1.2.3-71-gd317 From 8d7fc2994f4d1f431e280c9e21a139c18dc435ec Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:03 +0200 Subject: vt: Remove vc_panic_force_write It was only used by the panic support in fbcon, which is now gone. Remove this now dead code too. Acked-by: Greg Kroah-Hartman Cc: Greg Kroah-Hartman Cc: Kees Cook Cc: Joe Perches Cc: Daniel Vetter Cc: Meng Xu Cc: Nicolas Pitre Cc: Thomas Meyer Cc: Mike Frysinger Cc: Bartlomiej Zolnierkiewicz Cc: Hans de Goede Cc: Thierry Reding Cc: David Lechner Cc: Philippe Ombredanne Cc: Thomas Gleixner Cc: Kate Stewart Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-2-daniel.vetter@ffwll.ch --- drivers/tty/vt/vt.c | 12 ++++-------- drivers/video/fbdev/core/fbcon.c | 3 +-- include/linux/console_struct.h | 1 - include/linux/vt_kern.h | 7 ------- 4 files changed, 5 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 5f1183b0b89d..55370e651db3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1004,9 +1004,7 @@ void redraw_screen(struct vc_data *vc, int is_switch) clear_buffer_attributes(vc); } - /* Forcibly update if we're panicing */ - if ((update && vc->vc_mode != KD_GRAPHICS) || - vt_force_oops_output(vc)) + if (update && vc->vc_mode != KD_GRAPHICS) do_update_region(vc, vc->vc_origin, vc->vc_screenbuf_size / 2); } set_cursor(vc); @@ -1046,7 +1044,6 @@ static void visual_init(struct vc_data *vc, int num, int init) vc->vc_hi_font_mask = 0; vc->vc_complement_mask = 0; vc->vc_can_do_color = 0; - vc->vc_panic_force_write = false; vc->vc_cur_blink_ms = DEFAULT_CURSOR_BLINK_MS; vc->vc_sw->con_init(vc, init); if (!vc->vc_complement_mask) @@ -2911,7 +2908,7 @@ static void vt_console_print(struct console *co, const char *b, unsigned count) goto quit; } - if (vc->vc_mode != KD_TEXT && !vt_force_oops_output(vc)) + if (vc->vc_mode != KD_TEXT) goto quit; /* undraw cursor first */ @@ -4229,8 +4226,7 @@ void do_unblank_screen(int leaving_gfx) return; } vc = vc_cons[fg_console].d; - /* Try to unblank in oops case too */ - if (vc->vc_mode != KD_TEXT && !vt_force_oops_output(vc)) + if (vc->vc_mode != KD_TEXT) return; /* but leave console_blanked != 0 */ if (blankinterval) { @@ -4239,7 +4235,7 @@ void do_unblank_screen(int leaving_gfx) } console_blanked = 0; - if (vc->vc_sw->con_blank(vc, 0, leaving_gfx) || vt_force_oops_output(vc)) + if (vc->vc_sw->con_blank(vc, 0, leaving_gfx)) /* Low-level driver cannot restore -> do it ourselves */ update_screen(vc); if (console_blank_hook) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 9fd99681a7f2..8958ccc8b1ac 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -284,8 +284,7 @@ static inline int fbcon_is_inactive(struct vc_data *vc, struct fb_info *info) struct fbcon_ops *ops = info->fbcon_par; return (info->state != FBINFO_STATE_RUNNING || - vc->vc_mode != KD_TEXT || ops->graphics) && - !vt_force_oops_output(vc); + vc->vc_mode != KD_TEXT || ops->graphics); } static int get_color(struct vc_data *vc, struct fb_info *info, diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index fea64f2692a0..ab137f97ecbd 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -141,7 +141,6 @@ struct vc_data { struct uni_pagedir *vc_uni_pagedir; struct uni_pagedir **vc_uni_pagedir_loc; /* [!] Location of uni_pagedir variable for this console */ struct uni_screen *vc_uni_screen; /* unicode screen content */ - bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */ /* additional information is in vt_kern.h */ }; diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 3fd07912909c..8dc77e40bc03 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -135,13 +135,6 @@ extern int do_unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); -static inline bool vt_force_oops_output(struct vc_data *vc) -{ - if (oops_in_progress && vc->vc_panic_force_write && panic_timeout >= 0) - return true; - return false; -} - extern char vt_dont_switch; extern int default_utf8; extern int global_cursor_default; -- cgit v1.2.3-71-gd317 From da6c7707caf3736c1cf968606bd97c07e79625d4 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Wed, 22 Aug 2018 10:54:04 +0200 Subject: fbdev: Add FBINFO_HIDE_SMEM_START flag DRM drivers really, really, really don't want random userspace to share buffer behind it's back, bypassing the dma-buf buffer sharing machanism. For that reason we've ruthlessly rejected any IOCTL exposing the physical address of any graphics buffer. Unfortunately fbdev comes with that built-in. We could just set smem_start to 0, but that means we'd have to hand-roll our own fb_mmap implementation. For good reasons many drivers do that, but smem_start/length is still super convenient. Hence instead just stop the leak in the ioctl, to keep fb mmap working as-is. A second patch will set this flag for all drm drivers. Acked-by: Bartlomiej Zolnierkiewicz Cc: Bartlomiej Zolnierkiewicz Cc: Kees Cook Cc: Daniel Vetter Cc: linux-fbdev@vger.kernel.org Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20180822085405.10787-3-daniel.vetter@ffwll.ch --- drivers/video/fbdev/core/fbmem.c | 4 ++++ include/linux/fb.h | 7 +++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 0da75c55660d..861bf8081619 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1117,6 +1117,8 @@ static long do_fb_ioctl(struct fb_info *info, unsigned int cmd, if (!lock_fb_info(info)) return -ENODEV; fix = info->fix; + if (info->flags & FBINFO_HIDE_SMEM_START) + fix.smem_start = 0; unlock_fb_info(info); ret = copy_to_user(argp, &fix, sizeof(fix)) ? -EFAULT : 0; @@ -1327,6 +1329,8 @@ static int fb_get_fscreeninfo(struct fb_info *info, unsigned int cmd, if (!lock_fb_info(info)) return -ENODEV; fix = info->fix; + if (info->flags & FBINFO_HIDE_SMEM_START) + fix.smem_start = 0; unlock_fb_info(info); return do_fscreeninfo_to_user(&fix, compat_ptr(arg)); } diff --git a/include/linux/fb.h b/include/linux/fb.h index b1db5c5eb671..a3cab6dc9b44 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -456,6 +456,13 @@ struct fb_tile_ops { * and host endianness. Drivers should not use this flag. */ #define FBINFO_BE_MATH 0x100000 +/* + * Hide smem_start in the FBIOGET_FSCREENINFO IOCTL. This is used by modern DRM + * drivers to stop userspace from trying to share buffers behind the kernel's + * back. Instead dma-buf based buffer sharing should be used. + */ +#define FBINFO_HIDE_SMEM_START 0x200000 + struct fb_info { atomic_t count; -- cgit v1.2.3-71-gd317 From cdc3d7f346476b4a4d1c4738b7dcdda4b3d5d870 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Sun, 5 Aug 2018 23:18:05 -0400 Subject: media: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Reviewed-by: Simon Horman Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/shmob_drm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3-71-gd317 From 0789724f86a59fa7078d67dfeb1ee4a15ae3c693 Mon Sep 17 00:00:00 2001 From: Neil Armstrong Date: Thu, 26 Jul 2018 15:59:16 +0200 Subject: firmware: meson_sm: Add serial number sysfs entry The Amlogic Meson SoC Secure Monitor implements a call to retrieve an unique SoC ID starting from the GX Family and all new families. The serial number is simply exposed as a sysfs entry under the firmware sysfs directory. Signed-off-by: Neil Armstrong Signed-off-by: Kevin Hilman --- drivers/firmware/meson/meson_sm.c | 56 +++++++++++++++++++++++++++++++++ include/linux/firmware/meson/meson_sm.h | 1 + 2 files changed, 57 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/meson/meson_sm.c b/drivers/firmware/meson/meson_sm.c index 0ec2ca87318c..29fbc818a573 100644 --- a/drivers/firmware/meson/meson_sm.c +++ b/drivers/firmware/meson/meson_sm.c @@ -24,6 +24,7 @@ #include #include #include + #include #include @@ -48,6 +49,7 @@ struct meson_sm_chip gxbb_chip = { CMD(SM_EFUSE_READ, 0x82000030), CMD(SM_EFUSE_WRITE, 0x82000031), CMD(SM_EFUSE_USER_MAX, 0x82000033), + CMD(SM_GET_CHIP_ID, 0x82000044), { /* sentinel */ }, }, }; @@ -214,6 +216,57 @@ int meson_sm_call_write(void *buffer, unsigned int size, unsigned int cmd_index, } EXPORT_SYMBOL(meson_sm_call_write); +#define SM_CHIP_ID_LENGTH 119 +#define SM_CHIP_ID_OFFSET 4 +#define SM_CHIP_ID_SIZE 12 + +static ssize_t serial_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + uint8_t *id_buf; + int ret; + + id_buf = kmalloc(SM_CHIP_ID_LENGTH, GFP_KERNEL); + if (!id_buf) + return -ENOMEM; + + ret = meson_sm_call_read(id_buf, SM_CHIP_ID_LENGTH, SM_GET_CHIP_ID, + 0, 0, 0, 0, 0); + if (ret < 0) { + kfree(id_buf); + return ret; + } + + ret = sprintf(buf, "%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n", + id_buf[SM_CHIP_ID_OFFSET + 0], + id_buf[SM_CHIP_ID_OFFSET + 1], + id_buf[SM_CHIP_ID_OFFSET + 2], + id_buf[SM_CHIP_ID_OFFSET + 3], + id_buf[SM_CHIP_ID_OFFSET + 4], + id_buf[SM_CHIP_ID_OFFSET + 5], + id_buf[SM_CHIP_ID_OFFSET + 6], + id_buf[SM_CHIP_ID_OFFSET + 7], + id_buf[SM_CHIP_ID_OFFSET + 8], + id_buf[SM_CHIP_ID_OFFSET + 9], + id_buf[SM_CHIP_ID_OFFSET + 10], + id_buf[SM_CHIP_ID_OFFSET + 11]); + + kfree(id_buf); + + return ret; +} + +static DEVICE_ATTR_RO(serial); + +static struct attribute *meson_sm_sysfs_attributes[] = { + &dev_attr_serial.attr, + NULL, +}; + +static const struct attribute_group meson_sm_sysfs_attr_group = { + .attrs = meson_sm_sysfs_attributes, +}; + static const struct of_device_id meson_sm_ids[] = { { .compatible = "amlogic,meson-gxbb-sm", .data = &gxbb_chip }, { /* sentinel */ }, @@ -242,6 +295,9 @@ static int __init meson_sm_probe(struct platform_device *pdev) fw.chip = chip; pr_info("secure-monitor enabled\n"); + if (sysfs_create_group(&pdev->dev.kobj, &meson_sm_sysfs_attr_group)) + goto out_in_base; + return 0; out_in_base: diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h index 37a5eaea69dd..f98c20dd266e 100644 --- a/include/linux/firmware/meson/meson_sm.h +++ b/include/linux/firmware/meson/meson_sm.h @@ -17,6 +17,7 @@ enum { SM_EFUSE_READ, SM_EFUSE_WRITE, SM_EFUSE_USER_MAX, + SM_GET_CHIP_ID, }; struct meson_sm_firmware; -- cgit v1.2.3-71-gd317 From d4983983d98710e4927fdb8de8e987c303b3fba3 Mon Sep 17 00:00:00 2001 From: Maxime Jourdan Date: Thu, 23 Aug 2018 13:49:53 +0200 Subject: soc: amlogic: add meson-canvas driver Amlogic SoCs have a repository of 256 canvas which they use to describe pixel buffers. They contain metadata like width, height, block mode, endianness [..] Many IPs within those SoCs like vdec/vpu rely on those canvas to read/write pixels. Reviewed-by: Jerome Brunet Tested-by: Neil Armstrong Signed-off-by: Maxime Jourdan Signed-off-by: Kevin Hilman --- drivers/soc/amlogic/Kconfig | 7 ++ drivers/soc/amlogic/Makefile | 1 + drivers/soc/amlogic/meson-canvas.c | 185 +++++++++++++++++++++++++++++++ include/linux/soc/amlogic/meson-canvas.h | 65 +++++++++++ 4 files changed, 258 insertions(+) create mode 100644 drivers/soc/amlogic/meson-canvas.c create mode 100644 include/linux/soc/amlogic/meson-canvas.h (limited to 'include/linux') diff --git a/drivers/soc/amlogic/Kconfig b/drivers/soc/amlogic/Kconfig index b04f6e4aedbc..2f282b472912 100644 --- a/drivers/soc/amlogic/Kconfig +++ b/drivers/soc/amlogic/Kconfig @@ -1,5 +1,12 @@ menu "Amlogic SoC drivers" +config MESON_CANVAS + tristate "Amlogic Meson Canvas driver" + depends on ARCH_MESON || COMPILE_TEST + default n + help + Say yes to support the canvas IP for Amlogic SoCs. + config MESON_GX_SOCINFO bool "Amlogic Meson GX SoC Information driver" depends on ARCH_MESON || COMPILE_TEST diff --git a/drivers/soc/amlogic/Makefile b/drivers/soc/amlogic/Makefile index 8fa321893928..0ab16d35ac36 100644 --- a/drivers/soc/amlogic/Makefile +++ b/drivers/soc/amlogic/Makefile @@ -1,3 +1,4 @@ +obj-$(CONFIG_MESON_CANVAS) += meson-canvas.o obj-$(CONFIG_MESON_GX_SOCINFO) += meson-gx-socinfo.o obj-$(CONFIG_MESON_GX_PM_DOMAINS) += meson-gx-pwrc-vpu.o obj-$(CONFIG_MESON_MX_SOCINFO) += meson-mx-socinfo.o diff --git a/drivers/soc/amlogic/meson-canvas.c b/drivers/soc/amlogic/meson-canvas.c new file mode 100644 index 000000000000..fce33ca76bb6 --- /dev/null +++ b/drivers/soc/amlogic/meson-canvas.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2018 BayLibre, SAS + * Copyright (C) 2015 Amlogic, Inc. All rights reserved. + * Copyright (C) 2014 Endless Mobile + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define NUM_CANVAS 256 + +/* DMC Registers */ +#define DMC_CAV_LUT_DATAL 0x00 + #define CANVAS_WIDTH_LBIT 29 + #define CANVAS_WIDTH_LWID 3 +#define DMC_CAV_LUT_DATAH 0x04 + #define CANVAS_WIDTH_HBIT 0 + #define CANVAS_HEIGHT_BIT 9 + #define CANVAS_WRAP_BIT 22 + #define CANVAS_BLKMODE_BIT 24 + #define CANVAS_ENDIAN_BIT 26 +#define DMC_CAV_LUT_ADDR 0x08 + #define CANVAS_LUT_WR_EN BIT(9) + #define CANVAS_LUT_RD_EN BIT(8) + +struct meson_canvas { + struct device *dev; + void __iomem *reg_base; + spinlock_t lock; /* canvas device lock */ + u8 used[NUM_CANVAS]; +}; + +static void canvas_write(struct meson_canvas *canvas, u32 reg, u32 val) +{ + writel_relaxed(val, canvas->reg_base + reg); +} + +static u32 canvas_read(struct meson_canvas *canvas, u32 reg) +{ + return readl_relaxed(canvas->reg_base + reg); +} + +struct meson_canvas *meson_canvas_get(struct device *dev) +{ + struct device_node *canvas_node; + struct platform_device *canvas_pdev; + + canvas_node = of_parse_phandle(dev->of_node, "amlogic,canvas", 0); + if (!canvas_node) + return ERR_PTR(-ENODEV); + + canvas_pdev = of_find_device_by_node(canvas_node); + if (!canvas_pdev) + return ERR_PTR(-EPROBE_DEFER); + + return dev_get_drvdata(&canvas_pdev->dev); +} +EXPORT_SYMBOL_GPL(meson_canvas_get); + +int meson_canvas_config(struct meson_canvas *canvas, u8 canvas_index, + u32 addr, u32 stride, u32 height, + unsigned int wrap, + unsigned int blkmode, + unsigned int endian) +{ + unsigned long flags; + + spin_lock_irqsave(&canvas->lock, flags); + if (!canvas->used[canvas_index]) { + dev_err(canvas->dev, + "Trying to setup non allocated canvas %u\n", + canvas_index); + spin_unlock_irqrestore(&canvas->lock, flags); + return -EINVAL; + } + + canvas_write(canvas, DMC_CAV_LUT_DATAL, + ((addr + 7) >> 3) | + (((stride + 7) >> 3) << CANVAS_WIDTH_LBIT)); + + canvas_write(canvas, DMC_CAV_LUT_DATAH, + ((((stride + 7) >> 3) >> CANVAS_WIDTH_LWID) << + CANVAS_WIDTH_HBIT) | + (height << CANVAS_HEIGHT_BIT) | + (wrap << CANVAS_WRAP_BIT) | + (blkmode << CANVAS_BLKMODE_BIT) | + (endian << CANVAS_ENDIAN_BIT)); + + canvas_write(canvas, DMC_CAV_LUT_ADDR, + CANVAS_LUT_WR_EN | canvas_index); + + /* Force a read-back to make sure everything is flushed. */ + canvas_read(canvas, DMC_CAV_LUT_DATAH); + spin_unlock_irqrestore(&canvas->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(meson_canvas_config); + +int meson_canvas_alloc(struct meson_canvas *canvas, u8 *canvas_index) +{ + int i; + unsigned long flags; + + spin_lock_irqsave(&canvas->lock, flags); + for (i = 0; i < NUM_CANVAS; ++i) { + if (!canvas->used[i]) { + canvas->used[i] = 1; + spin_unlock_irqrestore(&canvas->lock, flags); + *canvas_index = i; + return 0; + } + } + spin_unlock_irqrestore(&canvas->lock, flags); + + dev_err(canvas->dev, "No more canvas available\n"); + return -ENODEV; +} +EXPORT_SYMBOL_GPL(meson_canvas_alloc); + +int meson_canvas_free(struct meson_canvas *canvas, u8 canvas_index) +{ + unsigned long flags; + + spin_lock_irqsave(&canvas->lock, flags); + if (!canvas->used[canvas_index]) { + dev_err(canvas->dev, + "Trying to free unused canvas %u\n", canvas_index); + spin_unlock_irqrestore(&canvas->lock, flags); + return -EINVAL; + } + canvas->used[canvas_index] = 0; + spin_unlock_irqrestore(&canvas->lock, flags); + + return 0; +} +EXPORT_SYMBOL_GPL(meson_canvas_free); + +static int meson_canvas_probe(struct platform_device *pdev) +{ + struct resource *res; + struct meson_canvas *canvas; + struct device *dev = &pdev->dev; + + canvas = devm_kzalloc(dev, sizeof(*canvas), GFP_KERNEL); + if (!canvas) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + canvas->reg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(canvas->reg_base)) + return PTR_ERR(canvas->reg_base); + + canvas->dev = dev; + spin_lock_init(&canvas->lock); + dev_set_drvdata(dev, canvas); + + return 0; +} + +static const struct of_device_id canvas_dt_match[] = { + { .compatible = "amlogic,canvas" }, + {} +}; +MODULE_DEVICE_TABLE(of, canvas_dt_match); + +static struct platform_driver meson_canvas_driver = { + .probe = meson_canvas_probe, + .driver = { + .name = "amlogic-canvas", + .of_match_table = canvas_dt_match, + }, +}; +module_platform_driver(meson_canvas_driver); + +MODULE_DESCRIPTION("Amlogic Canvas driver"); +MODULE_AUTHOR("Maxime Jourdan "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/soc/amlogic/meson-canvas.h b/include/linux/soc/amlogic/meson-canvas.h new file mode 100644 index 000000000000..b4dde2fbeb3f --- /dev/null +++ b/include/linux/soc/amlogic/meson-canvas.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2018 BayLibre, SAS + */ +#ifndef __SOC_MESON_CANVAS_H +#define __SOC_MESON_CANVAS_H + +#include + +#define MESON_CANVAS_WRAP_NONE 0x00 +#define MESON_CANVAS_WRAP_X 0x01 +#define MESON_CANVAS_WRAP_Y 0x02 + +#define MESON_CANVAS_BLKMODE_LINEAR 0x00 +#define MESON_CANVAS_BLKMODE_32x32 0x01 +#define MESON_CANVAS_BLKMODE_64x64 0x02 + +#define MESON_CANVAS_ENDIAN_SWAP16 0x1 +#define MESON_CANVAS_ENDIAN_SWAP32 0x3 +#define MESON_CANVAS_ENDIAN_SWAP64 0x7 +#define MESON_CANVAS_ENDIAN_SWAP128 0xf + +struct meson_canvas; + +/** + * meson_canvas_get() - get a canvas provider instance + * + * @dev: consumer device pointer + */ +struct meson_canvas *meson_canvas_get(struct device *dev); + +/** + * meson_canvas_alloc() - take ownership of a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: will be filled with the canvas ID + */ +int meson_canvas_alloc(struct meson_canvas *canvas, u8 *canvas_index); + +/** + * meson_canvas_free() - remove ownership from a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + */ +int meson_canvas_free(struct meson_canvas *canvas, u8 canvas_index); + +/** + * meson_canvas_config() - configure a canvas + * + * @canvas: canvas provider instance retrieved from meson_canvas_get() + * @canvas_index: canvas ID that was obtained via meson_canvas_alloc() + * @addr: physical address to the pixel buffer + * @stride: width of the buffer + * @height: height of the buffer + * @wrap: undocumented + * @blkmode: block mode (linear, 32x32, 64x64) + * @endian: byte swapping (swap16, swap32, swap64, swap128) + */ +int meson_canvas_config(struct meson_canvas *canvas, u8 canvas_index, + u32 addr, u32 stride, u32 height, + unsigned int wrap, unsigned int blkmode, + unsigned int endian); + +#endif -- cgit v1.2.3-71-gd317 From 1e479c619b2ac983fdea1a8212c7b822b5098da0 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 12 Sep 2018 22:22:45 +0200 Subject: rtc: unexport non devm managed registration Ensure the non managed version of the un/registration functions is not used anymore. No driver is using it anymore and they should not be necessary. Signed-off-by: Alexandre Belloni --- drivers/rtc/class.c | 12 +++++------- include/linux/rtc.h | 5 ----- 2 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index 0fca4d74c76b..3b43787f154b 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -286,9 +286,10 @@ static void rtc_device_get_offset(struct rtc_device *rtc) * * Returns the pointer to the new struct class device. */ -struct rtc_device *rtc_device_register(const char *name, struct device *dev, - const struct rtc_class_ops *ops, - struct module *owner) +static struct rtc_device *rtc_device_register(const char *name, + struct device *dev, + const struct rtc_class_ops *ops, + struct module *owner) { struct rtc_device *rtc; struct rtc_wkalrm alrm; @@ -351,15 +352,13 @@ exit: name, err); return ERR_PTR(err); } -EXPORT_SYMBOL_GPL(rtc_device_register); - /** * rtc_device_unregister - removes the previously registered RTC class device * * @rtc: the RTC class device to destroy */ -void rtc_device_unregister(struct rtc_device *rtc) +static void rtc_device_unregister(struct rtc_device *rtc) { mutex_lock(&rtc->ops_lock); /* @@ -372,7 +371,6 @@ void rtc_device_unregister(struct rtc_device *rtc) mutex_unlock(&rtc->ops_lock); put_device(&rtc->dev); } -EXPORT_SYMBOL_GPL(rtc_device_unregister); static void devm_rtc_device_release(struct device *dev, void *res) { diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 6aedc30003e7..faf00a1472d4 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -167,17 +167,12 @@ struct rtc_device { #define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ #define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ -extern struct rtc_device *rtc_device_register(const char *name, - struct device *dev, - const struct rtc_class_ops *ops, - struct module *owner); extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); struct rtc_device *devm_rtc_allocate_device(struct device *dev); int __rtc_register_device(struct module *owner, struct rtc_device *rtc); -extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); -- cgit v1.2.3-71-gd317 From 7f9c136216c745099f36a4e0c3b2e63eedeb442f Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:32 -0700 Subject: soc: qcom: Add broadcast base for Last Level Cache Controller (LLCC) Currently, broadcast base is set to end of the LLCC banks, which may not be correct always. As the number of banks may vary for each chipset and the broadcast base could be at a different address as well. This info depends on the chipset, so get the broadcast base info from the device tree (DT). Add broadcast base in LLCC driver and use this for broadcast writes. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- drivers/soc/qcom/llcc-slice.c | 55 +++++++++++++++++++++++--------------- include/linux/soc/qcom/llcc-qcom.h | 4 +-- 2 files changed, 35 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c index 54063a31132f..08e3d388e153 100644 --- a/drivers/soc/qcom/llcc-slice.c +++ b/drivers/soc/qcom/llcc-slice.c @@ -106,22 +106,24 @@ static int llcc_update_act_ctrl(u32 sid, u32 slice_status; int ret; - act_ctrl_reg = drv_data->bcast_off + LLCC_TRP_ACT_CTRLn(sid); - status_reg = drv_data->bcast_off + LLCC_TRP_STATUSn(sid); + act_ctrl_reg = LLCC_TRP_ACT_CTRLn(sid); + status_reg = LLCC_TRP_STATUSn(sid); /* Set the ACTIVE trigger */ act_ctrl_reg_val |= ACT_CTRL_ACT_TRIG; - ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val); + ret = regmap_write(drv_data->bcast_regmap, act_ctrl_reg, + act_ctrl_reg_val); if (ret) return ret; /* Clear the ACTIVE trigger */ act_ctrl_reg_val &= ~ACT_CTRL_ACT_TRIG; - ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val); + ret = regmap_write(drv_data->bcast_regmap, act_ctrl_reg, + act_ctrl_reg_val); if (ret) return ret; - ret = regmap_read_poll_timeout(drv_data->regmap, status_reg, + ret = regmap_read_poll_timeout(drv_data->bcast_regmap, status_reg, slice_status, !(slice_status & status), 0, LLCC_STATUS_READ_DELAY); return ret; @@ -226,16 +228,13 @@ static int qcom_llcc_cfg_program(struct platform_device *pdev) int ret; const struct llcc_slice_config *llcc_table; struct llcc_slice_desc desc; - u32 bcast_off = drv_data->bcast_off; sz = drv_data->cfg_size; llcc_table = drv_data->cfg; for (i = 0; i < sz; i++) { - attr1_cfg = bcast_off + - LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id); - attr0_cfg = bcast_off + - LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id); + attr1_cfg = LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id); + attr0_cfg = LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id); attr1_val = llcc_table[i].cache_mode; attr1_val |= llcc_table[i].probe_target_ways << @@ -260,10 +259,12 @@ static int qcom_llcc_cfg_program(struct platform_device *pdev) attr0_val = llcc_table[i].res_ways & ATTR0_RES_WAYS_MASK; attr0_val |= llcc_table[i].bonus_ways << ATTR0_BONUS_WAYS_SHIFT; - ret = regmap_write(drv_data->regmap, attr1_cfg, attr1_val); + ret = regmap_write(drv_data->bcast_regmap, attr1_cfg, + attr1_val); if (ret) return ret; - ret = regmap_write(drv_data->regmap, attr0_cfg, attr0_val); + ret = regmap_write(drv_data->bcast_regmap, attr0_cfg, + attr0_val); if (ret) return ret; if (llcc_table[i].activate_on_init) { @@ -279,24 +280,36 @@ int qcom_llcc_probe(struct platform_device *pdev, { u32 num_banks; struct device *dev = &pdev->dev; - struct resource *res; - void __iomem *base; + struct resource *llcc_banks_res, *llcc_bcast_res; + void __iomem *llcc_banks_base, *llcc_bcast_base; int ret, i; drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL); if (!drv_data) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); + llcc_banks_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "llcc_base"); + llcc_banks_base = devm_ioremap_resource(&pdev->dev, llcc_banks_res); + if (IS_ERR(llcc_banks_base)) + return PTR_ERR(llcc_banks_base); - drv_data->regmap = devm_regmap_init_mmio(dev, base, - &llcc_regmap_config); + drv_data->regmap = devm_regmap_init_mmio(dev, llcc_banks_base, + &llcc_regmap_config); if (IS_ERR(drv_data->regmap)) return PTR_ERR(drv_data->regmap); + llcc_bcast_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "llcc_broadcast_base"); + llcc_bcast_base = devm_ioremap_resource(&pdev->dev, llcc_bcast_res); + if (IS_ERR(llcc_bcast_base)) + return PTR_ERR(llcc_bcast_base); + + drv_data->bcast_regmap = devm_regmap_init_mmio(dev, llcc_bcast_base, + &llcc_regmap_config); + if (IS_ERR(drv_data->bcast_regmap)) + return PTR_ERR(drv_data->bcast_regmap); + ret = regmap_read(drv_data->regmap, LLCC_COMMON_STATUS0, &num_banks); if (ret) @@ -318,8 +331,6 @@ int qcom_llcc_probe(struct platform_device *pdev, for (i = 0; i < num_banks; i++) drv_data->offsets[i] = i * BANK_OFFSET_STRIDE; - drv_data->bcast_off = num_banks * BANK_OFFSET_STRIDE; - drv_data->bitmap = devm_kcalloc(dev, BITS_TO_LONGS(drv_data->max_slices), sizeof(unsigned long), GFP_KERNEL); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 7e3b9c605ab2..c681e795b587 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -70,22 +70,22 @@ struct llcc_slice_config { /** * llcc_drv_data - Data associated with the llcc driver * @regmap: regmap associated with the llcc device + * @bcast_regmap: regmap associated with llcc broadcast offset * @cfg: pointer to the data structure for slice configuration * @lock: mutex associated with each slice * @cfg_size: size of the config data table * @max_slices: max slices as read from device tree - * @bcast_off: Offset of the broadcast bank * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array */ struct llcc_drv_data { struct regmap *regmap; + struct regmap *bcast_regmap; const struct llcc_slice_config *cfg; struct mutex lock; u32 cfg_size; u32 max_slices; - u32 bcast_off; u32 num_banks; unsigned long *bitmap; u32 *offsets; -- cgit v1.2.3-71-gd317 From c081f3060fab316fcf103967a24e502d58488849 Mon Sep 17 00:00:00 2001 From: Venkata Narendra Kumar Gutta Date: Wed, 12 Sep 2018 11:06:33 -0700 Subject: soc: qcom: Add support to register LLCC EDAC driver Cache error reporting controller detects and reports single and double bit errors on Last Level Cache Controller (LLCC) cache. Add required support to register LLCC EDAC driver as platform driver, from LLCC driver. Signed-off-by: Venkata Narendra Kumar Gutta Reviewed-by: Evan Green Signed-off-by: Andy Gross --- drivers/soc/qcom/llcc-slice.c | 18 ++++++++++++++++-- include/linux/soc/qcom/llcc-qcom.h | 2 ++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c index 08e3d388e153..d78926742510 100644 --- a/drivers/soc/qcom/llcc-slice.c +++ b/drivers/soc/qcom/llcc-slice.c @@ -225,7 +225,7 @@ static int qcom_llcc_cfg_program(struct platform_device *pdev) u32 attr0_val; u32 max_cap_cacheline; u32 sz; - int ret; + int ret = 0; const struct llcc_slice_config *llcc_table; struct llcc_slice_desc desc; @@ -283,6 +283,7 @@ int qcom_llcc_probe(struct platform_device *pdev, struct resource *llcc_banks_res, *llcc_bcast_res; void __iomem *llcc_banks_base, *llcc_bcast_base; int ret, i; + struct platform_device *llcc_edac; drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL); if (!drv_data) @@ -342,7 +343,20 @@ int qcom_llcc_probe(struct platform_device *pdev, mutex_init(&drv_data->lock); platform_set_drvdata(pdev, drv_data); - return qcom_llcc_cfg_program(pdev); + ret = qcom_llcc_cfg_program(pdev); + if (ret) + return ret; + + drv_data->ecc_irq = platform_get_irq(pdev, 0); + if (drv_data->ecc_irq >= 0) { + llcc_edac = platform_device_register_data(&pdev->dev, + "qcom_llcc_edac", -1, drv_data, + sizeof(*drv_data)); + if (IS_ERR(llcc_edac)) + dev_err(dev, "Failed to register llcc edac driver\n"); + } + + return ret; } EXPORT_SYMBOL_GPL(qcom_llcc_probe); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index c681e795b587..2e4b34d2617e 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -78,6 +78,7 @@ struct llcc_slice_config { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array + * @ecc_irq: interrupt for llcc cache error detection and reporting */ struct llcc_drv_data { struct regmap *regmap; @@ -89,6 +90,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; u32 *offsets; + int ecc_irq; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) -- cgit v1.2.3-71-gd317 From 27450653f1db0b9d5b5048a246c850c52ee4aa61 Mon Sep 17 00:00:00 2001 From: Channagoud Kadabi Date: Wed, 12 Sep 2018 11:06:34 -0700 Subject: drivers: edac: Add EDAC driver support for QCOM SoCs Add error reporting driver for Single Bit Errors (SBEs) and Double Bit Errors (DBEs). As of now, this driver supports error reporting for Last Level Cache Controller (LLCC) of Tag RAM and Data RAM. Interrupts are triggered when the errors happen in the cache, the driver handles those interrupts and dumps the syndrome registers. Signed-off-by: Channagoud Kadabi Signed-off-by: Venkata Narendra Kumar Gutta Co-developed-by: Venkata Narendra Kumar Gutta Acked-by: Borislav Petkov Signed-off-by: Andy Gross --- MAINTAINERS | 8 + drivers/edac/Kconfig | 14 ++ drivers/edac/Makefile | 1 + drivers/edac/qcom_edac.c | 414 +++++++++++++++++++++++++++++++++++++ include/linux/soc/qcom/llcc-qcom.h | 24 +++ 5 files changed, 461 insertions(+) create mode 100644 drivers/edac/qcom_edac.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index a5b256b25905..f7d7213ca293 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5346,6 +5346,14 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/ti_edac.c +EDAC-QCOM +M: Channagoud Kadabi +M: Venkata Narendra Kumar Gutta +L: linux-arm-msm@vger.kernel.org +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/edac/qcom_edac.c + EDIROL UA-101/UA-1000 DRIVER M: Clemens Ladisch L: alsa-devel@alsa-project.org (moderated for non-subscribers) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 57304b2e989f..df9467eef32a 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -460,4 +460,18 @@ config EDAC_TI Support for error detection and correction on the TI SoCs. +config EDAC_QCOM + tristate "QCOM EDAC Controller" + depends on ARCH_QCOM && QCOM_LLCC + help + Support for error detection and correction on the + Qualcomm Technologies, Inc. SoCs. + + This driver reports Single Bit Errors (SBEs) and Double Bit Errors (DBEs). + As of now, it supports error reporting for Last Level Cache Controller (LLCC) + of Tag RAM and Data RAM. + + For debugging issues having to do with stability and overall system + health, you should probably say 'Y' here. + endif # EDAC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index 02b43a7d8c3e..716096d08ea0 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -77,3 +77,4 @@ obj-$(CONFIG_EDAC_ALTERA) += altera_edac.o obj-$(CONFIG_EDAC_SYNOPSYS) += synopsys_edac.o obj-$(CONFIG_EDAC_XGENE) += xgene_edac.o obj-$(CONFIG_EDAC_TI) += ti_edac.o +obj-$(CONFIG_EDAC_QCOM) += qcom_edac.o diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c new file mode 100644 index 000000000000..82bd775124f2 --- /dev/null +++ b/drivers/edac/qcom_edac.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "edac_mc.h" +#include "edac_device.h" + +#define EDAC_LLCC "qcom_llcc" + +#define LLCC_ERP_PANIC_ON_UE 1 + +#define TRP_SYN_REG_CNT 6 +#define DRP_SYN_REG_CNT 8 + +#define LLCC_COMMON_STATUS0 0x0003000c +#define LLCC_LB_CNT_MASK GENMASK(31, 28) +#define LLCC_LB_CNT_SHIFT 28 + +/* Single & double bit syndrome register offsets */ +#define TRP_ECC_SB_ERR_SYN0 0x0002304c +#define TRP_ECC_DB_ERR_SYN0 0x00020370 +#define DRP_ECC_SB_ERR_SYN0 0x0004204c +#define DRP_ECC_DB_ERR_SYN0 0x00042070 + +/* Error register offsets */ +#define TRP_ECC_ERROR_STATUS1 0x00020348 +#define TRP_ECC_ERROR_STATUS0 0x00020344 +#define DRP_ECC_ERROR_STATUS1 0x00042048 +#define DRP_ECC_ERROR_STATUS0 0x00042044 + +/* TRP, DRP interrupt register offsets */ +#define DRP_INTERRUPT_STATUS 0x00041000 +#define TRP_INTERRUPT_0_STATUS 0x00020480 +#define DRP_INTERRUPT_CLEAR 0x00041008 +#define DRP_ECC_ERROR_CNTR_CLEAR 0x00040004 +#define TRP_INTERRUPT_0_CLEAR 0x00020484 +#define TRP_ECC_ERROR_CNTR_CLEAR 0x00020440 + +/* Mask and shift macros */ +#define ECC_DB_ERR_COUNT_MASK GENMASK(4, 0) +#define ECC_DB_ERR_WAYS_MASK GENMASK(31, 16) +#define ECC_DB_ERR_WAYS_SHIFT BIT(4) + +#define ECC_SB_ERR_COUNT_MASK GENMASK(23, 16) +#define ECC_SB_ERR_COUNT_SHIFT BIT(4) +#define ECC_SB_ERR_WAYS_MASK GENMASK(15, 0) + +#define SB_ECC_ERROR BIT(0) +#define DB_ECC_ERROR BIT(1) + +#define DRP_TRP_INT_CLEAR GENMASK(1, 0) +#define DRP_TRP_CNT_CLEAR GENMASK(1, 0) + +/* Config registers offsets*/ +#define DRP_ECC_ERROR_CFG 0x00040000 + +/* Tag RAM, Data RAM interrupt register offsets */ +#define CMN_INTERRUPT_0_ENABLE 0x0003001c +#define CMN_INTERRUPT_2_ENABLE 0x0003003c +#define TRP_INTERRUPT_0_ENABLE 0x00020488 +#define DRP_INTERRUPT_ENABLE 0x0004100c + +#define SB_ERROR_THRESHOLD 0x1 +#define SB_ERROR_THRESHOLD_SHIFT 24 +#define SB_DB_TRP_INTERRUPT_ENABLE 0x3 +#define TRP0_INTERRUPT_ENABLE 0x1 +#define DRP0_INTERRUPT_ENABLE BIT(6) +#define SB_DB_DRP_INTERRUPT_ENABLE 0x3 + +enum { + LLCC_DRAM_CE = 0, + LLCC_DRAM_UE, + LLCC_TRAM_CE, + LLCC_TRAM_UE, +}; + +static const struct llcc_edac_reg_data edac_reg_data[] = { + [LLCC_DRAM_CE] = { + .name = "DRAM Single-bit", + .synd_reg = DRP_ECC_SB_ERR_SYN0, + .count_status_reg = DRP_ECC_ERROR_STATUS1, + .ways_status_reg = DRP_ECC_ERROR_STATUS0, + .reg_cnt = DRP_SYN_REG_CNT, + .count_mask = ECC_SB_ERR_COUNT_MASK, + .ways_mask = ECC_SB_ERR_WAYS_MASK, + .count_shift = ECC_SB_ERR_COUNT_SHIFT, + }, + [LLCC_DRAM_UE] = { + .name = "DRAM Double-bit", + .synd_reg = DRP_ECC_DB_ERR_SYN0, + .count_status_reg = DRP_ECC_ERROR_STATUS1, + .ways_status_reg = DRP_ECC_ERROR_STATUS0, + .reg_cnt = DRP_SYN_REG_CNT, + .count_mask = ECC_DB_ERR_COUNT_MASK, + .ways_mask = ECC_DB_ERR_WAYS_MASK, + .ways_shift = ECC_DB_ERR_WAYS_SHIFT, + }, + [LLCC_TRAM_CE] = { + .name = "TRAM Single-bit", + .synd_reg = TRP_ECC_SB_ERR_SYN0, + .count_status_reg = TRP_ECC_ERROR_STATUS1, + .ways_status_reg = TRP_ECC_ERROR_STATUS0, + .reg_cnt = TRP_SYN_REG_CNT, + .count_mask = ECC_SB_ERR_COUNT_MASK, + .ways_mask = ECC_SB_ERR_WAYS_MASK, + .count_shift = ECC_SB_ERR_COUNT_SHIFT, + }, + [LLCC_TRAM_UE] = { + .name = "TRAM Double-bit", + .synd_reg = TRP_ECC_DB_ERR_SYN0, + .count_status_reg = TRP_ECC_ERROR_STATUS1, + .ways_status_reg = TRP_ECC_ERROR_STATUS0, + .reg_cnt = TRP_SYN_REG_CNT, + .count_mask = ECC_DB_ERR_COUNT_MASK, + .ways_mask = ECC_DB_ERR_WAYS_MASK, + .ways_shift = ECC_DB_ERR_WAYS_SHIFT, + }, +}; + +static int qcom_llcc_core_setup(struct regmap *llcc_bcast_regmap) +{ + u32 sb_err_threshold; + int ret; + + /* + * Configure interrupt enable registers such that Tag, Data RAM related + * interrupts are propagated to interrupt controller for servicing + */ + ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + TRP0_INTERRUPT_ENABLE, + TRP0_INTERRUPT_ENABLE); + if (ret) + return ret; + + ret = regmap_update_bits(llcc_bcast_regmap, TRP_INTERRUPT_0_ENABLE, + SB_DB_TRP_INTERRUPT_ENABLE, + SB_DB_TRP_INTERRUPT_ENABLE); + if (ret) + return ret; + + sb_err_threshold = (SB_ERROR_THRESHOLD << SB_ERROR_THRESHOLD_SHIFT); + ret = regmap_write(llcc_bcast_regmap, DRP_ECC_ERROR_CFG, + sb_err_threshold); + if (ret) + return ret; + + ret = regmap_update_bits(llcc_bcast_regmap, CMN_INTERRUPT_2_ENABLE, + DRP0_INTERRUPT_ENABLE, + DRP0_INTERRUPT_ENABLE); + if (ret) + return ret; + + ret = regmap_write(llcc_bcast_regmap, DRP_INTERRUPT_ENABLE, + SB_DB_DRP_INTERRUPT_ENABLE); + return ret; +} + +/* Clear the error interrupt and counter registers */ +static int +qcom_llcc_clear_error_status(int err_type, struct llcc_drv_data *drv) +{ + int ret = 0; + + switch (err_type) { + case LLCC_DRAM_CE: + case LLCC_DRAM_UE: + ret = regmap_write(drv->bcast_regmap, DRP_INTERRUPT_CLEAR, + DRP_TRP_INT_CLEAR); + if (ret) + return ret; + + ret = regmap_write(drv->bcast_regmap, DRP_ECC_ERROR_CNTR_CLEAR, + DRP_TRP_CNT_CLEAR); + if (ret) + return ret; + break; + case LLCC_TRAM_CE: + case LLCC_TRAM_UE: + ret = regmap_write(drv->bcast_regmap, TRP_INTERRUPT_0_CLEAR, + DRP_TRP_INT_CLEAR); + if (ret) + return ret; + + ret = regmap_write(drv->bcast_regmap, TRP_ECC_ERROR_CNTR_CLEAR, + DRP_TRP_CNT_CLEAR); + if (ret) + return ret; + break; + default: + ret = -EINVAL; + edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n", + err_type); + } + return ret; +} + +/* Dump Syndrome registers data for Tag RAM, Data RAM bit errors*/ +static int +dump_syn_reg_values(struct llcc_drv_data *drv, u32 bank, int err_type) +{ + struct llcc_edac_reg_data reg_data = edac_reg_data[err_type]; + int err_cnt, err_ways, ret, i; + u32 synd_reg, synd_val; + + for (i = 0; i < reg_data.reg_cnt; i++) { + synd_reg = reg_data.synd_reg + (i * 4); + ret = regmap_read(drv->regmap, drv->offsets[bank] + synd_reg, + &synd_val); + if (ret) + goto clear; + + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: ECC_SYN%d: 0x%8x\n", + reg_data.name, i, synd_val); + } + + ret = regmap_read(drv->regmap, + drv->offsets[bank] + reg_data.count_status_reg, + &err_cnt); + if (ret) + goto clear; + + err_cnt &= reg_data.count_mask; + err_cnt >>= reg_data.count_shift; + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error count: 0x%4x\n", + reg_data.name, err_cnt); + + ret = regmap_read(drv->regmap, + drv->offsets[bank] + reg_data.ways_status_reg, + &err_ways); + if (ret) + goto clear; + + err_ways &= reg_data.ways_mask; + err_ways >>= reg_data.ways_shift; + + edac_printk(KERN_CRIT, EDAC_LLCC, "%s: Error ways: 0x%4x\n", + reg_data.name, err_ways); + +clear: + return qcom_llcc_clear_error_status(err_type, drv); +} + +static int +dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) +{ + struct llcc_drv_data *drv = edev_ctl->pvt_info; + int ret; + + ret = dump_syn_reg_values(drv, bank, err_type); + if (ret) + return ret; + + switch (err_type) { + case LLCC_DRAM_CE: + edac_device_handle_ce(edev_ctl, 0, bank, + "LLCC Data RAM correctable Error"); + break; + case LLCC_DRAM_UE: + edac_device_handle_ue(edev_ctl, 0, bank, + "LLCC Data RAM uncorrectable Error"); + break; + case LLCC_TRAM_CE: + edac_device_handle_ce(edev_ctl, 0, bank, + "LLCC Tag RAM correctable Error"); + break; + case LLCC_TRAM_UE: + edac_device_handle_ue(edev_ctl, 0, bank, + "LLCC Tag RAM uncorrectable Error"); + break; + default: + ret = -EINVAL; + edac_printk(KERN_CRIT, EDAC_LLCC, "Unexpected error type: %d\n", + err_type); + } + + return ret; +} + +static irqreturn_t +llcc_ecc_irq_handler(int irq, void *edev_ctl) +{ + struct edac_device_ctl_info *edac_dev_ctl = edev_ctl; + struct llcc_drv_data *drv = edac_dev_ctl->pvt_info; + irqreturn_t irq_rc = IRQ_NONE; + u32 drp_error, trp_error, i; + bool irq_handled; + int ret; + + /* Iterate over the banks and look for Tag RAM or Data RAM errors */ + for (i = 0; i < drv->num_banks; i++) { + ret = regmap_read(drv->regmap, + drv->offsets[i] + DRP_INTERRUPT_STATUS, + &drp_error); + + if (!ret && (drp_error & SB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Single Bit Error detected in Data RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_DRAM_CE, i); + } else if (!ret && (drp_error & DB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Double Bit Error detected in Data RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_DRAM_UE, i); + } + if (!ret) + irq_handled = true; + + ret = regmap_read(drv->regmap, + drv->offsets[i] + TRP_INTERRUPT_0_STATUS, + &trp_error); + + if (!ret && (trp_error & SB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Single Bit Error detected in Tag RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_TRAM_CE, i); + } else if (!ret && (trp_error & DB_ECC_ERROR)) { + edac_printk(KERN_CRIT, EDAC_LLCC, + "Double Bit Error detected in Tag RAM\n"); + ret = dump_syn_reg(edev_ctl, LLCC_TRAM_UE, i); + } + if (!ret) + irq_handled = true; + } + + if (irq_handled) + irq_rc = IRQ_HANDLED; + + return irq_rc; +} + +static int qcom_llcc_edac_probe(struct platform_device *pdev) +{ + struct llcc_drv_data *llcc_driv_data = pdev->dev.platform_data; + struct edac_device_ctl_info *edev_ctl; + struct device *dev = &pdev->dev; + int ecc_irq; + int rc; + + rc = qcom_llcc_core_setup(llcc_driv_data->bcast_regmap); + if (rc) + return rc; + + /* Allocate edac control info */ + edev_ctl = edac_device_alloc_ctl_info(0, "qcom-llcc", 1, "bank", + llcc_driv_data->num_banks, 1, + NULL, 0, + edac_device_alloc_index()); + + if (!edev_ctl) + return -ENOMEM; + + edev_ctl->dev = dev; + edev_ctl->mod_name = dev_name(dev); + edev_ctl->dev_name = dev_name(dev); + edev_ctl->ctl_name = "llcc"; + edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE; + edev_ctl->pvt_info = llcc_driv_data; + + rc = edac_device_add_device(edev_ctl); + if (rc) + goto out_mem; + + platform_set_drvdata(pdev, edev_ctl); + + /* Request for ecc irq */ + ecc_irq = llcc_driv_data->ecc_irq; + if (ecc_irq < 0) { + rc = -ENODEV; + goto out_dev; + } + rc = devm_request_irq(dev, ecc_irq, llcc_ecc_irq_handler, + IRQF_TRIGGER_HIGH, "llcc_ecc", edev_ctl); + if (rc) + goto out_dev; + + return rc; + +out_dev: + edac_device_del_device(edev_ctl->dev); +out_mem: + edac_device_free_ctl_info(edev_ctl); + + return rc; +} + +static int qcom_llcc_edac_remove(struct platform_device *pdev) +{ + struct edac_device_ctl_info *edev_ctl = dev_get_drvdata(&pdev->dev); + + edac_device_del_device(edev_ctl->dev); + edac_device_free_ctl_info(edev_ctl); + + return 0; +} + +static struct platform_driver qcom_llcc_edac_driver = { + .probe = qcom_llcc_edac_probe, + .remove = qcom_llcc_edac_remove, + .driver = { + .name = "qcom_llcc_edac", + }, +}; +module_platform_driver(qcom_llcc_edac_driver); + +MODULE_DESCRIPTION("QCOM EDAC driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 2e4b34d2617e..69c285b1c990 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -93,6 +93,30 @@ struct llcc_drv_data { int ecc_irq; }; +/** + * llcc_edac_reg_data - llcc edac registers data for each error type + * @name: Name of the error + * @synd_reg: Syndrome register address + * @count_status_reg: Status register address to read the error count + * @ways_status_reg: Status register address to read the error ways + * @reg_cnt: Number of registers + * @count_mask: Mask value to get the error count + * @ways_mask: Mask value to get the error ways + * @count_shift: Shift value to get the error count + * @ways_shift: Shift value to get the error ways + */ +struct llcc_edac_reg_data { + char *name; + u64 synd_reg; + u64 count_status_reg; + u64 ways_status_reg; + u32 reg_cnt; + u32 count_mask; + u32 ways_mask; + u8 count_shift; + u8 ways_shift; +}; + #if IS_ENABLED(CONFIG_QCOM_LLCC) /** * llcc_slice_getd - get llcc slice descriptor -- cgit v1.2.3-71-gd317 From f4926ef76e23e291fcd38bd107c0a9bb8e2db505 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 18 May 2018 15:47:50 -0700 Subject: soc: qcom: geni: Make version macros simpler This macro doesn't work, because it hides a local variable inside of the macro to hold the version and that variable name is called 'ver' and 'version' sometimes. Let's change this to be more explicit. Introduce three macros for the major, minor, and step of the version, and require callers to pass the version in to get the part of the version out. This way we don't hide local variables inside macros and things are less evil overall. Cc: Karthikeyan Ramasubramanian Cc: Sagar Dharia Cc: Girish Mahadevan Signed-off-by: Stephen Boyd Reviewed-by: Douglas Anderson Reviewed-by: Bjorn Andersson Signed-off-by: Andy Gross --- include/linux/qcom-geni-se.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index 5d6144977828..3bcd67fd5548 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -225,19 +225,14 @@ struct geni_se { #define HW_VER_MINOR_SHFT 16 #define HW_VER_STEP_MASK GENMASK(15, 0) +#define GENI_SE_VERSION_MAJOR(ver) ((ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT) +#define GENI_SE_VERSION_MINOR(ver) ((ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT) +#define GENI_SE_VERSION_STEP(ver) (ver & HW_VER_STEP_MASK) + #if IS_ENABLED(CONFIG_QCOM_GENI_SE) u32 geni_se_get_qup_hw_version(struct geni_se *se); -#define geni_se_get_wrapper_version(se, major, minor, step) do { \ - u32 ver; \ -\ - ver = geni_se_get_qup_hw_version(se); \ - major = (ver & HW_VER_MAJOR_MASK) >> HW_VER_MAJOR_SHFT; \ - minor = (ver & HW_VER_MINOR_MASK) >> HW_VER_MINOR_SHFT; \ - step = version & HW_VER_STEP_MASK; \ -} while (0) - /** * geni_se_read_proto() - Read the protocol configured for a serial engine * @se: Pointer to the concerned serial engine. -- cgit v1.2.3-71-gd317 From 59104f239b9ed6cf3986e4228173ff2f4c95039e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Thu, 26 Jul 2018 02:37:49 +0000 Subject: drm: shmobile: convert to SPDX identifiers Signed-off-by: Kuninori Morimoto Acked-by: Laurent Pinchart Reviewed-by: Simon Horman Signed-off-by: Laurent Pinchart --- drivers/gpu/drm/shmobile/Kconfig | 1 + drivers/gpu/drm/shmobile/shmob_drm_backlight.c | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_backlight.h | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_crtc.c | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_crtc.h | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_drv.c | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_drv.h | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_kms.c | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_kms.h | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_plane.c | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_plane.h | 6 +----- drivers/gpu/drm/shmobile/shmob_drm_regs.h | 6 +----- include/linux/platform_data/shmob_drm.h | 6 +----- 13 files changed, 13 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/shmobile/Kconfig b/drivers/gpu/drm/shmobile/Kconfig index 0426d66660d1..61bbe8e8bcc5 100644 --- a/drivers/gpu/drm/shmobile/Kconfig +++ b/drivers/gpu/drm/shmobile/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 config DRM_SHMOBILE tristate "DRM Support for SH Mobile" depends on DRM && ARM diff --git a/drivers/gpu/drm/shmobile/shmob_drm_backlight.c b/drivers/gpu/drm/shmobile/shmob_drm_backlight.c index 33dd41afea0e..f6628a5ee95f 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_backlight.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_backlight.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * shmob_drm_backlight.c -- SH Mobile DRM Backlight * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include diff --git a/drivers/gpu/drm/shmobile/shmob_drm_backlight.h b/drivers/gpu/drm/shmobile/shmob_drm_backlight.h index bac719ecc301..d9abb7a60be5 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_backlight.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_backlight.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm_backlight.h -- SH Mobile DRM Backlight * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_BACKLIGHT_H__ diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c index fc66167b0641..499b5fdb869f 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * shmob_drm_crtc.c -- SH Mobile DRM CRTCs * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.h b/drivers/gpu/drm/shmobile/shmob_drm_crtc.h index c11f421737dc..9ca6920641d8 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm_crtc.h -- SH Mobile DRM CRTCs * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_CRTC_H__ diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c index 592572554eb0..6ececad6f845 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * shmob_drm_drv.c -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.h b/drivers/gpu/drm/shmobile/shmob_drm_drv.h index 088a6e55fa29..80dc4b1020aa 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_drv.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_DRV_H__ diff --git a/drivers/gpu/drm/shmobile/shmob_drm_kms.c b/drivers/gpu/drm/shmobile/shmob_drm_kms.c index 447638581c08..a17268444c6d 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_kms.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_kms.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * shmob_drm_kms.c -- SH Mobile DRM Mode Setting * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include diff --git a/drivers/gpu/drm/shmobile/shmob_drm_kms.h b/drivers/gpu/drm/shmobile/shmob_drm_kms.h index 753e2817dc2c..6ec2b732bb94 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_kms.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_kms.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm_kms.h -- SH Mobile DRM Mode Setting * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_KMS_H__ diff --git a/drivers/gpu/drm/shmobile/shmob_drm_plane.c b/drivers/gpu/drm/shmobile/shmob_drm_plane.c index 1d0359f713ca..1d1ee5e51351 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_plane.c +++ b/drivers/gpu/drm/shmobile/shmob_drm_plane.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * shmob_drm_plane.c -- SH Mobile DRM Planes * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #include diff --git a/drivers/gpu/drm/shmobile/shmob_drm_plane.h b/drivers/gpu/drm/shmobile/shmob_drm_plane.h index a58cc1fc3240..bae67cc8c628 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_plane.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_plane.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm_plane.h -- SH Mobile DRM Planes * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_PLANE_H__ diff --git a/drivers/gpu/drm/shmobile/shmob_drm_regs.h b/drivers/gpu/drm/shmobile/shmob_drm_regs.h index ea17d4415b9e..9eb0b3d01df8 100644 --- a/drivers/gpu/drm/shmobile/shmob_drm_regs.h +++ b/drivers/gpu/drm/shmobile/shmob_drm_regs.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm_regs.h -- SH Mobile DRM registers * * Copyright (C) 2012 Renesas Electronics Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_REGS_H__ diff --git a/include/linux/platform_data/shmob_drm.h b/include/linux/platform_data/shmob_drm.h index ee495d707f17..fe815d7d9f58 100644 --- a/include/linux/platform_data/shmob_drm.h +++ b/include/linux/platform_data/shmob_drm.h @@ -1,14 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * shmob_drm.h -- SH Mobile DRM driver * * Copyright (C) 2012 Renesas Corporation * * Laurent Pinchart (laurent.pinchart@ideasonboard.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __SHMOB_DRM_H__ -- cgit v1.2.3-71-gd317 From 10c63443b74d1ef5c1b3bb104a9e6e40dc2437ff Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 30 Aug 2018 14:54:03 +0200 Subject: Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE" This reverts commit 7acece71a517cad83a0842a94d94c13f271b680c. Signed-off-by: Geert Uytterhoeven Acked-by: Chris Brandt Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/sh-sci.c | 31 +++++++++++++++++++++++++++++++ include/linux/serial_sci.h | 1 + 2 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ac4424bf6b13..5d42c9a63001 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -291,6 +291,33 @@ static const struct sci_port_params sci_port_params[SCIx_NR_REGTYPES] = { .error_clear = SCIF_ERROR_CLEAR, }, + /* + * The "SCIFA" that is in RZ/T and RZ/A2. + * It looks like a normal SCIF with FIFO data, but with a + * compressed address space. Also, the break out of interrupts + * are different: ERI/BRI, RXI, TXI, TEI, DRI. + */ + [SCIx_RZ_SCIFA_REGTYPE] = { + .regs = { + [SCSMR] = { 0x00, 16 }, + [SCBRR] = { 0x02, 8 }, + [SCSCR] = { 0x04, 16 }, + [SCxTDR] = { 0x06, 8 }, + [SCxSR] = { 0x08, 16 }, + [SCxRDR] = { 0x0A, 8 }, + [SCFCR] = { 0x0C, 16 }, + [SCFDR] = { 0x0E, 16 }, + [SCSPTR] = { 0x10, 16 }, + [SCLSR] = { 0x12, 16 }, + }, + .fifosize = 16, + .overrun_reg = SCLSR, + .overrun_mask = SCLSR_ORER, + .sampling_rate_mask = SCI_SR(32), + .error_mask = SCIF_DEFAULT_ERROR_MASK, + .error_clear = SCIF_ERROR_CLEAR, + }, + /* * Common SH-3 SCIF definitions. */ @@ -3110,6 +3137,10 @@ static const struct of_device_id of_sci_match[] = { .compatible = "renesas,scif-r7s72100", .data = SCI_OF_DATA(PORT_SCIF, SCIx_SH2_SCIF_FIFODATA_REGTYPE), }, + { + .compatible = "renesas,scif-r7s9210", + .data = SCI_OF_DATA(PORT_SCIF, SCIx_RZ_SCIFA_REGTYPE), + }, /* Family-specific types */ { .compatible = "renesas,rcar-gen1-scif", diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index c0e795d95477..1c89611e0e06 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -36,6 +36,7 @@ enum { SCIx_SH4_SCIF_FIFODATA_REGTYPE, SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, + SCIx_RZ_SCIFA_REGTYPE, SCIx_NR_REGTYPES, }; -- cgit v1.2.3-71-gd317 From b1078c355d76769b5ddefc67d143fbd9b6e52c05 Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Thu, 20 Sep 2018 13:41:52 +0200 Subject: of: base: Introduce of_alias_get_alias_list() to check alias IDs The function travels the lookup table to record alias ids for the given device match structures and alias stem. This function will be used by serial drivers to check if requested alias is allocated or free to use. Signed-off-by: Michal Simek Reviewed-by: Rob Herring Signed-off-by: Greg Kroah-Hartman --- drivers/of/base.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/of.h | 10 ++++++++++ 2 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 74eaedd5b860..33011b88ed3f 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) "OF: " fmt +#include #include #include #include @@ -1942,6 +1943,57 @@ int of_alias_get_id(struct device_node *np, const char *stem) } EXPORT_SYMBOL_GPL(of_alias_get_id); +/** + * of_alias_get_alias_list - Get alias list for the given device driver + * @matches: Array of OF device match structures to search in + * @stem: Alias stem of the given device_node + * @bitmap: Bitmap field pointer + * @nbits: Maximum number of alias ID which can be recorded it bitmap + * + * The function travels the lookup table to record alias ids for the given + * device match structures and alias stem. + * + * Return: 0 or -ENOSYS when !CONFIG_OF + */ +int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits) +{ + struct alias_prop *app; + + /* Zero bitmap field to make sure that all the time it is clean */ + bitmap_zero(bitmap, nbits); + + mutex_lock(&of_mutex); + pr_debug("%s: Looking for stem: %s\n", __func__, stem); + list_for_each_entry(app, &aliases_lookup, link) { + pr_debug("%s: stem: %s, id: %d\n", + __func__, app->stem, app->id); + + if (strcmp(app->stem, stem) != 0) { + pr_debug("%s: stem comparison doesn't passed %s\n", + __func__, app->stem); + continue; + } + + if (app->id >= nbits) { + pr_debug("%s: ID %d greater then bitmap field %d\n", + __func__, app->id, nbits); + continue; + } + + if (of_match_node(matches, app->np)) { + pr_debug("%s: Allocated ID %d\n", __func__, app->id); + set_bit(app->id, bitmap); + } + /* Alias exist but it not compatible with matches */ + } + mutex_unlock(&of_mutex); + + return 0; +} +EXPORT_SYMBOL_GPL(of_alias_get_alias_list); + /** * of_alias_get_highest_id - Get highest alias id for the given stem * @stem: Alias stem to be examined diff --git a/include/linux/of.h b/include/linux/of.h index 99b0ebf49632..d51457b40725 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -392,6 +392,9 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); +extern int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -893,6 +896,13 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } +static inline int of_alias_get_alias_list(const struct of_device_id *matches, + const char *stem, unsigned long *bitmap, + unsigned int nbits) +{ + return -ENOSYS; +} + static inline int of_machine_is_compatible(const char *compat) { return 0; -- cgit v1.2.3-71-gd317 From 26683316c92ab2d1b330a3a38548328c9b136ad1 Mon Sep 17 00:00:00 2001 From: Janusz Krzysztofik Date: Mon, 10 Sep 2018 19:47:22 +0200 Subject: ARM: OMAP1: ams-delta-fiq: Use Instead of defining symbols already defined in linux/platform_data/gpio-omap.h, use that header file. Since we include the header into an assembler code, prevent C only bits from being read in. Signed-off-by: Janusz Krzysztofik Signed-off-by: Tony Lindgren --- arch/arm/mach-omap1/ams-delta-fiq-handler.S | 12 +++--------- include/linux/platform_data/gpio-omap.h | 4 ++++ 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S index ddc27638ba2a..e3faa0274b56 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S +++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S @@ -15,6 +15,7 @@ #include #include +#include #include #include @@ -24,17 +25,10 @@ #include "soc.h" /* - * GPIO related definitions, copied from arch/arm/plat-omap/gpio.c. - * Unfortunately, those were not placed in a separate header file. + * OMAP1510 GPIO related symbol copied from arch/arm/mach-omap1/gpio15xx.c. + * Unfortunately, it was not placed in a separate header file. */ #define OMAP1510_GPIO_BASE 0xFFFCE000 -#define OMAP1510_GPIO_DATA_INPUT 0x00 -#define OMAP1510_GPIO_DATA_OUTPUT 0x04 -#define OMAP1510_GPIO_DIR_CONTROL 0x08 -#define OMAP1510_GPIO_INT_CONTROL 0x0c -#define OMAP1510_GPIO_INT_MASK 0x10 -#define OMAP1510_GPIO_INT_STATUS 0x14 -#define OMAP1510_GPIO_PIN_CONTROL 0x18 /* GPIO register bitmasks */ #define KEYBRD_DATA_MASK (0x1 << AMS_DELTA_GPIO_PIN_KEYBRD_DATA) diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8612855691b2..ed071f76b642 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -24,8 +24,10 @@ #ifndef __ASM_ARCH_OMAP_GPIO_H #define __ASM_ARCH_OMAP_GPIO_H +#ifndef __ASSEMBLER__ #include #include +#endif #define OMAP1_MPUIO_BASE 0xfffb5000 @@ -157,6 +159,7 @@ #define OMAP_MPUIO(nr) (OMAP_MAX_GPIO_LINES + (nr)) #define OMAP_GPIO_IS_MPUIO(nr) ((nr) >= OMAP_MAX_GPIO_LINES) +#ifndef __ASSEMBLER__ struct omap_gpio_reg_offs { u16 revision; u16 direction; @@ -215,5 +218,6 @@ static inline void omap2_gpio_resume_after_idle(void) { } #endif +#endif /* __ASSEMBLER__ */ #endif -- cgit v1.2.3-71-gd317 From 1cc33161a83d20b5462b1e93f95d3ce6388079ee Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Mon, 20 Aug 2018 10:12:47 +0530 Subject: uprobes: Support SDT markers having reference count (semaphore) Userspace Statically Defined Tracepoints[1] are dtrace style markers inside userspace applications. Applications like PostgreSQL, MySQL, Pthread, Perl, Python, Java, Ruby, Node.js, libvirt, QEMU, glib etc have these markers embedded in them. These markers are added by developer at important places in the code. Each marker source expands to a single nop instruction in the compiled code but there may be additional overhead for computing the marker arguments which expands to couple of instructions. In case the overhead is more, execution of it can be omitted by runtime if() condition when no one is tracing on the marker: if (reference_counter > 0) { Execute marker instructions; } Default value of reference counter is 0. Tracer has to increment the reference counter before tracing on a marker and decrement it when done with the tracing. Implement the reference counter logic in core uprobe. User will be able to use it from trace_uprobe as well as from kernel module. New trace_uprobe definition with reference counter will now be: :[(ref_ctr_offset)] where ref_ctr_offset is an optional field. For kernel module, new variant of uprobe_register() has been introduced: uprobe_register_refctr(inode, offset, ref_ctr_offset, consumer) No new variant for uprobe_unregister() because it's assumed to have only one reference counter for one uprobe. [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation Note: 'reference counter' is called as 'semaphore' in original Dtrace (or Systemtap, bcc and even in ELF) documentation and code. But the term 'semaphore' is misleading in this context. This is just a counter used to hold number of tracers tracing on a marker. This is not really used for any synchronization. So we are calling it a 'reference counter' in kernel / perf code. Link: http://lkml.kernel.org/r/20180820044250.11659-2-ravi.bangoria@linux.ibm.com Reviewed-by: Masami Hiramatsu [Only trace_uprobe.c] Reviewed-by: Oleg Nesterov Reviewed-by: Song Liu Tested-by: Song Liu Signed-off-by: Ravi Bangoria Signed-off-by: Steven Rostedt (VMware) --- include/linux/uprobes.h | 5 + kernel/events/uprobes.c | 259 ++++++++++++++++++++++++++++++++++++++++++-- kernel/trace/trace.c | 2 +- kernel/trace/trace_uprobe.c | 38 ++++++- 4 files changed, 293 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index bb9d2084af03..103a48a48872 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -123,6 +123,7 @@ extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs); extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs); extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t); extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); +extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc); extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool); extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc); extern int uprobe_mmap(struct vm_area_struct *vma); @@ -160,6 +161,10 @@ uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return -ENOSYS; } +static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) +{ + return -ENOSYS; +} static inline int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 3207a4d26849..934feb39f6be 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -73,6 +73,7 @@ struct uprobe { struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; + loff_t ref_ctr_offset; unsigned long flags; /* @@ -88,6 +89,15 @@ struct uprobe { struct arch_uprobe arch; }; +struct delayed_uprobe { + struct list_head list; + struct uprobe *uprobe; + struct mm_struct *mm; +}; + +static DEFINE_MUTEX(delayed_uprobe_lock); +static LIST_HEAD(delayed_uprobe_list); + /* * Execute out of line area: anonymous executable mapping installed * by the probed task to execute the copy of the original instruction @@ -282,6 +292,166 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t return 1; } +static struct delayed_uprobe * +delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct delayed_uprobe *du; + + list_for_each_entry(du, &delayed_uprobe_list, list) + if (du->uprobe == uprobe && du->mm == mm) + return du; + return NULL; +} + +static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct delayed_uprobe *du; + + if (delayed_uprobe_check(uprobe, mm)) + return 0; + + du = kzalloc(sizeof(*du), GFP_KERNEL); + if (!du) + return -ENOMEM; + + du->uprobe = uprobe; + du->mm = mm; + list_add(&du->list, &delayed_uprobe_list); + return 0; +} + +static void delayed_uprobe_delete(struct delayed_uprobe *du) +{ + if (WARN_ON(!du)) + return; + list_del(&du->list); + kfree(du); +} + +static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct list_head *pos, *q; + struct delayed_uprobe *du; + + if (!uprobe && !mm) + return; + + list_for_each_safe(pos, q, &delayed_uprobe_list) { + du = list_entry(pos, struct delayed_uprobe, list); + + if (uprobe && du->uprobe != uprobe) + continue; + if (mm && du->mm != mm) + continue; + + delayed_uprobe_delete(du); + } +} + +static bool valid_ref_ctr_vma(struct uprobe *uprobe, + struct vm_area_struct *vma) +{ + unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset); + + return uprobe->ref_ctr_offset && + vma->vm_file && + file_inode(vma->vm_file) == uprobe->inode && + (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && + vma->vm_start <= vaddr && + vma->vm_end > vaddr; +} + +static struct vm_area_struct * +find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) +{ + struct vm_area_struct *tmp; + + for (tmp = mm->mmap; tmp; tmp = tmp->vm_next) + if (valid_ref_ctr_vma(uprobe, tmp)) + return tmp; + + return NULL; +} + +static int +__update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) +{ + void *kaddr; + struct page *page; + struct vm_area_struct *vma; + int ret; + short *ptr; + + if (!vaddr || !d) + return -EINVAL; + + ret = get_user_pages_remote(NULL, mm, vaddr, 1, + FOLL_WRITE, &page, &vma, NULL); + if (unlikely(ret <= 0)) { + /* + * We are asking for 1 page. If get_user_pages_remote() fails, + * it may return 0, in that case we have to return error. + */ + return ret == 0 ? -EBUSY : ret; + } + + kaddr = kmap_atomic(page); + ptr = kaddr + (vaddr & ~PAGE_MASK); + + if (unlikely(*ptr + d < 0)) { + pr_warn("ref_ctr going negative. vaddr: 0x%lx, " + "curr val: %d, delta: %d\n", vaddr, *ptr, d); + ret = -EINVAL; + goto out; + } + + *ptr += d; + ret = 0; +out: + kunmap_atomic(kaddr); + put_page(page); + return ret; +} + +static void update_ref_ctr_warn(struct uprobe *uprobe, + struct mm_struct *mm, short d) +{ + pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " + "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", + d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, + (unsigned long long) uprobe->offset, + (unsigned long long) uprobe->ref_ctr_offset, mm); +} + +static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, + short d) +{ + struct vm_area_struct *rc_vma; + unsigned long rc_vaddr; + int ret = 0; + + rc_vma = find_ref_ctr_vma(uprobe, mm); + + if (rc_vma) { + rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset); + ret = __update_ref_ctr(mm, rc_vaddr, d); + if (ret) + update_ref_ctr_warn(uprobe, mm, d); + + if (d > 0) + return ret; + } + + mutex_lock(&delayed_uprobe_lock); + if (d > 0) + ret = delayed_uprobe_add(uprobe, mm); + else + delayed_uprobe_remove(uprobe, mm); + mutex_unlock(&delayed_uprobe_lock); + + return ret; +} + /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for @@ -302,9 +472,13 @@ static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { + struct uprobe *uprobe; struct page *old_page, *new_page; struct vm_area_struct *vma; - int ret; + int ret, is_register, ref_ctr_updated = 0; + + is_register = is_swbp_insn(&opcode); + uprobe = container_of(auprobe, struct uprobe, arch); retry: /* Read the page with vaddr into memory */ @@ -317,6 +491,15 @@ retry: if (ret <= 0) goto put_old; + /* We are going to replace instruction, update ref_ctr. */ + if (!ref_ctr_updated && uprobe->ref_ctr_offset) { + ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); + if (ret) + goto put_old; + + ref_ctr_updated = 1; + } + ret = anon_vma_prepare(vma); if (ret) goto put_old; @@ -337,6 +520,11 @@ put_old: if (unlikely(ret == -EAGAIN)) goto retry; + + /* Revert back reference counter if instruction update failed. */ + if (ret && is_register && ref_ctr_updated) + update_ref_ctr(uprobe, mm, -1); + return ret; } @@ -378,8 +566,15 @@ static struct uprobe *get_uprobe(struct uprobe *uprobe) static void put_uprobe(struct uprobe *uprobe) { - if (atomic_dec_and_test(&uprobe->ref)) + if (atomic_dec_and_test(&uprobe->ref)) { + /* + * If application munmap(exec_vma) before uprobe_unregister() + * gets called, we don't get a chance to remove uprobe from + * delayed_uprobe_list from remove_breakpoint(). Do it here. + */ + delayed_uprobe_remove(uprobe, NULL); kfree(uprobe); + } } static int match_uprobe(struct uprobe *l, struct uprobe *r) @@ -484,7 +679,8 @@ static struct uprobe *insert_uprobe(struct uprobe *uprobe) return u; } -static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) +static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, + loff_t ref_ctr_offset) { struct uprobe *uprobe, *cur_uprobe; @@ -494,6 +690,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = inode; uprobe->offset = offset; + uprobe->ref_ctr_offset = ref_ctr_offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); @@ -895,7 +1092,7 @@ EXPORT_SYMBOL_GPL(uprobe_unregister); * else return 0 (success) */ static int __uprobe_register(struct inode *inode, loff_t offset, - struct uprobe_consumer *uc) + loff_t ref_ctr_offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; @@ -912,7 +1109,7 @@ static int __uprobe_register(struct inode *inode, loff_t offset, return -EINVAL; retry: - uprobe = alloc_uprobe(inode, offset); + uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (!uprobe) return -ENOMEM; /* @@ -938,10 +1135,17 @@ static int __uprobe_register(struct inode *inode, loff_t offset, int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { - return __uprobe_register(inode, offset, uc); + return __uprobe_register(inode, offset, 0, uc); } EXPORT_SYMBOL_GPL(uprobe_register); +int uprobe_register_refctr(struct inode *inode, loff_t offset, + loff_t ref_ctr_offset, struct uprobe_consumer *uc) +{ + return __uprobe_register(inode, offset, ref_ctr_offset, uc); +} +EXPORT_SYMBOL_GPL(uprobe_register_refctr); + /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. @@ -1060,6 +1264,35 @@ static void build_probe_list(struct inode *inode, spin_unlock(&uprobes_treelock); } +/* @vma contains reference counter, not the probed instruction. */ +static int delayed_ref_ctr_inc(struct vm_area_struct *vma) +{ + struct list_head *pos, *q; + struct delayed_uprobe *du; + unsigned long vaddr; + int ret = 0, err = 0; + + mutex_lock(&delayed_uprobe_lock); + list_for_each_safe(pos, q, &delayed_uprobe_list) { + du = list_entry(pos, struct delayed_uprobe, list); + + if (du->mm != vma->vm_mm || + !valid_ref_ctr_vma(du->uprobe, vma)) + continue; + + vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset); + ret = __update_ref_ctr(vma->vm_mm, vaddr, 1); + if (ret) { + update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1); + if (!err) + err = ret; + } + delayed_uprobe_delete(du); + } + mutex_unlock(&delayed_uprobe_lock); + return err; +} + /* * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * @@ -1072,7 +1305,15 @@ int uprobe_mmap(struct vm_area_struct *vma) struct uprobe *uprobe, *u; struct inode *inode; - if (no_uprobe_events() || !valid_vma(vma, true)) + if (no_uprobe_events()) + return 0; + + if (vma->vm_file && + (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && + test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags)) + delayed_ref_ctr_inc(vma); + + if (!valid_vma(vma, true)) return 0; inode = file_inode(vma->vm_file); @@ -1246,6 +1487,10 @@ void uprobe_clear_state(struct mm_struct *mm) { struct xol_area *area = mm->uprobes_state.xol_area; + mutex_lock(&delayed_uprobe_lock); + delayed_uprobe_remove(NULL, mm); + mutex_unlock(&delayed_uprobe_lock); + if (!area) return; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bf6f1d70484d..147be8523560 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4621,7 +4621,7 @@ static const char readme_msg[] = "place (kretprobe): [:][+]|\n" #endif #ifdef CONFIG_UPROBE_EVENTS - "\t place: :\n" + " place (uprobe): :[(ref_ctr_offset)]\n" #endif "\t args: =fetcharg[:type]\n" "\t fetcharg: %, @
, @[+|-],\n" diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e696667da29a..7b85172beab6 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -47,6 +47,7 @@ struct trace_uprobe { struct inode *inode; char *filename; unsigned long offset; + unsigned long ref_ctr_offset; unsigned long nhit; struct trace_probe tp; }; @@ -352,10 +353,10 @@ end: static int create_trace_uprobe(int argc, char **argv) { struct trace_uprobe *tu; - char *arg, *event, *group, *filename; + char *arg, *event, *group, *filename, *rctr, *rctr_end; char buf[MAX_EVENT_NAME_LEN]; struct path path; - unsigned long offset; + unsigned long offset, ref_ctr_offset; bool is_delete, is_return; int i, ret; @@ -364,6 +365,7 @@ static int create_trace_uprobe(int argc, char **argv) is_return = false; event = NULL; group = NULL; + ref_ctr_offset = 0; /* argc must be >= 1 */ if (argv[0][0] == '-') @@ -438,6 +440,26 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } + /* Parse reference counter offset if specified. */ + rctr = strchr(arg, '('); + if (rctr) { + rctr_end = strchr(rctr, ')'); + if (rctr > rctr_end || *(rctr_end + 1) != 0) { + ret = -EINVAL; + pr_info("Invalid reference counter offset.\n"); + goto fail_address_parse; + } + + *rctr++ = '\0'; + *rctr_end = '\0'; + ret = kstrtoul(rctr, 0, &ref_ctr_offset); + if (ret) { + pr_info("Invalid reference counter offset.\n"); + goto fail_address_parse; + } + } + + /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) goto fail_address_parse; @@ -472,6 +494,7 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } tu->offset = offset; + tu->ref_ctr_offset = ref_ctr_offset; tu->path = path; tu->filename = kstrdup(filename, GFP_KERNEL); @@ -590,6 +613,9 @@ static int probes_seq_show(struct seq_file *m, void *v) trace_event_name(&tu->tp.call), tu->filename, (int)(sizeof(void *) * 2), tu->offset); + if (tu->ref_ctr_offset) + seq_printf(m, "(0x%lx)", tu->ref_ctr_offset); + for (i = 0; i < tu->tp.nr_args; i++) seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm); @@ -905,7 +931,13 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, tu->consumer.filter = filter; tu->inode = d_real_inode(tu->path.dentry); - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + if (tu->ref_ctr_offset) { + ret = uprobe_register_refctr(tu->inode, tu->offset, + tu->ref_ctr_offset, &tu->consumer); + } else { + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + } + if (ret) goto err_buffer; -- cgit v1.2.3-71-gd317 From 463659a08d7999d5461fa45b35b17686189a70ca Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 13 Sep 2018 07:47:29 -0400 Subject: media: hdmi.h: rename ADOBE_RGB to OPRGB and ADOBE_YCC to OPYCC These names have been renamed in the CTA-861 standard due to trademark issues. Replace them here as well so they are in sync with the standard. Signed-off-by: Hans Verkuil Cc: stable@vger.kernel.org Acked-by: Daniel Vetter Signed-off-by: Mauro Carvalho Chehab --- drivers/media/i2c/adv7511.c | 4 ++-- drivers/media/v4l2-core/v4l2-dv-timings.c | 4 ++-- drivers/video/hdmi.c | 8 ++++---- include/linux/hdmi.h | 4 ++-- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c index a1f73d998495..f3899cc84e27 100644 --- a/drivers/media/i2c/adv7511.c +++ b/drivers/media/i2c/adv7511.c @@ -1357,8 +1357,8 @@ static int adv7511_set_fmt(struct v4l2_subdev *sd, switch (format->format.colorspace) { case V4L2_COLORSPACE_OPRGB: c = HDMI_COLORIMETRY_EXTENDED; - ec = y ? HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601 : - HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB; + ec = y ? HDMI_EXTENDED_COLORIMETRY_OPYCC_601 : + HDMI_EXTENDED_COLORIMETRY_OPRGB; break; case V4L2_COLORSPACE_SMPTE170M: c = y ? HDMI_COLORIMETRY_ITU_601 : HDMI_COLORIMETRY_NONE; diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index 19aabd1fcd2b..4f23e939ead0 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -877,7 +877,7 @@ v4l2_hdmi_rx_colorimetry(const struct hdmi_avi_infoframe *avi, switch (avi->colorimetry) { case HDMI_COLORIMETRY_EXTENDED: switch (avi->extended_colorimetry) { - case HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB: + case HDMI_EXTENDED_COLORIMETRY_OPRGB: c.colorspace = V4L2_COLORSPACE_OPRGB; c.xfer_func = V4L2_XFER_FUNC_OPRGB; break; @@ -948,7 +948,7 @@ v4l2_hdmi_rx_colorimetry(const struct hdmi_avi_infoframe *avi, c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_SRGB; break; - case HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601: + case HDMI_EXTENDED_COLORIMETRY_OPYCC_601: c.colorspace = V4L2_COLORSPACE_OPRGB; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_OPRGB; diff --git a/drivers/video/hdmi.c b/drivers/video/hdmi.c index 38716eb50408..8a3e8f61b991 100644 --- a/drivers/video/hdmi.c +++ b/drivers/video/hdmi.c @@ -592,10 +592,10 @@ hdmi_extended_colorimetry_get_name(enum hdmi_extended_colorimetry ext_col) return "xvYCC 709"; case HDMI_EXTENDED_COLORIMETRY_S_YCC_601: return "sYCC 601"; - case HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601: - return "Adobe YCC 601"; - case HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB: - return "Adobe RGB"; + case HDMI_EXTENDED_COLORIMETRY_OPYCC_601: + return "opYCC 601"; + case HDMI_EXTENDED_COLORIMETRY_OPRGB: + return "opRGB"; case HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM: return "BT.2020 Constant Luminance"; case HDMI_EXTENDED_COLORIMETRY_BT2020: diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h index d271ff23984f..4f3febc0f971 100644 --- a/include/linux/hdmi.h +++ b/include/linux/hdmi.h @@ -101,8 +101,8 @@ enum hdmi_extended_colorimetry { HDMI_EXTENDED_COLORIMETRY_XV_YCC_601, HDMI_EXTENDED_COLORIMETRY_XV_YCC_709, HDMI_EXTENDED_COLORIMETRY_S_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_YCC_601, - HDMI_EXTENDED_COLORIMETRY_ADOBE_RGB, + HDMI_EXTENDED_COLORIMETRY_OPYCC_601, + HDMI_EXTENDED_COLORIMETRY_OPRGB, /* The following EC values are only defined in CEA-861-F. */ HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM, -- cgit v1.2.3-71-gd317 From 40d9f9124822013331367fb4ab59936c3ac944d6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Mon, 24 Sep 2018 12:16:54 -0700 Subject: bus: ti-sysc: Defer suspend as needed We don't care when we suspend but some our children do. In order to avoid tagging various modules with SYSC_QUIRK_RESOURCE_PROVIDER, let's do it automatically by tagging modules that are busy on suspend for noirq suspend. This way we can just do module detection on define DEBUG. Note that we still need to keep SYSC_QUIRK_LEGACY_IDLE flag around so the our legacy single-child devices that set pm_runtime_irq_safe() can manage the interconnect target module themselves. Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 118 ++++++++++++++++++---------------- include/linux/platform_data/ti-sysc.h | 1 - 2 files changed, 61 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index c9bac9dc4637..087a67617eef 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -87,6 +87,7 @@ struct sysc { u32 revision; bool enabled; bool needs_resume; + unsigned int noirq_suspend:1; bool child_needs_resume; struct delayed_work idle_work; }; @@ -712,19 +713,25 @@ static int sysc_suspend(struct device *dev) ddata = dev_get_drvdata(dev); - if (ddata->cfg.quirks & (SYSC_QUIRK_RESOURCE_PROVIDER | - SYSC_QUIRK_LEGACY_IDLE)) + if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE) return 0; - if (!ddata->enabled) + if (!ddata->enabled || ddata->noirq_suspend) return 0; dev_dbg(ddata->dev, "%s %s\n", __func__, ddata->name ? ddata->name : ""); error = pm_runtime_put_sync_suspend(dev); - if (error < 0) { - dev_warn(ddata->dev, "%s not idle %i %s\n", + if (error == -EBUSY) { + dev_dbg(ddata->dev, "%s busy, tagging for noirq suspend %s\n", + __func__, ddata->name ? ddata->name : ""); + + ddata->noirq_suspend = true; + + return 0; + } else if (error < 0) { + dev_warn(ddata->dev, "%s cannot suspend %i %s\n", __func__, error, ddata->name ? ddata->name : ""); @@ -743,73 +750,86 @@ static int sysc_resume(struct device *dev) ddata = dev_get_drvdata(dev); - if (ddata->cfg.quirks & (SYSC_QUIRK_RESOURCE_PROVIDER | - SYSC_QUIRK_LEGACY_IDLE)) + if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE) return 0; - if (ddata->needs_resume) { - dev_dbg(ddata->dev, "%s %s\n", __func__, - ddata->name ? ddata->name : ""); + if (!ddata->needs_resume || ddata->noirq_suspend) + return 0; - error = pm_runtime_get_sync(dev); - if (error < 0) { - dev_err(ddata->dev, "%s error %i %s\n", - __func__, error, - ddata->name ? ddata->name : ""); + dev_dbg(ddata->dev, "%s %s\n", __func__, + ddata->name ? ddata->name : ""); - return error; - } + error = pm_runtime_get_sync(dev); + if (error < 0) { + dev_err(ddata->dev, "%s error %i %s\n", + __func__, error, + ddata->name ? ddata->name : ""); - ddata->needs_resume = false; + return error; } + ddata->needs_resume = false; + return 0; } static int sysc_noirq_suspend(struct device *dev) { struct sysc *ddata; + int error; ddata = dev_get_drvdata(dev); if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE) return 0; - if (!(ddata->cfg.quirks & SYSC_QUIRK_RESOURCE_PROVIDER)) - return 0; - - if (!ddata->enabled) + if (!ddata->enabled || !ddata->noirq_suspend) return 0; dev_dbg(ddata->dev, "%s %s\n", __func__, ddata->name ? ddata->name : ""); + error = sysc_runtime_suspend(dev); + if (error) { + dev_warn(ddata->dev, "%s busy %i %s\n", + __func__, error, ddata->name ? ddata->name : ""); + + return 0; + } + ddata->needs_resume = true; - return sysc_runtime_suspend(dev); + return 0; } static int sysc_noirq_resume(struct device *dev) { struct sysc *ddata; + int error; ddata = dev_get_drvdata(dev); if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE) return 0; - if (!(ddata->cfg.quirks & SYSC_QUIRK_RESOURCE_PROVIDER)) + if (!ddata->needs_resume || !ddata->noirq_suspend) return 0; - if (ddata->needs_resume) { - dev_dbg(ddata->dev, "%s %s\n", __func__, - ddata->name ? ddata->name : ""); + dev_dbg(ddata->dev, "%s %s\n", __func__, + ddata->name ? ddata->name : ""); - ddata->needs_resume = false; + error = sysc_runtime_resume(dev); + if (error) { + dev_warn(ddata->dev, "%s cannot resume %i %s\n", + __func__, error, + ddata->name ? ddata->name : ""); - return sysc_runtime_resume(dev); + return error; } + /* Maybe also reconsider clearing noirq_suspend at some point */ + ddata->needs_resume = false; + return 0; } #endif @@ -848,26 +868,6 @@ struct sysc_revision_quirk { } static const struct sysc_revision_quirk sysc_revision_quirks[] = { - /* These need to use noirq_suspend */ - SYSC_QUIRK("control", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("mcspi", 0, 0, 0x10, -1, 0x40300a0b, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("prcm", 0, 0, -1, -1, 0x40000100, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("ocp2scp", 0, 0, 0x10, 0x14, 0x50060005, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("padconf", 0, 0, 0x10, -1, 0x4fff0800, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("scm", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("scrm", 0, 0, -1, -1, 0x00000010, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - SYSC_QUIRK("sdma", 0, 0, 0x2c, 0x28, 0x00010900, 0xffffffff, - SYSC_QUIRK_RESOURCE_PROVIDER), - /* These drivers need to be fixed to not use pm_runtime_irq_safe() */ SYSC_QUIRK("gpio", 0, 0, 0x10, 0x114, 0x50600801, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_OPT_CLKS_IN_RESET), @@ -892,23 +892,25 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x50411e03, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), - /* These devices don't yet suspend properly without legacy setting */ - SYSC_QUIRK("sdio", 0, 0, 0x10, -1, 0x40202301, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), - SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), - SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0d00, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), - #ifdef DEBUG SYSC_QUIRK("aess", 0, 0, 0x10, -1, 0x40000000, 0xffffffff, 0), + SYSC_QUIRK("control", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, 0), SYSC_QUIRK("gpu", 0, 0x1fc00, 0x1fc10, -1, 0, 0, 0), SYSC_QUIRK("hdq1w", 0, 0, 0x14, 0x18, 0x00000006, 0xffffffff, 0), SYSC_QUIRK("hsi", 0, 0, 0x10, 0x14, 0x50043101, 0xffffffff, 0), SYSC_QUIRK("iss", 0, 0, 0x10, -1, 0x40000101, 0xffffffff, 0), + SYSC_QUIRK("i2c", 0, 0, 0x10, 0x90, 0x5040000a, 0xffffffff, 0), SYSC_QUIRK("mcasp", 0, 0, 0x4, -1, 0x44306302, 0xffffffff, 0), SYSC_QUIRK("mcbsp", 0, -1, 0x8c, -1, 0, 0, 0), + SYSC_QUIRK("mcspi", 0, 0, 0x10, -1, 0x40300a0b, 0xffffffff, 0), SYSC_QUIRK("mailbox", 0, 0, 0x10, -1, 0x00000400, 0xffffffff, 0), + SYSC_QUIRK("ocp2scp", 0, 0, 0x10, 0x14, 0x50060005, 0xffffffff, 0), + SYSC_QUIRK("padconf", 0, 0, 0x10, -1, 0x4fff0800, 0xffffffff, 0), + SYSC_QUIRK("prcm", 0, 0, -1, -1, 0x40000100, 0xffffffff, 0), + SYSC_QUIRK("scm", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, 0), + SYSC_QUIRK("scrm", 0, 0, -1, -1, 0x00000010, 0xffffffff, 0), + SYSC_QUIRK("sdio", 0, 0, 0x10, -1, 0x40202301, 0xffffffff, 0), + SYSC_QUIRK("sdma", 0, 0, 0x2c, 0x28, 0x00010900, 0xffffffff, 0), SYSC_QUIRK("slimbus", 0, 0, 0x10, -1, 0x40000902, 0xffffffff, 0), SYSC_QUIRK("slimbus", 0, 0, 0x10, -1, 0x40002903, 0xffffffff, 0), SYSC_QUIRK("spinlock", 0, 0, 0x10, -1, 0x50020000, 0xffffffff, 0), @@ -916,6 +918,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, 0x14, 0x50700100, 0xffffffff, 0), SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050, 0xffffffff, 0), + SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xffffffff, 0), + SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0d00, 0xffffffff, 0), #endif }; diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 2efa3470a451..1ea3aab972b4 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -46,7 +46,6 @@ struct sysc_regbits { s8 emufree_shift; }; -#define SYSC_QUIRK_RESOURCE_PROVIDER BIT(9) #define SYSC_QUIRK_LEGACY_IDLE BIT(8) #define SYSC_QUIRK_RESET_STATUS BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) -- cgit v1.2.3-71-gd317 From 76582671eb5d006a78420776cc5f73195b867e81 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:36 -0700 Subject: firmware: xilinx: Add Zynqmp firmware driver This patch is adding communication layer with firmware. Firmware driver provides an interface to firmware APIs. Interface APIs can be used by any driver to communicate to PMUFW(Platform Management Unit). All requests go through ATF. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- arch/arm64/Kconfig.platforms | 1 + drivers/firmware/Kconfig | 1 + drivers/firmware/Makefile | 1 + drivers/firmware/xilinx/Kconfig | 16 ++ drivers/firmware/xilinx/Makefile | 4 + drivers/firmware/xilinx/zynqmp.c | 322 +++++++++++++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 63 +++++++ 7 files changed, 408 insertions(+) create mode 100644 drivers/firmware/xilinx/Kconfig create mode 100644 drivers/firmware/xilinx/Makefile create mode 100644 drivers/firmware/xilinx/zynqmp.c create mode 100644 include/linux/firmware/xlnx-zynqmp.h (limited to 'include/linux') diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 393d2b524284..23f3928743c9 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -301,6 +301,7 @@ config ARCH_ZX config ARCH_ZYNQMP bool "Xilinx ZynqMP Family" + select ZYNQMP_FIRMWARE help This enables support for Xilinx ZynqMP Family diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 6e83880046d7..36344cba764e 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -291,5 +291,6 @@ source "drivers/firmware/google/Kconfig" source "drivers/firmware/efi/Kconfig" source "drivers/firmware/meson/Kconfig" source "drivers/firmware/tegra/Kconfig" +source "drivers/firmware/xilinx/Kconfig" endmenu diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index e18a041cfc53..99583d3df52f 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -32,3 +32,4 @@ obj-$(CONFIG_GOOGLE_FIRMWARE) += google/ obj-$(CONFIG_EFI) += efi/ obj-$(CONFIG_UEFI_CPER) += efi/ obj-y += tegra/ +obj-y += xilinx/ diff --git a/drivers/firmware/xilinx/Kconfig b/drivers/firmware/xilinx/Kconfig new file mode 100644 index 000000000000..64d976e31010 --- /dev/null +++ b/drivers/firmware/xilinx/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +# Kconfig for Xilinx firmwares + +menu "Zynq MPSoC Firmware Drivers" + depends on ARCH_ZYNQMP + +config ZYNQMP_FIRMWARE + bool "Enable Xilinx Zynq MPSoC firmware interface" + help + Firmware interface driver is used by different + drivers to communicate with the firmware for + various platform management services. + Say yes to enable ZynqMP firmware interface driver. + If in doubt, say N. + +endmenu diff --git a/drivers/firmware/xilinx/Makefile b/drivers/firmware/xilinx/Makefile new file mode 100644 index 000000000000..29f7bf2fd094 --- /dev/null +++ b/drivers/firmware/xilinx/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for Xilinx firmwares + +obj-$(CONFIG_ZYNQMP_FIRMWARE) += zynqmp.o diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c new file mode 100644 index 000000000000..5bf64acc7b44 --- /dev/null +++ b/drivers/firmware/xilinx/zynqmp.c @@ -0,0 +1,322 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Xilinx Zynq MPSoC Firmware layer + * + * Copyright (C) 2014-2018 Xilinx, Inc. + * + * Michal Simek + * Davorin Mista + * Jolly Shah + * Rajan Vaja + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/** + * zynqmp_pm_ret_code() - Convert PMU-FW error codes to Linux error codes + * @ret_status: PMUFW return code + * + * Return: corresponding Linux error code + */ +static int zynqmp_pm_ret_code(u32 ret_status) +{ + switch (ret_status) { + case XST_PM_SUCCESS: + case XST_PM_DOUBLE_REQ: + return 0; + case XST_PM_NO_ACCESS: + return -EACCES; + case XST_PM_ABORT_SUSPEND: + return -ECANCELED; + case XST_PM_INTERNAL: + case XST_PM_CONFLICT: + case XST_PM_INVALID_NODE: + default: + return -EINVAL; + } +} + +static noinline int do_fw_call_fail(u64 arg0, u64 arg1, u64 arg2, + u32 *ret_payload) +{ + return -ENODEV; +} + +/* + * PM function call wrapper + * Invoke do_fw_call_smc or do_fw_call_hvc, depending on the configuration + */ +static int (*do_fw_call)(u64, u64, u64, u32 *ret_payload) = do_fw_call_fail; + +/** + * do_fw_call_smc() - Call system-level platform management layer (SMC) + * @arg0: Argument 0 to SMC call + * @arg1: Argument 1 to SMC call + * @arg2: Argument 2 to SMC call + * @ret_payload: Returned value array + * + * Invoke platform management function via SMC call (no hypervisor present). + * + * Return: Returns status, either success or error+reason + */ +static noinline int do_fw_call_smc(u64 arg0, u64 arg1, u64 arg2, + u32 *ret_payload) +{ + struct arm_smccc_res res; + + arm_smccc_smc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res); + + if (ret_payload) { + ret_payload[0] = lower_32_bits(res.a0); + ret_payload[1] = upper_32_bits(res.a0); + ret_payload[2] = lower_32_bits(res.a1); + ret_payload[3] = upper_32_bits(res.a1); + } + + return zynqmp_pm_ret_code((enum pm_ret_status)res.a0); +} + +/** + * do_fw_call_hvc() - Call system-level platform management layer (HVC) + * @arg0: Argument 0 to HVC call + * @arg1: Argument 1 to HVC call + * @arg2: Argument 2 to HVC call + * @ret_payload: Returned value array + * + * Invoke platform management function via HVC + * HVC-based for communication through hypervisor + * (no direct communication with ATF). + * + * Return: Returns status, either success or error+reason + */ +static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2, + u32 *ret_payload) +{ + struct arm_smccc_res res; + + arm_smccc_hvc(arg0, arg1, arg2, 0, 0, 0, 0, 0, &res); + + if (ret_payload) { + ret_payload[0] = lower_32_bits(res.a0); + ret_payload[1] = upper_32_bits(res.a0); + ret_payload[2] = lower_32_bits(res.a1); + ret_payload[3] = upper_32_bits(res.a1); + } + + return zynqmp_pm_ret_code((enum pm_ret_status)res.a0); +} + +/** + * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer + * caller function depending on the configuration + * @pm_api_id: Requested PM-API call + * @arg0: Argument 0 to requested PM-API call + * @arg1: Argument 1 to requested PM-API call + * @arg2: Argument 2 to requested PM-API call + * @arg3: Argument 3 to requested PM-API call + * @ret_payload: Returned value array + * + * Invoke platform management function for SMC or HVC call, depending on + * configuration. + * Following SMC Calling Convention (SMCCC) for SMC64: + * Pm Function Identifier, + * PM_SIP_SVC + PM_API_ID = + * ((SMC_TYPE_FAST << FUNCID_TYPE_SHIFT) + * ((SMC_64) << FUNCID_CC_SHIFT) + * ((SIP_START) << FUNCID_OEN_SHIFT) + * ((PM_API_ID) & FUNCID_NUM_MASK)) + * + * PM_SIP_SVC - Registered ZynqMP SIP Service Call. + * PM_API_ID - Platform Management API ID. + * + * Return: Returns status, either success or error+reason + */ +int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1, + u32 arg2, u32 arg3, u32 *ret_payload) +{ + /* + * Added SIP service call Function Identifier + * Make sure to stay in x0 register + */ + u64 smc_arg[4]; + + smc_arg[0] = PM_SIP_SVC | pm_api_id; + smc_arg[1] = ((u64)arg1 << 32) | arg0; + smc_arg[2] = ((u64)arg3 << 32) | arg2; + + return do_fw_call(smc_arg[0], smc_arg[1], smc_arg[2], ret_payload); +} + +static u32 pm_api_version; +static u32 pm_tz_version; + +/** + * zynqmp_pm_get_api_version() - Get version number of PMU PM firmware + * @version: Returned version value + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_get_api_version(u32 *version) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + if (!version) + return -EINVAL; + + /* Check is PM API version already verified */ + if (pm_api_version > 0) { + *version = pm_api_version; + return 0; + } + ret = zynqmp_pm_invoke_fn(PM_GET_API_VERSION, 0, 0, 0, 0, ret_payload); + *version = ret_payload[1]; + + return ret; +} + +/** + * zynqmp_pm_get_trustzone_version() - Get secure trustzone firmware version + * @version: Returned version value + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_get_trustzone_version(u32 *version) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + if (!version) + return -EINVAL; + + /* Check is PM trustzone version already verified */ + if (pm_tz_version > 0) { + *version = pm_tz_version; + return 0; + } + ret = zynqmp_pm_invoke_fn(PM_GET_TRUSTZONE_VERSION, 0, 0, + 0, 0, ret_payload); + *version = ret_payload[1]; + + return ret; +} + +/** + * get_set_conduit_method() - Choose SMC or HVC based communication + * @np: Pointer to the device_node structure + * + * Use SMC or HVC-based functions to communicate with EL2/EL3. + * + * Return: Returns 0 on success or error code + */ +static int get_set_conduit_method(struct device_node *np) +{ + const char *method; + + if (of_property_read_string(np, "method", &method)) { + pr_warn("%s missing \"method\" property\n", __func__); + return -ENXIO; + } + + if (!strcmp("hvc", method)) { + do_fw_call = do_fw_call_hvc; + } else if (!strcmp("smc", method)) { + do_fw_call = do_fw_call_smc; + } else { + pr_warn("%s Invalid \"method\" property: %s\n", + __func__, method); + return -EINVAL; + } + + return 0; +} + +static const struct zynqmp_eemi_ops eemi_ops = { + .get_api_version = zynqmp_pm_get_api_version, +}; + +/** + * zynqmp_pm_get_eemi_ops - Get eemi ops functions + * + * Return: Pointer of eemi_ops structure + */ +const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) +{ + return &eemi_ops; +} +EXPORT_SYMBOL_GPL(zynqmp_pm_get_eemi_ops); + +static int zynqmp_firmware_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np; + int ret; + + np = of_find_compatible_node(NULL, NULL, "xlnx,zynqmp"); + if (!np) + return 0; + of_node_put(np); + + ret = get_set_conduit_method(dev->of_node); + if (ret) + return ret; + + /* Check PM API version number */ + zynqmp_pm_get_api_version(&pm_api_version); + if (pm_api_version < ZYNQMP_PM_VERSION) { + panic("%s Platform Management API version error. Expected: v%d.%d - Found: v%d.%d\n", + __func__, + ZYNQMP_PM_VERSION_MAJOR, ZYNQMP_PM_VERSION_MINOR, + pm_api_version >> 16, pm_api_version & 0xFFFF); + } + + pr_info("%s Platform Management API v%d.%d\n", __func__, + pm_api_version >> 16, pm_api_version & 0xFFFF); + + /* Check trustzone version number */ + ret = zynqmp_pm_get_trustzone_version(&pm_tz_version); + if (ret) + panic("Legacy trustzone found without version support\n"); + + if (pm_tz_version < ZYNQMP_TZ_VERSION) + panic("%s Trustzone version error. Expected: v%d.%d - Found: v%d.%d\n", + __func__, + ZYNQMP_TZ_VERSION_MAJOR, ZYNQMP_TZ_VERSION_MINOR, + pm_tz_version >> 16, pm_tz_version & 0xFFFF); + + pr_info("%s Trustzone version v%d.%d\n", __func__, + pm_tz_version >> 16, pm_tz_version & 0xFFFF); + + return of_platform_populate(dev->of_node, NULL, NULL, dev); +} + +static int zynqmp_firmware_remove(struct platform_device *pdev) +{ + return 0; +} + +static const struct of_device_id zynqmp_firmware_of_match[] = { + {.compatible = "xlnx,zynqmp-firmware"}, + {}, +}; +MODULE_DEVICE_TABLE(of, zynqmp_firmware_of_match); + +static struct platform_driver zynqmp_firmware_driver = { + .driver = { + .name = "zynqmp_firmware", + .of_match_table = zynqmp_firmware_of_match, + }, + .probe = zynqmp_firmware_probe, + .remove = zynqmp_firmware_remove, +}; +module_platform_driver(zynqmp_firmware_driver); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h new file mode 100644 index 000000000000..cb63bedf3dcf --- /dev/null +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Xilinx Zynq MPSoC Firmware layer + * + * Copyright (C) 2014-2018 Xilinx + * + * Michal Simek + * Davorin Mista + * Jolly Shah + * Rajan Vaja + */ + +#ifndef __FIRMWARE_ZYNQMP_H__ +#define __FIRMWARE_ZYNQMP_H__ + +#define ZYNQMP_PM_VERSION_MAJOR 1 +#define ZYNQMP_PM_VERSION_MINOR 0 + +#define ZYNQMP_PM_VERSION ((ZYNQMP_PM_VERSION_MAJOR << 16) | \ + ZYNQMP_PM_VERSION_MINOR) + +#define ZYNQMP_TZ_VERSION_MAJOR 1 +#define ZYNQMP_TZ_VERSION_MINOR 0 + +#define ZYNQMP_TZ_VERSION ((ZYNQMP_TZ_VERSION_MAJOR << 16) | \ + ZYNQMP_TZ_VERSION_MINOR) + +/* SMC SIP service Call Function Identifier Prefix */ +#define PM_SIP_SVC 0xC2000000 +#define PM_GET_TRUSTZONE_VERSION 0xa03 + +/* Number of 32bits values in payload */ +#define PAYLOAD_ARG_CNT 4U + +enum pm_api_id { + PM_GET_API_VERSION = 1, +}; + +/* PMU-FW return status codes */ +enum pm_ret_status { + XST_PM_SUCCESS = 0, + XST_PM_INTERNAL = 2000, + XST_PM_CONFLICT, + XST_PM_NO_ACCESS, + XST_PM_INVALID_NODE, + XST_PM_DOUBLE_REQ, + XST_PM_ABORT_SUSPEND, +}; + +struct zynqmp_eemi_ops { + int (*get_api_version)(u32 *version); +}; + +#if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) +const struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void); +#else +static inline struct zynqmp_eemi_ops *zynqmp_pm_get_eemi_ops(void) +{ + return NULL; +} +#endif + +#endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3-71-gd317 From 59ecdd778879f171072b663f91de6c3a595e2ed4 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:37 -0700 Subject: firmware: xilinx: Add query data API Add ZynqMP firmware query data API to query platform specific information(clocks, pins) from firmware. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 14 ++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 20 ++++++++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 5bf64acc7b44..2a333c04955b 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -241,8 +241,22 @@ static int get_set_conduit_method(struct device_node *np) return 0; } +/** + * zynqmp_pm_query_data() - Get query data from firmware + * @qdata: Variable to the zynqmp_pm_query_data structure + * @out: Returned output value + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out) +{ + return zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1, + qdata.arg2, qdata.arg3, out); +} + static const struct zynqmp_eemi_ops eemi_ops = { .get_api_version = zynqmp_pm_get_api_version, + .query_data = zynqmp_pm_query_data, }; /** diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index cb63bedf3dcf..287f42caa623 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,6 +34,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_QUERY_DATA = 35, }; /* PMU-FW return status codes */ @@ -47,8 +48,27 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_query_id { + PM_QID_INVALID, +}; + +/** + * struct zynqmp_pm_query_data - PM query data + * @qid: query ID + * @arg1: Argument 1 of query data + * @arg2: Argument 2 of query data + * @arg3: Argument 3 of query data + */ +struct zynqmp_pm_query_data { + u32 qid; + u32 arg1; + u32 arg2; + u32 arg3; +}; + struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); + int (*query_data)(struct zynqmp_pm_query_data qdata, u32 *out); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3-71-gd317 From f9627312e20721681ea326bd2b7935bf8034b288 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Wed, 12 Sep 2018 12:38:38 -0700 Subject: firmware: xilinx: Add clock APIs Add clock APIs to control clocks through firmware interface. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 186 ++++++++++++++++++++++++++++++++++- include/linux/firmware/xlnx-zynqmp.h | 30 ++++++ 2 files changed, 214 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 2a333c04955b..697f4fa23a45 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -250,13 +250,195 @@ static int get_set_conduit_method(struct device_node *np) */ static int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out) { - return zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1, - qdata.arg2, qdata.arg3, out); + int ret; + + ret = zynqmp_pm_invoke_fn(PM_QUERY_DATA, qdata.qid, qdata.arg1, + qdata.arg2, qdata.arg3, out); + + /* + * For clock name query, all bytes in SMC response are clock name + * characters and return code is always success. For invalid clocks, + * clock name bytes would be zeros. + */ + return qdata.qid == PM_QID_CLOCK_GET_NAME ? 0 : ret; +} + +/** + * zynqmp_pm_clock_enable() - Enable the clock for given id + * @clock_id: ID of the clock to be enabled + * + * This function is used by master to enable the clock + * including peripherals and PLL clocks. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_enable(u32 clock_id) +{ + return zynqmp_pm_invoke_fn(PM_CLOCK_ENABLE, clock_id, 0, 0, 0, NULL); +} + +/** + * zynqmp_pm_clock_disable() - Disable the clock for given id + * @clock_id: ID of the clock to be disable + * + * This function is used by master to disable the clock + * including peripherals and PLL clocks. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_disable(u32 clock_id) +{ + return zynqmp_pm_invoke_fn(PM_CLOCK_DISABLE, clock_id, 0, 0, 0, NULL); +} + +/** + * zynqmp_pm_clock_getstate() - Get the clock state for given id + * @clock_id: ID of the clock to be queried + * @state: 1/0 (Enabled/Disabled) + * + * This function is used by master to get the state of clock + * including peripherals and PLL clocks. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETSTATE, clock_id, 0, + 0, 0, ret_payload); + *state = ret_payload[1]; + + return ret; +} + +/** + * zynqmp_pm_clock_setdivider() - Set the clock divider for given id + * @clock_id: ID of the clock + * @divider: divider value + * + * This function is used by master to set divider for any clock + * to achieve desired rate. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider) +{ + return zynqmp_pm_invoke_fn(PM_CLOCK_SETDIVIDER, clock_id, divider, + 0, 0, NULL); +} + +/** + * zynqmp_pm_clock_getdivider() - Get the clock divider for given id + * @clock_id: ID of the clock + * @divider: divider value + * + * This function is used by master to get divider values + * for any clock. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETDIVIDER, clock_id, 0, + 0, 0, ret_payload); + *divider = ret_payload[1]; + + return ret; +} + +/** + * zynqmp_pm_clock_setrate() - Set the clock rate for given id + * @clock_id: ID of the clock + * @rate: rate value in hz + * + * This function is used by master to set rate for any clock. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate) +{ + return zynqmp_pm_invoke_fn(PM_CLOCK_SETRATE, clock_id, + lower_32_bits(rate), + upper_32_bits(rate), + 0, NULL); +} + +/** + * zynqmp_pm_clock_getrate() - Get the clock rate for given id + * @clock_id: ID of the clock + * @rate: rate value in hz + * + * This function is used by master to get rate + * for any clock. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETRATE, clock_id, 0, + 0, 0, ret_payload); + *rate = ((u64)ret_payload[2] << 32) | ret_payload[1]; + + return ret; +} + +/** + * zynqmp_pm_clock_setparent() - Set the clock parent for given id + * @clock_id: ID of the clock + * @parent_id: parent id + * + * This function is used by master to set parent for any clock. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id) +{ + return zynqmp_pm_invoke_fn(PM_CLOCK_SETPARENT, clock_id, + parent_id, 0, 0, NULL); +} + +/** + * zynqmp_pm_clock_getparent() - Get the clock parent for given id + * @clock_id: ID of the clock + * @parent_id: parent id + * + * This function is used by master to get parent index + * for any clock. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) +{ + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + ret = zynqmp_pm_invoke_fn(PM_CLOCK_GETPARENT, clock_id, 0, + 0, 0, ret_payload); + *parent_id = ret_payload[1]; + + return ret; } static const struct zynqmp_eemi_ops eemi_ops = { .get_api_version = zynqmp_pm_get_api_version, .query_data = zynqmp_pm_query_data, + .clock_enable = zynqmp_pm_clock_enable, + .clock_disable = zynqmp_pm_clock_disable, + .clock_getstate = zynqmp_pm_clock_getstate, + .clock_setdivider = zynqmp_pm_clock_setdivider, + .clock_getdivider = zynqmp_pm_clock_getdivider, + .clock_setrate = zynqmp_pm_clock_setrate, + .clock_getrate = zynqmp_pm_clock_getrate, + .clock_setparent = zynqmp_pm_clock_setparent, + .clock_getparent = zynqmp_pm_clock_getparent, }; /** diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 287f42caa623..015e130431e6 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -35,6 +35,15 @@ enum pm_api_id { PM_GET_API_VERSION = 1, PM_QUERY_DATA = 35, + PM_CLOCK_ENABLE, + PM_CLOCK_DISABLE, + PM_CLOCK_GETSTATE, + PM_CLOCK_SETDIVIDER, + PM_CLOCK_GETDIVIDER, + PM_CLOCK_SETRATE, + PM_CLOCK_GETRATE, + PM_CLOCK_SETPARENT, + PM_CLOCK_GETPARENT, }; /* PMU-FW return status codes */ @@ -48,8 +57,20 @@ enum pm_ret_status { XST_PM_ABORT_SUSPEND, }; +enum pm_ioctl_id { + IOCTL_SET_PLL_FRAC_MODE = 8, + IOCTL_GET_PLL_FRAC_MODE, + IOCTL_SET_PLL_FRAC_DATA, + IOCTL_GET_PLL_FRAC_DATA, +}; + enum pm_query_id { PM_QID_INVALID, + PM_QID_CLOCK_GET_NAME, + PM_QID_CLOCK_GET_TOPOLOGY, + PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, + PM_QID_CLOCK_GET_PARENTS, + PM_QID_CLOCK_GET_ATTRIBUTES, }; /** @@ -69,6 +90,15 @@ struct zynqmp_pm_query_data { struct zynqmp_eemi_ops { int (*get_api_version)(u32 *version); 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); + 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); + int (*clock_setparent)(u32 clock_id, u32 parent_id); + int (*clock_getparent)(u32 clock_id, u32 *parent_id); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3-71-gd317 From 96a71f21ef1fcc32bea07c612a332a89a213f054 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Fri, 21 Sep 2018 21:20:30 +0300 Subject: fanotify: store fanotify_init() flags in group's fanotify_data This averts the need to re-generate flags in fanotify_show_fdinfo() and sets the scene for addition of more upcoming flags without growing new members to the fanotify_data struct. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 8 ++++---- fs/notify/fdinfo.c | 24 +----------------------- include/linux/fanotify.h | 4 ++++ include/linux/fsnotify_backend.h | 4 ++-- 4 files changed, 11 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 1347c588f778..15719d4aa4b5 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -191,7 +191,7 @@ static int process_access_response(struct fsnotify_group *group, if (fd < 0) return -EINVAL; - if ((response & FAN_AUDIT) && !group->fanotify_data.audit) + if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT)) return -EINVAL; event = dequeue_event(group, fd); @@ -701,8 +701,8 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) struct user_struct *user; struct fanotify_event_info *oevent; - pr_debug("%s: flags=%d event_f_flags=%d\n", - __func__, flags, event_f_flags); + pr_debug("%s: flags=%x event_f_flags=%x\n", + __func__, flags, event_f_flags); if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -746,6 +746,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) } group->fanotify_data.user = user; + group->fanotify_data.flags = flags; atomic_inc(&user->fanotify_listeners); group->memcg = get_mem_cgroup_from_mm(current->mm); @@ -798,7 +799,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) fd = -EPERM; if (!capable(CAP_AUDIT_WRITE)) goto out_destroy_group; - group->fanotify_data.audit = true; } fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags); diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 25385e336ac7..348a184bcdda 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -142,31 +142,9 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark) void fanotify_show_fdinfo(struct seq_file *m, struct file *f) { struct fsnotify_group *group = f->private_data; - unsigned int flags = 0; - - switch (group->priority) { - case FS_PRIO_0: - flags |= FAN_CLASS_NOTIF; - break; - case FS_PRIO_1: - flags |= FAN_CLASS_CONTENT; - break; - case FS_PRIO_2: - flags |= FAN_CLASS_PRE_CONTENT; - break; - } - - if (group->max_events == UINT_MAX) - flags |= FAN_UNLIMITED_QUEUE; - - if (group->fanotify_data.max_marks == UINT_MAX) - flags |= FAN_UNLIMITED_MARKS; - - if (group->fanotify_data.audit) - flags |= FAN_ENABLE_AUDIT; seq_printf(m, "fanotify flags:%x event-flags:%x\n", - flags, group->fanotify_data.f_flags); + group->fanotify_data.flags, group->fanotify_data.f_flags); show_fdinfo(m, f, fanotify_fdinfo); } diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 096c96f4f16a..9c5ea3bdfaa0 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -6,4 +6,8 @@ /* not valid from userspace, only kernel internal */ #define FAN_MARK_ONDIR 0x00000100 + +#define FAN_GROUP_FLAG(group, flag) \ + ((group)->fanotify_data.flags & (flag)) + #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 81b88fc9df31..8e91341cbd8a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -189,10 +189,10 @@ struct fsnotify_group { /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; - int f_flags; + int flags; /* flags from fanotify_init() */ + int f_flags; /* event_f_flags from fanotify_init() */ unsigned int max_marks; struct user_struct *user; - bool audit; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; -- cgit v1.2.3-71-gd317 From eb2bccb70b979d996ecb769d692b92ff12eabbb7 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 19 Sep 2018 03:13:21 +0200 Subject: rtc: move rtc_add_group/s definitions Move rtc_add_group and rtc_add_groups definition to rtc.h that is available for all RTC drivers. Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-core.h | 14 -------------- include/linux/rtc.h | 16 ++++++++++++++++ 2 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-core.h b/drivers/rtc/rtc-core.h index ccc17a2e293d..0abf98983e13 100644 --- a/drivers/rtc/rtc-core.h +++ b/drivers/rtc/rtc-core.h @@ -40,23 +40,9 @@ static inline void rtc_proc_del_device(struct rtc_device *rtc) #ifdef CONFIG_RTC_INTF_SYSFS const struct attribute_group **rtc_get_dev_attribute_groups(void); -int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp); -int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps); #else static inline const struct attribute_group **rtc_get_dev_attribute_groups(void) { return NULL; } - -static inline -int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp) -{ - return 0; -} - -static inline -int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) -{ - return 0; -} #endif diff --git a/include/linux/rtc.h b/include/linux/rtc.h index faf00a1472d4..c8bb4a2b48c3 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -272,4 +272,20 @@ static inline int rtc_nvmem_register(struct rtc_device *rtc, static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} #endif +#ifdef CONFIG_RTC_INTF_SYSFS +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp); +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps); +#else +static inline +int rtc_add_group(struct rtc_device *rtc, const struct attribute_group *grp) +{ + return 0; +} + +static inline +int rtc_add_groups(struct rtc_device *rtc, const struct attribute_group **grps) +{ + return 0; +} +#endif #endif /* _LINUX_RTC_H_ */ -- cgit v1.2.3-71-gd317 From 9e288cefcc551c7b5b04f8abc7099d3451a70f5f Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 25 Sep 2018 09:34:05 +0200 Subject: clk: renesas: Convert to SPDX identifiers This patch updates license to use SPDX-License-Identifier instead of verbose license text. Signed-off-by: Kuninori Morimoto [rebased against clk-spdx] Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Signed-off-by: Stephen Boyd --- drivers/clk/renesas/Kconfig | 2 ++ drivers/clk/renesas/clk-emev2.c | 14 +------------- drivers/clk/renesas/clk-mstp.c | 5 +---- drivers/clk/renesas/clk-r8a73a4.c | 5 +---- drivers/clk/renesas/clk-r8a7740.c | 5 +---- drivers/clk/renesas/clk-r8a7778.c | 5 +---- drivers/clk/renesas/clk-r8a7779.c | 5 +---- drivers/clk/renesas/clk-rcar-gen2.c | 5 +---- drivers/clk/renesas/clk-rz.c | 5 +---- drivers/clk/renesas/clk-sh73a0.c | 5 +---- drivers/clk/renesas/r8a7743-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a7745-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a7790-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a7791-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a7792-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a7794-cpg-mssr.c | 5 +---- drivers/clk/renesas/r8a77970-cpg-mssr.c | 5 +---- drivers/clk/renesas/rcar-gen2-cpg.c | 5 +---- drivers/clk/renesas/rcar-gen2-cpg.h | 7 ++----- drivers/clk/renesas/rcar-gen3-cpg.h | 7 ++----- drivers/clk/renesas/renesas-cpg-mssr.h | 4 ++-- include/linux/clk/renesas.h | 8 ++------ 22 files changed, 27 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig index 9022bbe1297e..ab2110f96225 100644 --- a/drivers/clk/renesas/Kconfig +++ b/drivers/clk/renesas/Kconfig @@ -1,3 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + config CLK_RENESAS bool "Renesas SoC clock support" if COMPILE_TEST && !ARCH_RENESAS default y if ARCH_RENESAS diff --git a/drivers/clk/renesas/clk-emev2.c b/drivers/clk/renesas/clk-emev2.c index a91825471c79..7f3b5f9631bd 100644 --- a/drivers/clk/renesas/clk-emev2.c +++ b/drivers/clk/renesas/clk-emev2.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * EMMA Mobile EV2 common clock framework support * * Copyright (C) 2013 Takashi Yoshii * Copyright (C) 2012 Magnus Damm - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include #include diff --git a/drivers/clk/renesas/clk-mstp.c b/drivers/clk/renesas/clk-mstp.c index e82adcb16a52..7df14bb1cbbc 100644 --- a/drivers/clk/renesas/clk-mstp.c +++ b/drivers/clk/renesas/clk-mstp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Car MSTP clocks * @@ -5,10 +6,6 @@ * Copyright (C) 2015 Glider bvba * * Contact: Laurent Pinchart - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-r8a73a4.c b/drivers/clk/renesas/clk-r8a73a4.c index 7b903ce4c901..e1a9e89defdd 100644 --- a/drivers/clk/renesas/clk-r8a73a4.c +++ b/drivers/clk/renesas/clk-r8a73a4.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a73a4 Core CPG Clocks * * Copyright (C) 2014 Ulrich Hecht - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-r8a7740.c b/drivers/clk/renesas/clk-r8a7740.c index a7a30d2eca41..d68171263137 100644 --- a/drivers/clk/renesas/clk-r8a7740.c +++ b/drivers/clk/renesas/clk-r8a7740.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7740 Core CPG Clocks * * Copyright (C) 2014 Ulrich Hecht - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-r8a7778.c b/drivers/clk/renesas/clk-r8a7778.c index 886a8380e912..f986ba34661d 100644 --- a/drivers/clk/renesas/clk-r8a7778.c +++ b/drivers/clk/renesas/clk-r8a7778.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7778 Core CPG Clocks * * Copyright (C) 2014 Ulrich Hecht - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-r8a7779.c b/drivers/clk/renesas/clk-r8a7779.c index 5adcca4656c3..437d92cb0630 100644 --- a/drivers/clk/renesas/clk-r8a7779.c +++ b/drivers/clk/renesas/clk-r8a7779.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7779 Core CPG Clocks * * Copyright (C) 2013, 2014 Horms Solutions Ltd. * * Contact: Simon Horman - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-rcar-gen2.c b/drivers/clk/renesas/clk-rcar-gen2.c index bccd62f2cb09..738b723045ce 100644 --- a/drivers/clk/renesas/clk-rcar-gen2.c +++ b/drivers/clk/renesas/clk-rcar-gen2.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * rcar_gen2 Core CPG Clocks * * Copyright (C) 2013 Ideas On Board SPRL * * Contact: Laurent Pinchart - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-rz.c b/drivers/clk/renesas/clk-rz.c index ac2f86d626b6..7fe8729bf66c 100644 --- a/drivers/clk/renesas/clk-rz.c +++ b/drivers/clk/renesas/clk-rz.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * RZ/A1 Core CPG Clocks * * Copyright (C) 2013 Ideas On Board SPRL * Copyright (C) 2014 Wolfram Sang, Sang Engineering - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/clk-sh73a0.c b/drivers/clk/renesas/clk-sh73a0.c index bab33610eb6c..576259237666 100644 --- a/drivers/clk/renesas/clk-sh73a0.c +++ b/drivers/clk/renesas/clk-sh73a0.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * sh73a0 Core CPG Clocks * * Copyright (C) 2014 Ulrich Hecht - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/r8a7743-cpg-mssr.c b/drivers/clk/renesas/r8a7743-cpg-mssr.c index 011c170ec3f9..f880b9cb72e0 100644 --- a/drivers/clk/renesas/r8a7743-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7743-cpg-mssr.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7743 Clock Pulse Generator / Module Standby and Software Reset * * Copyright (C) 2016 Cogent Embedded Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation; of the License. */ #include diff --git a/drivers/clk/renesas/r8a7745-cpg-mssr.c b/drivers/clk/renesas/r8a7745-cpg-mssr.c index 4b0a9243b748..493874e5ebee 100644 --- a/drivers/clk/renesas/r8a7745-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7745-cpg-mssr.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7745 Clock Pulse Generator / Module Standby and Software Reset * * Copyright (C) 2016 Cogent Embedded Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation; of the License. */ #include diff --git a/drivers/clk/renesas/r8a7790-cpg-mssr.c b/drivers/clk/renesas/r8a7790-cpg-mssr.c index f936cb74b681..c57cb93f8315 100644 --- a/drivers/clk/renesas/r8a7790-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7790-cpg-mssr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7790 Clock Pulse Generator / Module Standby and Software Reset * @@ -6,10 +7,6 @@ * Based on clk-rcar-gen2.c * * Copyright (C) 2013 Ideas On Board SPRL - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/r8a7791-cpg-mssr.c b/drivers/clk/renesas/r8a7791-cpg-mssr.c index 1b91f03b7598..65702debcabb 100644 --- a/drivers/clk/renesas/r8a7791-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7791-cpg-mssr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7791 Clock Pulse Generator / Module Standby and Software Reset * @@ -6,10 +7,6 @@ * Based on clk-rcar-gen2.c * * Copyright (C) 2013 Ideas On Board SPRL - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/r8a7792-cpg-mssr.c b/drivers/clk/renesas/r8a7792-cpg-mssr.c index 493e07859f5f..cf8b84a3a060 100644 --- a/drivers/clk/renesas/r8a7792-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7792-cpg-mssr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7792 Clock Pulse Generator / Module Standby and Software Reset * @@ -6,10 +7,6 @@ * Based on clk-rcar-gen2.c * * Copyright (C) 2013 Ideas On Board SPRL - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/r8a7794-cpg-mssr.c b/drivers/clk/renesas/r8a7794-cpg-mssr.c index 088f4b79fdfc..c1948693c5c1 100644 --- a/drivers/clk/renesas/r8a7794-cpg-mssr.c +++ b/drivers/clk/renesas/r8a7794-cpg-mssr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a7794 Clock Pulse Generator / Module Standby and Software Reset * @@ -6,10 +7,6 @@ * Based on clk-rcar-gen2.c * * Copyright (C) 2013 Ideas On Board SPRL - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/r8a77970-cpg-mssr.c b/drivers/clk/renesas/r8a77970-cpg-mssr.c index f55842917e8d..38509873d06c 100644 --- a/drivers/clk/renesas/r8a77970-cpg-mssr.c +++ b/drivers/clk/renesas/r8a77970-cpg-mssr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * r8a77970 Clock Pulse Generator / Module Standby and Software Reset * @@ -6,10 +7,6 @@ * Based on r8a7795-cpg-mssr.c * * Copyright (C) 2015 Glider bvba - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include diff --git a/drivers/clk/renesas/rcar-gen2-cpg.c b/drivers/clk/renesas/rcar-gen2-cpg.c index daf88bc2cdae..f596a2dafcf4 100644 --- a/drivers/clk/renesas/rcar-gen2-cpg.c +++ b/drivers/clk/renesas/rcar-gen2-cpg.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Car Gen2 Clock Pulse Generator * * Copyright (C) 2016 Cogent Embedded Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. */ #include diff --git a/drivers/clk/renesas/rcar-gen2-cpg.h b/drivers/clk/renesas/rcar-gen2-cpg.h index 020a3baad015..bff9551c7a38 100644 --- a/drivers/clk/renesas/rcar-gen2-cpg.h +++ b/drivers/clk/renesas/rcar-gen2-cpg.h @@ -1,11 +1,8 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * R-Car Gen2 Clock Pulse Generator * * Copyright (C) 2016 Cogent Embedded Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation; version 2 of the License. */ #ifndef __CLK_RENESAS_RCAR_GEN2_CPG_H__ diff --git a/drivers/clk/renesas/rcar-gen3-cpg.h b/drivers/clk/renesas/rcar-gen3-cpg.h index ea4f8fc3c4c9..6ebc4b42c5a3 100644 --- a/drivers/clk/renesas/rcar-gen3-cpg.h +++ b/drivers/clk/renesas/rcar-gen3-cpg.h @@ -1,11 +1,8 @@ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * R-Car Gen3 Clock Pulse Generator * * Copyright (C) 2015-2016 Glider bvba - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #ifndef __CLK_RENESAS_RCAR_GEN3_CPG_H__ diff --git a/drivers/clk/renesas/renesas-cpg-mssr.h b/drivers/clk/renesas/renesas-cpg-mssr.h index 59b1b30c1dba..d52d1f8da9d7 100644 --- a/drivers/clk/renesas/renesas-cpg-mssr.h +++ b/drivers/clk/renesas/renesas-cpg-mssr.h @@ -1,5 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* +/* SPDX-License-Identifier: GPL-2.0 + * * Renesas Clock Pulse Generator / Module Standby and Software Reset * * Copyright (C) 2015 Glider bvba diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 9ebf1f8243bb..0ebbe2f0b45e 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -1,14 +1,10 @@ -/* +/* SPDX-License-Identifier: GPL-2.0+ + * * Copyright 2013 Ideas On Board SPRL * Copyright 2013, 2014 Horms Solutions Ltd. * * Contact: Laurent Pinchart * Contact: Simon Horman - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. */ #ifndef __LINUX_CLK_RENESAS_H_ -- cgit v1.2.3-71-gd317 From 3d0186bb068e6cc6c23dc1d2f0b1cf64894c40ea Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 16 Jun 2018 17:32:07 -0400 Subject: Update email address Redirect some older email addresses that are in the git logs. Signed-off-by: Matthew Wilcox --- .mailmap | 7 +++++++ MAINTAINERS | 6 +++--- arch/parisc/kernel/syscall.S | 2 +- drivers/input/keyboard/hilkbd.c | 2 +- drivers/pci/hotplug/acpiphp.h | 2 +- drivers/pci/hotplug/acpiphp_core.c | 4 ++-- drivers/pci/hotplug/acpiphp_glue.c | 2 +- fs/isofs/dir.c | 2 +- include/linux/xarray.h | 2 +- 9 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/.mailmap b/.mailmap index 285e09645b31..89f532caf639 100644 --- a/.mailmap +++ b/.mailmap @@ -119,6 +119,13 @@ Mark Brown Mark Yao Martin Kepplinger Martin Kepplinger +Matthew Wilcox +Matthew Wilcox +Matthew Wilcox +Matthew Wilcox +Matthew Wilcox +Matthew Wilcox +Matthew Wilcox Matthieu CASTET Mauro Carvalho Chehab Mauro Carvalho Chehab diff --git a/MAINTAINERS b/MAINTAINERS index a255240d1452..612e5dbf3431 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -536,7 +536,7 @@ F: Documentation/hwmon/adt7475 F: drivers/hwmon/adt7475.c ADVANSYS SCSI DRIVER -M: Matthew Wilcox +M: Matthew Wilcox M: Hannes Reinecke L: linux-scsi@vger.kernel.org S: Maintained @@ -4364,7 +4364,7 @@ S: Maintained F: drivers/i2c/busses/i2c-diolan-u2c.c FILESYSTEM DIRECT ACCESS (DAX) -M: Matthew Wilcox +M: Matthew Wilcox M: Ross Zwisler M: Jan Kara L: linux-fsdevel@vger.kernel.org @@ -8626,7 +8626,7 @@ F: drivers/message/fusion/ F: drivers/scsi/mpt3sas/ LSILOGIC/SYMBIOS/NCR 53C8XX and 53C1010 PCI-SCSI drivers -M: Matthew Wilcox +M: Matthew Wilcox L: linux-scsi@vger.kernel.org S: Maintained F: drivers/scsi/sym53c8xx_2/ diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index f453997a7b8f..a9bc90dc4ae7 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -2,7 +2,7 @@ * Linux/PA-RISC Project (http://www.parisc-linux.org/) * * System call entry code / Linux gateway page - * Copyright (c) Matthew Wilcox 1999 + * Copyright (c) Matthew Wilcox 1999 * Licensed under the GNU GPL. * thanks to Philipp Rumpf, Mike Shaver and various others * sorry about the wall, puffin.. diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c index 5c7afdec192c..f5c5ae8b6c06 100644 --- a/drivers/input/keyboard/hilkbd.c +++ b/drivers/input/keyboard/hilkbd.c @@ -2,7 +2,7 @@ * linux/drivers/hil/hilkbd.c * * Copyright (C) 1998 Philip Blundell - * Copyright (C) 1999 Matthew Wilcox + * Copyright (C) 1999 Matthew Wilcox * Copyright (C) 1999-2007 Helge Deller * * Very basic HP Human Interface Loop (HIL) driver. diff --git a/drivers/pci/hotplug/acpiphp.h b/drivers/pci/hotplug/acpiphp.h index e438a2d734f2..14cef4cf592b 100644 --- a/drivers/pci/hotplug/acpiphp.h +++ b/drivers/pci/hotplug/acpiphp.h @@ -8,7 +8,7 @@ * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com) * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com) * Copyright (C) 2002,2003 NEC Corporation - * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com) + * Copyright (C) 2003-2005 Matthew Wilcox (willy@infradead.org) * Copyright (C) 2003-2005 Hewlett Packard * * All rights reserved. diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index ad32ffbc4b91..0447b169e7ff 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -8,7 +8,7 @@ * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com) * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com) * Copyright (C) 2002,2003 NEC Corporation - * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com) + * Copyright (C) 2003-2005 Matthew Wilcox (willy@infradead.org) * Copyright (C) 2003-2005 Hewlett Packard * * All rights reserved. @@ -40,7 +40,7 @@ bool acpiphp_disabled; static struct acpiphp_attention_info *attention_info; #define DRIVER_VERSION "0.5" -#define DRIVER_AUTHOR "Greg Kroah-Hartman , Takayoshi Kochi , Matthew Wilcox " +#define DRIVER_AUTHOR "Greg Kroah-Hartman , Takayoshi Kochi , Matthew Wilcox " #define DRIVER_DESC "ACPI Hot Plug PCI Controller Driver" MODULE_AUTHOR(DRIVER_AUTHOR); diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 12afa7fdf77e..e4c46637f32f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -5,7 +5,7 @@ * Copyright (C) 2002,2003 Takayoshi Kochi (t-kochi@bq.jp.nec.com) * Copyright (C) 2002 Hiroshi Aono (h-aono@ap.jp.nec.com) * Copyright (C) 2002,2003 NEC Corporation - * Copyright (C) 2003-2005 Matthew Wilcox (matthew.wilcox@hp.com) + * Copyright (C) 2003-2005 Matthew Wilcox (willy@infradead.org) * Copyright (C) 2003-2005 Hewlett Packard * Copyright (C) 2005 Rajesh Shah (rajesh.shah@intel.com) * Copyright (C) 2005 Intel Corporation diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c index 947ce22f5b3c..f0fe641893a5 100644 --- a/fs/isofs/dir.c +++ b/fs/isofs/dir.c @@ -46,7 +46,7 @@ int isofs_name_translate(struct iso_directory_record *de, char *new, struct inod return i; } -/* Acorn extensions written by Matthew Wilcox 1998 */ +/* Acorn extensions written by Matthew Wilcox 1998 */ int get_acorn_filename(struct iso_directory_record *de, char *retname, struct inode *inode) { diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2dfc8006fe64..9e4c86853fa4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -4,7 +4,7 @@ /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation - * Author: Matthew Wilcox + * Author: Matthew Wilcox */ #include -- cgit v1.2.3-71-gd317 From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 13:30:42 -0400 Subject: xarray: Replace exceptional entries Introduce xarray value entries and tagged pointers to replace radix tree exceptional entries. This is a slight change in encoding to allow the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a value entry). It is also a change in emphasis; exceptional entries are intimidating and different. As the comment explains, you can choose to store values or pointers in the xarray and they are both first-class citizens. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- arch/powerpc/include/asm/book3s/64/pgtable.h | 4 +- arch/powerpc/include/asm/nohash/64/pgtable.h | 4 +- drivers/gpu/drm/i915/i915_gem.c | 17 ++-- drivers/staging/erofs/utils.c | 18 ++--- fs/btrfs/compression.c | 2 +- fs/dax.c | 112 +++++++++++++-------------- fs/proc/task_mmu.c | 2 +- include/linux/radix-tree.h | 36 ++------- include/linux/swapops.h | 19 ++--- include/linux/xarray.h | 102 ++++++++++++++++++++++++ lib/idr.c | 60 ++++++-------- lib/radix-tree.c | 21 +++-- mm/filemap.c | 10 +-- mm/khugepaged.c | 2 +- mm/madvise.c | 2 +- mm/memcontrol.c | 2 +- mm/mincore.c | 2 +- mm/readahead.c | 2 +- mm/shmem.c | 10 +-- mm/swap.c | 2 +- mm/truncate.c | 12 +-- mm/workingset.c | 13 ++-- tools/testing/radix-tree/idr-test.c | 6 +- tools/testing/radix-tree/linux/radix-tree.h | 1 - tools/testing/radix-tree/multiorder.c | 47 ++++++----- tools/testing/radix-tree/test.c | 2 +- 26 files changed, 278 insertions(+), 232 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2fdc865ca374..62039e557ac0 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -723,9 +723,7 @@ static inline bool pte_user(pte_t pte) BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ } while (0) -/* - * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; - */ + #define SWP_TYPE_BITS 5 #define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ & ((1UL << SWP_TYPE_BITS) - 1)) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 7cd6809f4d33..05765c2d2c1f 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -313,9 +313,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define MAX_SWAPFILES_CHECK() do { \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ } while (0) -/* - * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; - */ + #define SWP_TYPE_BITS 5 #define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ & ((1UL << SWP_TYPE_BITS) - 1)) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index fcc73a6ab503..316730b45f84 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5996,7 +5996,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, count = __sg_page_count(sg); while (idx + count <= n) { - unsigned long exception, i; + void *entry; + unsigned long i; int ret; /* If we cannot allocate and insert this entry, or the @@ -6011,12 +6012,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, if (ret && ret != -EEXIST) goto scan; - exception = - RADIX_TREE_EXCEPTIONAL_ENTRY | - idx << RADIX_TREE_EXCEPTIONAL_SHIFT; + entry = xa_mk_value(idx); for (i = 1; i < count; i++) { - ret = radix_tree_insert(&iter->radix, idx + i, - (void *)exception); + ret = radix_tree_insert(&iter->radix, idx + i, entry); if (ret && ret != -EEXIST) goto scan; } @@ -6054,15 +6052,14 @@ lookup: GEM_BUG_ON(!sg); /* If this index is in the middle of multi-page sg entry, - * the radixtree will contain an exceptional entry that points + * the radix tree will contain a value entry that points * to the start of that range. We will return the pointer to * the base page and the offset of this page within the * sg entry's range. */ *offset = 0; - if (unlikely(radix_tree_exception(sg))) { - unsigned long base = - (unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + if (unlikely(xa_is_value(sg))) { + unsigned long base = xa_to_value(sg); sg = radix_tree_lookup(&iter->radix, base); GEM_BUG_ON(!sg); diff --git a/drivers/staging/erofs/utils.c b/drivers/staging/erofs/utils.c index 595cf90af9bb..bdee9bd09f11 100644 --- a/drivers/staging/erofs/utils.c +++ b/drivers/staging/erofs/utils.c @@ -35,7 +35,6 @@ static atomic_long_t erofs_global_shrink_cnt; #ifdef CONFIG_EROFS_FS_ZIP -/* radix_tree and the future XArray both don't use tagptr_t yet */ struct erofs_workgroup *erofs_find_workgroup( struct super_block *sb, pgoff_t index, bool *tag) { @@ -47,9 +46,8 @@ repeat: rcu_read_lock(); grp = radix_tree_lookup(&sbi->workstn_tree, index); if (grp != NULL) { - *tag = radix_tree_exceptional_entry(grp); - grp = (void *)((unsigned long)grp & - ~RADIX_TREE_EXCEPTIONAL_ENTRY); + *tag = xa_pointer_tag(grp); + grp = xa_untag_pointer(grp); if (erofs_workgroup_get(grp, &oldcount)) { /* prefer to relax rcu read side */ @@ -83,9 +81,7 @@ int erofs_register_workgroup(struct super_block *sb, sbi = EROFS_SB(sb); erofs_workstn_lock(sbi); - if (tag) - grp = (void *)((unsigned long)grp | - 1UL << RADIX_TREE_EXCEPTIONAL_SHIFT); + grp = xa_tag_pointer(grp, tag); err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp); @@ -131,9 +127,7 @@ repeat: for (i = 0; i < found; ++i) { int cnt; - struct erofs_workgroup *grp = (void *) - ((unsigned long)batch[i] & - ~RADIX_TREE_EXCEPTIONAL_ENTRY); + struct erofs_workgroup *grp = xa_untag_pointer(batch[i]); first_index = grp->index + 1; @@ -150,8 +144,8 @@ repeat: #endif continue; - if (radix_tree_delete(&sbi->workstn_tree, - grp->index) != grp) { + if (xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree, + grp->index)) != grp) { #ifdef EROFS_FS_HAS_MANAGED_CACHE skip: erofs_workgroup_unfreeze(grp, 1); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 9bfa66592aa7..fd25e125303c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -440,7 +440,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->i_pages, pg_index); rcu_read_unlock(); - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { misses++; if (misses > 4) break; diff --git a/fs/dax.c b/fs/dax.c index b68ce484e1be..ebcec36335eb 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -59,56 +59,57 @@ static int __init init_dax_wait_table(void) fs_initcall(init_dax_wait_table); /* - * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a zero page or - * an empty entry that is just used for locking. In total four special bits. + * DAX pagecache entries use XArray value entries so they can't be mistaken + * for pages. We use one bit for locking, one bit for the entry size (PMD) + * and two more to tell us if the entry is a zero page or an empty entry that + * is just used for locking. In total four special bits. * * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem * block allocation. */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) -#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) +#define DAX_SHIFT (4) +#define DAX_LOCKED (1UL << 0) +#define DAX_PMD (1UL << 1) +#define DAX_ZERO_PAGE (1UL << 2) +#define DAX_EMPTY (1UL << 3) static unsigned long dax_radix_pfn(void *entry) { - return (unsigned long)entry >> RADIX_DAX_SHIFT; + return xa_to_value(entry) >> DAX_SHIFT; } static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags) { - return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | - (pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK); + return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) | + DAX_LOCKED); } static unsigned int dax_radix_order(void *entry) { - if ((unsigned long)entry & RADIX_DAX_PMD) + if (xa_to_value(entry) & DAX_PMD) return PMD_SHIFT - PAGE_SHIFT; return 0; } static int dax_is_pmd_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_PMD; + return xa_to_value(entry) & DAX_PMD; } static int dax_is_pte_entry(void *entry) { - return !((unsigned long)entry & RADIX_DAX_PMD); + return !(xa_to_value(entry) & DAX_PMD); } static int dax_is_zero_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_ZERO_PAGE; + return xa_to_value(entry) & DAX_ZERO_PAGE; } static int dax_is_empty_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_EMPTY; + return xa_to_value(entry) & DAX_EMPTY; } /* @@ -186,9 +187,9 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping, */ static inline int slot_locked(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - return entry & RADIX_DAX_ENTRY_LOCK; + unsigned long entry = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + return entry & DAX_LOCKED; } /* @@ -196,12 +197,11 @@ static inline int slot_locked(struct address_space *mapping, void **slot) */ static inline void *lock_slot(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - - entry |= RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); - return (void *)entry; + unsigned long v = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + void *entry = xa_mk_value(v | DAX_LOCKED); + radix_tree_replace_slot(&mapping->i_pages, slot, entry); + return entry; } /* @@ -209,17 +209,16 @@ static inline void *lock_slot(struct address_space *mapping, void **slot) */ static inline void *unlock_slot(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - - entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); - return (void *)entry; + unsigned long v = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + void *entry = xa_mk_value(v & ~DAX_LOCKED); + radix_tree_replace_slot(&mapping->i_pages, slot, entry); + return entry; } /* * Lookup entry in radix tree, wait for it to become unlocked if it is - * exceptional entry and return it. The caller must call + * a DAX entry and return it. The caller must call * put_unlocked_mapping_entry() when he decided not to lock the entry or * put_locked_mapping_entry() when he locked the entry and now wants to * unlock it. @@ -242,7 +241,7 @@ static void *__get_unlocked_mapping_entry(struct address_space *mapping, entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); if (!entry || - WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) || + WARN_ON_ONCE(!xa_is_value(entry)) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; @@ -283,7 +282,7 @@ static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index) xa_lock_irq(&mapping->i_pages); entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); - if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) || + if (WARN_ON_ONCE(!entry || !xa_is_value(entry) || !slot_locked(mapping, slot))) { xa_unlock_irq(&mapping->i_pages); return; @@ -472,12 +471,11 @@ void dax_unlock_mapping_entry(struct page *page) } /* - * Find radix tree entry at given index. If it points to an exceptional entry, - * return it with the radix tree entry locked. If the radix tree doesn't - * contain given index, create an empty exceptional entry for the index and - * return with it locked. + * Find radix tree entry at given index. If it is a DAX entry, return it + * with the radix tree entry locked. If the radix tree doesn't contain the + * given index, create an empty entry for the index and return with it locked. * - * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will + * When requesting an entry with size DAX_PMD, grab_mapping_entry() will * either return that locked entry or will return an error. This error will * happen if there are any 4k entries within the 2MiB range that we are * requesting. @@ -507,13 +505,13 @@ restart: xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, &slot); - if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) { + if (WARN_ON_ONCE(entry && !xa_is_value(entry))) { entry = ERR_PTR(-EIO); goto out_unlock; } if (entry) { - if (size_flag & RADIX_DAX_PMD) { + if (size_flag & DAX_PMD) { if (dax_is_pte_entry(entry)) { put_unlocked_mapping_entry(mapping, index, entry); @@ -584,7 +582,7 @@ restart: true); } - entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY); + entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY); err = __radix_tree_insert(&mapping->i_pages, index, dax_radix_order(entry), entry); @@ -673,8 +671,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping) if (index >= end) break; - if (WARN_ON_ONCE( - !radix_tree_exceptional_entry(pvec_ent))) + if (WARN_ON_ONCE(!xa_is_value(pvec_ent))) continue; xa_lock_irq(&mapping->i_pages); @@ -713,7 +710,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping, xa_lock_irq(pages); entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry))) + if (!entry || WARN_ON_ONCE(!xa_is_value(entry))) goto out; if (!trunc && (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) || @@ -729,8 +726,8 @@ out: return ret; } /* - * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree - * entry to get unlocked before deleting it. + * Delete DAX entry at @index from @mapping. Wait for it + * to be unlocked before deleting it. */ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) { @@ -740,7 +737,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) * This gets called from truncate / punch_hole path. As such, the caller * must hold locks protecting against concurrent modifications of the * radix tree (usually fs-private i_mmap_sem for writing). Since the - * caller has seen exceptional entry for this index, we better find it + * caller has seen a DAX entry for this index, we better find it * at that index as well... */ WARN_ON_ONCE(!ret); @@ -748,7 +745,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) } /* - * Invalidate exceptional DAX entry if it is clean. + * Invalidate DAX entry if it is clean. */ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index) @@ -802,7 +799,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) { + if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) { /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR, @@ -940,13 +937,13 @@ static int dax_writeback_one(struct dax_device *dax_dev, * A page got tagged dirty in DAX mapping? Something is seriously * wrong. */ - if (WARN_ON(!radix_tree_exceptional_entry(entry))) + if (WARN_ON(!xa_is_value(entry))) return -EIO; xa_lock_irq(pages); entry2 = get_unlocked_mapping_entry(mapping, index, &slot); /* Entry got punched out / reallocated? */ - if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2))) + if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2))) goto put_unlocked; /* * Entry got reallocated elsewhere? No need to writeback. We have to @@ -1123,8 +1120,9 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry, pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); vm_fault_t ret; - dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE, - false); + dax_insert_mapping_entry(mapping, vmf, entry, pfn, + DAX_ZERO_PAGE, false); + ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); trace_dax_load_hole(inode, vmf, ret); return ret; @@ -1514,7 +1512,7 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, pfn = page_to_pfn_t(zero_page); ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn, - RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false); + DAX_PMD | DAX_ZERO_PAGE, false); ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { @@ -1597,7 +1595,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * is already in the tree, for instance), it will return -EEXIST and * we just fall back to 4k entries. */ - entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD); + entry = grab_mapping_entry(mapping, pgoff, DAX_PMD); if (IS_ERR(entry)) goto fallback; @@ -1635,7 +1633,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, goto finish_iomap; entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn, - RADIX_DAX_PMD, write && !sync); + DAX_PMD, write && !sync); /* * If we are doing synchronous page fault and inode needs fsync, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5ea1d64cb0b4..669abb617321 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -521,7 +521,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) mss->swap += PAGE_SIZE; else put_page(page); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 34149e8b5f73..e9e76ab4fbbf 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -28,34 +28,26 @@ #include #include #include +#include /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer - * 01 - internal entry - * 10 - exceptional entry - * 11 - this bit combination is currently unused/reserved + * 10 - internal entry + * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). - * This means that you cannot store NULL in the tree as a value for the index. + * This means that storing a NULL entry in the tree is the same as deleting + * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL -#define RADIX_TREE_INTERNAL_NODE 1UL - -/* - * Most users of the radix tree store pointers but shmem/tmpfs stores swap - * entries in the same tree. They are marked as exceptional entries to - * distinguish them from pointers to struct page. - * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. - */ -#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 -#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 +#define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { @@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) /* * @count is the count of every non-NULL element in the ->slots array - * whether that is an exceptional entry, a retry entry, a user pointer, + * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @exceptional is the count of every element in ->slots which is - * either radix_tree_exceptional_entry() or is a sibling entry for an - * exceptional entry. + * either a value entry or a sibling of a value entry. */ struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ @@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely(radix_tree_is_internal_node(arg)); } -/** - * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? - * @arg: value returned by radix_tree_deref_slot - * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. - */ -static inline int radix_tree_exceptional_entry(void *arg) -{ - /* Not unlikely because radix_tree_exception often tested first */ - return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; -} - /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 22af9d8a84ae..4d961668e5fc 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -18,9 +18,8 @@ * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -#define SWP_TYPE_SHIFT(e) ((sizeof(e.val) * 8) - \ - (MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT)) -#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1) +#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) +#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Store a type+offset into a swp_entry_t in an arch-independent format @@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; - ret.val = (type << SWP_TYPE_SHIFT(ret)) | - (offset & SWP_OFFSET_MASK(ret)); + ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } @@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) */ static inline unsigned swp_type(swp_entry_t entry) { - return (entry.val >> SWP_TYPE_SHIFT(entry)); + return (entry.val >> SWP_TYPE_SHIFT); } /* @@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry) */ static inline pgoff_t swp_offset(swp_entry_t entry) { - return entry.val & SWP_OFFSET_MASK(entry); + return entry.val & SWP_OFFSET_MASK; } #ifdef CONFIG_MMU @@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; - entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { - unsigned long value; - - value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; - return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9e4c86853fa4..5c8acfc4ff55 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -5,9 +5,111 @@ * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox + * + * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include #include +#include + +/* + * The bottom two bits of the entry determine how the XArray interprets + * the contents: + * + * 00: Pointer entry + * 10: Internal entry + * x1: Value entry or tagged pointer + * + * Attempting to store internal entries in the XArray is a bug. + */ + +#define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) + +/** + * xa_mk_value() - Create an XArray entry from an integer. + * @v: Value to store in XArray. + * + * Context: Any context. + * Return: An entry suitable for storing in the XArray. + */ +static inline void *xa_mk_value(unsigned long v) +{ + WARN_ON((long)v < 0); + return (void *)((v << 1) | 1); +} + +/** + * xa_to_value() - Get value stored in an XArray entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value stored in the XArray entry. + */ +static inline unsigned long xa_to_value(const void *entry) +{ + return (unsigned long)entry >> 1; +} + +/** + * xa_is_value() - Determine if an entry is a value. + * @entry: XArray entry. + * + * Context: Any context. + * Return: True if the entry is a value, false if it is a pointer. + */ +static inline bool xa_is_value(const void *entry) +{ + return (unsigned long)entry & 1; +} + +/** + * xa_tag_pointer() - Create an XArray entry for a tagged pointer. + * @p: Plain pointer. + * @tag: Tag value (0, 1 or 3). + * + * If the user of the XArray prefers, they can tag their pointers instead + * of storing value entries. Three tags are available (0, 1 and 3). + * These are distinct from the xa_mark_t as they are not replicated up + * through the array and cannot be searched for. + * + * Context: Any context. + * Return: An XArray entry. + */ +static inline void *xa_tag_pointer(void *p, unsigned long tag) +{ + return (void *)((unsigned long)p | tag); +} + +/** + * xa_untag_pointer() - Turn an XArray entry into a plain pointer. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the untagged version of the pointer. + * + * Context: Any context. + * Return: A pointer. + */ +static inline void *xa_untag_pointer(void *entry) +{ + return (void *)((unsigned long)entry & ~3UL); +} + +/** + * xa_pointer_tag() - Get the tag stored in an XArray entry. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the tag of that pointer. + * + * Context: Any context. + * Return: A tag. + */ +static inline unsigned int xa_pointer_tag(void *entry) +{ + return (unsigned long)entry & 3UL; +} #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) diff --git a/lib/idr.c b/lib/idr.c index 729e381e23b4..88419fbc5737 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -338,11 +338,8 @@ EXPORT_SYMBOL(idr_replace); * by the number of bits in the leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given - * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional - * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits - * directly in the entry. By being really tricksy, we could store - * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising - * for 0-3 allocated IDs. + * leaf, instead of allocating a 128-byte bitmap, we store the bits + * directly in the entry. * * We allow the radix tree 'exceptional' count to get out of date. Nothing * in the IDA nor the radix tree code checks it. If it becomes important @@ -366,12 +363,11 @@ static int ida_get_new_above(struct ida *ida, int start) struct radix_tree_iter iter; struct ida_bitmap *bitmap; unsigned long index; - unsigned bit, ebit; + unsigned bit; int new; index = start / IDA_BITMAP_BITS; bit = start % IDA_BITMAP_BITS; - ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT; slot = radix_tree_iter_init(&iter, index); for (;;) { @@ -386,25 +382,23 @@ static int ida_get_new_above(struct ida *ida, int start) return PTR_ERR(slot); } } - if (iter.index > index) { + if (iter.index > index) bit = 0; - ebit = RADIX_TREE_EXCEPTIONAL_SHIFT; - } new = iter.index * IDA_BITMAP_BITS; bitmap = rcu_dereference_raw(*slot); - if (radix_tree_exception(bitmap)) { - unsigned long tmp = (unsigned long)bitmap; - ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit); - if (ebit < BITS_PER_LONG) { - tmp |= 1UL << ebit; - rcu_assign_pointer(*slot, (void *)tmp); - return new + ebit - - RADIX_TREE_EXCEPTIONAL_SHIFT; + if (xa_is_value(bitmap)) { + unsigned long tmp = xa_to_value(bitmap); + int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, + bit); + if (vbit < BITS_PER_XA_VALUE) { + tmp |= 1UL << vbit; + rcu_assign_pointer(*slot, xa_mk_value(tmp)); + return new + vbit; } bitmap = this_cpu_xchg(ida_bitmap, NULL); if (!bitmap) return -EAGAIN; - bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT; + bitmap->bitmap[0] = tmp; rcu_assign_pointer(*slot, bitmap); } @@ -425,17 +419,14 @@ static int ida_get_new_above(struct ida *ida, int start) new += bit; if (new < 0) return -ENOSPC; - if (ebit < BITS_PER_LONG) { - bitmap = (void *)((1UL << ebit) | - RADIX_TREE_EXCEPTIONAL_ENTRY); - radix_tree_iter_replace(root, &iter, slot, - bitmap); - return new; + if (bit < BITS_PER_XA_VALUE) { + bitmap = xa_mk_value(1UL << bit); + } else { + bitmap = this_cpu_xchg(ida_bitmap, NULL); + if (!bitmap) + return -EAGAIN; + __set_bit(bit, bitmap->bitmap); } - bitmap = this_cpu_xchg(ida_bitmap, NULL); - if (!bitmap) - return -EAGAIN; - __set_bit(bit, bitmap->bitmap); radix_tree_iter_replace(root, &iter, slot, bitmap); } @@ -457,9 +448,9 @@ static void ida_remove(struct ida *ida, int id) goto err; bitmap = rcu_dereference_raw(*slot); - if (radix_tree_exception(bitmap)) { + if (xa_is_value(bitmap)) { btmp = (unsigned long *)slot; - offset += RADIX_TREE_EXCEPTIONAL_SHIFT; + offset += 1; /* Intimate knowledge of the value encoding */ if (offset >= BITS_PER_LONG) goto err; } else { @@ -470,9 +461,8 @@ static void ida_remove(struct ida *ida, int id) __clear_bit(offset, btmp); radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE); - if (radix_tree_exception(bitmap)) { - if (rcu_dereference_raw(*slot) == - (void *)RADIX_TREE_EXCEPTIONAL_ENTRY) + if (xa_is_value(bitmap)) { + if (xa_to_value(rcu_dereference_raw(*slot)) == 0) radix_tree_iter_delete(&ida->ida_rt, &iter, slot); } else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) { kfree(bitmap); @@ -503,7 +493,7 @@ void ida_destroy(struct ida *ida) xa_lock_irqsave(&ida->ida_rt, flags); radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) { struct ida_bitmap *bitmap = rcu_dereference_raw(*slot); - if (!radix_tree_exception(bitmap)) + if (!xa_is_value(bitmap)) kfree(bitmap); radix_tree_iter_delete(&ida->ida_rt, &iter, slot); } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index a904a8ddd174..b6c0e7f3a894 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -340,14 +340,12 @@ static void dump_ida_node(void *entry, unsigned long index) for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) dump_ida_node(node->slots[i], index | (i << node->shift)); - } else if (radix_tree_exceptional_entry(entry)) { + } else if (xa_is_value(entry)) { pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n", entry, (int)(index & RADIX_TREE_MAP_MASK), index * IDA_BITMAP_BITS, - index * IDA_BITMAP_BITS + BITS_PER_LONG - - RADIX_TREE_EXCEPTIONAL_SHIFT, - (unsigned long)entry >> - RADIX_TREE_EXCEPTIONAL_SHIFT); + index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE, + xa_to_value(entry)); } else { struct ida_bitmap *bitmap = entry; @@ -656,7 +654,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; - } else if (radix_tree_exceptional_entry(entry)) { + } else if (xa_is_value(entry)) { /* Moving an exceptional root->rnode to a node */ node->exceptional = 1; } @@ -955,12 +953,12 @@ static inline int insert_entries(struct radix_tree_node *node, !is_sibling_entry(node, old) && (old != RADIX_TREE_RETRY)) radix_tree_free_nodes(old); - if (radix_tree_exceptional_entry(old)) + if (xa_is_value(old)) node->exceptional--; } if (node) { node->count += n; - if (radix_tree_exceptional_entry(item)) + if (xa_is_value(item)) node->exceptional += n; } return n; @@ -974,7 +972,7 @@ static inline int insert_entries(struct radix_tree_node *node, rcu_assign_pointer(*slot, item); if (node) { node->count++; - if (radix_tree_exceptional_entry(item)) + if (xa_is_value(item)) node->exceptional++; } return 1; @@ -1190,8 +1188,7 @@ void __radix_tree_replace(struct radix_tree_root *root, radix_tree_update_node_t update_node) { void *old = rcu_dereference_raw(*slot); - int exceptional = !!radix_tree_exceptional_entry(item) - - !!radix_tree_exceptional_entry(old); + int exceptional = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* @@ -1992,7 +1989,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); - int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0; + int exceptional = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..4de14e75c4ec 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -127,7 +127,7 @@ static int page_cache_tree_insert(struct address_space *mapping, p = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (!radix_tree_exceptional_entry(p)) + if (!xa_is_value(p)) return -EEXIST; mapping->nrexceptional--; @@ -336,7 +336,7 @@ page_cache_tree_delete_batch(struct address_space *mapping, break; page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; if (!tail_pages) { /* @@ -1355,7 +1355,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || radix_tree_exceptional_entry(page)) + if (!page || xa_is_value(page)) break; index++; if (index == 0) @@ -1396,7 +1396,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || radix_tree_exceptional_entry(page)) + if (!page || xa_is_value(page)) break; index--; if (index == ULONG_MAX) @@ -1539,7 +1539,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, repeat: page = find_get_entry(mapping, offset); - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) page = NULL; if (!page) goto no_page; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a31d740e6cd1..4820e4adf853 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1369,7 +1369,7 @@ static void collapse_shmem(struct mm_struct *mm, page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) { + if (xa_is_value(page) || !PageUptodate(page)) { xa_unlock_irq(&mapping->i_pages); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, diff --git a/mm/madvise.c b/mm/madvise.c index 972a9eaa898b..9d802566c494 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -251,7 +251,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; page = find_get_entry(mapping, index); - if (!radix_tree_exceptional_entry(page)) { + if (!xa_is_value(page)) { if (page) put_page(page); continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e79cb59552d9..29d9d1a69b36 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4750,7 +4750,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, /* shmem/tmpfs may report page out on swap: account for that too. */ if (shmem_mapping(mapping)) { page = find_get_entry(mapping, pgoff); - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swp_entry_t swp = radix_to_swp_entry(page); if (do_memsw_account()) *entry = swp; diff --git a/mm/mincore.c b/mm/mincore.c index fc37afe226e6..4985965aa20a 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -66,7 +66,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * shmem/tmpfs may return swap: account for swapcache * page too. */ - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swp_entry_t swp = radix_to_swp_entry(page); page = find_get_page(swap_address_space(swp), swp_offset(swp)); diff --git a/mm/readahead.c b/mm/readahead.c index 4e630143a0ba..de657077d41d 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -179,7 +179,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping, rcu_read_lock(); page = radix_tree_lookup(&mapping->i_pages, page_offset); rcu_read_unlock(); - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { /* * Page already present? Kick off the current batch of * contiguous pages before continuing with the next diff --git a/mm/shmem.c b/mm/shmem.c index 446942677cd4..c1062760fe41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, continue; } - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) swapped++; if (need_resched()) { @@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, @@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, page)) { @@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, repeat: swap.val = 0; page = find_lock_entry(mapping, index); - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swap = radix_to_swp_entry(page); page = NULL; } @@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, index = indices[i]; } page = pvec.pages[i]; - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { if (!PageUptodate(page)) page = NULL; } diff --git a/mm/swap.c b/mm/swap.c index 26fc9b5f1b6c..4c5c7fcc6e46 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -965,7 +965,7 @@ void pagevec_remove_exceptionals(struct pagevec *pvec) for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) + if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; diff --git a/mm/truncate.c b/mm/truncate.c index 1d2fb2dca96f..ed778555c9f3 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -70,7 +70,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, return; for (j = 0; j < pagevec_count(pvec); j++) - if (radix_tree_exceptional_entry(pvec->pages[j])) + if (xa_is_value(pvec->pages[j])) break; if (j == pagevec_count(pvec)) @@ -85,7 +85,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, struct page *page = pvec->pages[i]; pgoff_t index = indices[i]; - if (!radix_tree_exceptional_entry(page)) { + if (!xa_is_value(page)) { pvec->pages[j++] = page; continue; } @@ -347,7 +347,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; if (!trylock_page(page)) @@ -442,7 +442,7 @@ void truncate_inode_pages_range(struct address_space *mapping, break; } - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; lock_page(page); @@ -561,7 +561,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (index > end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; @@ -692,7 +692,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (index > end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, index, page)) ret = -EBUSY; diff --git a/mm/workingset.c b/mm/workingset.c index 4516dd790129..bb109b3afac2 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -155,8 +155,8 @@ * refault distance will immediately activate the refaulting page. */ -#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ +#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ + NODES_SHIFT + \ MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) @@ -173,20 +173,19 @@ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) { eviction >>= bucket_order; + eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; - eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); - return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp) { - unsigned long entry = (unsigned long)shadow; + unsigned long entry = xa_to_value(shadow); int memcgid, nid; - entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -453,7 +452,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { - if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i]))) + if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) goto out_invalid; if (WARN_ON_ONCE(!node->exceptional)) goto out_invalid; diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index f620c831a4b5..a5a4494922a6 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -19,7 +19,7 @@ #include "test.h" -#define DUMMY_PTR ((void *)0x12) +#define DUMMY_PTR ((void *)0x10) int item_idr_free(int id, void *p, void *data) { @@ -411,11 +411,11 @@ void ida_check_conv_user(void) int id = ida_alloc(&ida, GFP_NOWAIT); if (id == -ENOMEM) { IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) != - BITS_PER_LONG - 2); + BITS_PER_XA_VALUE); id = ida_alloc(&ida, GFP_KERNEL); } else { IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) == - BITS_PER_LONG - 2); + BITS_PER_XA_VALUE); } IDA_BUG_ON(&ida, id != i); } diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h index 24f13d27a8da..d1635a5bef02 100644 --- a/tools/testing/radix-tree/linux/radix-tree.h +++ b/tools/testing/radix-tree/linux/radix-tree.h @@ -2,7 +2,6 @@ #ifndef _TEST_RADIX_TREE_H #define _TEST_RADIX_TREE_H -#include "generated/map-shift.h" #include "../../../../include/linux/radix-tree.h" extern int kmalloc_verbose; diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 7bf405638b0b..2b4f4dba1882 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -39,12 +39,11 @@ static void __multiorder_tag_test(int index, int order) /* * Verify we get collisions for covered indices. We try and fail to - * insert an exceptional entry so we don't leak memory via + * insert a value entry so we don't leak memory via * item_insert_order(). */ for_each_index(i, base, order) { - err = __radix_tree_insert(&tree, i, order, - (void *)(0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY)); + err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0)); assert(err == -EEXIST); } @@ -380,8 +379,8 @@ static void multiorder_join1(unsigned long index, } /* - * Check that the accounting of exceptional entries is handled correctly - * by joining an exceptional entry to a normal pointer. + * Check that the accounting of value entries is handled correctly + * by joining a value entry to a normal pointer. */ static void multiorder_join2(unsigned order1, unsigned order2) { @@ -391,9 +390,9 @@ static void multiorder_join2(unsigned order1, unsigned order2) void *item2; item_insert_order(&tree, 0, order2); - radix_tree_insert(&tree, 1 << order2, (void *)0x12UL); + radix_tree_insert(&tree, 1 << order2, xa_mk_value(5)); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); - assert(item2 == (void *)0x12UL); + assert(item2 == xa_mk_value(5)); assert(node->exceptional == 1); item2 = radix_tree_lookup(&tree, 0); @@ -407,7 +406,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) } /* - * This test revealed an accounting bug for exceptional entries at one point. + * This test revealed an accounting bug for value entries at one point. * Nodes were being freed back into the pool with an elevated exception count * by radix_tree_join() and then radix_tree_split() was failing to zero the * count of exceptional entries. @@ -421,16 +420,16 @@ static void multiorder_join3(unsigned int order) unsigned long i; for (i = 0; i < (1 << order); i++) { - radix_tree_insert(&tree, i, (void *)0x12UL); + radix_tree_insert(&tree, i, xa_mk_value(5)); } - radix_tree_join(&tree, 0, order, (void *)0x16UL); + radix_tree_join(&tree, 0, order, xa_mk_value(7)); rcu_barrier(); radix_tree_split(&tree, 0, 0); radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL); + radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5)); } __radix_tree_lookup(&tree, 0, &node, NULL); @@ -517,10 +516,10 @@ static void __multiorder_split2(int old_order, int new_order) struct radix_tree_node *node; void *item; - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); @@ -530,7 +529,7 @@ static void __multiorder_split2(int old_order, int new_order) } item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item != (void *)0x12); + assert(item != xa_mk_value(5)); assert(node->exceptional == 0); item_kill_tree(&tree); @@ -544,40 +543,40 @@ static void __multiorder_split3(int old_order, int new_order) struct radix_tree_node *node; void *item; - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16); + radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7)); } item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x16); + assert(item == xa_mk_value(7)); assert(node->exceptional > 0); item_kill_tree(&tree); - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { if (iter.index == (1 << new_order)) radix_tree_iter_replace(&tree, &iter, slot, - (void *)0x16); + xa_mk_value(7)); else radix_tree_iter_replace(&tree, &iter, slot, NULL); } item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); - assert(item == (void *)0x16); + assert(item == xa_mk_value(7)); assert(node->count == node->exceptional); do { node = node->parent; @@ -610,13 +609,13 @@ static void multiorder_account(void) item_insert_order(&tree, 0, 5); - __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 0, &node, NULL); assert(node->count == node->exceptional * 2); radix_tree_delete(&tree, 1 << 5); assert(node->exceptional == 0); - __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 1 << 5, &node, &slot); assert(node->count == node->exceptional * 2); __radix_tree_replace(&tree, node, slot, NULL, NULL); diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index def6015570b2..62de66c314b7 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -295,7 +295,7 @@ void item_kill_tree(struct radix_tree_root *root) int nfound; radix_tree_for_each_slot(slot, root, &iter, 0) { - if (radix_tree_exceptional_entry(*slot)) + if (xa_is_value(*slot)) radix_tree_delete(root, iter.index); } -- cgit v1.2.3-71-gd317 From 02c02bf12c5d838603eed44195d3e91f094e2ab2 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 23:09:45 -0400 Subject: xarray: Change definition of sibling entries Instead of storing a pointer to the slot containing the canonical entry, store the offset of the slot. Produces slightly more efficient code (~300 bytes) and simplifies the implementation. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 5 +- include/linux/xarray.h | 92 +++++++++++++++++++++++++++ lib/Kconfig | 7 ++ lib/radix-tree.c | 64 ++++++------------- tools/testing/radix-tree/Makefile | 2 +- tools/testing/radix-tree/generated/autoconf.h | 1 + 6 files changed, 121 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index e9e76ab4fbbf..60f3d8eb2cb7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -59,10 +59,7 @@ static inline bool radix_tree_is_internal_node(void *ptr) #define RADIX_TREE_MAX_TAGS 3 -#ifndef RADIX_TREE_MAP_SHIFT -#define RADIX_TREE_MAP_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) -#endif - +#define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5c8acfc4ff55..4d1cd7a083e8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -22,6 +22,12 @@ * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. + * + * Most internal entries are pointers to the next node in the tree. + * The following internal entries have a special meaning: + * + * 0-62: Sibling entries + * 256: Retry entry */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -111,6 +117,42 @@ static inline unsigned int xa_pointer_tag(void *entry) return (unsigned long)entry & 3UL; } +/* + * xa_mk_internal() - Create an internal entry. + * @v: Value to turn into an internal entry. + * + * Context: Any context. + * Return: An XArray internal entry corresponding to this value. + */ +static inline void *xa_mk_internal(unsigned long v) +{ + return (void *)((v << 2) | 2); +} + +/* + * xa_to_internal() - Extract the value from an internal entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value which was stored in the internal entry. + */ +static inline unsigned long xa_to_internal(const void *entry) +{ + return (unsigned long)entry >> 2; +} + +/* + * xa_is_internal() - Is the entry an internal entry? + * @entry: XArray entry. + * + * Context: Any context. + * Return: %true if the entry is an internal entry. + */ +static inline bool xa_is_internal(const void *entry) +{ + return ((unsigned long)entry & 3) == 2; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -123,4 +165,54 @@ static inline unsigned int xa_pointer_tag(void *entry) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* Everything below here is the Advanced API. Proceed with caution. */ + +/* + * The xarray is constructed out of a set of 'chunks' of pointers. Choosing + * the best chunk size requires some tradeoffs. A power of two recommends + * itself so that we can walk the tree based purely on shifts and masks. + * Generally, the larger the better; as the number of slots per level of the + * tree increases, the less tall the tree needs to be. But that needs to be + * balanced against the memory consumption of each node. On a 64-bit system, + * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we + * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. + */ +#ifndef XA_CHUNK_SHIFT +#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) +#endif +#define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) +#define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) + +/* Private */ +static inline bool xa_is_node(const void *entry) +{ + return xa_is_internal(entry) && (unsigned long)entry > 4096; +} + +/* Private */ +static inline void *xa_mk_sibling(unsigned int offset) +{ + return xa_mk_internal(offset); +} + +/* Private */ +static inline unsigned long xa_to_sibling(const void *entry) +{ + return xa_to_internal(entry); +} + +/** + * xa_is_sibling() - Is the entry a sibling entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a sibling entry. + */ +static inline bool xa_is_sibling(const void *entry) +{ + return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && + (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); +} + +#define XA_RETRY_ENTRY xa_mk_internal(256) + #endif /* _LINUX_XARRAY_H */ diff --git a/lib/Kconfig b/lib/Kconfig index a3928d4438b5..40bfa6ccd294 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -399,8 +399,15 @@ config INTERVAL_TREE for more information. +config XARRAY_MULTI + bool + help + Support entries which occupy multiple consecutive indices in the + XArray. + config RADIX_TREE_MULTIORDER bool + select XARRAY_MULTI config ASSOCIATIVE_ARRAY bool diff --git a/lib/radix-tree.c b/lib/radix-tree.c index b6c0e7f3a894..59b28111eabc 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -38,6 +38,7 @@ #include #include #include +#include /* Number of nodes in fully populated tree of given height */ @@ -98,24 +99,7 @@ static inline void *node_to_entry(void *ptr) return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } -#define RADIX_TREE_RETRY node_to_entry(NULL) - -#ifdef CONFIG_RADIX_TREE_MULTIORDER -/* Sibling slots point directly to another slot in the same node */ -static inline -bool is_sibling_entry(const struct radix_tree_node *parent, void *node) -{ - void __rcu **ptr = node; - return (parent->slots <= ptr) && - (ptr < parent->slots + RADIX_TREE_MAP_SIZE); -} -#else -static inline -bool is_sibling_entry(const struct radix_tree_node *parent, void *node) -{ - return false; -} -#endif +#define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) @@ -129,16 +113,10 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); -#ifdef CONFIG_RADIX_TREE_MULTIORDER - if (radix_tree_is_internal_node(entry)) { - if (is_sibling_entry(parent, entry)) { - void __rcu **sibentry; - sibentry = (void __rcu **) entry_to_node(entry); - offset = get_slot_offset(parent, sibentry); - entry = rcu_dereference_raw(*sibentry); - } + if (xa_is_sibling(entry)) { + offset = xa_to_sibling(entry); + entry = rcu_dereference_raw(parent->slots[offset]); } -#endif *nodep = (void *)entry; return offset; @@ -300,10 +278,10 @@ static void dump_node(struct radix_tree_node *node, unsigned long index) } else if (!radix_tree_is_internal_node(entry)) { pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n", entry, i, first, last, node); - } else if (is_sibling_entry(node, entry)) { + } else if (xa_is_sibling(entry)) { pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n", entry, i, first, last, node, - *(void **)entry_to_node(entry)); + node->slots[xa_to_sibling(entry)]); } else { dump_node(entry_to_node(entry), first); } @@ -881,8 +859,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); - if (radix_tree_is_internal_node(entry) && child->shift && - !is_sibling_entry(child, entry)) { + if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; @@ -904,7 +881,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item, unsigned order, bool replace) { - struct radix_tree_node *child; + void *sibling; unsigned i, n, tag, offset, tags = 0; if (node) { @@ -922,7 +899,7 @@ static inline int insert_entries(struct radix_tree_node *node, offset = offset & ~(n - 1); slot = &node->slots[offset]; } - child = node_to_entry(slot); + sibling = xa_mk_sibling(offset); for (i = 0; i < n; i++) { if (slot[i]) { @@ -939,7 +916,7 @@ static inline int insert_entries(struct radix_tree_node *node, for (i = 0; i < n; i++) { struct radix_tree_node *old = rcu_dereference_raw(slot[i]); if (i) { - rcu_assign_pointer(slot[i], child); + rcu_assign_pointer(slot[i], sibling); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_clear(node, tag, offset + i); @@ -949,9 +926,7 @@ static inline int insert_entries(struct radix_tree_node *node, if (tags & (1 << tag)) tag_set(node, tag, offset); } - if (radix_tree_is_internal_node(old) && - !is_sibling_entry(node, old) && - (old != RADIX_TREE_RETRY)) + if (xa_is_node(old)) radix_tree_free_nodes(old); if (xa_is_value(old)) node->exceptional--; @@ -1112,10 +1087,10 @@ static inline void replace_sibling_entries(struct radix_tree_node *node, void __rcu **slot, int count, int exceptional) { #ifdef CONFIG_RADIX_TREE_MULTIORDER - void *ptr = node_to_entry(slot); - unsigned offset = get_slot_offset(node, slot) + 1; + unsigned offset = get_slot_offset(node, slot); + void *ptr = xa_mk_sibling(offset); - while (offset < RADIX_TREE_MAP_SIZE) { + while (++offset < RADIX_TREE_MAP_SIZE) { if (rcu_dereference_raw(node->slots[offset]) != ptr) break; if (count < 0) { @@ -1123,7 +1098,6 @@ static inline void replace_sibling_entries(struct radix_tree_node *node, node->count--; } node->exceptional += exceptional; - offset++; } #endif } @@ -1319,8 +1293,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, tags |= 1 << tag; for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) { - if (!is_sibling_entry(parent, - rcu_dereference_raw(parent->slots[end]))) + if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end]))) break; for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) @@ -1618,7 +1591,7 @@ static void __rcu **skip_siblings(struct radix_tree_node **nodep, { while (iter->index < iter->next_index) { *nodep = rcu_dereference_raw(*slot); - if (*nodep && !is_sibling_entry(iter->node, *nodep)) + if (*nodep && !xa_is_sibling(*nodep)) return slot; slot++; iter->index = __radix_tree_iter_add(iter, 1); @@ -1769,7 +1742,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); - if (is_sibling_entry(node, slot)) + if (xa_is_sibling(slot)) continue; if (slot) break; @@ -2283,6 +2256,7 @@ void __init radix_tree_init(void) BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); + BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 37baecc3766f..12adcf9ffe86 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -46,6 +46,6 @@ idr.c: ../../../lib/idr.c generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ - echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ + echo "#define XA_CHUNK_SHIFT $(SHIFT)" > \ generated/map-shift.h; \ fi diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h index cf88dc5b8832..ca8e03ad19ac 100644 --- a/tools/testing/radix-tree/generated/autoconf.h +++ b/tools/testing/radix-tree/generated/autoconf.h @@ -1 +1,2 @@ #define CONFIG_RADIX_TREE_MULTIORDER 1 +#define CONFIG_XARRAY_MULTI 1 -- cgit v1.2.3-71-gd317 From 29efbc6aea9d9bd9aa9870a9afc1882046303cf9 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:07:27 +0200 Subject: Compiler Attributes: remove unused attributes __optimize and __deprecate_for_modules are unused in the whole kernel tree. Simply drop them. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 2 -- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 1 - 3 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 4d36b27214fd..1302b425e625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -81,8 +81,6 @@ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define __optimize(level) __attribute__((__optimize__(level))) - #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..7c0157d50964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -301,10 +301,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ -#ifndef __optimize -# define __optimize(level) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index db192becfec4..a19562cb047c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -108,7 +108,6 @@ struct ftrace_likely_data { /* Don't. Just don't. */ #define __deprecated -#define __deprecated_for_modules #endif /* __KERNEL__ */ -- cgit v1.2.3-71-gd317 From 5c67a52f3da0f0d22764f2daec417702695a8112 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:13:37 +0200 Subject: Compiler Attributes: always use the extra-underscores syntax The attribute syntax optionally allows to surround attribute names with "__" in order to avoid collisions with macros of the same name (see https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html). This homogenizes all attributes to use the syntax with underscores. While there are currently only a handful of cases of some TUs defining macros like "error" which may collide with the attributes, this should prevent futures surprises. This has been done only for "standard" attributes supported by the major compilers. In other words, those of third-party tools (e.g. sparse, plugins...) have not been changed for the moment. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 2 +- include/linux/compiler-gcc.h | 12 ++++++------ include/linux/compiler-intel.h | 2 +- include/linux/compiler.h | 8 ++++---- include/linux/compiler_types.h | 42 +++++++++++++++++++++--------------------- 5 files changed, 33 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index b1ce500fe8b3..d11cad61ba5c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,7 +21,7 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((no_sanitize("address"))) +#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) /* * Not all versions of clang implement the the type-generic versions diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1302b425e625..7a1de7683df5 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,7 +76,7 @@ #endif #ifdef RETPOLINE -#define __noretpoline __attribute__((indirect_branch("keep"))) +#define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) @@ -84,8 +84,8 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #ifndef __CHECKER__ -#define __compiletime_warning(message) __attribute__((warning(message))) -#define __compiletime_error(message) __attribute__((error(message))) +#define __compiletime_warning(message) __attribute__((__warning__(message))) +#define __compiletime_error(message) __attribute__((__error__(message))) #ifdef LATENT_ENTROPY_PLUGIN #define __latent_entropy __attribute__((latent_entropy)) @@ -134,7 +134,7 @@ * optimizer that something else uses this function or variable, thus preventing * this. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) /* gcc version specific checks */ @@ -191,7 +191,7 @@ * should not be applied to that function. * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 */ -#define __no_sanitize_address __attribute__((no_sanitize_address)) +#define __no_sanitize_address __attribute__((__no_sanitize_address__)) #endif #if GCC_VERSION >= 50100 @@ -199,7 +199,7 @@ * Mark structures as requiring designated initializers. * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html */ -#define __designated_init __attribute__((designated_init)) +#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 4c7f9befa9f6..fef8bb3e53ef 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -42,4 +42,4 @@ * and may be redefined here because they should not be shared with other * compilers, like clang. */ -#define __visible __attribute__((externally_visible)) +#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 7c0157d50964..ec4a28bad2c6 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -24,7 +24,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, long ______r; \ static struct ftrace_likely_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_annotated_branch"))) \ + __attribute__((__section__("_ftrace_annotated_branch"))) \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -60,7 +60,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, int ______r; \ static struct ftrace_branch_data \ __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_branch"))) \ + __attribute__((__section__("_ftrace_branch"))) \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((section("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ), used)) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((section(".discard.addressable"), used)) \ + static void * __attribute__((__section__(".discard.addressable"), used)) \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a19562cb047c..8fbdd47dd3d0 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -195,26 +195,26 @@ struct ftrace_likely_data { * would be. * [...] */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __aligned_largest __attribute__((aligned)) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) -#define __mode(x) __attribute__((mode(x))) +#define __pure __attribute__((__pure__)) +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) +#define __maybe_unused __attribute__((__unused__)) +#define __always_unused __attribute__((__unused__)) +#define __mode(x) __attribute__((__mode__(x))) #define __malloc __attribute__((__malloc__)) #define __used __attribute__((__used__)) -#define __noreturn __attribute__((noreturn)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) -#define __cold __attribute__((cold)) +#define __noreturn __attribute__((__noreturn__)) +#define __packed __attribute__((__packed__)) +#define __weak __attribute__((__weak__)) +#define __alias(symbol) __attribute__((__alias__(#symbol))) +#define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) #ifdef CONFIG_ENABLE_MUST_CHECK -#define __must_check __attribute__((warn_unused_result)) +#define __must_check __attribute__((__warn_unused_result__)) #else #define __must_check #endif @@ -222,7 +222,7 @@ struct ftrace_likely_data { #if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) #define notrace __attribute__((hotpatch(0, 0))) #else -#define notrace __attribute__((no_instrument_function)) +#define notrace __attribute__((__no_instrument_function__)) #endif /* @@ -231,7 +231,7 @@ struct ftrace_likely_data { * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. */ -#define __naked __attribute__((naked)) notrace +#define __naked __attribute__((__naked__)) notrace #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) @@ -242,7 +242,7 @@ struct ftrace_likely_data { * defined so the gnu89 semantics are the default. */ #ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((gnu_inline)) +# define __gnu_inline __attribute__((__gnu_inline__)) #else # define __gnu_inline #endif @@ -262,17 +262,17 @@ struct ftrace_likely_data { #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) #define inline \ - inline __attribute__((always_inline, unused)) notrace __gnu_inline + inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline #else -#define inline inline __attribute__((unused)) notrace __gnu_inline +#define inline inline __attribute__((__unused__)) notrace __gnu_inline #endif #define __inline__ inline #define __inline inline -#define noinline __attribute__((noinline)) +#define noinline __attribute__((__noinline__)) #ifndef __always_inline -#define __always_inline inline __attribute__((always_inline)) +#define __always_inline inline __attribute__((__always_inline__)) #endif /* -- cgit v1.2.3-71-gd317 From c2c640aa04cc4e6caf0ff17ff18b3784e0c99566 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:45:01 +0200 Subject: Compiler Attributes: remove unneeded tests Attributes const and always_inline have tests around them which are unneeded, since they are supported by gcc >= 4.6, clang >= 3 and icc >= 13. https://godbolt.org/z/DFPq37 In the case of gnu_inline, we do not need to test for __GNUC_STDC_INLINE__ because, regardless of the current inlining behavior, we can simply always force the old GCC inlining behavior by using the attribute in all cases. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 8fbdd47dd3d0..5ff9cda893f4 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -158,10 +158,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __attribute_const__ -#define __attribute_const__ __attribute__((__const__)) -#endif - #ifndef __noclone #define __noclone #endif @@ -196,6 +192,7 @@ struct ftrace_likely_data { * [...] */ #define __pure __attribute__((__pure__)) +#define __attribute_const__ __attribute__((__const__)) #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) #define __printf(a, b) __attribute__((__format__(printf, a, b))) @@ -211,6 +208,8 @@ struct ftrace_likely_data { #define __alias(symbol) __attribute__((__alias__(#symbol))) #define __cold __attribute__((__cold__)) #define __section(S) __attribute__((__section__(#S))) +#define __always_inline inline __attribute__((__always_inline__)) +#define __gnu_inline __attribute__((__gnu_inline__)) #ifdef CONFIG_ENABLE_MUST_CHECK @@ -235,18 +234,6 @@ struct ftrace_likely_data { #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) -/* - * Feature detection for gnu_inline (gnu89 extern inline semantics). Either - * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, - * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not - * defined so the gnu89 semantics are the default. - */ -#ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((__gnu_inline__)) -#else -# define __gnu_inline -#endif - /* * Force always-inline if the user requests it so via the .config. * GCC does not warn about unused static inline functions for @@ -271,10 +258,6 @@ struct ftrace_likely_data { #define __inline inline #define noinline __attribute__((__noinline__)) -#ifndef __always_inline -#define __always_inline inline __attribute__((__always_inline__)) -#endif - /* * Rather then using noinline to prevent stack consumption, use * noinline_for_stack instead. For documentation reasons. -- cgit v1.2.3-71-gd317 From ec0bbef66f867854691d5af18c2231d746958e0e Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 19:25:14 +0200 Subject: Compiler Attributes: homogenize __must_be_array Different definitions of __must_be_array: * gcc: disabled for __CHECKER__ * clang: same definition as gcc's, but without __CHECKER__ * intel: the comment claims __builtin_types_compatible_p() is unsupported; but icc seems to support it since 13.0.1 (released in 2012). See https://godbolt.org/z/S0l6QQ Therefore, we can remove all of them and have a single definition in compiler.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 1 - include/linux/compiler-gcc.h | 7 ------- include/linux/compiler-intel.h | 3 --- include/linux/compiler.h | 7 +++++++ 4 files changed, 7 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d11cad61ba5c..fa9532f8d885 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -41,6 +41,5 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) #define __assume_aligned(a, ...) \ __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 7a1de7683df5..3b32bbfa5a49 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,13 +68,6 @@ */ #define uninitialized_var(x) x = x -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else -/* &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])) -#endif - #ifdef RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index fef8bb3e53ef..6004b4588bd4 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,9 +29,6 @@ */ #define OPTIMIZER_HIDE_VAR(var) barrier() -/* Intel ECC compiler doesn't support __builtin_types_compatible_p() */ -#define __must_be_array(a) 0 - #endif /* icc has this, but it's called _bswap16 */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ec4a28bad2c6..165b1d5683ed 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,4 +357,11 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +#ifdef __CHECKER__ +#define __must_be_array(a) 0 +#else +/* &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])) +#endif + #endif /* __LINUX_COMPILER_H */ -- cgit v1.2.3-71-gd317 From 989bd5000f36052df604888ed12bb6ef390786b7 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 31 Aug 2018 18:00:16 +0200 Subject: Compiler Attributes: remove unneeded sparse (__CHECKER__) tests Sparse knows about a few more attributes now, so we can remove the __CHECKER__ conditions from them (which, in turn, allow us to move some of them later on to compiler_attributes.h). * assume_aligned: since sparse's commit ffc860b ("sparse: ignore __assume_aligned__ attribute"), included in 0.5.1 * error: since sparse's commit 0a04210 ("sparse: Add 'error' to ignored attributes"), included in 0.5.0 * hotpatch: since sparse's commit 6043210 ("sparse/parse.c: ignore hotpatch attribute"), included in 0.5.1 * warning: since sparse's commit 977365d ("Avoid "attribute 'warning': unknown attribute" warning"), included in 0.4.2 On top of that, __must_be_array does not need it either because: * Even ancient versions of sparse do not have a problem * BUILD_BUG_ON_ZERO() is currently disabled for __CHECKER__ Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 6 ++---- include/linux/compiler.h | 4 ---- include/linux/compiler_types.h | 2 +- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3b32bbfa5a49..1ca6a51cfaa9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -76,14 +76,12 @@ #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#ifndef __CHECKER__ #define __compiletime_warning(message) __attribute__((__warning__(message))) #define __compiletime_error(message) __attribute__((__error__(message))) -#ifdef LATENT_ENTROPY_PLUGIN +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif -#endif /* __CHECKER__ */ /* * calling noreturn functions, __builtin_unreachable() and __builtin_trap() @@ -131,7 +129,7 @@ /* gcc version specific checks */ -#if GCC_VERSION >= 40900 && !defined(__CHECKER__) +#if GCC_VERSION >= 40900 /* * __assume_aligned(n, k): Tell the optimizer that the returned * pointer can be assumed to be k modulo n. The second argument is diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 165b1d5683ed..4030a2940d6b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -357,11 +357,7 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else /* &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])) -#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 5ff9cda893f4..a3eceb3ad1b3 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -218,7 +218,7 @@ struct ftrace_likely_data { #define __must_check #endif -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#if defined(CC_USING_HOTPATCH) #define notrace __attribute__((hotpatch(0, 0))) #else #define notrace __attribute__((__no_instrument_function__)) -- cgit v1.2.3-71-gd317 From 66dbeef915f275dad6c8656b31667ef9640f5639 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 18:34:18 +0200 Subject: Compiler Attributes: add missing SPDX ID in compiler_types.h Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index a3eceb3ad1b3..ed7c0e4a180e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H -- cgit v1.2.3-71-gd317 From a3f8a30f3f0079c7edfc72e329eee8594fb3e3cb Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 30 Aug 2018 20:36:59 +0200 Subject: Compiler Attributes: use feature checks instead of version checks Instead of using version checks per-compiler to define (or not) each attribute, use __has_attribute to test for them, following the cleanup started with commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"), which is supported on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute by hand. All the attributes that can be unconditionally defined and directly map to compiler attribute(s) (even if optional) have been moved to a new file include/linux/compiler_attributes.h In an effort to make the file as regular as possible, comments stating the purpose of attributes have been removed. Instead, links to the compiler docs have been added (i.e. to gcc and, if available, to clang as well). In addition, they have been sorted. Finally, if an attribute is optional (i.e. if it is guarded by __has_attribute), the reason has been stated for future reference. Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 4 - include/linux/compiler-gcc.h | 51 -------- include/linux/compiler-intel.h | 6 - include/linux/compiler_attributes.h | 244 ++++++++++++++++++++++++++++++++++++ include/linux/compiler_types.h | 74 ++--------- 5 files changed, 254 insertions(+), 125 deletions(-) create mode 100644 include/linux/compiler_attributes.h (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index fa9532f8d885..3e7dafb3ea80 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,8 +21,6 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((__no_sanitize__("address"))) - /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements @@ -41,5 +39,3 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __assume_aligned(a, ...) \ - __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 1ca6a51cfaa9..cfac027e1625 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -108,9 +108,6 @@ __builtin_unreachable(); \ } while (0) -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) - #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) #define __randomize_layout __attribute__((randomize_layout)) #define __no_randomize_layout __attribute__((no_randomize_layout)) @@ -119,32 +116,6 @@ #define randomized_struct_fields_end } __randomize_layout; #endif -/* - * When used with Link Time Optimization, gcc can optimize away C functions or - * variables which are referenced only from assembly code. __visible tells the - * optimizer that something else uses this function or variable, thus preventing - * this. - */ -#define __visible __attribute__((__externally_visible__)) - -/* gcc version specific checks */ - -#if GCC_VERSION >= 40900 -/* - * __assume_aligned(n, k): Tell the optimizer that the returned - * pointer can be assumed to be k modulo n. The second argument is - * optional (default 0), so we use a variadic macro to make the - * shorthand. - * - * Beware: Do not apply this to functions which may return - * ERR_PTRs. Also, it is probably unwise to apply it to functions - * returning extra information in the low bits (but in that case the - * compiler should see some alignment anyway, when the return value is - * massaged by 'flags = ptr & 3; ptr &= ~3;'). - */ -#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) -#endif - /* * GCC 'asm goto' miscompiles certain code sequences: * @@ -176,32 +147,10 @@ #define KASAN_ABI_VERSION 3 #endif -#if GCC_VERSION >= 40902 -/* - * Tell the compiler that address safety instrumentation (KASAN) - * should not be applied to that function. - * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - */ -#define __no_sanitize_address __attribute__((__no_sanitize_address__)) -#endif - #if GCC_VERSION >= 50100 -/* - * Mark structures as requiring designated initializers. - * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html - */ -#define __designated_init __attribute__((__designated_init__)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -#if !defined(__noclone) -#define __noclone /* not needed */ -#endif - -#if !defined(__no_sanitize_address) -#define __no_sanitize_address -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 6004b4588bd4..517bd14e1222 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -34,9 +34,3 @@ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ #define __builtin_bswap16 _bswap16 - -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like clang. - */ -#define __visible __attribute__((__externally_visible__)) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h new file mode 100644 index 000000000000..f0f9fc398440 --- /dev/null +++ b/include/linux/compiler_attributes.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COMPILER_ATTRIBUTES_H +#define __LINUX_COMPILER_ATTRIBUTES_H + +/* + * The attributes in this file are unconditionally defined and they directly + * map to compiler attribute(s) -- except those that are optional. + * + * Any other "attributes" (i.e. those that depend on a configuration option, + * on a compiler, on an architecture, on plugins, on other attributes...) + * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * + * This file is meant to be sorted (by actual attribute name, + * not by #define identifier). Use the __attribute__((__name__)) syntax + * (i.e. with underscores) to avoid future collisions with other macros. + * If an attribute is optional, state the reason in the comment. + */ + +/* + * To check for optional attributes, we use __has_attribute, which is supported + * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support + * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * + * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ + * depending on the compiler used to build it; however, these attributes have + * no semantic effects for sparse, so it does not matter. Also note that, + * in order to avoid sparse's warnings, even the unsupported ones must be + * defined to 0. + */ +#ifndef __has_attribute +# define __has_attribute(x) __GCC4_has_attribute_##x +# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___designated_init__ 0 +# define __GCC4_has_attribute___externally_visible__ 1 +# define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute + */ +#define __alias(symbol) __attribute__((__alias__(#symbol))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-aligned-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-aligned-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-aligned-variable-attribute + */ +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) + +/* + * Note: users of __always_inline currently do not write "inline" themselves, + * which seems to be required by gcc to apply the attribute according + * to its docs (and also "warning: always_inline function might not be + * inlinable [-Wattributes]" is emitted). + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-always_005finline-function-attribute + * clang: mentioned + */ +#define __always_inline inline __attribute__((__always_inline__)) + +/* + * The second argument is optional (default 0), so we use a variadic macro + * to make the shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + * + * Optional: only supported since gcc >= 4.9 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned + */ +#if __has_attribute(__assume_aligned__) +# define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#else +# define __assume_aligned(a, ...) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute + */ +#define __cold __attribute__((__cold__)) + +/* + * Note the long name. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute + */ +#define __attribute_const__ __attribute__((__const__)) + +/* + * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' + * attribute warnings entirely and for good") for more information. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-deprecated-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-deprecated-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-deprecated-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Enumerator-Attributes.html#index-deprecated-enumerator-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#deprecated + */ +#define __deprecated + +/* + * Optional: only supported since gcc >= 5.1 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute + */ +#if __has_attribute(__designated_init__) +# define __designated_init __attribute__((__designated_init__)) +#else +# define __designated_init +#endif + +/* + * Optional: not supported by clang + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-externally_005fvisible-function-attribute + */ +#if __has_attribute(__externally_visible__) +# define __visible __attribute__((__externally_visible__)) +#else +# define __visible +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-format-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#format + */ +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-gnu_005finline-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#gnu-inline + */ +#define __gnu_inline __attribute__((__gnu_inline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + */ +#define __malloc __attribute__((__malloc__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-mode-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-mode-variable-attribute + */ +#define __mode(x) __attribute__((__mode__(x))) + +/* + * Optional: not supported by clang + * Note: icc does not recognize gcc's no-tracer + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noclone-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-optimize-function-attribute + */ +#if __has_attribute(__noclone__) +# if __has_attribute(__optimize__) +# define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +# else +# define __noclone __attribute__((__noclone__)) +# endif +#else +# define __noclone +#endif + +/* + * Note the missing underscores. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute + * clang: mentioned + */ +#define noinline __attribute__((__noinline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn + * clang: https://clang.llvm.org/docs/AttributeReference.html#id1 + */ +#define __noreturn __attribute__((__noreturn__)) + +/* + * Optional: only supported since gcc >= 4.8 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fsanitize_005faddress-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-sanitize-address-no-address-safety-analysis + */ +#if __has_attribute(__no_sanitize_address__) +# define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#else +# define __no_sanitize_address +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute + * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute + */ +#define __packed __attribute__((__packed__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute + */ +#define __pure __attribute__((__pure__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-section-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate + */ +#define __section(S) __attribute__((__section__(#S))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-unused-label-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#maybe-unused-unused + */ +#define __always_unused __attribute__((__unused__)) +#define __maybe_unused __attribute__((__unused__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-used-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-used-variable-attribute + */ +#define __used __attribute__((__used__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute + */ +#define __weak __attribute__((__weak__)) + +#endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index ed7c0e4a180e..3439d7d0249a 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -55,6 +55,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); #ifdef __KERNEL__ +/* Attributes */ +#include + /* Compiler specific macros. */ #ifdef __clang__ #include @@ -79,12 +82,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include #endif -/* - * Generic compiler-independent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - struct ftrace_branch_data { const char *func; const char *file; @@ -107,9 +104,6 @@ struct ftrace_likely_data { unsigned long constant; }; -/* Don't. Just don't. */ -#define __deprecated - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -119,10 +113,6 @@ struct ftrace_likely_data { * compilers. We don't consider that to be an error, so set them to nothing. * For example, some of them are for compiler specific plugins. */ -#ifndef __designated_init -# define __designated_init -#endif - #ifndef __latent_entropy # define __latent_entropy #endif @@ -140,17 +130,6 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif -#ifndef __visible -#define __visible -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -159,10 +138,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __noclone -#define __noclone -#endif - /* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) @@ -182,37 +157,6 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#define __pure __attribute__((__pure__)) -#define __attribute_const__ __attribute__((__const__)) -#define __aligned(x) __attribute__((__aligned__(x))) -#define __aligned_largest __attribute__((__aligned__)) -#define __printf(a, b) __attribute__((__format__(printf, a, b))) -#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) -#define __maybe_unused __attribute__((__unused__)) -#define __always_unused __attribute__((__unused__)) -#define __mode(x) __attribute__((__mode__(x))) -#define __malloc __attribute__((__malloc__)) -#define __used __attribute__((__used__)) -#define __noreturn __attribute__((__noreturn__)) -#define __packed __attribute__((__packed__)) -#define __weak __attribute__((__weak__)) -#define __alias(symbol) __attribute__((__alias__(#symbol))) -#define __cold __attribute__((__cold__)) -#define __section(S) __attribute__((__section__(#S))) -#define __always_inline inline __attribute__((__always_inline__)) -#define __gnu_inline __attribute__((__gnu_inline__)) - - #ifdef CONFIG_ENABLE_MUST_CHECK #define __must_check __attribute__((__warn_unused_result__)) #else @@ -246,18 +190,20 @@ struct ftrace_likely_data { * semantics rather than c99. This prevents multiple symbol definition errors * of extern inline functions at link time. * A lot of inline functions can cause havoc with function tracing. + * Do not use __always_inline here, since currently it expands to inline again + * (which would break users of __always_inline). */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) -#define inline \ - inline __attribute__((__always_inline__, __unused__)) notrace __gnu_inline +#define inline inline __attribute__((__always_inline__)) __gnu_inline \ + __maybe_unused notrace #else -#define inline inline __attribute__((__unused__)) notrace __gnu_inline +#define inline inline __gnu_inline \ + __maybe_unused notrace #endif #define __inline__ inline -#define __inline inline -#define noinline __attribute__((__noinline__)) +#define __inline inline /* * Rather then using noinline to prevent stack consumption, use -- cgit v1.2.3-71-gd317 From 06e3727e02f9ee9cf571692cd5c74fc5a8a2af52 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:22:13 +0200 Subject: Compiler Attributes: KENTRY used twice the "used" attribute Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4030a2940d6b..17ee9165ca51 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ), used)) \ + __attribute__((__section__("___kentry" "+" #sym ))) \ = (unsigned long)&sym; #endif -- cgit v1.2.3-71-gd317 From e04462fb82f8dd98288c0e7ab1eec79c92537d25 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Mon, 3 Sep 2018 19:17:50 +0200 Subject: Compiler Attributes: remove uses of __attribute__ from compiler.h Suggested-by: Nick Desaulniers Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 17ee9165ca51..b5fb034fa6fa 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -23,8 +23,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __branch_check__(x, expect, is_constant) ({ \ long ______r; \ static struct ftrace_likely_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_annotated_branch"))) \ + __aligned(4) \ + __section("_ftrace_annotated_branch") \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -59,8 +59,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ({ \ int ______r; \ static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((__section__("_ftrace_branch"))) \ + __aligned(4) \ + __section("_ftrace_branch") \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -146,7 +146,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((__section__("___kentry" "+" #sym ))) \ + __section("___kentry" "+" #sym ) \ = (unsigned long)&sym; #endif @@ -287,7 +287,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((__section__(".discard.addressable"), used)) \ + static void * __section(".discard.addressable") __used \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** -- cgit v1.2.3-71-gd317 From 92676236917d8e2e0de1d8612686d3d04a6a245b Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Wed, 19 Sep 2018 01:06:24 +0200 Subject: Compiler Attributes: add support for __nonstring (gcc >= 8) From the GCC manual: nonstring The nonstring variable attribute specifies that an object or member declaration with type array of char, signed char, or unsigned char, or pointer to such a type is intended to store character arrays that do not necessarily contain a terminating NUL. This is useful in detecting uses of such arrays or pointers with functions that expect NUL-terminated strings, and to avoid warnings when such an array or pointer is used as an argument to a bounded string manipulation function such as strncpy. https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html This attribute can be used for documentation purposes (i.e. replacing comments), but it is most helpful when the following warnings are enabled: -Wstringop-overflow Warn for calls to string manipulation functions such as memcpy and strcpy that are determined to overflow the destination buffer. [...] -Wstringop-truncation Warn for calls to bounded string manipulation functions such as strncat, strncpy, and stpncpy that may either truncate the copied string or leave the destination unchanged. [...] In situations where a character array is intended to store a sequence of bytes with no terminating NUL such an array may be annotated with attribute nonstring to avoid this warning. Such arrays, however, are not suitable arguments to functions that expect NUL-terminated strings. To help detect accidental misuses of such arrays GCC issues warnings unless it can prove that the use is safe. https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html Tested-by: Sedat Dilek # on top of v4.19-rc5, clang 7 Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Reviewed-by: Luc Van Oostenryck Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index f0f9fc398440..6b28c1b7310c 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) #endif @@ -181,6 +182,19 @@ */ #define noinline __attribute__((__noinline__)) +/* + * Optional: only supported since gcc >= 8 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute + */ +#if __has_attribute(__nonstring__) +# define __nonstring __attribute__((__nonstring__)) +#else +# define __nonstring +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn -- cgit v1.2.3-71-gd317 From c550f01c810f2197c98e6e3103f81797f5e063be Mon Sep 17 00:00:00 2001 From: Steve Sakoman Date: Thu, 20 Sep 2018 09:20:34 -1000 Subject: serial:serial_core: Allow use of CTS for PPS line discipline Add a "pps_4wire" file to serial ports in sysfs in case the kernel is configured with CONFIG_PPS_CLIENT_LDISC. Writing 1 to the file enables the use of CTS instead of DCD for PPS signal input. This is necessary in case a serial port is not completely wired. Though this affects PPS processing the patch is against the serial core as the source of the serial port PPS event dispatching has to be modified. Furthermore it should be possible to modify the source of serial port PPS event dispatching before changing the line discipline. Signed-off-by: Andreas Steinmetz Signed-off-by: Steve Sakoman Tested-by: Steve Sakoman Tested-by: Eric Gallimore Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-tty | 9 +++++ drivers/tty/serial/serial_core.c | 70 ++++++++++++++++++++++++++++++++++++- include/linux/serial_core.h | 3 +- 3 files changed, 80 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-tty b/Documentation/ABI/testing/sysfs-tty index 9eb3c2b6b040..441105a75d1f 100644 --- a/Documentation/ABI/testing/sysfs-tty +++ b/Documentation/ABI/testing/sysfs-tty @@ -154,3 +154,12 @@ Description: device specification. For example, when user sets 7bytes on 16550A, which has 1/4/8/14 bytes trigger, the RX trigger is automatically changed to 4 bytes. + +What: /sys/class/tty/ttyS0/pps_4wire +Date: September 2018 +Contact: Steve Sakoman +Description: + Shows/sets "4 wire" mode for the PPS input to the serial driver. + For fully implemented serial ports PPS is normally provided + on the DCD line. For partial "4 wire" implementations CTS is + used instead of DCD. diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 80bb56facfb6..ed0133395cc7 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2664,6 +2664,57 @@ static ssize_t uart_get_attr_iomem_reg_shift(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", tmp.iomem_reg_shift); } +static ssize_t pps_4wire_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tty_port *port = dev_get_drvdata(dev); + struct uart_state *state = container_of(port, struct uart_state, port); + struct uart_port *uport; + int mode = 0; + + mutex_lock(&port->mutex); + uport = uart_port_check(state); + if (!uport) + goto out; + + mode = uport->pps_4wire; + +out: + mutex_unlock(&port->mutex); + return sprintf(buf, mode ? "yes\n" : "no\n"); +} + +static ssize_t pps_4wire_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct tty_port *port = dev_get_drvdata(dev); + struct uart_state *state = container_of(port, struct uart_state, port); + struct uart_port *uport; + bool mode; + int ret; + + if (!count) + return -EINVAL; + + ret = kstrtobool(buf, &mode); + if (ret < 0) + return ret; + + mutex_lock(&port->mutex); + uport = uart_port_check(state); + if (!uport) + goto out; + + spin_lock_irq(&uport->lock); + uport->pps_4wire = mode; + spin_unlock_irq(&uport->lock); + +out: + mutex_unlock(&port->mutex); + return count; +} +static DEVICE_ATTR_RW(pps_4wire); + static DEVICE_ATTR(type, S_IRUSR | S_IRGRP, uart_get_attr_type, NULL); static DEVICE_ATTR(line, S_IRUSR | S_IRGRP, uart_get_attr_line, NULL); static DEVICE_ATTR(port, S_IRUSR | S_IRGRP, uart_get_attr_port, NULL); @@ -2692,6 +2743,7 @@ static struct attribute *tty_dev_attrs[] = { &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, + &dev_attr_pps_4wire.attr, NULL, }; @@ -2748,6 +2800,9 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) goto out; } + /* assert that pps handling is done via DCD as default */ + uport->pps_4wire = 0; + /* * If this port is a console, then the spinlock is already * initialised. @@ -2923,7 +2978,7 @@ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) lockdep_assert_held_once(&uport->lock); - if (tty) { + if (tty && !uport->pps_4wire) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) @@ -2952,8 +3007,21 @@ EXPORT_SYMBOL_GPL(uart_handle_dcd_change); */ void uart_handle_cts_change(struct uart_port *uport, unsigned int status) { + struct tty_port *port = &uport->state->port; + struct tty_struct *tty = port->tty; + struct tty_ldisc *ld; + lockdep_assert_held_once(&uport->lock); + if (tty && uport->pps_4wire) { + ld = tty_ldisc_ref(tty); + if (ld) { + if (ld->ops->dcd_change) + ld->ops->dcd_change(tty, status); + tty_ldisc_deref(ld); + } + } + uport->icount.cts++; if (uart_softcts_mode(uport)) { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 406edae44ca3..079793e5d3fa 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -255,7 +255,8 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char unused[2]; + unsigned char pps_4wire; /* CTS instead of DCD */ + unsigned char unused; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3-71-gd317 From ad8c0eaa0a418ae8ef3f9217638bb86439399eac Mon Sep 17 00:00:00 2001 From: Nicolas Ferre Date: Wed, 26 Sep 2018 14:58:47 +0200 Subject: tty/serial_core: add ISO7816 infrastructure Add the ISO7816 ioctl and associated accessors and data structure. Drivers can then use this common implementation to handle ISO7816 (smart cards). Signed-off-by: Nicolas Ferre [ludovic.desroches@microchip.com: squash and rebase, removal of gpios, checkpatch fixes] Signed-off-by: Ludovic Desroches Signed-off-by: Greg Kroah-Hartman --- Documentation/serial/serial-iso7816.txt | 83 +++++++++++++++++++++++++++++++++ arch/alpha/include/uapi/asm/ioctls.h | 2 + arch/mips/include/uapi/asm/ioctls.h | 2 + arch/parisc/include/uapi/asm/ioctls.h | 2 + arch/powerpc/include/uapi/asm/ioctls.h | 2 + arch/sh/include/uapi/asm/ioctls.h | 2 + arch/sparc/include/uapi/asm/ioctls.h | 2 + arch/xtensa/include/uapi/asm/ioctls.h | 2 + drivers/tty/serial/serial_core.c | 60 ++++++++++++++++++++++++ include/linux/serial_core.h | 3 ++ include/uapi/asm-generic/ioctls.h | 2 + include/uapi/linux/serial.h | 17 +++++++ 12 files changed, 179 insertions(+) create mode 100644 Documentation/serial/serial-iso7816.txt (limited to 'include/linux') diff --git a/Documentation/serial/serial-iso7816.txt b/Documentation/serial/serial-iso7816.txt new file mode 100644 index 000000000000..3193d24a2b0f --- /dev/null +++ b/Documentation/serial/serial-iso7816.txt @@ -0,0 +1,83 @@ + ISO7816 SERIAL COMMUNICATIONS + +1. INTRODUCTION + + ISO/IEC7816 is a series of standards specifying integrated circuit cards (ICC) + also known as smart cards. + +2. HARDWARE-RELATED CONSIDERATIONS + + Some CPUs/UARTs (e.g., Microchip AT91) contain a built-in mode capable of + handling communication with a smart card. + + For these microcontrollers, the Linux driver should be made capable of + working in both modes, and proper ioctls (see later) should be made + available at user-level to allow switching from one mode to the other, and + vice versa. + +3. DATA STRUCTURES ALREADY AVAILABLE IN THE KERNEL + + The Linux kernel provides the serial_iso7816 structure (see [1]) to handle + ISO7816 communications. This data structure is used to set and configure + ISO7816 parameters in ioctls. + + Any driver for devices capable of working both as RS232 and ISO7816 should + implement the iso7816_config callback in the uart_port structure. The + serial_core calls iso7816_config to do the device specific part in response + to TIOCGISO7816 and TIOCSISO7816 ioctls (see below). The iso7816_config + callback receives a pointer to struct serial_iso7816. + +4. USAGE FROM USER-LEVEL + + From user-level, ISO7816 configuration can be get/set using the previous + ioctls. For instance, to set ISO7816 you can use the following code: + + #include + + /* Include definition for ISO7816 ioctls: TIOCSISO7816 and TIOCGISO7816 */ + #include + + /* Open your specific device (e.g., /dev/mydevice): */ + int fd = open ("/dev/mydevice", O_RDWR); + if (fd < 0) { + /* Error handling. See errno. */ + } + + struct serial_iso7816 iso7816conf; + + /* Reserved fields as to be zeroed */ + memset(&iso7816conf, 0, sizeof(iso7816conf)); + + /* Enable ISO7816 mode: */ + iso7816conf.flags |= SER_ISO7816_ENABLED; + + /* Select the protocol: */ + /* T=0 */ + iso7816conf.flags |= SER_ISO7816_T(0); + /* or T=1 */ + iso7816conf.flags |= SER_ISO7816_T(1); + + /* Set the guard time: */ + iso7816conf.tg = 2; + + /* Set the clock frequency*/ + iso7816conf.clk = 3571200; + + /* Set transmission factors: */ + iso7816conf.sc_fi = 372; + iso7816conf.sc_di = 1; + + if (ioctl(fd_usart, TIOCSISO7816, &iso7816conf) < 0) { + /* Error handling. See errno. */ + } + + /* Use read() and write() syscalls here... */ + + /* Close the device when finished: */ + if (close (fd) < 0) { + /* Error handling. See errno. */ + } + +5. REFERENCES + + [1] include/uapi/linux/serial.h diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 3729d92d3fa8..1e9121c9b3c7 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -102,6 +102,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define TIOCSERCONFIG 0x5453 #define TIOCSERGWILD 0x5454 diff --git a/arch/mips/include/uapi/asm/ioctls.h b/arch/mips/include/uapi/asm/ioctls.h index 890245a9f0c4..16aa8a766aec 100644 --- a/arch/mips/include/uapi/asm/ioctls.h +++ b/arch/mips/include/uapi/asm/ioctls.h @@ -93,6 +93,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) /* I hope the range from 0x5480 on is free ... */ #define TIOCSCTTY 0x5480 /* become controlling tty */ diff --git a/arch/parisc/include/uapi/asm/ioctls.h b/arch/parisc/include/uapi/asm/ioctls.h index aafb1c0ca0af..82d1148c6379 100644 --- a/arch/parisc/include/uapi/asm/ioctls.h +++ b/arch/parisc/include/uapi/asm/ioctls.h @@ -62,6 +62,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define FIONCLEX 0x5450 /* these numbers need to be adjusted. */ #define FIOCLEX 0x5451 diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h index 41b1a5c15734..2c145da3b774 100644 --- a/arch/powerpc/include/uapi/asm/ioctls.h +++ b/arch/powerpc/include/uapi/asm/ioctls.h @@ -102,6 +102,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define TIOCSERCONFIG 0x5453 #define TIOCSERGWILD 0x5454 diff --git a/arch/sh/include/uapi/asm/ioctls.h b/arch/sh/include/uapi/asm/ioctls.h index cc62f6f98103..11866d4f60e1 100644 --- a/arch/sh/include/uapi/asm/ioctls.h +++ b/arch/sh/include/uapi/asm/ioctls.h @@ -95,6 +95,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define TIOCSERCONFIG _IO('T', 83) /* 0x5453 */ #define TIOCSERGWILD _IOR('T', 84, int) /* 0x5454 */ diff --git a/arch/sparc/include/uapi/asm/ioctls.h b/arch/sparc/include/uapi/asm/ioctls.h index 2df52711e170..7fd2f5873c9e 100644 --- a/arch/sparc/include/uapi/asm/ioctls.h +++ b/arch/sparc/include/uapi/asm/ioctls.h @@ -27,6 +27,8 @@ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGRS485 _IOR('T', 0x41, struct serial_rs485) #define TIOCSRS485 _IOWR('T', 0x42, struct serial_rs485) +#define TIOCGISO7816 _IOR('T', 0x43, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x44, struct serial_iso7816) /* Note that all the ioctls that are not available in Linux have a * double underscore on the front to: a) avoid some programs to diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h index ec43609cbfc5..6d4a87296c95 100644 --- a/arch/xtensa/include/uapi/asm/ioctls.h +++ b/arch/xtensa/include/uapi/asm/ioctls.h @@ -107,6 +107,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define TIOCSERCONFIG _IO('T', 83) #define TIOCSERGWILD _IOR('T', 84, int) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index ed0133395cc7..0a4e6eeb5ff3 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1308,6 +1308,58 @@ static int uart_set_rs485_config(struct uart_port *port, return 0; } +static int uart_get_iso7816_config(struct uart_port *port, + struct serial_iso7816 __user *iso7816) +{ + unsigned long flags; + struct serial_iso7816 aux; + + if (!port->iso7816_config) + return -ENOIOCTLCMD; + + spin_lock_irqsave(&port->lock, flags); + aux = port->iso7816; + spin_unlock_irqrestore(&port->lock, flags); + + if (copy_to_user(iso7816, &aux, sizeof(aux))) + return -EFAULT; + + return 0; +} + +static int uart_set_iso7816_config(struct uart_port *port, + struct serial_iso7816 __user *iso7816_user) +{ + struct serial_iso7816 iso7816; + int i, ret; + unsigned long flags; + + if (!port->iso7816_config) + return -ENOIOCTLCMD; + + if (copy_from_user(&iso7816, iso7816_user, sizeof(*iso7816_user))) + return -EFAULT; + + /* + * There are 5 words reserved for future use. Check that userspace + * doesn't put stuff in there to prevent breakages in the future. + */ + for (i = 0; i < 5; i++) + if (iso7816.reserved[i]) + return -EINVAL; + + spin_lock_irqsave(&port->lock, flags); + ret = port->iso7816_config(port, &iso7816); + spin_unlock_irqrestore(&port->lock, flags); + if (ret) + return ret; + + if (copy_to_user(iso7816_user, &port->iso7816, sizeof(port->iso7816))) + return -EFAULT; + + return 0; +} + /* * Called via sys_ioctl. We can use spin_lock_irq() here. */ @@ -1392,6 +1444,14 @@ uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) case TIOCSRS485: ret = uart_set_rs485_config(uport, uarg); break; + + case TIOCSISO7816: + ret = uart_set_iso7816_config(state->uart_port, uarg); + break; + + case TIOCGISO7816: + ret = uart_get_iso7816_config(state->uart_port, uarg); + break; default: if (uport->ops->ioctl) ret = uport->ops->ioctl(uport, cmd, arg); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 079793e5d3fa..4e2ba4894dcc 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -144,6 +144,8 @@ struct uart_port { void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct serial_rs485 *rs485); + int (*iso7816_config)(struct uart_port *, + struct serial_iso7816 *iso7816); unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ @@ -261,6 +263,7 @@ 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 serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; diff --git a/include/uapi/asm-generic/ioctls.h b/include/uapi/asm-generic/ioctls.h index 040651735662..cdc9f4ca8c27 100644 --- a/include/uapi/asm-generic/ioctls.h +++ b/include/uapi/asm-generic/ioctls.h @@ -79,6 +79,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define FIONCLEX 0x5450 #define FIOCLEX 0x5451 diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index 3fdd0dee8b41..93eb3c496ff1 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -132,4 +132,21 @@ struct serial_rs485 { are a royal PITA .. */ }; +/* + * Serial interface for controlling ISO7816 settings on chips with suitable + * support. Set with TIOCSISO7816 and get with TIOCGISO7816 if supported by + * your platform. + */ +struct serial_iso7816 { + __u32 flags; /* ISO7816 feature flags */ +#define SER_ISO7816_ENABLED (1 << 0) +#define SER_ISO7816_T_PARAM (0x0f << 4) +#define SER_ISO7816_T(t) (((t) & 0x0f) << 4) + __u32 tg; + __u32 sc_fi; + __u32 sc_di; + __u32 clk; + __u32 reserved[5]; +}; + #endif /* _UAPI_LINUX_SERIAL_H */ -- cgit v1.2.3-71-gd317 From 47b00dcf141172c4c1c583701ec91923672cec39 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 10 Aug 2018 11:29:09 +0300 Subject: clk: ti: clkctrl: support multiple clkctrl nodes under a cm node Currently, only one clkctrl node can be added under a specific CM node due to limitation with the implementation. Modify the code to pick-up clockdomain name from the clkctrl node instead of CM node if provided. Also, add a new flag to the TI clock driver so that both modes can be supported simultaneously. Signed-off-by: Tero Kristo Tested-by: Tony Lindgren --- drivers/clk/ti/clk.c | 7 ++++-- drivers/clk/ti/clkctrl.c | 61 +++++++++++++++++++++++++++++++++++------------- drivers/clk/ti/clock.h | 2 ++ include/linux/clk/ti.h | 1 + 4 files changed, 53 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 27e0979b3158..8b89be18e39e 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -34,7 +34,7 @@ struct ti_clk_ll_ops *ti_clk_ll_ops; static struct device_node *clocks_node_ptr[CLK_MAX_MEMMAPS]; -static struct ti_clk_features ti_clk_features; +struct ti_clk_features ti_clk_features; struct clk_iomap { struct regmap *regmap; @@ -140,6 +140,9 @@ void __init ti_dt_clocks_register(struct ti_dt_clk oclks[]) int ret; static bool clkctrl_nodes_missing; static bool has_clkctrl_data; + static bool compat_mode; + + compat_mode = ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT; for (c = oclks; c->node_name != NULL; c++) { strcpy(buf, c->node_name); @@ -164,7 +167,7 @@ void __init ti_dt_clocks_register(struct ti_dt_clk oclks[]) continue; node = of_find_node_by_name(NULL, buf); - if (num_args) { + if (num_args && compat_mode) { parent = node; node = of_get_child_by_name(parent, "clk"); of_node_put(parent); diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 421b05392220..9bff57f0345d 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -259,8 +259,13 @@ _ti_clkctrl_clk_register(struct omap_clkctrl_provider *provider, struct omap_clkctrl_clk *clkctrl_clk; int ret = 0; - init.name = kasprintf(GFP_KERNEL, "%s:%s:%04x:%d", node->parent->name, - node->name, offset, bit); + if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) + init.name = kasprintf(GFP_KERNEL, "%s:%s:%04x:%d", + node->parent->name, node->name, offset, + bit); + else + init.name = kasprintf(GFP_KERNEL, "%s:%04x:%d", node->name, + offset, bit); clkctrl_clk = kzalloc(sizeof(*clkctrl_clk), GFP_KERNEL); if (!init.name || !clkctrl_clk) { ret = -ENOMEM; @@ -441,6 +446,10 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) u32 addr; int ret; + if (!(ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) && + !strcmp(node->name, "clk")) + ti_clk_features.flags |= TI_CLK_CLKCTRL_COMPAT; + addrp = of_get_address(node, 0, NULL, NULL); addr = (u32)of_translate_address(node, addrp); @@ -492,19 +501,35 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) provider->base = of_iomap(node, 0); - provider->clkdm_name = kmalloc(strlen(node->parent->name) + 3, - GFP_KERNEL); - if (!provider->clkdm_name) { - kfree(provider); - return; + if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) { + provider->clkdm_name = kmalloc(strlen(node->parent->name) + 3, + GFP_KERNEL); + if (!provider->clkdm_name) { + kfree(provider); + return; + } + + /* + * Create default clkdm name, replace _cm from end of parent + * node name with _clkdm + */ + strcpy(provider->clkdm_name, node->parent->name); + provider->clkdm_name[strlen(provider->clkdm_name) - 2] = 0; + } else { + provider->clkdm_name = kmalloc(strlen(node->name), GFP_KERNEL); + if (!provider->clkdm_name) { + kfree(provider); + return; + } + + /* + * Create default clkdm name, replace _clkctrl from end of + * node name with _clkdm + */ + strcpy(provider->clkdm_name, node->name); + provider->clkdm_name[strlen(provider->clkdm_name) - 7] = 0; } - /* - * Create default clkdm name, replace _cm from end of parent node - * name with _clkdm - */ - strcpy(provider->clkdm_name, node->parent->name); - provider->clkdm_name[strlen(provider->clkdm_name) - 2] = 0; strcat(provider->clkdm_name, "clkdm"); INIT_LIST_HEAD(&provider->clocks); @@ -539,9 +564,13 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node) init.flags = 0; if (reg_data->flags & CLKF_SET_RATE_PARENT) init.flags |= CLK_SET_RATE_PARENT; - init.name = kasprintf(GFP_KERNEL, "%s:%s:%04x:%d", - node->parent->name, node->name, - reg_data->offset, 0); + if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) + init.name = kasprintf(GFP_KERNEL, "%s:%s:%04x:%d", + node->parent->name, node->name, + reg_data->offset, 0); + else + init.name = kasprintf(GFP_KERNEL, "%s:%04x:%d", + node->name, reg_data->offset, 0); clkctrl_clk = kzalloc(sizeof(*clkctrl_clk), GFP_KERNEL); if (!init.name || !clkctrl_clk) goto cleanup; diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h index b58278077226..ce4aad6c4c7c 100644 --- a/drivers/clk/ti/clock.h +++ b/drivers/clk/ti/clock.h @@ -233,6 +233,8 @@ extern const struct clk_ops ti_clk_divider_ops; extern const struct clk_ops ti_clk_mux_ops; extern const struct clk_ops omap_gate_clk_ops; +extern struct ti_clk_features ti_clk_features; + void omap2_init_clk_clkdm(struct clk_hw *hw); int omap2_clkops_enable_clkdm(struct clk_hw *hw); void omap2_clkops_disable_clkdm(struct clk_hw *hw); diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index a8faa38b1ed6..3301bd025a2c 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -290,6 +290,7 @@ struct ti_clk_features { #define TI_CLK_DPLL4_DENY_REPROGRAM BIT(1) #define TI_CLK_DISABLE_CLKDM_CONTROL BIT(2) #define TI_CLK_ERRATA_I810 BIT(3) +#define TI_CLK_CLKCTRL_COMPAT BIT(4) void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); -- cgit v1.2.3-71-gd317 From 8b95d1ce3300c411728954473316bd04d0ba9883 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:35 +0530 Subject: clk: Add functions to save/restore clock context en-masse Deep enough power saving mode can result into losing context of the clock registers also, and they need to be restored once coming back from the power saving mode. Hence add functions to save/restore clock context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- drivers/clk/clk.c | 74 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/clk-provider.h | 7 +++++ include/linux/clk.h | 25 +++++++++++++++ 3 files changed, 106 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index d31055ae6ec6..8a0254a1c303 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -923,6 +923,80 @@ static int clk_core_enable_lock(struct clk_core *core) return ret; } +static int _clk_save_context(struct clk_core *clk) +{ + struct clk_core *child; + int ret = 0; + + hlist_for_each_entry(child, &clk->children, child_node) { + ret = _clk_save_context(child); + if (ret < 0) + return ret; + } + + if (clk->ops && clk->ops->save_context) + ret = clk->ops->save_context(clk->hw); + + return ret; +} + +static void _clk_restore_context(struct clk_core *clk) +{ + struct clk_core *child; + + if (clk->ops && clk->ops->restore_context) + clk->ops->restore_context(clk->hw); + + hlist_for_each_entry(child, &clk->children, child_node) + _clk_restore_context(child); +} + +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code. Returns 0 on success. + */ +int clk_save_context(void) +{ + struct clk_core *clk; + int ret; + + hlist_for_each_entry(clk, &clk_root_list, child_node) { + ret = _clk_save_context(clk); + if (ret < 0) + return ret; + } + + hlist_for_each_entry(clk, &clk_orphan_list, child_node) { + ret = _clk_save_context(clk); + if (ret < 0) + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(clk_save_context); + +/** + * clk_restore_context - restore clock context after poweroff + * + * Restore the saved clock context upon resume. + * + */ +void clk_restore_context(void) +{ + struct clk_core *clk; + + hlist_for_each_entry(clk, &clk_root_list, child_node) + _clk_restore_context(clk); + + hlist_for_each_entry(clk, &clk_orphan_list, child_node) + _clk_restore_context(clk); +} +EXPORT_SYMBOL_GPL(clk_restore_context); + /** * clk_enable - ungate a clock * @clk: the clk being ungated diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 08b1aa70a38d..df7379da6269 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -119,6 +119,11 @@ struct clk_duty { * Called with enable_lock held. This function must not * sleep. * + * @save_context: Save the context of the clock in prepration for poweroff. + * + * @restore_context: Restore the context of the clock after a restoration + * of power. + * * @recalc_rate Recalculate the rate of this clock, by querying hardware. The * parent rate is an input parameter. It is up to the caller to * ensure that the prepare_mutex is held across this call. @@ -223,6 +228,8 @@ struct clk_ops { void (*disable)(struct clk_hw *hw); int (*is_enabled)(struct clk_hw *hw); void (*disable_unused)(struct clk_hw *hw); + int (*save_context)(struct clk_hw *hw); + void (*restore_context)(struct clk_hw *hw); unsigned long (*recalc_rate)(struct clk_hw *hw, unsigned long parent_rate); long (*round_rate)(struct clk_hw *hw, unsigned long rate, diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..7da754d79f9d 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -629,6 +629,23 @@ struct clk *clk_get_parent(struct clk *clk); */ struct clk *clk_get_sys(const char *dev_id, const char *con_id); +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code so locking is not necessary. + */ +int clk_save_context(void); + +/** + * clk_restore_context - restore clock context after poweroff + * + * This occurs with all clocks enabled. Occurs deep within the resume code + * so locking is not necessary. + */ +void clk_restore_context(void); + #else /* !CONFIG_HAVE_CLK */ static inline struct clk *clk_get(struct device *dev, const char *id) @@ -728,6 +745,14 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) { return NULL; } + +static inline int clk_save_context(void) +{ + return 0; +} + +static inline void clk_restore_context(void) {} + #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ -- cgit v1.2.3-71-gd317 From 435365485f40cf12747d1daa2253a4f4b46b8148 Mon Sep 17 00:00:00 2001 From: Keerthy Date: Tue, 4 Sep 2018 12:19:36 +0530 Subject: clk: clk: Add clk_gate_restore_context function The clock gate restore context function enables or disables the gate clocks based on the enable_count. This is done in cases where the clock context is lost and based on the enable_count the clock either needs to be enabled/disabled. Signed-off-by: Keerthy Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- drivers/clk/clk.c | 19 +++++++++++++++++++ include/linux/clk-provider.h | 2 ++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 8a0254a1c303..dd775771a7cc 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -923,6 +923,25 @@ static int clk_core_enable_lock(struct clk_core *core) return ret; } +/** + * clk_gate_restore_context - restore context for poweroff + * @hw: the clk_hw pointer of clock whose state is to be restored + * + * The clock gate restore context function enables or disables + * the gate clocks based on the enable_count. This is done in cases + * where the clock context is lost and based on the enable_count + * the clock either needs to be enabled/disabled. This + * helps restore the state of gate clocks. + */ +void clk_gate_restore_context(struct clk_hw *hw) +{ + if (hw->clk->core->enable_count) + hw->clk->core->ops->enable(hw); + else + hw->clk->core->ops->disable(hw); +} +EXPORT_SYMBOL_GPL(clk_gate_restore_context); + static int _clk_save_context(struct clk_core *clk) { struct clk_core *child; diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index df7379da6269..60c51871b04b 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1018,5 +1018,7 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) #endif /* platform dependent I/O accessors */ +void clk_gate_restore_context(struct clk_hw *hw); + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3-71-gd317 From d6e7bbc148f9fbec8a0117b0d0f420c9710e6d81 Mon Sep 17 00:00:00 2001 From: Russ Dill Date: Tue, 4 Sep 2018 12:19:37 +0530 Subject: clk: ti: Add functions to save/restore clk context SoCs like AM43XX lose clock registers context during RTC-only suspend. Hence add functions to save/restore the clock registers context. Signed-off-by: Keerthy Signed-off-by: Russ Dill Acked-by: Tony Lindgren Signed-off-by: Tero Kristo --- drivers/clk/ti/clock.h | 2 + drivers/clk/ti/divider.c | 36 ++++++++++++++ drivers/clk/ti/dpll.c | 6 +++ drivers/clk/ti/dpll3xxx.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/clk/ti/gate.c | 3 ++ drivers/clk/ti/mux.c | 29 +++++++++++ include/linux/clk/ti.h | 6 +++ 7 files changed, 206 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h index 5a781067a0e7..9f312a219510 100644 --- a/drivers/clk/ti/clock.h +++ b/drivers/clk/ti/clock.h @@ -24,6 +24,7 @@ struct clk_omap_divider { u8 flags; s8 latch; const struct clk_div_table *table; + u32 context; }; #define to_clk_omap_divider(_hw) container_of(_hw, struct clk_omap_divider, hw) @@ -36,6 +37,7 @@ struct clk_omap_mux { u8 shift; s8 latch; u8 flags; + u8 saved_parent; }; #define to_clk_omap_mux(_hw) container_of(_hw, struct clk_omap_mux, hw) diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c index ccfb4d9a152a..373f620f49cb 100644 --- a/drivers/clk/ti/divider.c +++ b/drivers/clk/ti/divider.c @@ -268,10 +268,46 @@ static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, return 0; } +/** + * clk_divider_save_context - Save the divider value + * @hw: pointer struct clk_hw + * + * Save the divider value + */ +static int clk_divider_save_context(struct clk_hw *hw) +{ + struct clk_omap_divider *divider = to_clk_omap_divider(hw); + u32 val; + + val = ti_clk_ll_ops->clk_readl(÷r->reg) >> divider->shift; + divider->context = val & div_mask(divider); + + return 0; +} + +/** + * clk_divider_restore_context - restore the saved the divider value + * @hw: pointer struct clk_hw + * + * Restore the saved the divider value + */ +static void clk_divider_restore_context(struct clk_hw *hw) +{ + struct clk_omap_divider *divider = to_clk_omap_divider(hw); + u32 val; + + val = ti_clk_ll_ops->clk_readl(÷r->reg); + val &= ~(div_mask(divider) << divider->shift); + val |= divider->context << divider->shift; + ti_clk_ll_ops->clk_writel(val, ÷r->reg); +} + const struct clk_ops ti_clk_divider_ops = { .recalc_rate = ti_clk_divider_recalc_rate, .round_rate = ti_clk_divider_round_rate, .set_rate = ti_clk_divider_set_rate, + .save_context = clk_divider_save_context, + .restore_context = clk_divider_restore_context, }; static struct clk *_register_divider(struct device *dev, const char *name, diff --git a/drivers/clk/ti/dpll.c b/drivers/clk/ti/dpll.c index dc86d07d0921..25d86d5ebb36 100644 --- a/drivers/clk/ti/dpll.c +++ b/drivers/clk/ti/dpll.c @@ -39,6 +39,8 @@ static const struct clk_ops dpll_m4xen_ck_ops = { .set_rate_and_parent = &omap3_noncore_dpll_set_rate_and_parent, .determine_rate = &omap4_dpll_regm4xen_determine_rate, .get_parent = &omap2_init_dpll_parent, + .save_context = &omap3_core_dpll_save_context, + .restore_context = &omap3_core_dpll_restore_context, }; #else static const struct clk_ops dpll_m4xen_ck_ops = {}; @@ -62,6 +64,8 @@ static const struct clk_ops dpll_ck_ops = { .set_rate_and_parent = &omap3_noncore_dpll_set_rate_and_parent, .determine_rate = &omap3_noncore_dpll_determine_rate, .get_parent = &omap2_init_dpll_parent, + .save_context = &omap3_noncore_dpll_save_context, + .restore_context = &omap3_noncore_dpll_restore_context, }; static const struct clk_ops dpll_no_gate_ck_ops = { @@ -72,6 +76,8 @@ static const struct clk_ops dpll_no_gate_ck_ops = { .set_parent = &omap3_noncore_dpll_set_parent, .set_rate_and_parent = &omap3_noncore_dpll_set_rate_and_parent, .determine_rate = &omap3_noncore_dpll_determine_rate, + .save_context = &omap3_noncore_dpll_save_context, + .restore_context = &omap3_noncore_dpll_restore_context }; #else static const struct clk_ops dpll_core_ck_ops = {}; diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c index 4534de2ef455..44b6b6403753 100644 --- a/drivers/clk/ti/dpll3xxx.c +++ b/drivers/clk/ti/dpll3xxx.c @@ -782,6 +782,130 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, return rate; } +/** + * omap3_core_dpll_save_context - Save the m and n values of the divider + * @hw: pointer struct clk_hw + * + * Before the dpll registers are lost save the last rounded rate m and n + * and the enable mask. + */ +int omap3_core_dpll_save_context(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + struct dpll_data *dd; + u32 v; + + dd = clk->dpll_data; + + v = ti_clk_ll_ops->clk_readl(&dd->control_reg); + clk->context = (v & dd->enable_mask) >> __ffs(dd->enable_mask); + + if (clk->context == DPLL_LOCKED) { + v = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg); + dd->last_rounded_m = (v & dd->mult_mask) >> + __ffs(dd->mult_mask); + dd->last_rounded_n = ((v & dd->div1_mask) >> + __ffs(dd->div1_mask)) + 1; + } + + return 0; +} + +/** + * omap3_core_dpll_restore_context - restore the m and n values of the divider + * @hw: pointer struct clk_hw + * + * Restore the last rounded rate m and n + * and the enable mask. + */ +void omap3_core_dpll_restore_context(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + const struct dpll_data *dd; + u32 v; + + dd = clk->dpll_data; + + if (clk->context == DPLL_LOCKED) { + _omap3_dpll_write_clken(clk, 0x4); + _omap3_wait_dpll_status(clk, 0); + + v = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg); + v &= ~(dd->mult_mask | dd->div1_mask); + v |= dd->last_rounded_m << __ffs(dd->mult_mask); + v |= (dd->last_rounded_n - 1) << __ffs(dd->div1_mask); + ti_clk_ll_ops->clk_writel(v, &dd->mult_div1_reg); + + _omap3_dpll_write_clken(clk, DPLL_LOCKED); + _omap3_wait_dpll_status(clk, 1); + } else { + _omap3_dpll_write_clken(clk, clk->context); + } +} + +/** + * omap3_non_core_dpll_save_context - Save the m and n values of the divider + * @hw: pointer struct clk_hw + * + * Before the dpll registers are lost save the last rounded rate m and n + * and the enable mask. + */ +int omap3_noncore_dpll_save_context(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + struct dpll_data *dd; + u32 v; + + dd = clk->dpll_data; + + v = ti_clk_ll_ops->clk_readl(&dd->control_reg); + clk->context = (v & dd->enable_mask) >> __ffs(dd->enable_mask); + + if (clk->context == DPLL_LOCKED) { + v = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg); + dd->last_rounded_m = (v & dd->mult_mask) >> + __ffs(dd->mult_mask); + dd->last_rounded_n = ((v & dd->div1_mask) >> + __ffs(dd->div1_mask)) + 1; + } + + return 0; +} + +/** + * omap3_core_dpll_restore_context - restore the m and n values of the divider + * @hw: pointer struct clk_hw + * + * Restore the last rounded rate m and n + * and the enable mask. + */ +void omap3_noncore_dpll_restore_context(struct clk_hw *hw) +{ + struct clk_hw_omap *clk = to_clk_hw_omap(hw); + const struct dpll_data *dd; + u32 ctrl, mult_div1; + + dd = clk->dpll_data; + + ctrl = ti_clk_ll_ops->clk_readl(&dd->control_reg); + mult_div1 = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg); + + if (clk->context == ((ctrl & dd->enable_mask) >> + __ffs(dd->enable_mask)) && + dd->last_rounded_m == ((mult_div1 & dd->mult_mask) >> + __ffs(dd->mult_mask)) && + dd->last_rounded_n == ((mult_div1 & dd->div1_mask) >> + __ffs(dd->div1_mask)) + 1) { + /* nothing to be done */ + return; + } + + if (clk->context == DPLL_LOCKED) + omap3_noncore_dpll_program(clk, 0); + else + _omap3_dpll_write_clken(clk, clk->context); +} + /* OMAP3/4 non-CORE DPLL clkops */ const struct clk_hw_omap_ops clkhwops_omap3_dpll = { .allow_idle = omap3_dpll_allow_idle, diff --git a/drivers/clk/ti/gate.c b/drivers/clk/ti/gate.c index 935b2de5fb88..cf9e9f5fc007 100644 --- a/drivers/clk/ti/gate.c +++ b/drivers/clk/ti/gate.c @@ -33,6 +33,7 @@ static const struct clk_ops omap_gate_clkdm_clk_ops = { .init = &omap2_init_clk_clkdm, .enable = &omap2_clkops_enable_clkdm, .disable = &omap2_clkops_disable_clkdm, + .restore_context = clk_gate_restore_context, }; const struct clk_ops omap_gate_clk_ops = { @@ -40,6 +41,7 @@ const struct clk_ops omap_gate_clk_ops = { .enable = &omap2_dflt_clk_enable, .disable = &omap2_dflt_clk_disable, .is_enabled = &omap2_dflt_clk_is_enabled, + .restore_context = clk_gate_restore_context, }; static const struct clk_ops omap_gate_clk_hsdiv_restore_ops = { @@ -47,6 +49,7 @@ static const struct clk_ops omap_gate_clk_hsdiv_restore_ops = { .enable = &omap36xx_gate_clk_enable_with_hsdiv_restore, .disable = &omap2_dflt_clk_disable, .is_enabled = &omap2_dflt_clk_is_enabled, + .restore_context = clk_gate_restore_context, }; /** diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c index 69a4308a5a98..5749b2b4fa61 100644 --- a/drivers/clk/ti/mux.c +++ b/drivers/clk/ti/mux.c @@ -91,10 +91,39 @@ static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index) return 0; } +/** + * clk_mux_save_context - Save the parent selcted in the mux + * @hw: pointer struct clk_hw + * + * Save the parent mux value. + */ +static int clk_mux_save_context(struct clk_hw *hw) +{ + struct clk_omap_mux *mux = to_clk_omap_mux(hw); + + mux->saved_parent = ti_clk_mux_get_parent(hw); + return 0; +} + +/** + * clk_mux_restore_context - Restore the parent in the mux + * @hw: pointer struct clk_hw + * + * Restore the saved parent mux value. + */ +static void clk_mux_restore_context(struct clk_hw *hw) +{ + struct clk_omap_mux *mux = to_clk_omap_mux(hw); + + ti_clk_mux_set_parent(hw, mux->saved_parent); +} + const struct clk_ops ti_clk_mux_ops = { .get_parent = ti_clk_mux_get_parent, .set_parent = ti_clk_mux_set_parent, .determine_rate = __clk_mux_determine_rate, + .save_context = clk_mux_save_context, + .restore_context = clk_mux_restore_context, }; static struct clk *_register_mux(struct device *dev, const char *name, diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3301bd025a2c..eacc5df57b99 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -159,6 +159,7 @@ struct clk_hw_omap { const char *clkdm_name; struct clockdomain *clkdm; const struct clk_hw_omap_ops *ops; + u32 context; }; /* @@ -294,6 +295,11 @@ struct ti_clk_features { void ti_clk_setup_features(struct ti_clk_features *features); const struct ti_clk_features *ti_clk_get_features(void); +int omap3_noncore_dpll_save_context(struct clk_hw *hw); +void omap3_noncore_dpll_restore_context(struct clk_hw *hw); + +int omap3_core_dpll_save_context(struct clk_hw *hw); +void omap3_core_dpll_restore_context(struct clk_hw *hw); extern const struct clk_hw_omap_ops clkhwops_omap2xxx_dpll; -- cgit v1.2.3-71-gd317 From 608a0ab2f54ab0e301ad76a41aad979ea0d02670 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:44 -0400 Subject: SUNRPC: Add lockless lookup of the server's auth domain Avoid taking the global auth_domain_lock in most lookups of the auth domain by adding an RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svcauth.h | 1 + net/sunrpc/auth_gss/svcauth_gss.c | 9 ++++++++- net/sunrpc/svcauth.c | 22 +++++++++++++++++++--- net/sunrpc/svcauth_unix.c | 10 ++++++++-- 4 files changed, 36 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 04e404a07882..3e53a6e2ada7 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -82,6 +82,7 @@ struct auth_domain { struct hlist_node hash; char *name; struct auth_ops *flavour; + struct rcu_head rcu_head; }; /* diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 860f2a1bbb67..87c71fb0f0ea 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1764,14 +1764,21 @@ out_err: } static void -svcauth_gss_domain_release(struct auth_domain *dom) +svcauth_gss_domain_release_rcu(struct rcu_head *head) { + struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct gss_domain *gd = container_of(dom, struct gss_domain, h); kfree(dom->name); kfree(gd); } +static void +svcauth_gss_domain_release(struct auth_domain *dom) +{ + call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu); +} + static struct auth_ops svcauthops_gss = { .name = "rpcsec_gss", .owner = THIS_MODULE, diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index f83443856cd1..775b8c94265b 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -143,10 +143,11 @@ static struct hlist_head auth_domain_table[DN_HASHMAX]; static DEFINE_SPINLOCK(auth_domain_lock); static void auth_domain_release(struct kref *kref) + __releases(&auth_domain_lock) { struct auth_domain *dom = container_of(kref, struct auth_domain, ref); - hlist_del(&dom->hash); + hlist_del_rcu(&dom->hash); dom->flavour->domain_release(dom); spin_unlock(&auth_domain_lock); } @@ -175,7 +176,7 @@ auth_domain_lookup(char *name, struct auth_domain *new) } } if (new) - hlist_add_head(&new->hash, head); + hlist_add_head_rcu(&new->hash, head); spin_unlock(&auth_domain_lock); return new; } @@ -183,6 +184,21 @@ EXPORT_SYMBOL_GPL(auth_domain_lookup); struct auth_domain *auth_domain_find(char *name) { - return auth_domain_lookup(name, NULL); + struct auth_domain *hp; + struct hlist_head *head; + + head = &auth_domain_table[hash_str(name, DN_HASHBITS)]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(hp, head, hash) { + if (strcmp(hp->name, name)==0) { + if (!kref_get_unless_zero(&hp->ref)) + hp = NULL; + rcu_read_unlock(); + return hp; + } + } + rcu_read_unlock(); + return NULL; } EXPORT_SYMBOL_GPL(auth_domain_find); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index af7f28fb8102..84cf39021a03 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -37,20 +37,26 @@ struct unix_domain { extern struct auth_ops svcauth_null; extern struct auth_ops svcauth_unix; -static void svcauth_unix_domain_release(struct auth_domain *dom) +static void svcauth_unix_domain_release_rcu(struct rcu_head *head) { + struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct unix_domain *ud = container_of(dom, struct unix_domain, h); kfree(dom->name); kfree(ud); } +static void svcauth_unix_domain_release(struct auth_domain *dom) +{ + call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu); +} + struct auth_domain *unix_domain_find(char *name) { struct auth_domain *rv; struct unix_domain *new = NULL; - rv = auth_domain_lookup(name, NULL); + rv = auth_domain_find(name); while(1) { if (rv) { if (new && rv != &new->h) -- cgit v1.2.3-71-gd317 From 34845c939082093354a6ffbb1ebff599e30b9b22 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 26 Sep 2018 15:20:03 +0200 Subject: reset: Grammar s/more then once/more than once/ Fix grammar in reset_control_get_exclusive() documentation comment. Signed-off-by: Geert Uytterhoeven Signed-off-by: Philipp Zabel --- include/linux/reset.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 09732c36f351..29af6d6b2f4b 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -116,7 +116,7 @@ static inline int device_reset_optional(struct device *dev) * @id: reset line name * * Returns a struct reset_control or IS_ERR() condition containing errno. - * If this function is called more then once for the same reset_control it will + * If this function is called more than once for the same reset_control it will * return -EBUSY. * * See reset_control_get_shared for details on shared references to -- cgit v1.2.3-71-gd317 From b723a7911d028fb55f67a63c4c4d895f72e059d4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:32 +0300 Subject: fanotify: fix collision of internal and uapi mark flags The new mark flag FAN_MARK_FILESYSTEMS collides with existing internal flag FAN_MARK_ONDIR. Change internal flag value to avoid the collision. Fixes: d54f4fba889b ("fanotify: add API to attach/detach super block mark") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fanotify.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 9c5ea3bdfaa0..e70fccc3757e 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,7 +5,7 @@ #include /* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x00000100 +#define FAN_MARK_ONDIR 0x80000000 #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3-71-gd317 From 007d1e8395eaa59b0e7ad9eb2b53a40859446a88 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:33 +0300 Subject: fsnotify: generalize handling of extra event flags FS_EVENT_ON_CHILD gets a special treatment in fsnotify() because it is not a flag specifying an event type, but rather an extra flags that may be reported along with another event and control the handling of the event by the backend. FS_ISDIR is also an "extra flag" and not an "event type" and therefore desrves the same treatment. With inotify/dnotify backends it was never possible to set FS_ISDIR in mark masks, so it did not matter. With fanotify backend, mark adding code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. Separate the constant ALL_FSNOTIFY_EVENTS to ALL_FSNOTIFY_FLAGS and ALL_FSNOTIFY_EVENTS, so the latter can be used to test for specific event types. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 7 +++---- include/linux/fsnotify_backend.h | 9 +++++++-- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 422fbc6dffde..7391a02bf723 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -196,7 +196,7 @@ static int send_to_group(struct inode *to_tell, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; - __u32 test_mask = (mask & ~FS_EVENT_ON_CHILD); + __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignored_mask = 0; struct fsnotify_mark *mark; @@ -329,8 +329,7 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, struct mount *mnt = NULL; __u32 mnt_or_sb_mask = 0; int ret = 0; - /* global tests shouldn't care about events on child only the specific event */ - __u32 test_mask = (mask & ~FS_EVENT_ON_CHILD); + __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (data_is == FSNOTIFY_EVENT_PATH) { mnt = real_mount(((const struct path *)data)->mnt); @@ -396,7 +395,7 @@ static __init int fsnotify_init(void) { int ret; - BUG_ON(hweight32(ALL_FSNOTIFY_EVENTS) != 23); + BUG_ON(hweight32(ALL_FSNOTIFY_BITS) != 23); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8e91341cbd8a..135b973e44d1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -68,15 +68,20 @@ #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM) +/* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \ FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \ FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ - FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \ - FS_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \ + FS_OPEN_PERM | FS_ACCESS_PERM | FS_DN_RENAME) + +/* Extra flags that may be reported with event or control handling of events */ +#define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ FS_DN_MULTISHOT | FS_EVENT_ON_CHILD) +#define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) + struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; -- cgit v1.2.3-71-gd317 From a72fd224e37bf6a0630bce302deebbccbc236ba2 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:34 +0300 Subject: fanotify: simplify handling of FAN_ONDIR fanotify mark add/remove code jumps through hoops to avoid setting the FS_ISDIR in the commulative object mask. That was just papering over a bug in fsnotify() handling of the FS_ISDIR extra flag. This bug is now fixed, so all the hoops can be removed along with the unneeded internal flag FAN_MARK_ONDIR. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 32 +++++--------------------------- include/linux/fanotify.h | 3 --- 2 files changed, 5 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 15719d4aa4b5..34b511407035 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -506,18 +506,10 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { - __u32 tmask = fsn_mark->mask & ~mask; - - if (flags & FAN_MARK_ONDIR) - tmask &= ~FAN_ONDIR; - oldmask = fsn_mark->mask; - fsn_mark->mask = tmask; + fsn_mark->mask &= ~mask; } else { - __u32 tmask = fsn_mark->ignored_mask & ~mask; - if (flags & FAN_MARK_ONDIR) - tmask &= ~FAN_ONDIR; - fsn_mark->ignored_mask = tmask; + fsn_mark->ignored_mask &= ~mask; } *destroy = !(fsn_mark->mask | fsn_mark->ignored_mask); spin_unlock(&fsn_mark->lock); @@ -586,19 +578,10 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, spin_lock(&fsn_mark->lock); if (!(flags & FAN_MARK_IGNORED_MASK)) { - __u32 tmask = fsn_mark->mask | mask; - - if (flags & FAN_MARK_ONDIR) - tmask |= FAN_ONDIR; - oldmask = fsn_mark->mask; - fsn_mark->mask = tmask; + fsn_mark->mask |= mask; } else { - __u32 tmask = fsn_mark->ignored_mask | mask; - if (flags & FAN_MARK_ONDIR) - tmask |= FAN_ONDIR; - - fsn_mark->ignored_mask = tmask; + fsn_mark->ignored_mask |= mask; if (flags & FAN_MARK_IGNORED_SURV_MODIFY) fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY; } @@ -820,7 +803,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, struct fsnotify_group *group; struct fd f; struct path path; - u32 valid_mask = FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD; + u32 valid_mask = FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD | FAN_ONDIR; unsigned int mark_type = flags & FAN_MARK_TYPE_MASK; int ret; @@ -857,11 +840,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EINVAL; } - if (mask & FAN_ONDIR) { - flags |= FAN_MARK_ONDIR; - mask &= ~FAN_ONDIR; - } - if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) valid_mask |= FAN_ALL_PERM_EVENTS; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index e70fccc3757e..a8c3fc54276d 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -4,9 +4,6 @@ #include -/* not valid from userspace, only kernel internal */ -#define FAN_MARK_ONDIR 0x80000000 - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) -- cgit v1.2.3-71-gd317 From 23c9deeb3285d34fd243abb3d6b9f07db60c3cf4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:35 +0300 Subject: fanotify: deprecate uapi FAN_ALL_* constants We do not want to add new bits to the FAN_ALL_* uapi constants because they have been exposed to userspace. If there are programs out there using these constants, those programs could break if re-compiled with modified FAN_ALL_* constants and run on an old kernel. We deprecate the uapi constants FAN_ALL_* and define new FANOTIFY_* constants for internal use to replace them. New feature bits will be added only to the new constants. Cc: Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 6 ++--- fs/notify/fanotify/fanotify.h | 2 +- fs/notify/fanotify/fanotify_user.c | 22 +++++++++--------- include/linux/fanotify.h | 47 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fanotify.h | 18 +++++++-------- 5 files changed, 71 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 94b52157bf8d..03498eb995be 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -131,8 +131,8 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info, !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) return false; - if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask & - ~marks_ignored_mask) + if (event_mask & FANOTIFY_OUTGOING_EVENTS & + marks_mask & ~marks_ignored_mask) return true; return false; @@ -236,7 +236,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, ret = fsnotify_add_event(group, fsn_event, fanotify_merge); if (ret) { /* Permission events shouldn't be merged */ - BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS); + BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS); /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 8609ba06f474..88a8290a61cb 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -44,7 +44,7 @@ FANOTIFY_PE(struct fsnotify_event *fse) static inline bool fanotify_is_perm_event(u32 mask) { return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) && - mask & FAN_ALL_PERM_EVENTS; + mask & FANOTIFY_PERM_EVENTS; } static inline struct fanotify_event_info *FANOTIFY_E(struct fsnotify_event *fse) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 34b511407035..530e5e486105 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -131,7 +131,7 @@ static int fill_event_metadata(struct fsnotify_group *group, metadata->metadata_len = FAN_EVENT_METADATA_LEN; metadata->vers = FANOTIFY_METADATA_VERSION; metadata->reserved = 0; - metadata->mask = fsn_event->mask & FAN_ALL_OUTGOING_EVENTS; + metadata->mask = fsn_event->mask & FANOTIFY_OUTGOING_EVENTS; metadata->pid = pid_vnr(event->tgid); if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW)) metadata->fd = FAN_NOFD; @@ -395,7 +395,7 @@ static int fanotify_release(struct inode *ignored, struct file *file) */ while (!fsnotify_notify_queue_is_empty(group)) { fsn_event = fsnotify_remove_first_event(group); - if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) { + if (!(fsn_event->mask & FANOTIFY_PERM_EVENTS)) { spin_unlock(&group->notification_lock); fsnotify_destroy_event(group, fsn_event); spin_lock(&group->notification_lock); @@ -691,9 +691,9 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) return -EPERM; #ifdef CONFIG_AUDITSYSCALL - if (flags & ~(FAN_ALL_INIT_FLAGS | FAN_ENABLE_AUDIT)) + if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT)) #else - if (flags & ~FAN_ALL_INIT_FLAGS) + if (flags & ~FANOTIFY_INIT_FLAGS) #endif return -EINVAL; @@ -745,7 +745,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.f_flags = event_f_flags; init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); - switch (flags & FAN_ALL_CLASS_BITS) { + switch (flags & FANOTIFY_CLASS_BITS) { case FAN_CLASS_NOTIF: group->priority = FS_PRIO_0; break; @@ -803,8 +803,8 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, struct fsnotify_group *group; struct fd f; struct path path; - u32 valid_mask = FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD | FAN_ONDIR; - unsigned int mark_type = flags & FAN_MARK_TYPE_MASK; + u32 valid_mask = FANOTIFY_EVENTS | FAN_EVENT_ON_CHILD | FAN_ONDIR; + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; int ret; pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n", @@ -814,7 +814,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (mask & ((__u64)0xffffffff << 32)) return -EINVAL; - if (flags & ~FAN_ALL_MARK_FLAGS) + if (flags & ~FANOTIFY_MARK_FLAGS) return -EINVAL; switch (mark_type) { @@ -833,7 +833,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, return -EINVAL; break; case FAN_MARK_FLUSH: - if (flags & ~(FAN_MARK_TYPE_MASK | FAN_MARK_FLUSH)) + if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH)) return -EINVAL; break; default: @@ -841,7 +841,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, } if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) - valid_mask |= FAN_ALL_PERM_EVENTS; + valid_mask |= FANOTIFY_PERM_EVENTS; if (mask & ~valid_mask) return -EINVAL; @@ -861,7 +861,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, * allowed to set permissions events. */ ret = -EINVAL; - if (mask & FAN_ALL_PERM_EVENTS && + if (mask & FANOTIFY_PERM_EVENTS && group->priority == FS_PRIO_0) goto fput_and_out; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index a8c3fc54276d..4519b0988afe 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -7,4 +7,51 @@ #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) +/* + * Flags allowed to be passed from/to userspace. + * + * We intentionally do not add new bits to the old FAN_ALL_* constants, because + * they are uapi exposed constants. If there are programs out there using + * these constant, the programs may break if re-compiled with new uapi headers + * and then run on an old kernel. + */ +#define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ + FAN_CLASS_PRE_CONTENT) + +#define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_CLOEXEC | FAN_NONBLOCK | \ + FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) + +#define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ + FAN_MARK_FILESYSTEM) + +#define FANOTIFY_MARK_FLAGS (FANOTIFY_MARK_TYPE_BITS | \ + FAN_MARK_ADD | \ + FAN_MARK_REMOVE | \ + FAN_MARK_DONT_FOLLOW | \ + FAN_MARK_ONLYDIR | \ + FAN_MARK_IGNORED_MASK | \ + FAN_MARK_IGNORED_SURV_MODIFY | \ + FAN_MARK_FLUSH) + +/* Events that user can request to be notified on */ +#define FANOTIFY_EVENTS (FAN_ACCESS | FAN_MODIFY | \ + FAN_CLOSE | FAN_OPEN) + +/* Events that require a permission response from user */ +#define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) + +/* Events that may be reported to user */ +#define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ + FANOTIFY_PERM_EVENTS | \ + FAN_Q_OVERFLOW) + +/* Do not use these old uapi constants internally */ +#undef FAN_ALL_CLASS_BITS +#undef FAN_ALL_INIT_FLAGS +#undef FAN_ALL_MARK_FLAGS +#undef FAN_ALL_EVENTS +#undef FAN_ALL_PERM_EVENTS +#undef FAN_ALL_OUTGOING_EVENTS + #endif /* _LINUX_FANOTIFY_H */ diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index ad81234d1919..d0c05de670ef 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -31,6 +31,8 @@ #define FAN_CLASS_NOTIF 0x00000000 #define FAN_CLASS_CONTENT 0x00000004 #define FAN_CLASS_PRE_CONTENT 0x00000008 + +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ FAN_CLASS_PRE_CONTENT) @@ -38,6 +40,7 @@ #define FAN_UNLIMITED_MARKS 0x00000020 #define FAN_ENABLE_AUDIT 0x00000040 +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\ FAN_UNLIMITED_MARKS) @@ -57,23 +60,18 @@ #define FAN_MARK_INODE 0x00000000 #define FAN_MARK_MOUNT 0x00000010 #define FAN_MARK_FILESYSTEM 0x00000100 -#define FAN_MARK_TYPE_MASK (FAN_MARK_INODE | FAN_MARK_MOUNT | \ - FAN_MARK_FILESYSTEM) +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ FAN_MARK_REMOVE |\ FAN_MARK_DONT_FOLLOW |\ FAN_MARK_ONLYDIR |\ + FAN_MARK_MOUNT |\ FAN_MARK_IGNORED_MASK |\ FAN_MARK_IGNORED_SURV_MODIFY |\ - FAN_MARK_FLUSH|\ - FAN_MARK_TYPE_MASK) + FAN_MARK_FLUSH) -/* - * All of the events - we build the list by hand so that we can add flags in - * the future and not break backward compatibility. Apps will get only the - * events that they originally wanted. Be sure to add new events here! - */ +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_EVENTS (FAN_ACCESS |\ FAN_MODIFY |\ FAN_CLOSE |\ @@ -82,9 +80,11 @@ /* * All events which require a permission response from userspace */ +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\ FAN_ACCESS_PERM) +/* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ FAN_ALL_PERM_EVENTS |\ FAN_Q_OVERFLOW) -- cgit v1.2.3-71-gd317 From bdd5a46fe30653cb4d26c7c787a22159bf79eed9 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:37 +0300 Subject: fanotify: add BUILD_BUG_ON() to count the bits of fanotify constants Also define the FANOTIFY_EVENT_FLAGS consisting of the extra flags FAN_ONDIR and FAN_ON_CHILD. Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 2 ++ fs/notify/fanotify/fanotify_user.c | 5 ++++- include/linux/fanotify.h | 6 ++++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 03498eb995be..361e3a0a445c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -205,6 +205,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM); BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 10); + if (!fanotify_should_send_event(iter_info, mask, data, data_type)) return 0; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 530e5e486105..14594e491d2b 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -803,7 +803,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, struct fsnotify_group *group; struct fd f; struct path path; - u32 valid_mask = FANOTIFY_EVENTS | FAN_EVENT_ON_CHILD | FAN_ONDIR; + u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS; unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; int ret; @@ -944,6 +944,9 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, */ static int __init fanotify_user_setup(void) { + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 6); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); + fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC); diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 4519b0988afe..caf55c67fc6c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -41,11 +41,17 @@ /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM) +/* Extra flags that may be reported with event or control handling of events */ +#define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) + /* Events that may be reported to user */ #define FANOTIFY_OUTGOING_EVENTS (FANOTIFY_EVENTS | \ FANOTIFY_PERM_EVENTS | \ FAN_Q_OVERFLOW) +#define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \ + FANOTIFY_EVENT_FLAGS) + /* Do not use these old uapi constants internally */ #undef FAN_ALL_CLASS_BITS #undef FAN_ALL_INIT_FLAGS -- cgit v1.2.3-71-gd317 From 817e9bc8cc04e5c70592525b96812c46c1aa1c46 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 4 Oct 2018 09:57:23 -0700 Subject: Revert "serial:serial_core: Allow use of CTS for PPS line discipline" This reverts commit c550f01c810f2197c98e6e3103f81797f5e063be. Turns out the samsung tty driver is mucking around in the "unused" port fields and this patch breaks that code :( So we need to fix that driver up before this can be accepted. Reported-by: Stephen Rothwell Cc: Steve Sakoman Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-tty | 9 ----- drivers/tty/serial/serial_core.c | 70 +------------------------------------ include/linux/serial_core.h | 3 +- 3 files changed, 2 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-tty b/Documentation/ABI/testing/sysfs-tty index 441105a75d1f..9eb3c2b6b040 100644 --- a/Documentation/ABI/testing/sysfs-tty +++ b/Documentation/ABI/testing/sysfs-tty @@ -154,12 +154,3 @@ Description: device specification. For example, when user sets 7bytes on 16550A, which has 1/4/8/14 bytes trigger, the RX trigger is automatically changed to 4 bytes. - -What: /sys/class/tty/ttyS0/pps_4wire -Date: September 2018 -Contact: Steve Sakoman -Description: - Shows/sets "4 wire" mode for the PPS input to the serial driver. - For fully implemented serial ports PPS is normally provided - on the DCD line. For partial "4 wire" implementations CTS is - used instead of DCD. diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 0a4e6eeb5ff3..70402cdb4d8c 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2724,57 +2724,6 @@ static ssize_t uart_get_attr_iomem_reg_shift(struct device *dev, return snprintf(buf, PAGE_SIZE, "%d\n", tmp.iomem_reg_shift); } -static ssize_t pps_4wire_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct tty_port *port = dev_get_drvdata(dev); - struct uart_state *state = container_of(port, struct uart_state, port); - struct uart_port *uport; - int mode = 0; - - mutex_lock(&port->mutex); - uport = uart_port_check(state); - if (!uport) - goto out; - - mode = uport->pps_4wire; - -out: - mutex_unlock(&port->mutex); - return sprintf(buf, mode ? "yes\n" : "no\n"); -} - -static ssize_t pps_4wire_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) -{ - struct tty_port *port = dev_get_drvdata(dev); - struct uart_state *state = container_of(port, struct uart_state, port); - struct uart_port *uport; - bool mode; - int ret; - - if (!count) - return -EINVAL; - - ret = kstrtobool(buf, &mode); - if (ret < 0) - return ret; - - mutex_lock(&port->mutex); - uport = uart_port_check(state); - if (!uport) - goto out; - - spin_lock_irq(&uport->lock); - uport->pps_4wire = mode; - spin_unlock_irq(&uport->lock); - -out: - mutex_unlock(&port->mutex); - return count; -} -static DEVICE_ATTR_RW(pps_4wire); - static DEVICE_ATTR(type, S_IRUSR | S_IRGRP, uart_get_attr_type, NULL); static DEVICE_ATTR(line, S_IRUSR | S_IRGRP, uart_get_attr_line, NULL); static DEVICE_ATTR(port, S_IRUSR | S_IRGRP, uart_get_attr_port, NULL); @@ -2803,7 +2752,6 @@ static struct attribute *tty_dev_attrs[] = { &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, - &dev_attr_pps_4wire.attr, NULL, }; @@ -2860,9 +2808,6 @@ int uart_add_one_port(struct uart_driver *drv, struct uart_port *uport) goto out; } - /* assert that pps handling is done via DCD as default */ - uport->pps_4wire = 0; - /* * If this port is a console, then the spinlock is already * initialised. @@ -3038,7 +2983,7 @@ void uart_handle_dcd_change(struct uart_port *uport, unsigned int status) lockdep_assert_held_once(&uport->lock); - if (tty && !uport->pps_4wire) { + if (tty) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) @@ -3067,21 +3012,8 @@ EXPORT_SYMBOL_GPL(uart_handle_dcd_change); */ void uart_handle_cts_change(struct uart_port *uport, unsigned int status) { - struct tty_port *port = &uport->state->port; - struct tty_struct *tty = port->tty; - struct tty_ldisc *ld; - lockdep_assert_held_once(&uport->lock); - if (tty && uport->pps_4wire) { - ld = tty_ldisc_ref(tty); - if (ld) { - if (ld->ops->dcd_change) - ld->ops->dcd_change(tty, status); - tty_ldisc_deref(ld); - } - } - uport->icount.cts++; if (uart_softcts_mode(uport)) { diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 4e2ba4894dcc..047fa67d039b 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -257,8 +257,7 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char pps_4wire; /* CTS instead of DCD */ - unsigned char unused; + unsigned char unused[2]; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ -- cgit v1.2.3-71-gd317 From 1bb89893d4fa8275333b3ed74fb0379d63025f9a Mon Sep 17 00:00:00 2001 From: Suman Anna Date: Fri, 14 Sep 2018 19:37:23 -0500 Subject: remoteproc: Add missing kernel-doc comment for auto-boot The commit ddf711872c9d ("remoteproc: Introduce auto-boot flag") introduced the auto-boot flag but missed adding the corresponding kernel-doc comment. Add the same. Signed-off-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e3c5d856b6da..75f9ca05b865 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -439,6 +439,7 @@ struct rproc_dump_segment { * @cached_table: copy of the resource table * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU + * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware */ struct rproc { -- cgit v1.2.3-71-gd317 From d0a6a87e40da49cfc7954c491d3065a25a641b29 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 4 Oct 2018 00:25:38 +0300 Subject: fanotify: support reporting thread id instead of process id In order to identify which thread triggered the event in a multi-threaded program, add the FAN_REPORT_TID flag in fanotify_init to opt-in for reporting the event creator's thread id information. Signed-off-by: nixiaoming Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 9 ++++++--- fs/notify/fanotify/fanotify.h | 2 +- fs/notify/fanotify/fanotify_user.c | 4 ++-- include/linux/fanotify.h | 1 + include/uapi/linux/fanotify.h | 3 +++ 5 files changed, 13 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 361e3a0a445c..5769cf3ff035 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -25,7 +25,7 @@ static bool should_merge(struct fsnotify_event *old_fsn, old = FANOTIFY_E(old_fsn); new = FANOTIFY_E(new_fsn); - if (old_fsn->inode == new_fsn->inode && old->tgid == new->tgid && + if (old_fsn->inode == new_fsn->inode && old->pid == new->pid && old->path.mnt == new->path.mnt && old->path.dentry == new->path.dentry) return true; @@ -171,7 +171,10 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group, goto out; init: __maybe_unused fsnotify_init_event(&event->fse, inode, mask); - event->tgid = get_pid(task_tgid(current)); + if (FAN_GROUP_FLAG(group, FAN_REPORT_TID)) + event->pid = get_pid(task_pid(current)); + else + event->pid = get_pid(task_tgid(current)); if (path) { event->path = *path; path_get(&event->path); @@ -270,7 +273,7 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event) event = FANOTIFY_E(fsn_event); path_put(&event->path); - put_pid(event->tgid); + put_pid(event->pid); if (fanotify_is_perm_event(fsn_event->mask)) { kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PE(fsn_event)); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 88a8290a61cb..ea05b8a401e7 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -19,7 +19,7 @@ struct fanotify_event_info { * during this object's lifetime */ struct path path; - struct pid *tgid; + struct pid *pid; }; /* diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 14594e491d2b..e03be5071362 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -132,7 +132,7 @@ static int fill_event_metadata(struct fsnotify_group *group, metadata->vers = FANOTIFY_METADATA_VERSION; metadata->reserved = 0; metadata->mask = fsn_event->mask & FANOTIFY_OUTGOING_EVENTS; - metadata->pid = pid_vnr(event->tgid); + metadata->pid = pid_vnr(event->pid); if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW)) metadata->fd = FAN_NOFD; else { @@ -944,7 +944,7 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark, */ static int __init fanotify_user_setup(void) { - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 6); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 7); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index caf55c67fc6c..a5a60691e48b 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -19,6 +19,7 @@ FAN_CLASS_PRE_CONTENT) #define FANOTIFY_INIT_FLAGS (FANOTIFY_CLASS_BITS | \ + FAN_REPORT_TID | \ FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_UNLIMITED_QUEUE | FAN_UNLIMITED_MARKS) diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index d0c05de670ef..b86740d1c50a 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -40,6 +40,9 @@ #define FAN_UNLIMITED_MARKS 0x00000020 #define FAN_ENABLE_AUDIT 0x00000040 +/* Flags to determine fanotify event format */ +#define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ + /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\ -- cgit v1.2.3-71-gd317 From edbee095fafb4b727b51032bdc41e345f95bbc20 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:42 +0800 Subject: firmware: imx: add SCU firmware driver support The System Controller Firmware (SCFW) is a low-level system function which runs on a dedicated Cortex-M core to provide power, clock, and resource management. It exists on some i.MX8 processors. e.g. i.MX8QM (QM, QP), and i.MX8QX (QXP, DX). This patch implements the SCU firmware IPC function and the common message sending API sc_call_rpc. Cc: Shawn Guo Cc: Fabio Estevam Cc: Jassi Brar Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- drivers/firmware/Kconfig | 1 + drivers/firmware/Makefile | 1 + drivers/firmware/imx/Kconfig | 11 + drivers/firmware/imx/Makefile | 2 + drivers/firmware/imx/imx-scu.c | 270 ++++++++++++++++ include/linux/firmware/imx/ipc.h | 59 ++++ include/linux/firmware/imx/sci.h | 16 + include/linux/firmware/imx/types.h | 617 +++++++++++++++++++++++++++++++++++++ 8 files changed, 977 insertions(+) create mode 100644 drivers/firmware/imx/Kconfig create mode 100644 drivers/firmware/imx/Makefile create mode 100644 drivers/firmware/imx/imx-scu.c create mode 100644 include/linux/firmware/imx/ipc.h create mode 100644 include/linux/firmware/imx/sci.h create mode 100644 include/linux/firmware/imx/types.h (limited to 'include/linux') diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 6e83880046d7..bd9e4e2c41db 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -289,6 +289,7 @@ config HAVE_ARM_SMCCC source "drivers/firmware/broadcom/Kconfig" source "drivers/firmware/google/Kconfig" source "drivers/firmware/efi/Kconfig" +source "drivers/firmware/imx/Kconfig" source "drivers/firmware/meson/Kconfig" source "drivers/firmware/tegra/Kconfig" diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index e18a041cfc53..e1281d6a03d4 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -31,4 +31,5 @@ obj-y += meson/ obj-$(CONFIG_GOOGLE_FIRMWARE) += google/ obj-$(CONFIG_EFI) += efi/ obj-$(CONFIG_UEFI_CPER) += efi/ +obj-y += imx/ obj-y += tegra/ diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig new file mode 100644 index 000000000000..b170c2851e48 --- /dev/null +++ b/drivers/firmware/imx/Kconfig @@ -0,0 +1,11 @@ +config IMX_SCU + bool "IMX SCU Protocol driver" + depends on IMX_MBOX + help + The System Controller Firmware (SCFW) is a low-level system function + which runs on a dedicated Cortex-M core to provide power, clock, and + resource management. It exists on some i.MX8 processors. e.g. i.MX8QM + (QM, QP), and i.MX8QX (QXP, DX). + + This driver manages the IPC interface between host CPU and the + SCU firmware running on M4. diff --git a/drivers/firmware/imx/Makefile b/drivers/firmware/imx/Makefile new file mode 100644 index 000000000000..9b1e2febb1aa --- /dev/null +++ b/drivers/firmware/imx/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_IMX_SCU) += imx-scu.o diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c new file mode 100644 index 000000000000..2bb1a19c413f --- /dev/null +++ b/drivers/firmware/imx/imx-scu.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018 NXP + * Author: Dong Aisheng + * + * Implementation of the SCU IPC functions using MUs (client side). + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SCU_MU_CHAN_NUM 8 +#define MAX_RX_TIMEOUT (msecs_to_jiffies(30)) + +struct imx_sc_chan { + struct imx_sc_ipc *sc_ipc; + + struct mbox_client cl; + struct mbox_chan *ch; + int idx; +}; + +struct imx_sc_ipc { + /* SCU uses 4 Tx and 4 Rx channels */ + struct imx_sc_chan chans[SCU_MU_CHAN_NUM]; + struct device *dev; + struct mutex lock; + struct completion done; + + /* temporarily store the SCU msg */ + u32 *msg; + u8 rx_size; + u8 count; +}; + +/* + * This type is used to indicate error response for most functions. + */ +enum imx_sc_error_codes { + IMX_SC_ERR_NONE = 0, /* Success */ + IMX_SC_ERR_VERSION = 1, /* Incompatible API version */ + IMX_SC_ERR_CONFIG = 2, /* Configuration error */ + IMX_SC_ERR_PARM = 3, /* Bad parameter */ + IMX_SC_ERR_NOACCESS = 4, /* Permission error (no access) */ + IMX_SC_ERR_LOCKED = 5, /* Permission error (locked) */ + IMX_SC_ERR_UNAVAILABLE = 6, /* Unavailable (out of resources) */ + IMX_SC_ERR_NOTFOUND = 7, /* Not found */ + IMX_SC_ERR_NOPOWER = 8, /* No power */ + IMX_SC_ERR_IPC = 9, /* Generic IPC error */ + IMX_SC_ERR_BUSY = 10, /* Resource is currently busy/active */ + IMX_SC_ERR_FAIL = 11, /* General I/O failure */ + IMX_SC_ERR_LAST +}; + +static int imx_sc_linux_errmap[IMX_SC_ERR_LAST] = { + 0, /* IMX_SC_ERR_NONE */ + -EINVAL, /* IMX_SC_ERR_VERSION */ + -EINVAL, /* IMX_SC_ERR_CONFIG */ + -EINVAL, /* IMX_SC_ERR_PARM */ + -EACCES, /* IMX_SC_ERR_NOACCESS */ + -EACCES, /* IMX_SC_ERR_LOCKED */ + -ERANGE, /* IMX_SC_ERR_UNAVAILABLE */ + -EEXIST, /* IMX_SC_ERR_NOTFOUND */ + -EPERM, /* IMX_SC_ERR_NOPOWER */ + -EPIPE, /* IMX_SC_ERR_IPC */ + -EBUSY, /* IMX_SC_ERR_BUSY */ + -EIO, /* IMX_SC_ERR_FAIL */ +}; + +static struct imx_sc_ipc *imx_sc_ipc_handle; + +static inline int imx_sc_to_linux_errno(int errno) +{ + if (errno >= IMX_SC_ERR_NONE && errno < IMX_SC_ERR_LAST) + return imx_sc_linux_errmap[errno]; + return -EIO; +} + +/* + * Get the default handle used by SCU + */ +int imx_scu_get_handle(struct imx_sc_ipc **ipc) +{ + if (!imx_sc_ipc_handle) + return -EPROBE_DEFER; + + *ipc = imx_sc_ipc_handle; + return 0; +} +EXPORT_SYMBOL(imx_scu_get_handle); + +static void imx_scu_rx_callback(struct mbox_client *c, void *msg) +{ + struct imx_sc_chan *sc_chan = container_of(c, struct imx_sc_chan, cl); + struct imx_sc_ipc *sc_ipc = sc_chan->sc_ipc; + struct imx_sc_rpc_msg *hdr; + u32 *data = msg; + + if (sc_chan->idx == 0) { + hdr = msg; + sc_ipc->rx_size = hdr->size; + dev_dbg(sc_ipc->dev, "msg rx size %u\n", sc_ipc->rx_size); + if (sc_ipc->rx_size > 4) + dev_warn(sc_ipc->dev, "RPC does not support receiving over 4 words: %u\n", + sc_ipc->rx_size); + } + + sc_ipc->msg[sc_chan->idx] = *data; + sc_ipc->count++; + + dev_dbg(sc_ipc->dev, "mu %u msg %u 0x%x\n", sc_chan->idx, + sc_ipc->count, *data); + + if ((sc_ipc->rx_size != 0) && (sc_ipc->count == sc_ipc->rx_size)) + complete(&sc_ipc->done); +} + +static int imx_scu_ipc_write(struct imx_sc_ipc *sc_ipc, void *msg) +{ + struct imx_sc_rpc_msg *hdr = msg; + struct imx_sc_chan *sc_chan; + u32 *data = msg; + int ret; + int i; + + /* Check size */ + if (hdr->size > IMX_SC_RPC_MAX_MSG) + return -EINVAL; + + dev_dbg(sc_ipc->dev, "RPC SVC %u FUNC %u SIZE %u\n", hdr->svc, + hdr->func, hdr->size); + + for (i = 0; i < hdr->size; i++) { + sc_chan = &sc_ipc->chans[i % 4]; + ret = mbox_send_message(sc_chan->ch, &data[i]); + if (ret < 0) + return ret; + } + + return 0; +} + +/* + * RPC command/response + */ +int imx_scu_call_rpc(struct imx_sc_ipc *sc_ipc, void *msg, bool have_resp) +{ + struct imx_sc_rpc_msg *hdr; + int ret; + + if (WARN_ON(!sc_ipc || !msg)) + return -EINVAL; + + mutex_lock(&sc_ipc->lock); + reinit_completion(&sc_ipc->done); + + sc_ipc->msg = msg; + sc_ipc->count = 0; + ret = imx_scu_ipc_write(sc_ipc, msg); + if (ret < 0) { + dev_err(sc_ipc->dev, "RPC send msg failed: %d\n", ret); + goto out; + } + + if (have_resp) { + if (!wait_for_completion_timeout(&sc_ipc->done, + MAX_RX_TIMEOUT)) { + dev_err(sc_ipc->dev, "RPC send msg timeout\n"); + mutex_unlock(&sc_ipc->lock); + return -ETIMEDOUT; + } + + /* response status is stored in hdr->func field */ + hdr = msg; + ret = hdr->func; + } + +out: + mutex_unlock(&sc_ipc->lock); + + dev_dbg(sc_ipc->dev, "RPC SVC done\n"); + + return imx_sc_to_linux_errno(ret); +} +EXPORT_SYMBOL(imx_scu_call_rpc); + +static int imx_scu_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct imx_sc_ipc *sc_ipc; + struct imx_sc_chan *sc_chan; + struct mbox_client *cl; + char *chan_name; + int ret; + int i; + + sc_ipc = devm_kzalloc(dev, sizeof(*sc_ipc), GFP_KERNEL); + if (!sc_ipc) + return -ENOMEM; + + for (i = 0; i < SCU_MU_CHAN_NUM; i++) { + if (i < 4) + chan_name = kasprintf(GFP_KERNEL, "tx%d", i); + else + chan_name = kasprintf(GFP_KERNEL, "rx%d", i - 4); + + if (!chan_name) + return -ENOMEM; + + sc_chan = &sc_ipc->chans[i]; + cl = &sc_chan->cl; + cl->dev = dev; + cl->tx_block = false; + cl->knows_txdone = true; + cl->rx_callback = imx_scu_rx_callback; + + sc_chan->sc_ipc = sc_ipc; + sc_chan->idx = i % 4; + sc_chan->ch = mbox_request_channel_byname(cl, chan_name); + if (IS_ERR(sc_chan->ch)) { + ret = PTR_ERR(sc_chan->ch); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to request mbox chan %s ret %d\n", + chan_name, ret); + return ret; + } + + dev_dbg(dev, "request mbox chan %s\n", chan_name); + /* chan_name is not used anymore by framework */ + kfree(chan_name); + } + + sc_ipc->dev = dev; + mutex_init(&sc_ipc->lock); + init_completion(&sc_ipc->done); + + imx_sc_ipc_handle = sc_ipc; + + dev_info(dev, "NXP i.MX SCU Initialized\n"); + + return devm_of_platform_populate(dev); +} + +static const struct of_device_id imx_scu_match[] = { + { .compatible = "fsl,imx-scu", }, + { /* Sentinel */ } +}; + +static struct platform_driver imx_scu_driver = { + .driver = { + .name = "imx-scu", + .of_match_table = imx_scu_match, + }, + .probe = imx_scu_probe, +}; +builtin_platform_driver(imx_scu_driver); + +MODULE_AUTHOR("Dong Aisheng "); +MODULE_DESCRIPTION("IMX SCU firmware protocol driver"); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/firmware/imx/ipc.h b/include/linux/firmware/imx/ipc.h new file mode 100644 index 000000000000..6312c8cb084a --- /dev/null +++ b/include/linux/firmware/imx/ipc.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018 NXP + * + * Header file for the IPC implementation. + */ + +#ifndef _SC_IPC_H +#define _SC_IPC_H + +#include +#include + +#define IMX_SC_RPC_VERSION 1 +#define IMX_SC_RPC_MAX_MSG 8 + +struct imx_sc_ipc; + +enum imx_sc_rpc_svc { + IMX_SC_RPC_SVC_UNKNOWN = 0, + IMX_SC_RPC_SVC_RETURN = 1, + IMX_SC_RPC_SVC_PM = 2, + IMX_SC_RPC_SVC_RM = 3, + IMX_SC_RPC_SVC_TIMER = 5, + IMX_SC_RPC_SVC_PAD = 6, + IMX_SC_RPC_SVC_MISC = 7, + IMX_SC_RPC_SVC_IRQ = 8, + IMX_SC_RPC_SVC_ABORT = 9 +}; + +struct imx_sc_rpc_msg { + uint8_t ver; + uint8_t size; + uint8_t svc; + uint8_t func; +}; + +/* + * This is an function to send an RPC message over an IPC channel. + * It is called by client-side SCFW API function shims. + * + * @param[in] ipc IPC handle + * @param[in,out] msg handle to a message + * @param[in] have_resp response flag + * + * If have_resp is true then this function waits for a response + * and returns the result in msg. + */ +int imx_scu_call_rpc(struct imx_sc_ipc *ipc, void *msg, bool have_resp); + +/* + * This function gets the default ipc handle used by SCU + * + * @param[out] ipc sc ipc handle + * + * @return Returns an error code (0 = success, failed if < 0) + */ +int imx_scu_get_handle(struct imx_sc_ipc **ipc); +#endif /* _SC_IPC_H */ diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h new file mode 100644 index 000000000000..ff3227ad8d7c --- /dev/null +++ b/include/linux/firmware/imx/sci.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public System Controller Interface (SCI) + * definitions. + */ + +#ifndef _SC_SCI_H +#define _SC_SCI_H + +#include +#include + +#endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/types.h b/include/linux/firmware/imx/types.h new file mode 100644 index 000000000000..9cbf0c4a6069 --- /dev/null +++ b/include/linux/firmware/imx/types.h @@ -0,0 +1,617 @@ +/* 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 resource. Resources include peripherals + * and bus masters (but not memory regions). Note items from list should + * never be changed or removed (only added to at the end of the list). + */ +enum imx_sc_rsrc { + IMX_SC_R_A53 = 0, + IMX_SC_R_A53_0 = 1, + IMX_SC_R_A53_1 = 2, + IMX_SC_R_A53_2 = 3, + IMX_SC_R_A53_3 = 4, + IMX_SC_R_A72 = 5, + IMX_SC_R_A72_0 = 6, + IMX_SC_R_A72_1 = 7, + IMX_SC_R_A72_2 = 8, + IMX_SC_R_A72_3 = 9, + IMX_SC_R_CCI = 10, + IMX_SC_R_DB = 11, + IMX_SC_R_DRC_0 = 12, + IMX_SC_R_DRC_1 = 13, + IMX_SC_R_GIC_SMMU = 14, + IMX_SC_R_IRQSTR_M4_0 = 15, + IMX_SC_R_IRQSTR_M4_1 = 16, + IMX_SC_R_SMMU = 17, + IMX_SC_R_GIC = 18, + IMX_SC_R_DC_0_BLIT0 = 19, + IMX_SC_R_DC_0_BLIT1 = 20, + IMX_SC_R_DC_0_BLIT2 = 21, + IMX_SC_R_DC_0_BLIT_OUT = 22, + IMX_SC_R_DC_0_CAPTURE0 = 23, + IMX_SC_R_DC_0_CAPTURE1 = 24, + IMX_SC_R_DC_0_WARP = 25, + IMX_SC_R_DC_0_INTEGRAL0 = 26, + IMX_SC_R_DC_0_INTEGRAL1 = 27, + IMX_SC_R_DC_0_VIDEO0 = 28, + IMX_SC_R_DC_0_VIDEO1 = 29, + IMX_SC_R_DC_0_FRAC0 = 30, + IMX_SC_R_DC_0_FRAC1 = 31, + IMX_SC_R_DC_0 = 32, + IMX_SC_R_GPU_2_PID0 = 33, + IMX_SC_R_DC_0_PLL_0 = 34, + IMX_SC_R_DC_0_PLL_1 = 35, + IMX_SC_R_DC_1_BLIT0 = 36, + IMX_SC_R_DC_1_BLIT1 = 37, + IMX_SC_R_DC_1_BLIT2 = 38, + IMX_SC_R_DC_1_BLIT_OUT = 39, + IMX_SC_R_DC_1_CAPTURE0 = 40, + IMX_SC_R_DC_1_CAPTURE1 = 41, + IMX_SC_R_DC_1_WARP = 42, + IMX_SC_R_DC_1_INTEGRAL0 = 43, + IMX_SC_R_DC_1_INTEGRAL1 = 44, + IMX_SC_R_DC_1_VIDEO0 = 45, + IMX_SC_R_DC_1_VIDEO1 = 46, + IMX_SC_R_DC_1_FRAC0 = 47, + IMX_SC_R_DC_1_FRAC1 = 48, + IMX_SC_R_DC_1 = 49, + IMX_SC_R_GPU_3_PID0 = 50, + IMX_SC_R_DC_1_PLL_0 = 51, + IMX_SC_R_DC_1_PLL_1 = 52, + IMX_SC_R_SPI_0 = 53, + IMX_SC_R_SPI_1 = 54, + IMX_SC_R_SPI_2 = 55, + IMX_SC_R_SPI_3 = 56, + IMX_SC_R_UART_0 = 57, + IMX_SC_R_UART_1 = 58, + IMX_SC_R_UART_2 = 59, + IMX_SC_R_UART_3 = 60, + IMX_SC_R_UART_4 = 61, + IMX_SC_R_EMVSIM_0 = 62, + IMX_SC_R_EMVSIM_1 = 63, + IMX_SC_R_DMA_0_CH0 = 64, + IMX_SC_R_DMA_0_CH1 = 65, + IMX_SC_R_DMA_0_CH2 = 66, + IMX_SC_R_DMA_0_CH3 = 67, + IMX_SC_R_DMA_0_CH4 = 68, + IMX_SC_R_DMA_0_CH5 = 69, + IMX_SC_R_DMA_0_CH6 = 70, + IMX_SC_R_DMA_0_CH7 = 71, + IMX_SC_R_DMA_0_CH8 = 72, + IMX_SC_R_DMA_0_CH9 = 73, + IMX_SC_R_DMA_0_CH10 = 74, + IMX_SC_R_DMA_0_CH11 = 75, + IMX_SC_R_DMA_0_CH12 = 76, + IMX_SC_R_DMA_0_CH13 = 77, + IMX_SC_R_DMA_0_CH14 = 78, + IMX_SC_R_DMA_0_CH15 = 79, + IMX_SC_R_DMA_0_CH16 = 80, + IMX_SC_R_DMA_0_CH17 = 81, + IMX_SC_R_DMA_0_CH18 = 82, + IMX_SC_R_DMA_0_CH19 = 83, + IMX_SC_R_DMA_0_CH20 = 84, + IMX_SC_R_DMA_0_CH21 = 85, + IMX_SC_R_DMA_0_CH22 = 86, + IMX_SC_R_DMA_0_CH23 = 87, + IMX_SC_R_DMA_0_CH24 = 88, + IMX_SC_R_DMA_0_CH25 = 89, + IMX_SC_R_DMA_0_CH26 = 90, + IMX_SC_R_DMA_0_CH27 = 91, + IMX_SC_R_DMA_0_CH28 = 92, + IMX_SC_R_DMA_0_CH29 = 93, + IMX_SC_R_DMA_0_CH30 = 94, + IMX_SC_R_DMA_0_CH31 = 95, + IMX_SC_R_I2C_0 = 96, + IMX_SC_R_I2C_1 = 97, + IMX_SC_R_I2C_2 = 98, + IMX_SC_R_I2C_3 = 99, + IMX_SC_R_I2C_4 = 100, + IMX_SC_R_ADC_0 = 101, + IMX_SC_R_ADC_1 = 102, + IMX_SC_R_FTM_0 = 103, + IMX_SC_R_FTM_1 = 104, + IMX_SC_R_CAN_0 = 105, + IMX_SC_R_CAN_1 = 106, + IMX_SC_R_CAN_2 = 107, + IMX_SC_R_DMA_1_CH0 = 108, + IMX_SC_R_DMA_1_CH1 = 109, + IMX_SC_R_DMA_1_CH2 = 110, + IMX_SC_R_DMA_1_CH3 = 111, + IMX_SC_R_DMA_1_CH4 = 112, + IMX_SC_R_DMA_1_CH5 = 113, + IMX_SC_R_DMA_1_CH6 = 114, + IMX_SC_R_DMA_1_CH7 = 115, + IMX_SC_R_DMA_1_CH8 = 116, + IMX_SC_R_DMA_1_CH9 = 117, + IMX_SC_R_DMA_1_CH10 = 118, + IMX_SC_R_DMA_1_CH11 = 119, + IMX_SC_R_DMA_1_CH12 = 120, + IMX_SC_R_DMA_1_CH13 = 121, + IMX_SC_R_DMA_1_CH14 = 122, + IMX_SC_R_DMA_1_CH15 = 123, + IMX_SC_R_DMA_1_CH16 = 124, + IMX_SC_R_DMA_1_CH17 = 125, + IMX_SC_R_DMA_1_CH18 = 126, + IMX_SC_R_DMA_1_CH19 = 127, + IMX_SC_R_DMA_1_CH20 = 128, + IMX_SC_R_DMA_1_CH21 = 129, + IMX_SC_R_DMA_1_CH22 = 130, + IMX_SC_R_DMA_1_CH23 = 131, + IMX_SC_R_DMA_1_CH24 = 132, + IMX_SC_R_DMA_1_CH25 = 133, + IMX_SC_R_DMA_1_CH26 = 134, + IMX_SC_R_DMA_1_CH27 = 135, + IMX_SC_R_DMA_1_CH28 = 136, + IMX_SC_R_DMA_1_CH29 = 137, + IMX_SC_R_DMA_1_CH30 = 138, + IMX_SC_R_DMA_1_CH31 = 139, + IMX_SC_R_UNUSED1 = 140, + IMX_SC_R_UNUSED2 = 141, + IMX_SC_R_UNUSED3 = 142, + IMX_SC_R_UNUSED4 = 143, + IMX_SC_R_GPU_0_PID0 = 144, + IMX_SC_R_GPU_0_PID1 = 145, + IMX_SC_R_GPU_0_PID2 = 146, + IMX_SC_R_GPU_0_PID3 = 147, + IMX_SC_R_GPU_1_PID0 = 148, + IMX_SC_R_GPU_1_PID1 = 149, + IMX_SC_R_GPU_1_PID2 = 150, + IMX_SC_R_GPU_1_PID3 = 151, + IMX_SC_R_PCIE_A = 152, + IMX_SC_R_SERDES_0 = 153, + IMX_SC_R_MATCH_0 = 154, + IMX_SC_R_MATCH_1 = 155, + IMX_SC_R_MATCH_2 = 156, + IMX_SC_R_MATCH_3 = 157, + IMX_SC_R_MATCH_4 = 158, + IMX_SC_R_MATCH_5 = 159, + IMX_SC_R_MATCH_6 = 160, + IMX_SC_R_MATCH_7 = 161, + IMX_SC_R_MATCH_8 = 162, + IMX_SC_R_MATCH_9 = 163, + IMX_SC_R_MATCH_10 = 164, + IMX_SC_R_MATCH_11 = 165, + IMX_SC_R_MATCH_12 = 166, + IMX_SC_R_MATCH_13 = 167, + IMX_SC_R_MATCH_14 = 168, + IMX_SC_R_PCIE_B = 169, + IMX_SC_R_SATA_0 = 170, + IMX_SC_R_SERDES_1 = 171, + IMX_SC_R_HSIO_GPIO = 172, + IMX_SC_R_MATCH_15 = 173, + IMX_SC_R_MATCH_16 = 174, + IMX_SC_R_MATCH_17 = 175, + IMX_SC_R_MATCH_18 = 176, + IMX_SC_R_MATCH_19 = 177, + IMX_SC_R_MATCH_20 = 178, + IMX_SC_R_MATCH_21 = 179, + IMX_SC_R_MATCH_22 = 180, + IMX_SC_R_MATCH_23 = 181, + IMX_SC_R_MATCH_24 = 182, + IMX_SC_R_MATCH_25 = 183, + IMX_SC_R_MATCH_26 = 184, + IMX_SC_R_MATCH_27 = 185, + IMX_SC_R_MATCH_28 = 186, + IMX_SC_R_LCD_0 = 187, + IMX_SC_R_LCD_0_PWM_0 = 188, + IMX_SC_R_LCD_0_I2C_0 = 189, + IMX_SC_R_LCD_0_I2C_1 = 190, + IMX_SC_R_PWM_0 = 191, + IMX_SC_R_PWM_1 = 192, + IMX_SC_R_PWM_2 = 193, + IMX_SC_R_PWM_3 = 194, + IMX_SC_R_PWM_4 = 195, + IMX_SC_R_PWM_5 = 196, + IMX_SC_R_PWM_6 = 197, + IMX_SC_R_PWM_7 = 198, + IMX_SC_R_GPIO_0 = 199, + IMX_SC_R_GPIO_1 = 200, + IMX_SC_R_GPIO_2 = 201, + IMX_SC_R_GPIO_3 = 202, + IMX_SC_R_GPIO_4 = 203, + IMX_SC_R_GPIO_5 = 204, + IMX_SC_R_GPIO_6 = 205, + IMX_SC_R_GPIO_7 = 206, + IMX_SC_R_GPT_0 = 207, + IMX_SC_R_GPT_1 = 208, + IMX_SC_R_GPT_2 = 209, + IMX_SC_R_GPT_3 = 210, + IMX_SC_R_GPT_4 = 211, + IMX_SC_R_KPP = 212, + IMX_SC_R_MU_0A = 213, + IMX_SC_R_MU_1A = 214, + IMX_SC_R_MU_2A = 215, + IMX_SC_R_MU_3A = 216, + IMX_SC_R_MU_4A = 217, + IMX_SC_R_MU_5A = 218, + IMX_SC_R_MU_6A = 219, + IMX_SC_R_MU_7A = 220, + IMX_SC_R_MU_8A = 221, + IMX_SC_R_MU_9A = 222, + IMX_SC_R_MU_10A = 223, + IMX_SC_R_MU_11A = 224, + IMX_SC_R_MU_12A = 225, + IMX_SC_R_MU_13A = 226, + IMX_SC_R_MU_5B = 227, + IMX_SC_R_MU_6B = 228, + IMX_SC_R_MU_7B = 229, + IMX_SC_R_MU_8B = 230, + IMX_SC_R_MU_9B = 231, + IMX_SC_R_MU_10B = 232, + IMX_SC_R_MU_11B = 233, + IMX_SC_R_MU_12B = 234, + IMX_SC_R_MU_13B = 235, + IMX_SC_R_ROM_0 = 236, + IMX_SC_R_FSPI_0 = 237, + IMX_SC_R_FSPI_1 = 238, + IMX_SC_R_IEE = 239, + IMX_SC_R_IEE_R0 = 240, + IMX_SC_R_IEE_R1 = 241, + IMX_SC_R_IEE_R2 = 242, + IMX_SC_R_IEE_R3 = 243, + IMX_SC_R_IEE_R4 = 244, + IMX_SC_R_IEE_R5 = 245, + IMX_SC_R_IEE_R6 = 246, + IMX_SC_R_IEE_R7 = 247, + IMX_SC_R_SDHC_0 = 248, + IMX_SC_R_SDHC_1 = 249, + IMX_SC_R_SDHC_2 = 250, + IMX_SC_R_ENET_0 = 251, + IMX_SC_R_ENET_1 = 252, + IMX_SC_R_MLB_0 = 253, + IMX_SC_R_DMA_2_CH0 = 254, + IMX_SC_R_DMA_2_CH1 = 255, + IMX_SC_R_DMA_2_CH2 = 256, + IMX_SC_R_DMA_2_CH3 = 257, + IMX_SC_R_DMA_2_CH4 = 258, + IMX_SC_R_USB_0 = 259, + IMX_SC_R_USB_1 = 260, + IMX_SC_R_USB_0_PHY = 261, + IMX_SC_R_USB_2 = 262, + IMX_SC_R_USB_2_PHY = 263, + IMX_SC_R_DTCP = 264, + IMX_SC_R_NAND = 265, + IMX_SC_R_LVDS_0 = 266, + IMX_SC_R_LVDS_0_PWM_0 = 267, + IMX_SC_R_LVDS_0_I2C_0 = 268, + IMX_SC_R_LVDS_0_I2C_1 = 269, + IMX_SC_R_LVDS_1 = 270, + IMX_SC_R_LVDS_1_PWM_0 = 271, + IMX_SC_R_LVDS_1_I2C_0 = 272, + IMX_SC_R_LVDS_1_I2C_1 = 273, + IMX_SC_R_LVDS_2 = 274, + IMX_SC_R_LVDS_2_PWM_0 = 275, + IMX_SC_R_LVDS_2_I2C_0 = 276, + IMX_SC_R_LVDS_2_I2C_1 = 277, + IMX_SC_R_M4_0_PID0 = 278, + IMX_SC_R_M4_0_PID1 = 279, + IMX_SC_R_M4_0_PID2 = 280, + IMX_SC_R_M4_0_PID3 = 281, + IMX_SC_R_M4_0_PID4 = 282, + IMX_SC_R_M4_0_RGPIO = 283, + IMX_SC_R_M4_0_SEMA42 = 284, + IMX_SC_R_M4_0_TPM = 285, + IMX_SC_R_M4_0_PIT = 286, + IMX_SC_R_M4_0_UART = 287, + IMX_SC_R_M4_0_I2C = 288, + IMX_SC_R_M4_0_INTMUX = 289, + IMX_SC_R_M4_0_SIM = 290, + IMX_SC_R_M4_0_WDOG = 291, + IMX_SC_R_M4_0_MU_0B = 292, + IMX_SC_R_M4_0_MU_0A0 = 293, + IMX_SC_R_M4_0_MU_0A1 = 294, + IMX_SC_R_M4_0_MU_0A2 = 295, + IMX_SC_R_M4_0_MU_0A3 = 296, + IMX_SC_R_M4_0_MU_1A = 297, + IMX_SC_R_M4_1_PID0 = 298, + IMX_SC_R_M4_1_PID1 = 299, + IMX_SC_R_M4_1_PID2 = 300, + IMX_SC_R_M4_1_PID3 = 301, + IMX_SC_R_M4_1_PID4 = 302, + IMX_SC_R_M4_1_RGPIO = 303, + IMX_SC_R_M4_1_SEMA42 = 304, + IMX_SC_R_M4_1_TPM = 305, + IMX_SC_R_M4_1_PIT = 306, + IMX_SC_R_M4_1_UART = 307, + IMX_SC_R_M4_1_I2C = 308, + IMX_SC_R_M4_1_INTMUX = 309, + IMX_SC_R_M4_1_SIM = 310, + IMX_SC_R_M4_1_WDOG = 311, + IMX_SC_R_M4_1_MU_0B = 312, + IMX_SC_R_M4_1_MU_0A0 = 313, + IMX_SC_R_M4_1_MU_0A1 = 314, + IMX_SC_R_M4_1_MU_0A2 = 315, + IMX_SC_R_M4_1_MU_0A3 = 316, + IMX_SC_R_M4_1_MU_1A = 317, + IMX_SC_R_SAI_0 = 318, + IMX_SC_R_SAI_1 = 319, + IMX_SC_R_SAI_2 = 320, + IMX_SC_R_IRQSTR_SCU2 = 321, + IMX_SC_R_IRQSTR_DSP = 322, + IMX_SC_R_UNUSED5 = 323, + IMX_SC_R_UNUSED6 = 324, + IMX_SC_R_AUDIO_PLL_0 = 325, + IMX_SC_R_PI_0 = 326, + IMX_SC_R_PI_0_PWM_0 = 327, + IMX_SC_R_PI_0_PWM_1 = 328, + IMX_SC_R_PI_0_I2C_0 = 329, + IMX_SC_R_PI_0_PLL = 330, + IMX_SC_R_PI_1 = 331, + IMX_SC_R_PI_1_PWM_0 = 332, + IMX_SC_R_PI_1_PWM_1 = 333, + IMX_SC_R_PI_1_I2C_0 = 334, + IMX_SC_R_PI_1_PLL = 335, + IMX_SC_R_SC_PID0 = 336, + IMX_SC_R_SC_PID1 = 337, + IMX_SC_R_SC_PID2 = 338, + IMX_SC_R_SC_PID3 = 339, + IMX_SC_R_SC_PID4 = 340, + IMX_SC_R_SC_SEMA42 = 341, + IMX_SC_R_SC_TPM = 342, + IMX_SC_R_SC_PIT = 343, + IMX_SC_R_SC_UART = 344, + IMX_SC_R_SC_I2C = 345, + IMX_SC_R_SC_MU_0B = 346, + IMX_SC_R_SC_MU_0A0 = 347, + IMX_SC_R_SC_MU_0A1 = 348, + IMX_SC_R_SC_MU_0A2 = 349, + IMX_SC_R_SC_MU_0A3 = 350, + IMX_SC_R_SC_MU_1A = 351, + IMX_SC_R_SYSCNT_RD = 352, + IMX_SC_R_SYSCNT_CMP = 353, + IMX_SC_R_DEBUG = 354, + IMX_SC_R_SYSTEM = 355, + IMX_SC_R_SNVS = 356, + IMX_SC_R_OTP = 357, + IMX_SC_R_VPU_PID0 = 358, + IMX_SC_R_VPU_PID1 = 359, + IMX_SC_R_VPU_PID2 = 360, + IMX_SC_R_VPU_PID3 = 361, + IMX_SC_R_VPU_PID4 = 362, + IMX_SC_R_VPU_PID5 = 363, + IMX_SC_R_VPU_PID6 = 364, + IMX_SC_R_VPU_PID7 = 365, + IMX_SC_R_VPU_UART = 366, + IMX_SC_R_VPUCORE = 367, + IMX_SC_R_VPUCORE_0 = 368, + IMX_SC_R_VPUCORE_1 = 369, + IMX_SC_R_VPUCORE_2 = 370, + IMX_SC_R_VPUCORE_3 = 371, + IMX_SC_R_DMA_4_CH0 = 372, + IMX_SC_R_DMA_4_CH1 = 373, + IMX_SC_R_DMA_4_CH2 = 374, + IMX_SC_R_DMA_4_CH3 = 375, + IMX_SC_R_DMA_4_CH4 = 376, + IMX_SC_R_ISI_CH0 = 377, + IMX_SC_R_ISI_CH1 = 378, + IMX_SC_R_ISI_CH2 = 379, + IMX_SC_R_ISI_CH3 = 380, + IMX_SC_R_ISI_CH4 = 381, + IMX_SC_R_ISI_CH5 = 382, + IMX_SC_R_ISI_CH6 = 383, + IMX_SC_R_ISI_CH7 = 384, + IMX_SC_R_MJPEG_DEC_S0 = 385, + IMX_SC_R_MJPEG_DEC_S1 = 386, + IMX_SC_R_MJPEG_DEC_S2 = 387, + IMX_SC_R_MJPEG_DEC_S3 = 388, + IMX_SC_R_MJPEG_ENC_S0 = 389, + IMX_SC_R_MJPEG_ENC_S1 = 390, + IMX_SC_R_MJPEG_ENC_S2 = 391, + IMX_SC_R_MJPEG_ENC_S3 = 392, + IMX_SC_R_MIPI_0 = 393, + IMX_SC_R_MIPI_0_PWM_0 = 394, + IMX_SC_R_MIPI_0_I2C_0 = 395, + IMX_SC_R_MIPI_0_I2C_1 = 396, + IMX_SC_R_MIPI_1 = 397, + IMX_SC_R_MIPI_1_PWM_0 = 398, + IMX_SC_R_MIPI_1_I2C_0 = 399, + IMX_SC_R_MIPI_1_I2C_1 = 400, + IMX_SC_R_CSI_0 = 401, + IMX_SC_R_CSI_0_PWM_0 = 402, + IMX_SC_R_CSI_0_I2C_0 = 403, + IMX_SC_R_CSI_1 = 404, + IMX_SC_R_CSI_1_PWM_0 = 405, + IMX_SC_R_CSI_1_I2C_0 = 406, + IMX_SC_R_HDMI = 407, + IMX_SC_R_HDMI_I2S = 408, + IMX_SC_R_HDMI_I2C_0 = 409, + IMX_SC_R_HDMI_PLL_0 = 410, + IMX_SC_R_HDMI_RX = 411, + IMX_SC_R_HDMI_RX_BYPASS = 412, + IMX_SC_R_HDMI_RX_I2C_0 = 413, + IMX_SC_R_ASRC_0 = 414, + IMX_SC_R_ESAI_0 = 415, + IMX_SC_R_SPDIF_0 = 416, + IMX_SC_R_SPDIF_1 = 417, + IMX_SC_R_SAI_3 = 418, + IMX_SC_R_SAI_4 = 419, + IMX_SC_R_SAI_5 = 420, + IMX_SC_R_GPT_5 = 421, + IMX_SC_R_GPT_6 = 422, + IMX_SC_R_GPT_7 = 423, + IMX_SC_R_GPT_8 = 424, + IMX_SC_R_GPT_9 = 425, + IMX_SC_R_GPT_10 = 426, + IMX_SC_R_DMA_2_CH5 = 427, + IMX_SC_R_DMA_2_CH6 = 428, + IMX_SC_R_DMA_2_CH7 = 429, + IMX_SC_R_DMA_2_CH8 = 430, + IMX_SC_R_DMA_2_CH9 = 431, + IMX_SC_R_DMA_2_CH10 = 432, + IMX_SC_R_DMA_2_CH11 = 433, + IMX_SC_R_DMA_2_CH12 = 434, + IMX_SC_R_DMA_2_CH13 = 435, + IMX_SC_R_DMA_2_CH14 = 436, + IMX_SC_R_DMA_2_CH15 = 437, + IMX_SC_R_DMA_2_CH16 = 438, + IMX_SC_R_DMA_2_CH17 = 439, + IMX_SC_R_DMA_2_CH18 = 440, + IMX_SC_R_DMA_2_CH19 = 441, + IMX_SC_R_DMA_2_CH20 = 442, + IMX_SC_R_DMA_2_CH21 = 443, + IMX_SC_R_DMA_2_CH22 = 444, + IMX_SC_R_DMA_2_CH23 = 445, + IMX_SC_R_DMA_2_CH24 = 446, + IMX_SC_R_DMA_2_CH25 = 447, + IMX_SC_R_DMA_2_CH26 = 448, + IMX_SC_R_DMA_2_CH27 = 449, + IMX_SC_R_DMA_2_CH28 = 450, + IMX_SC_R_DMA_2_CH29 = 451, + IMX_SC_R_DMA_2_CH30 = 452, + IMX_SC_R_DMA_2_CH31 = 453, + IMX_SC_R_ASRC_1 = 454, + IMX_SC_R_ESAI_1 = 455, + IMX_SC_R_SAI_6 = 456, + IMX_SC_R_SAI_7 = 457, + IMX_SC_R_AMIX = 458, + IMX_SC_R_MQS_0 = 459, + IMX_SC_R_DMA_3_CH0 = 460, + IMX_SC_R_DMA_3_CH1 = 461, + IMX_SC_R_DMA_3_CH2 = 462, + IMX_SC_R_DMA_3_CH3 = 463, + IMX_SC_R_DMA_3_CH4 = 464, + IMX_SC_R_DMA_3_CH5 = 465, + IMX_SC_R_DMA_3_CH6 = 466, + IMX_SC_R_DMA_3_CH7 = 467, + IMX_SC_R_DMA_3_CH8 = 468, + IMX_SC_R_DMA_3_CH9 = 469, + IMX_SC_R_DMA_3_CH10 = 470, + IMX_SC_R_DMA_3_CH11 = 471, + IMX_SC_R_DMA_3_CH12 = 472, + IMX_SC_R_DMA_3_CH13 = 473, + IMX_SC_R_DMA_3_CH14 = 474, + IMX_SC_R_DMA_3_CH15 = 475, + IMX_SC_R_DMA_3_CH16 = 476, + IMX_SC_R_DMA_3_CH17 = 477, + IMX_SC_R_DMA_3_CH18 = 478, + IMX_SC_R_DMA_3_CH19 = 479, + IMX_SC_R_DMA_3_CH20 = 480, + IMX_SC_R_DMA_3_CH21 = 481, + IMX_SC_R_DMA_3_CH22 = 482, + IMX_SC_R_DMA_3_CH23 = 483, + IMX_SC_R_DMA_3_CH24 = 484, + IMX_SC_R_DMA_3_CH25 = 485, + IMX_SC_R_DMA_3_CH26 = 486, + IMX_SC_R_DMA_3_CH27 = 487, + IMX_SC_R_DMA_3_CH28 = 488, + IMX_SC_R_DMA_3_CH29 = 489, + IMX_SC_R_DMA_3_CH30 = 490, + IMX_SC_R_DMA_3_CH31 = 491, + IMX_SC_R_AUDIO_PLL_1 = 492, + IMX_SC_R_AUDIO_CLK_0 = 493, + IMX_SC_R_AUDIO_CLK_1 = 494, + IMX_SC_R_MCLK_OUT_0 = 495, + IMX_SC_R_MCLK_OUT_1 = 496, + IMX_SC_R_PMIC_0 = 497, + IMX_SC_R_PMIC_1 = 498, + IMX_SC_R_SECO = 499, + IMX_SC_R_CAAM_JR1 = 500, + IMX_SC_R_CAAM_JR2 = 501, + IMX_SC_R_CAAM_JR3 = 502, + IMX_SC_R_SECO_MU_2 = 503, + IMX_SC_R_SECO_MU_3 = 504, + IMX_SC_R_SECO_MU_4 = 505, + IMX_SC_R_HDMI_RX_PWM_0 = 506, + IMX_SC_R_A35 = 507, + IMX_SC_R_A35_0 = 508, + IMX_SC_R_A35_1 = 509, + IMX_SC_R_A35_2 = 510, + IMX_SC_R_A35_3 = 511, + IMX_SC_R_DSP = 512, + IMX_SC_R_DSP_RAM = 513, + IMX_SC_R_CAAM_JR1_OUT = 514, + IMX_SC_R_CAAM_JR2_OUT = 515, + IMX_SC_R_CAAM_JR3_OUT = 516, + IMX_SC_R_VPU_DEC_0 = 517, + IMX_SC_R_VPU_ENC_0 = 518, + IMX_SC_R_CAAM_JR0 = 519, + IMX_SC_R_CAAM_JR0_OUT = 520, + IMX_SC_R_PMIC_2 = 521, + IMX_SC_R_DBLOGIC = 522, + IMX_SC_R_HDMI_PLL_1 = 523, + IMX_SC_R_BOARD_R0 = 524, + IMX_SC_R_BOARD_R1 = 525, + IMX_SC_R_BOARD_R2 = 526, + IMX_SC_R_BOARD_R3 = 527, + IMX_SC_R_BOARD_R4 = 528, + IMX_SC_R_BOARD_R5 = 529, + IMX_SC_R_BOARD_R6 = 530, + IMX_SC_R_BOARD_R7 = 531, + IMX_SC_R_MJPEG_DEC_MP = 532, + IMX_SC_R_MJPEG_ENC_MP = 533, + IMX_SC_R_VPU_TS_0 = 534, + IMX_SC_R_VPU_MU_0 = 535, + IMX_SC_R_VPU_MU_1 = 536, + IMX_SC_R_VPU_MU_2 = 537, + IMX_SC_R_VPU_MU_3 = 538, + IMX_SC_R_VPU_ENC_1 = 539, + IMX_SC_R_VPU = 540, + IMX_SC_R_LAST +}; + +/* NOTE - please add by replacing some of the UNUSED from above! */ + +/* + * 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 v1.2.3-71-gd317 From 15e1f2bc8b3b2d238b9e06b128d4a09d28f11733 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Sun, 7 Oct 2018 21:04:43 +0800 Subject: firmware: imx: add misc svc support Add SCU MISC SVC support which provides misc control get/set functions. Cc: Shawn Guo Reviewed-by: Sascha Hauer Signed-off-by: Dong Aisheng Signed-off-by: Shawn Guo --- drivers/firmware/imx/Makefile | 2 +- drivers/firmware/imx/misc.c | 99 +++++++++++++++++++++++++++++++++++ include/linux/firmware/imx/sci.h | 1 + include/linux/firmware/imx/svc/misc.h | 55 +++++++++++++++++++ 4 files changed, 156 insertions(+), 1 deletion(-) create mode 100644 drivers/firmware/imx/misc.c create mode 100644 include/linux/firmware/imx/svc/misc.h (limited to 'include/linux') diff --git a/drivers/firmware/imx/Makefile b/drivers/firmware/imx/Makefile index 9b1e2febb1aa..0ac04dfda8d4 100644 --- a/drivers/firmware/imx/Makefile +++ b/drivers/firmware/imx/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_IMX_SCU) += imx-scu.o +obj-$(CONFIG_IMX_SCU) += imx-scu.o misc.o diff --git a/drivers/firmware/imx/misc.c b/drivers/firmware/imx/misc.c new file mode 100644 index 000000000000..97f5424dbac9 --- /dev/null +++ b/drivers/firmware/imx/misc.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * Author: Dong Aisheng + * + * File containing client-side RPC functions for the MISC service. These + * function are ported to clients that communicate to the SC. + * + */ + +#include + +struct imx_sc_msg_req_misc_set_ctrl { + struct imx_sc_rpc_msg hdr; + u32 ctrl; + u32 val; + u16 resource; +} __packed; + +struct imx_sc_msg_req_misc_get_ctrl { + struct imx_sc_rpc_msg hdr; + u32 ctrl; + u16 resource; +} __packed; + +struct imx_sc_msg_resp_misc_get_ctrl { + struct imx_sc_rpc_msg hdr; + u32 val; +} __packed; + +/* + * This function sets a miscellaneous control value. + * + * @param[in] ipc IPC handle + * @param[in] resource resource the control is associated with + * @param[in] ctrl control to change + * @param[in] val value to apply to the control + * + * @return Returns 0 for success and < 0 for errors. + */ + +int imx_sc_misc_set_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 val) +{ + struct imx_sc_msg_req_misc_set_ctrl msg; + struct imx_sc_rpc_msg *hdr = &msg.hdr; + + hdr->ver = IMX_SC_RPC_VERSION; + hdr->svc = (uint8_t)IMX_SC_RPC_SVC_MISC; + hdr->func = (uint8_t)IMX_SC_MISC_FUNC_SET_CONTROL; + hdr->size = 4; + + msg.ctrl = ctrl; + msg.val = val; + msg.resource = resource; + + return imx_scu_call_rpc(ipc, &msg, true); +} +EXPORT_SYMBOL(imx_sc_misc_set_control); + +/* + * This function gets a miscellaneous control value. + * + * @param[in] ipc IPC handle + * @param[in] resource resource the control is associated with + * @param[in] ctrl control to get + * @param[out] val pointer to return the control value + * + * @return Returns 0 for success and < 0 for errors. + */ + +int imx_sc_misc_get_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 *val) +{ + struct imx_sc_msg_req_misc_get_ctrl msg; + struct imx_sc_msg_resp_misc_get_ctrl *resp; + struct imx_sc_rpc_msg *hdr = &msg.hdr; + int ret; + + hdr->ver = IMX_SC_RPC_VERSION; + hdr->svc = (uint8_t)IMX_SC_RPC_SVC_MISC; + hdr->func = (uint8_t)IMX_SC_MISC_FUNC_GET_CONTROL; + hdr->size = 3; + + msg.ctrl = ctrl; + msg.resource = resource; + + ret = imx_scu_call_rpc(ipc, &msg, true); + if (ret) + return ret; + + resp = (struct imx_sc_msg_resp_misc_get_ctrl *)&msg; + if (val != NULL) + *val = resp->val; + + return 0; +} +EXPORT_SYMBOL(imx_sc_misc_get_control); diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h index ff3227ad8d7c..29ada609de03 100644 --- a/include/linux/firmware/imx/sci.h +++ b/include/linux/firmware/imx/sci.h @@ -13,4 +13,5 @@ #include #include +#include #endif /* _SC_SCI_H */ diff --git a/include/linux/firmware/imx/svc/misc.h b/include/linux/firmware/imx/svc/misc.h new file mode 100644 index 000000000000..e21c49aba92f --- /dev/null +++ b/include/linux/firmware/imx/svc/misc.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2016 Freescale Semiconductor, Inc. + * Copyright 2017~2018 NXP + * + * Header file containing the public API for the System Controller (SC) + * Miscellaneous (MISC) function. + * + * MISC_SVC (SVC) Miscellaneous Service + * + * Module for the Miscellaneous (MISC) service. + */ + +#ifndef _SC_MISC_API_H +#define _SC_MISC_API_H + +#include + +/* + * This type is used to indicate RPC MISC function calls. + */ +enum imx_misc_func { + IMX_SC_MISC_FUNC_UNKNOWN = 0, + IMX_SC_MISC_FUNC_SET_CONTROL = 1, + IMX_SC_MISC_FUNC_GET_CONTROL = 2, + IMX_SC_MISC_FUNC_SET_MAX_DMA_GROUP = 4, + IMX_SC_MISC_FUNC_SET_DMA_GROUP = 5, + IMX_SC_MISC_FUNC_SECO_IMAGE_LOAD = 8, + IMX_SC_MISC_FUNC_SECO_AUTHENTICATE = 9, + IMX_SC_MISC_FUNC_DEBUG_OUT = 10, + IMX_SC_MISC_FUNC_WAVEFORM_CAPTURE = 6, + IMX_SC_MISC_FUNC_BUILD_INFO = 15, + IMX_SC_MISC_FUNC_UNIQUE_ID = 19, + IMX_SC_MISC_FUNC_SET_ARI = 3, + IMX_SC_MISC_FUNC_BOOT_STATUS = 7, + IMX_SC_MISC_FUNC_BOOT_DONE = 14, + IMX_SC_MISC_FUNC_OTP_FUSE_READ = 11, + IMX_SC_MISC_FUNC_OTP_FUSE_WRITE = 17, + IMX_SC_MISC_FUNC_SET_TEMP = 12, + IMX_SC_MISC_FUNC_GET_TEMP = 13, + IMX_SC_MISC_FUNC_GET_BOOT_DEV = 16, + IMX_SC_MISC_FUNC_GET_BUTTON_STATUS = 18, +}; + +/* + * Control Functions + */ + +int imx_sc_misc_set_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 val); + +int imx_sc_misc_get_control(struct imx_sc_ipc *ipc, u32 resource, + u8 ctrl, u32 *val); + +#endif /* _SC_MISC_API_H */ -- cgit v1.2.3-71-gd317 From 3b0296b8c893adb17b422179b9e779e4c32aa347 Mon Sep 17 00:00:00 2001 From: Rajan Vaja Date: Mon, 8 Oct 2018 11:21:44 -0700 Subject: firmware: xilinx: Add zynqmp IOCTL API for device control Add ZynqMP firmware IOCTL API to control and configure devices like PLLs, SD, Gem, etc. Signed-off-by: Rajan Vaja Signed-off-by: Jolly Shah Acked-by: Olof Johansson Signed-off-by: Michal Simek --- drivers/firmware/xilinx/zynqmp.c | 42 ++++++++++++++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 4 +++- 2 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 84b3fd2eca8b..9a1c72a9280f 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -428,6 +428,47 @@ static int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id) return ret; } +/** + * zynqmp_is_valid_ioctl() - Check whether IOCTL ID is valid or not + * @ioctl_id: IOCTL ID + * + * Return: 1 if IOCTL is valid else 0 + */ +static inline int zynqmp_is_valid_ioctl(u32 ioctl_id) +{ + switch (ioctl_id) { + case IOCTL_SET_PLL_FRAC_MODE: + case IOCTL_GET_PLL_FRAC_MODE: + case IOCTL_SET_PLL_FRAC_DATA: + case IOCTL_GET_PLL_FRAC_DATA: + return 1; + default: + return 0; + } +} + +/** + * zynqmp_pm_ioctl() - PM IOCTL API for device control and configs + * @node_id: Node ID of the device + * @ioctl_id: ID of the requested IOCTL + * @arg1: Argument 1 to requested IOCTL call + * @arg2: Argument 2 to requested IOCTL call + * @out: Returned output value + * + * This function calls IOCTL to firmware for device control and configuration. + * + * Return: Returns status, either success or error+reason + */ +static int zynqmp_pm_ioctl(u32 node_id, u32 ioctl_id, u32 arg1, u32 arg2, + u32 *out) +{ + if (!zynqmp_is_valid_ioctl(ioctl_id)) + return -EINVAL; + + return zynqmp_pm_invoke_fn(PM_IOCTL, node_id, ioctl_id, + arg1, arg2, out); +} + static const struct zynqmp_eemi_ops eemi_ops = { .get_api_version = zynqmp_pm_get_api_version, .query_data = zynqmp_pm_query_data, @@ -440,6 +481,7 @@ static const struct zynqmp_eemi_ops eemi_ops = { .clock_getrate = zynqmp_pm_clock_getrate, .clock_setparent = zynqmp_pm_clock_setparent, .clock_getparent = zynqmp_pm_clock_getparent, + .ioctl = zynqmp_pm_ioctl, }; /** diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 015e130431e6..7a9db0861803 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -34,7 +34,8 @@ enum pm_api_id { PM_GET_API_VERSION = 1, - PM_QUERY_DATA = 35, + PM_IOCTL = 34, + PM_QUERY_DATA, PM_CLOCK_ENABLE, PM_CLOCK_DISABLE, PM_CLOCK_GETSTATE, @@ -99,6 +100,7 @@ struct zynqmp_eemi_ops { 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); }; #if IS_REACHABLE(CONFIG_ARCH_ZYNQMP) -- cgit v1.2.3-71-gd317 From 3fde0e16d016ecb273f0fa404b5d56b947fc0576 Mon Sep 17 00:00:00 2001 From: Jolly Shah Date: Mon, 8 Oct 2018 11:21:46 -0700 Subject: drivers: clk: Add ZynqMP clock driver This patch adds CCF compliant clock driver for ZynqMP. Clock driver queries supported clock information from firmware and regiters pll and output clocks with CCF. Signed-off-by: Rajan Vaja Signed-off-by: Tejas Patel Signed-off-by: Shubhrajyoti Datta Signed-off-by: Jolly Shah Acked-by: Olof Johansson Reviewed-by: Stephen Boyd Signed-off-by: Michal Simek --- drivers/clk/Kconfig | 1 + drivers/clk/Makefile | 1 + drivers/clk/zynqmp/Kconfig | 10 + drivers/clk/zynqmp/Makefile | 4 + drivers/clk/zynqmp/clk-gate-zynqmp.c | 144 +++++++ drivers/clk/zynqmp/clk-mux-zynqmp.c | 141 +++++++ drivers/clk/zynqmp/clk-zynqmp.h | 68 ++++ drivers/clk/zynqmp/clkc.c | 716 +++++++++++++++++++++++++++++++++++ drivers/clk/zynqmp/divider.c | 217 +++++++++++ drivers/clk/zynqmp/pll.c | 335 ++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 1 + 11 files changed, 1638 insertions(+) create mode 100644 drivers/clk/zynqmp/Kconfig create mode 100644 drivers/clk/zynqmp/Makefile create mode 100644 drivers/clk/zynqmp/clk-gate-zynqmp.c create mode 100644 drivers/clk/zynqmp/clk-mux-zynqmp.c create mode 100644 drivers/clk/zynqmp/clk-zynqmp.h create mode 100644 drivers/clk/zynqmp/clkc.c create mode 100644 drivers/clk/zynqmp/divider.c create mode 100644 drivers/clk/zynqmp/pll.c (limited to 'include/linux') diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 292056bbb30e..1deafb4db60c 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -299,5 +299,6 @@ source "drivers/clk/sunxi-ng/Kconfig" source "drivers/clk/tegra/Kconfig" source "drivers/clk/ti/Kconfig" source "drivers/clk/uniphier/Kconfig" +source "drivers/clk/zynqmp/Kconfig" endmenu diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index a84c5573cabe..ad11421bdacd 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -108,3 +108,4 @@ obj-$(CONFIG_X86) += x86/ endif obj-$(CONFIG_ARCH_ZX) += zte/ obj-$(CONFIG_ARCH_ZYNQ) += zynq/ +obj-$(CONFIG_COMMON_CLK_ZYNQMP) += zynqmp/ diff --git a/drivers/clk/zynqmp/Kconfig b/drivers/clk/zynqmp/Kconfig new file mode 100644 index 000000000000..17086059be8b --- /dev/null +++ b/drivers/clk/zynqmp/Kconfig @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 + +config COMMON_CLK_ZYNQMP + bool "Support for Xilinx ZynqMP Ultrascale+ clock controllers" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on ZYNQMP_FIRMWARE + help + Support for the Zynqmp Ultrascale clock controller. + It has a dependency on the PMU firmware. + Say Y if you want to include clock support. diff --git a/drivers/clk/zynqmp/Makefile b/drivers/clk/zynqmp/Makefile new file mode 100644 index 000000000000..0ec24bfe0f18 --- /dev/null +++ b/drivers/clk/zynqmp/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +# Zynq Ultrascale+ MPSoC clock specific Makefile + +obj-$(CONFIG_ARCH_ZYNQMP) += pll.o clk-gate-zynqmp.o divider.o clk-mux-zynqmp.o clkc.o diff --git a/drivers/clk/zynqmp/clk-gate-zynqmp.c b/drivers/clk/zynqmp/clk-gate-zynqmp.c new file mode 100644 index 000000000000..83b236f20fff --- /dev/null +++ b/drivers/clk/zynqmp/clk-gate-zynqmp.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Zynq UltraScale+ MPSoC clock controller + * + * Copyright (C) 2016-2018 Xilinx + * + * Gated clock implementation + */ + +#include +#include +#include "clk-zynqmp.h" + +/** + * struct clk_gate - gating clock + * @hw: handle between common and hardware-specific interfaces + * @flags: hardware-specific flags + * @clk_id: Id of clock + */ +struct zynqmp_clk_gate { + struct clk_hw hw; + u8 flags; + u32 clk_id; +}; + +#define to_zynqmp_clk_gate(_hw) container_of(_hw, struct zynqmp_clk_gate, hw) + +/** + * zynqmp_clk_gate_enable() - Enable clock + * @hw: handle between common and hardware-specific interfaces + * + * Return: 0 on success else error code + */ +static int zynqmp_clk_gate_enable(struct clk_hw *hw) +{ + struct zynqmp_clk_gate *gate = to_zynqmp_clk_gate(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = gate->clk_id; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_enable(clk_id); + + if (ret) + pr_warn_once("%s() clock enabled failed for %s, ret = %d\n", + __func__, clk_name, ret); + + return ret; +} + +/* + * zynqmp_clk_gate_disable() - Disable clock + * @hw: handle between common and hardware-specific interfaces + */ +static void zynqmp_clk_gate_disable(struct clk_hw *hw) +{ + struct zynqmp_clk_gate *gate = to_zynqmp_clk_gate(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = gate->clk_id; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_disable(clk_id); + + if (ret) + pr_warn_once("%s() clock disable failed for %s, ret = %d\n", + __func__, clk_name, ret); +} + +/** + * zynqmp_clk_gate_is_enable() - Check clock state + * @hw: handle between common and hardware-specific interfaces + * + * Return: 1 if enabled, 0 if disabled else error code + */ +static int zynqmp_clk_gate_is_enabled(struct clk_hw *hw) +{ + struct zynqmp_clk_gate *gate = to_zynqmp_clk_gate(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = gate->clk_id; + int state, ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_getstate(clk_id, &state); + if (ret) { + pr_warn_once("%s() clock get state failed for %s, ret = %d\n", + __func__, clk_name, ret); + return -EIO; + } + + return state ? 1 : 0; +} + +static const struct clk_ops zynqmp_clk_gate_ops = { + .enable = zynqmp_clk_gate_enable, + .disable = zynqmp_clk_gate_disable, + .is_enabled = zynqmp_clk_gate_is_enabled, +}; + +/** + * zynqmp_clk_register_gate() - Register a gate clock with the clock framework + * @name: Name of this clock + * @clk_id: Id of this clock + * @parents: Name of this clock's parents + * @num_parents: Number of parents + * @nodes: Clock topology node + * + * Return: clock hardware of the registered clock gate + */ +struct clk_hw *zynqmp_clk_register_gate(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) +{ + struct zynqmp_clk_gate *gate; + struct clk_hw *hw; + int ret; + struct clk_init_data init; + + /* allocate the gate */ + gate = kzalloc(sizeof(*gate), GFP_KERNEL); + if (!gate) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = &zynqmp_clk_gate_ops; + init.flags = nodes->flag; + init.parent_names = parents; + init.num_parents = 1; + + /* struct clk_gate assignments */ + gate->flags = nodes->type_flag; + gate->hw.init = &init; + gate->clk_id = clk_id; + + hw = &gate->hw; + ret = clk_hw_register(NULL, hw); + if (ret) { + kfree(gate); + hw = ERR_PTR(ret); + } + + return hw; +} diff --git a/drivers/clk/zynqmp/clk-mux-zynqmp.c b/drivers/clk/zynqmp/clk-mux-zynqmp.c new file mode 100644 index 000000000000..4143f560c28d --- /dev/null +++ b/drivers/clk/zynqmp/clk-mux-zynqmp.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Zynq UltraScale+ MPSoC mux + * + * Copyright (C) 2016-2018 Xilinx + */ + +#include +#include +#include "clk-zynqmp.h" + +/* + * DOC: basic adjustable multiplexer clock that cannot gate + * + * Traits of this clock: + * prepare - clk_prepare only ensures that parents are prepared + * enable - clk_enable only ensures that parents are enabled + * rate - rate is only affected by parent switching. No clk_set_rate support + * parent - parent is adjustable through clk_set_parent + */ + +/** + * struct zynqmp_clk_mux - multiplexer clock + * + * @hw: handle between common and hardware-specific interfaces + * @flags: hardware-specific flags + * @clk_id: Id of clock + */ +struct zynqmp_clk_mux { + struct clk_hw hw; + u8 flags; + u32 clk_id; +}; + +#define to_zynqmp_clk_mux(_hw) container_of(_hw, struct zynqmp_clk_mux, hw) + +/** + * zynqmp_clk_mux_get_parent() - Get parent of clock + * @hw: handle between common and hardware-specific interfaces + * + * Return: Parent index + */ +static u8 zynqmp_clk_mux_get_parent(struct clk_hw *hw) +{ + struct zynqmp_clk_mux *mux = to_zynqmp_clk_mux(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = mux->clk_id; + u32 val; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_getparent(clk_id, &val); + + if (ret) + pr_warn_once("%s() getparent failed for clock: %s, ret = %d\n", + __func__, clk_name, ret); + + return val; +} + +/** + * zynqmp_clk_mux_set_parent() - Set parent of clock + * @hw: handle between common and hardware-specific interfaces + * @index: Parent index + * + * Return: 0 on success else error+reason + */ +static int zynqmp_clk_mux_set_parent(struct clk_hw *hw, u8 index) +{ + struct zynqmp_clk_mux *mux = to_zynqmp_clk_mux(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = mux->clk_id; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_setparent(clk_id, index); + + if (ret) + pr_warn_once("%s() set parent failed for clock: %s, ret = %d\n", + __func__, clk_name, ret); + + return ret; +} + +static const struct clk_ops zynqmp_clk_mux_ops = { + .get_parent = zynqmp_clk_mux_get_parent, + .set_parent = zynqmp_clk_mux_set_parent, + .determine_rate = __clk_mux_determine_rate, +}; + +static const struct clk_ops zynqmp_clk_mux_ro_ops = { + .get_parent = zynqmp_clk_mux_get_parent, +}; + +/** + * zynqmp_clk_register_mux() - Register a mux table with the clock + * framework + * @name: Name of this clock + * @clk_id: Id of this clock + * @parents: Name of this clock's parents + * @num_parents: Number of parents + * @nodes: Clock topology node + * + * Return: clock hardware of the registered clock mux + */ +struct clk_hw *zynqmp_clk_register_mux(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) +{ + struct zynqmp_clk_mux *mux; + struct clk_hw *hw; + struct clk_init_data init; + int ret; + + mux = kzalloc(sizeof(*mux), GFP_KERNEL); + if (!mux) + return ERR_PTR(-ENOMEM); + + init.name = name; + if (nodes->type_flag & CLK_MUX_READ_ONLY) + init.ops = &zynqmp_clk_mux_ro_ops; + else + init.ops = &zynqmp_clk_mux_ops; + init.flags = nodes->flag; + init.parent_names = parents; + init.num_parents = num_parents; + mux->flags = nodes->type_flag; + mux->hw.init = &init; + mux->clk_id = clk_id; + + hw = &mux->hw; + ret = clk_hw_register(NULL, hw); + if (ret) { + kfree(hw); + hw = ERR_PTR(ret); + } + + return hw; +} +EXPORT_SYMBOL_GPL(zynqmp_clk_register_mux); diff --git a/drivers/clk/zynqmp/clk-zynqmp.h b/drivers/clk/zynqmp/clk-zynqmp.h new file mode 100644 index 000000000000..7ab163b67249 --- /dev/null +++ b/drivers/clk/zynqmp/clk-zynqmp.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2016-2018 Xilinx + */ + +#ifndef __LINUX_CLK_ZYNQMP_H_ +#define __LINUX_CLK_ZYNQMP_H_ + +#include + +#include + +/* Clock APIs payload parameters */ +#define CLK_GET_NAME_RESP_LEN 16 +#define CLK_GET_TOPOLOGY_RESP_WORDS 3 +#define CLK_GET_PARENTS_RESP_WORDS 3 +#define CLK_GET_ATTR_RESP_WORDS 1 + +enum topology_type { + TYPE_INVALID, + TYPE_MUX, + TYPE_PLL, + TYPE_FIXEDFACTOR, + TYPE_DIV1, + TYPE_DIV2, + TYPE_GATE, +}; + +/** + * struct clock_topology - Clock topology + * @type: Type of topology + * @flag: Topology flags + * @type_flag: Topology type specific flag + */ +struct clock_topology { + u32 type; + u32 flag; + u32 type_flag; +}; + +struct clk_hw *zynqmp_clk_register_pll(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes); + +struct clk_hw *zynqmp_clk_register_gate(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes); + +struct clk_hw *zynqmp_clk_register_divider(const char *name, + u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes); + +struct clk_hw *zynqmp_clk_register_mux(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes); + +struct clk_hw *zynqmp_clk_register_fixed_factor(const char *name, + u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes); + +#endif diff --git a/drivers/clk/zynqmp/clkc.c b/drivers/clk/zynqmp/clkc.c new file mode 100644 index 000000000000..9d7d297f0ea8 --- /dev/null +++ b/drivers/clk/zynqmp/clkc.c @@ -0,0 +1,716 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Zynq UltraScale+ MPSoC clock controller + * + * Copyright (C) 2016-2018 Xilinx + * + * Based on drivers/clk/zynq/clkc.c + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "clk-zynqmp.h" + +#define MAX_PARENT 100 +#define MAX_NODES 6 +#define MAX_NAME_LEN 50 + +#define CLK_TYPE_SHIFT 2 + +#define PM_API_PAYLOAD_LEN 3 + +#define NA_PARENT 0xFFFFFFFF +#define DUMMY_PARENT 0xFFFFFFFE + +#define CLK_TYPE_FIELD_LEN 4 +#define CLK_TOPOLOGY_NODE_OFFSET 16 +#define NODES_PER_RESP 3 + +#define CLK_TYPE_FIELD_MASK 0xF +#define CLK_FLAG_FIELD_MASK GENMASK(21, 8) +#define CLK_TYPE_FLAG_FIELD_MASK GENMASK(31, 24) + +#define CLK_PARENTS_ID_LEN 16 +#define CLK_PARENTS_ID_MASK 0xFFFF + +/* Flags for parents */ +#define PARENT_CLK_SELF 0 +#define PARENT_CLK_NODE1 1 +#define PARENT_CLK_NODE2 2 +#define PARENT_CLK_NODE3 3 +#define PARENT_CLK_NODE4 4 +#define PARENT_CLK_EXTERNAL 5 + +#define END_OF_CLK_NAME "END_OF_CLK" +#define END_OF_TOPOLOGY_NODE 1 +#define END_OF_PARENTS 1 +#define RESERVED_CLK_NAME "" + +#define CLK_VALID_MASK 0x1 + +enum clk_type { + CLK_TYPE_OUTPUT, + CLK_TYPE_EXTERNAL, +}; + +/** + * struct clock_parent - Clock parent + * @name: Parent name + * @id: Parent clock ID + * @flag: Parent flags + */ +struct clock_parent { + char name[MAX_NAME_LEN]; + int id; + u32 flag; +}; + +/** + * struct zynqmp_clock - Clock + * @clk_name: Clock name + * @valid: Validity flag of clock + * @type: Clock type (Output/External) + * @node: Clock topology nodes + * @num_nodes: Number of nodes present in topology + * @parent: Parent of clock + * @num_parents: Number of parents of clock + */ +struct zynqmp_clock { + char clk_name[MAX_NAME_LEN]; + u32 valid; + enum clk_type type; + struct clock_topology node[MAX_NODES]; + u32 num_nodes; + struct clock_parent parent[MAX_PARENT]; + u32 num_parents; +}; + +static const char clk_type_postfix[][10] = { + [TYPE_INVALID] = "", + [TYPE_MUX] = "_mux", + [TYPE_GATE] = "", + [TYPE_DIV1] = "_div1", + [TYPE_DIV2] = "_div2", + [TYPE_FIXEDFACTOR] = "_ff", + [TYPE_PLL] = "" +}; + +static struct clk_hw *(* const clk_topology[]) (const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) + = { + [TYPE_INVALID] = NULL, + [TYPE_MUX] = zynqmp_clk_register_mux, + [TYPE_PLL] = zynqmp_clk_register_pll, + [TYPE_FIXEDFACTOR] = zynqmp_clk_register_fixed_factor, + [TYPE_DIV1] = zynqmp_clk_register_divider, + [TYPE_DIV2] = zynqmp_clk_register_divider, + [TYPE_GATE] = zynqmp_clk_register_gate +}; + +static struct zynqmp_clock *clock; +static struct clk_hw_onecell_data *zynqmp_data; +static unsigned int clock_max_idx; +static const struct zynqmp_eemi_ops *eemi_ops; + +/** + * zynqmp_is_valid_clock() - Check whether clock is valid or not + * @clk_id: Clock index + * + * Return: 1 if clock is valid, 0 if clock is invalid else error code + */ +static inline int zynqmp_is_valid_clock(u32 clk_id) +{ + if (clk_id > clock_max_idx) + return -ENODEV; + + return clock[clk_id].valid; +} + +/** + * zynqmp_get_clock_name() - Get name of clock from Clock index + * @clk_id: Clock index + * @clk_name: Name of clock + * + * Return: 0 on success else error code + */ +static int zynqmp_get_clock_name(u32 clk_id, char *clk_name) +{ + int ret; + + ret = zynqmp_is_valid_clock(clk_id); + if (ret == 1) { + strncpy(clk_name, clock[clk_id].clk_name, MAX_NAME_LEN); + return 0; + } + + return ret == 0 ? -EINVAL : ret; +} + +/** + * zynqmp_get_clock_type() - Get type of clock + * @clk_id: Clock index + * @type: Clock type: CLK_TYPE_OUTPUT or CLK_TYPE_EXTERNAL + * + * Return: 0 on success else error code + */ +static int zynqmp_get_clock_type(u32 clk_id, u32 *type) +{ + int ret; + + ret = zynqmp_is_valid_clock(clk_id); + if (ret == 1) { + *type = clock[clk_id].type; + return 0; + } + + return ret == 0 ? -EINVAL : ret; +} + +/** + * zynqmp_pm_clock_get_num_clocks() - Get number of clocks in system + * @nclocks: Number of clocks in system/board. + * + * Call firmware API to get number of clocks. + * + * Return: 0 on success else error code. + */ +static int zynqmp_pm_clock_get_num_clocks(u32 *nclocks) +{ + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + qdata.qid = PM_QID_CLOCK_GET_NUM_CLOCKS; + + ret = eemi_ops->query_data(qdata, ret_payload); + *nclocks = ret_payload[1]; + + return ret; +} + +/** + * zynqmp_pm_clock_get_name() - Get the name of clock for given id + * @clock_id: ID of the clock to be queried + * @name: Name of given clock + * + * This function is used to get name of clock specified by given + * clock ID. + * + * Return: Returns 0, in case of error name would be 0 + */ +static int zynqmp_pm_clock_get_name(u32 clock_id, char *name) +{ + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + + qdata.qid = PM_QID_CLOCK_GET_NAME; + qdata.arg1 = clock_id; + + eemi_ops->query_data(qdata, ret_payload); + memcpy(name, ret_payload, CLK_GET_NAME_RESP_LEN); + + return 0; +} + +/** + * zynqmp_pm_clock_get_topology() - Get the topology of clock for given id + * @clock_id: ID of the clock to be queried + * @index: Node index of clock topology + * @topology: Buffer to store nodes in topology and flags + * + * This function is used to get topology information for the clock + * specified by given clock ID. + * + * This API will return 3 node of topology with a single response. To get + * other nodes, master should call same API in loop with new + * index till error is returned. E.g First call should have + * index 0 which will return nodes 0,1 and 2. Next call, index + * should be 3 which will return nodes 3,4 and 5 and so on. + * + * Return: 0 on success else error+reason + */ +static int zynqmp_pm_clock_get_topology(u32 clock_id, u32 index, u32 *topology) +{ + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + qdata.qid = PM_QID_CLOCK_GET_TOPOLOGY; + qdata.arg1 = clock_id; + qdata.arg2 = index; + + ret = eemi_ops->query_data(qdata, ret_payload); + memcpy(topology, &ret_payload[1], CLK_GET_TOPOLOGY_RESP_WORDS * 4); + + return ret; +} + +/** + * zynqmp_clk_register_fixed_factor() - Register fixed factor with the + * clock framework + * @name: Name of this clock + * @clk_id: Clock ID + * @parents: Name of this clock's parents + * @num_parents: Number of parents + * @nodes: Clock topology node + * + * Return: clock hardware to the registered clock + */ +struct clk_hw *zynqmp_clk_register_fixed_factor(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) +{ + u32 mult, div; + struct clk_hw *hw; + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + qdata.qid = PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS; + qdata.arg1 = clk_id; + + ret = eemi_ops->query_data(qdata, ret_payload); + mult = ret_payload[1]; + div = ret_payload[2]; + + hw = clk_hw_register_fixed_factor(NULL, name, + parents[0], + nodes->flag, mult, + div); + + return hw; +} + +/** + * zynqmp_pm_clock_get_parents() - Get the first 3 parents of clock for given id + * @clock_id: Clock ID + * @index: Parent index + * @parents: 3 parents of the given clock + * + * This function is used to get 3 parents for the clock specified by + * given clock ID. + * + * This API will return 3 parents with a single response. To get + * other parents, master should call same API in loop with new + * parent index till error is returned. E.g First call should have + * index 0 which will return parents 0,1 and 2. Next call, index + * should be 3 which will return parent 3,4 and 5 and so on. + * + * Return: 0 on success else error+reason + */ +static int zynqmp_pm_clock_get_parents(u32 clock_id, u32 index, u32 *parents) +{ + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + qdata.qid = PM_QID_CLOCK_GET_PARENTS; + qdata.arg1 = clock_id; + qdata.arg2 = index; + + ret = eemi_ops->query_data(qdata, ret_payload); + memcpy(parents, &ret_payload[1], CLK_GET_PARENTS_RESP_WORDS * 4); + + return ret; +} + +/** + * zynqmp_pm_clock_get_attributes() - Get the attributes of clock for given id + * @clock_id: Clock ID + * @attr: Clock attributes + * + * This function is used to get clock's attributes(e.g. valid, clock type, etc). + * + * Return: 0 on success else error+reason + */ +static int zynqmp_pm_clock_get_attributes(u32 clock_id, u32 *attr) +{ + struct zynqmp_pm_query_data qdata = {0}; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + + qdata.qid = PM_QID_CLOCK_GET_ATTRIBUTES; + qdata.arg1 = clock_id; + + ret = eemi_ops->query_data(qdata, ret_payload); + memcpy(attr, &ret_payload[1], CLK_GET_ATTR_RESP_WORDS * 4); + + return ret; +} + +/** + * __zynqmp_clock_get_topology() - Get topology data of clock from firmware + * response data + * @topology: Clock topology + * @data: Clock topology data received from firmware + * @nnodes: Number of nodes + * + * Return: 0 on success else error+reason + */ +static int __zynqmp_clock_get_topology(struct clock_topology *topology, + u32 *data, u32 *nnodes) +{ + int i; + + for (i = 0; i < PM_API_PAYLOAD_LEN; i++) { + if (!(data[i] & CLK_TYPE_FIELD_MASK)) + return END_OF_TOPOLOGY_NODE; + topology[*nnodes].type = data[i] & CLK_TYPE_FIELD_MASK; + topology[*nnodes].flag = FIELD_GET(CLK_FLAG_FIELD_MASK, + data[i]); + topology[*nnodes].type_flag = + FIELD_GET(CLK_TYPE_FLAG_FIELD_MASK, data[i]); + (*nnodes)++; + } + + return 0; +} + +/** + * zynqmp_clock_get_topology() - Get topology of clock from firmware using + * PM_API + * @clk_id: Clock index + * @topology: Clock topology + * @num_nodes: Number of nodes + * + * Return: 0 on success else error+reason + */ +static int zynqmp_clock_get_topology(u32 clk_id, + struct clock_topology *topology, + u32 *num_nodes) +{ + int j, ret; + u32 pm_resp[PM_API_PAYLOAD_LEN] = {0}; + + *num_nodes = 0; + for (j = 0; j <= MAX_NODES; j += 3) { + ret = zynqmp_pm_clock_get_topology(clk_id, j, pm_resp); + if (ret) + return ret; + ret = __zynqmp_clock_get_topology(topology, pm_resp, num_nodes); + if (ret == END_OF_TOPOLOGY_NODE) + return 0; + } + + return 0; +} + +/** + * __zynqmp_clock_get_topology() - Get parents info of clock from firmware + * response data + * @parents: Clock parents + * @data: Clock parents data received from firmware + * @nparent: Number of parent + * + * Return: 0 on success else error+reason + */ +static int __zynqmp_clock_get_parents(struct clock_parent *parents, u32 *data, + u32 *nparent) +{ + int i; + struct clock_parent *parent; + + for (i = 0; i < PM_API_PAYLOAD_LEN; i++) { + if (data[i] == NA_PARENT) + return END_OF_PARENTS; + + parent = &parents[i]; + parent->id = data[i] & CLK_PARENTS_ID_MASK; + if (data[i] == DUMMY_PARENT) { + strcpy(parent->name, "dummy_name"); + parent->flag = 0; + } else { + parent->flag = data[i] >> CLK_PARENTS_ID_LEN; + if (zynqmp_get_clock_name(parent->id, parent->name)) + continue; + } + *nparent += 1; + } + + return 0; +} + +/** + * zynqmp_clock_get_parents() - Get parents info from firmware using PM_API + * @clk_id: Clock index + * @parents: Clock parents + * @num_parents: Total number of parents + * + * Return: 0 on success else error+reason + */ +static int zynqmp_clock_get_parents(u32 clk_id, struct clock_parent *parents, + u32 *num_parents) +{ + int j = 0, ret; + u32 pm_resp[PM_API_PAYLOAD_LEN] = {0}; + + *num_parents = 0; + do { + /* Get parents from firmware */ + ret = zynqmp_pm_clock_get_parents(clk_id, j, pm_resp); + if (ret) + return ret; + + ret = __zynqmp_clock_get_parents(&parents[j], pm_resp, + num_parents); + if (ret == END_OF_PARENTS) + return 0; + j += PM_API_PAYLOAD_LEN; + } while (*num_parents <= MAX_PARENT); + + return 0; +} + +/** + * zynqmp_get_parent_list() - Create list of parents name + * @np: Device node + * @clk_id: Clock index + * @parent_list: List of parent's name + * @num_parents: Total number of parents + * + * Return: 0 on success else error+reason + */ +static int zynqmp_get_parent_list(struct device_node *np, u32 clk_id, + const char **parent_list, u32 *num_parents) +{ + int i = 0, ret; + u32 total_parents = clock[clk_id].num_parents; + struct clock_topology *clk_nodes; + struct clock_parent *parents; + + clk_nodes = clock[clk_id].node; + parents = clock[clk_id].parent; + + for (i = 0; i < total_parents; i++) { + if (!parents[i].flag) { + parent_list[i] = parents[i].name; + } else if (parents[i].flag == PARENT_CLK_EXTERNAL) { + ret = of_property_match_string(np, "clock-names", + parents[i].name); + if (ret < 0) + strcpy(parents[i].name, "dummy_name"); + parent_list[i] = parents[i].name; + } else { + strcat(parents[i].name, + clk_type_postfix[clk_nodes[parents[i].flag - 1]. + type]); + parent_list[i] = parents[i].name; + } + } + + *num_parents = total_parents; + return 0; +} + +/** + * zynqmp_register_clk_topology() - Register clock topology + * @clk_id: Clock index + * @clk_name: Clock Name + * @num_parents: Total number of parents + * @parent_names: List of parents name + * + * Return: Returns either clock hardware or error+reason + */ +static struct clk_hw *zynqmp_register_clk_topology(int clk_id, char *clk_name, + int num_parents, + const char **parent_names) +{ + int j; + u32 num_nodes; + char *clk_out = NULL; + struct clock_topology *nodes; + struct clk_hw *hw = NULL; + + nodes = clock[clk_id].node; + num_nodes = clock[clk_id].num_nodes; + + for (j = 0; j < num_nodes; j++) { + /* + * Clock name received from firmware is output clock name. + * Intermediate clock names are postfixed with type of clock. + */ + if (j != (num_nodes - 1)) { + clk_out = kasprintf(GFP_KERNEL, "%s%s", clk_name, + clk_type_postfix[nodes[j].type]); + } else { + clk_out = kasprintf(GFP_KERNEL, "%s", clk_name); + } + + if (!clk_topology[nodes[j].type]) + continue; + + hw = (*clk_topology[nodes[j].type])(clk_out, clk_id, + parent_names, + num_parents, + &nodes[j]); + if (IS_ERR(hw)) + pr_warn_once("%s() %s register fail with %ld\n", + __func__, clk_name, PTR_ERR(hw)); + + parent_names[0] = clk_out; + } + kfree(clk_out); + return hw; +} + +/** + * zynqmp_register_clocks() - Register clocks + * @np: Device node + * + * Return: 0 on success else error code + */ +static int zynqmp_register_clocks(struct device_node *np) +{ + int ret; + u32 i, total_parents = 0, type = 0; + const char *parent_names[MAX_PARENT]; + + for (i = 0; i < clock_max_idx; i++) { + char clk_name[MAX_NAME_LEN]; + + /* get clock name, continue to next clock if name not found */ + if (zynqmp_get_clock_name(i, clk_name)) + continue; + + /* Check if clock is valid and output clock. + * Do not register invalid or external clock. + */ + ret = zynqmp_get_clock_type(i, &type); + if (ret || type != CLK_TYPE_OUTPUT) + continue; + + /* Get parents of clock*/ + if (zynqmp_get_parent_list(np, i, parent_names, + &total_parents)) { + WARN_ONCE(1, "No parents found for %s\n", + clock[i].clk_name); + continue; + } + + zynqmp_data->hws[i] = + zynqmp_register_clk_topology(i, clk_name, + total_parents, + parent_names); + } + + for (i = 0; i < clock_max_idx; i++) { + if (IS_ERR(zynqmp_data->hws[i])) { + pr_err("Zynq Ultrascale+ MPSoC clk %s: register failed with %ld\n", + clock[i].clk_name, PTR_ERR(zynqmp_data->hws[i])); + WARN_ON(1); + } + } + return 0; +} + +/** + * zynqmp_get_clock_info() - Get clock information from firmware using PM_API + */ +static void zynqmp_get_clock_info(void) +{ + int i, ret; + u32 attr, type = 0; + + for (i = 0; i < clock_max_idx; i++) { + zynqmp_pm_clock_get_name(i, clock[i].clk_name); + if (!strcmp(clock[i].clk_name, RESERVED_CLK_NAME)) + continue; + + ret = zynqmp_pm_clock_get_attributes(i, &attr); + if (ret) + continue; + + clock[i].valid = attr & CLK_VALID_MASK; + clock[i].type = attr >> CLK_TYPE_SHIFT ? CLK_TYPE_EXTERNAL : + CLK_TYPE_OUTPUT; + } + + /* Get topology of all clock */ + for (i = 0; i < clock_max_idx; i++) { + ret = zynqmp_get_clock_type(i, &type); + if (ret || type != CLK_TYPE_OUTPUT) + continue; + + ret = zynqmp_clock_get_topology(i, clock[i].node, + &clock[i].num_nodes); + if (ret) + continue; + + ret = zynqmp_clock_get_parents(i, clock[i].parent, + &clock[i].num_parents); + if (ret) + continue; + } +} + +/** + * zynqmp_clk_setup() - Setup the clock framework and register clocks + * @np: Device node + * + * Return: 0 on success else error code + */ +static int zynqmp_clk_setup(struct device_node *np) +{ + int ret; + + ret = zynqmp_pm_clock_get_num_clocks(&clock_max_idx); + if (ret) + return ret; + + zynqmp_data = kzalloc(sizeof(*zynqmp_data) + sizeof(*zynqmp_data) * + clock_max_idx, GFP_KERNEL); + if (!zynqmp_data) + return -ENOMEM; + + clock = kcalloc(clock_max_idx, sizeof(*clock), GFP_KERNEL); + if (!clock) { + kfree(zynqmp_data); + return -ENOMEM; + } + + zynqmp_get_clock_info(); + zynqmp_register_clocks(np); + + zynqmp_data->num = clock_max_idx; + of_clk_add_hw_provider(np, of_clk_hw_onecell_get, zynqmp_data); + + return 0; +} + +static int zynqmp_clock_probe(struct platform_device *pdev) +{ + int ret; + struct device *dev = &pdev->dev; + + eemi_ops = zynqmp_pm_get_eemi_ops(); + if (!eemi_ops) + return -ENXIO; + + ret = zynqmp_clk_setup(dev->of_node); + + return ret; +} + +static const struct of_device_id zynqmp_clock_of_match[] = { + {.compatible = "xlnx,zynqmp-clk"}, + {}, +}; +MODULE_DEVICE_TABLE(of, zynqmp_clock_of_match); + +static struct platform_driver zynqmp_clock_driver = { + .driver = { + .name = "zynqmp_clock", + .of_match_table = zynqmp_clock_of_match, + }, + .probe = zynqmp_clock_probe, +}; +module_platform_driver(zynqmp_clock_driver); diff --git a/drivers/clk/zynqmp/divider.c b/drivers/clk/zynqmp/divider.c new file mode 100644 index 000000000000..a371c66e72ef --- /dev/null +++ b/drivers/clk/zynqmp/divider.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Zynq UltraScale+ MPSoC Divider support + * + * Copyright (C) 2016-2018 Xilinx + * + * Adjustable divider clock implementation + */ + +#include +#include +#include +#include "clk-zynqmp.h" + +/* + * DOC: basic adjustable divider clock that cannot gate + * + * Traits of this clock: + * prepare - clk_prepare only ensures that parents are prepared + * enable - clk_enable only ensures that parents are enabled + * rate - rate is adjustable. clk->rate = ceiling(parent->rate / divisor) + * parent - fixed parent. No clk_set_parent support + */ + +#define to_zynqmp_clk_divider(_hw) \ + container_of(_hw, struct zynqmp_clk_divider, hw) + +#define CLK_FRAC BIT(13) /* has a fractional parent */ + +/** + * struct zynqmp_clk_divider - adjustable divider clock + * @hw: handle between common and hardware-specific interfaces + * @flags: Hardware specific flags + * @clk_id: Id of clock + * @div_type: divisor type (TYPE_DIV1 or TYPE_DIV2) + */ +struct zynqmp_clk_divider { + struct clk_hw hw; + u8 flags; + u32 clk_id; + u32 div_type; +}; + +static inline int zynqmp_divider_get_val(unsigned long parent_rate, + unsigned long rate) +{ + return DIV_ROUND_CLOSEST(parent_rate, rate); +} + +/** + * zynqmp_clk_divider_recalc_rate() - Recalc rate of divider clock + * @hw: handle between common and hardware-specific interfaces + * @parent_rate: rate of parent clock + * + * Return: 0 on success else error+reason + */ +static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct zynqmp_clk_divider *divider = to_zynqmp_clk_divider(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = divider->clk_id; + u32 div_type = divider->div_type; + u32 div, value; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_getdivider(clk_id, &div); + + if (ret) + pr_warn_once("%s() get divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + + if (div_type == TYPE_DIV1) + value = div & 0xFFFF; + else + value = div >> 16; + + return DIV_ROUND_UP_ULL(parent_rate, value); +} + +/** + * zynqmp_clk_divider_round_rate() - Round rate of divider clock + * @hw: handle between common and hardware-specific interfaces + * @rate: rate of clock to be set + * @prate: rate of parent clock + * + * Return: 0 on success else error+reason + */ +static long zynqmp_clk_divider_round_rate(struct clk_hw *hw, + unsigned long rate, + unsigned long *prate) +{ + struct zynqmp_clk_divider *divider = to_zynqmp_clk_divider(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = divider->clk_id; + u32 div_type = divider->div_type; + u32 bestdiv; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + /* if read only, just return current value */ + if (divider->flags & CLK_DIVIDER_READ_ONLY) { + ret = eemi_ops->clock_getdivider(clk_id, &bestdiv); + + if (ret) + pr_warn_once("%s() get divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + if (div_type == TYPE_DIV1) + bestdiv = bestdiv & 0xFFFF; + else + bestdiv = bestdiv >> 16; + + return DIV_ROUND_UP_ULL((u64)*prate, bestdiv); + } + + bestdiv = zynqmp_divider_get_val(*prate, rate); + + if ((clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && + (divider->flags & CLK_FRAC)) + bestdiv = rate % *prate ? 1 : bestdiv; + *prate = rate * bestdiv; + + return rate; +} + +/** + * zynqmp_clk_divider_set_rate() - Set rate of divider clock + * @hw: handle between common and hardware-specific interfaces + * @rate: rate of clock to be set + * @parent_rate: rate of parent clock + * + * Return: 0 on success else error+reason + */ +static int zynqmp_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct zynqmp_clk_divider *divider = to_zynqmp_clk_divider(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = divider->clk_id; + u32 div_type = divider->div_type; + u32 value, div; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + value = zynqmp_divider_get_val(parent_rate, rate); + if (div_type == TYPE_DIV1) { + div = value & 0xFFFF; + div |= 0xffff << 16; + } else { + div = 0xffff; + div |= value << 16; + } + + ret = eemi_ops->clock_setdivider(clk_id, div); + + if (ret) + pr_warn_once("%s() set divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + + return ret; +} + +static const struct clk_ops zynqmp_clk_divider_ops = { + .recalc_rate = zynqmp_clk_divider_recalc_rate, + .round_rate = zynqmp_clk_divider_round_rate, + .set_rate = zynqmp_clk_divider_set_rate, +}; + +/** + * zynqmp_clk_register_divider() - Register a divider clock + * @name: Name of this clock + * @clk_id: Id of clock + * @parents: Name of this clock's parents + * @num_parents: Number of parents + * @nodes: Clock topology node + * + * Return: clock hardware to registered clock divider + */ +struct clk_hw *zynqmp_clk_register_divider(const char *name, + u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) +{ + struct zynqmp_clk_divider *div; + struct clk_hw *hw; + struct clk_init_data init; + int ret; + + /* allocate the divider */ + div = kzalloc(sizeof(*div), GFP_KERNEL); + if (!div) + return ERR_PTR(-ENOMEM); + + init.name = name; + init.ops = &zynqmp_clk_divider_ops; + init.flags = nodes->flag; + init.parent_names = parents; + init.num_parents = 1; + + /* struct clk_divider assignments */ + div->flags = nodes->type_flag; + div->hw.init = &init; + div->clk_id = clk_id; + div->div_type = nodes->type; + + hw = &div->hw; + ret = clk_hw_register(NULL, hw); + if (ret) { + kfree(div); + hw = ERR_PTR(ret); + } + + return hw; +} +EXPORT_SYMBOL_GPL(zynqmp_clk_register_divider); diff --git a/drivers/clk/zynqmp/pll.c b/drivers/clk/zynqmp/pll.c new file mode 100644 index 000000000000..a541397a172c --- /dev/null +++ b/drivers/clk/zynqmp/pll.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Zynq UltraScale+ MPSoC PLL driver + * + * Copyright (C) 2016-2018 Xilinx + */ + +#include +#include +#include +#include "clk-zynqmp.h" + +/** + * struct zynqmp_pll - PLL clock + * @hw: Handle between common and hardware-specific interfaces + * @clk_id: PLL clock ID + */ +struct zynqmp_pll { + struct clk_hw hw; + u32 clk_id; +}; + +#define to_zynqmp_pll(_hw) container_of(_hw, struct zynqmp_pll, hw) + +#define PLL_FBDIV_MIN 25 +#define PLL_FBDIV_MAX 125 + +#define PS_PLL_VCO_MIN 1500000000 +#define PS_PLL_VCO_MAX 3000000000UL + +enum pll_mode { + PLL_MODE_INT, + PLL_MODE_FRAC, +}; + +#define FRAC_OFFSET 0x8 +#define PLLFCFG_FRAC_EN BIT(31) +#define FRAC_DIV BIT(16) /* 2^16 */ + +/** + * zynqmp_pll_get_mode() - Get mode of PLL + * @hw: Handle between common and hardware-specific interfaces + * + * Return: Mode of PLL + */ +static inline enum pll_mode zynqmp_pll_get_mode(struct clk_hw *hw) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + u32 clk_id = clk->clk_id; + const char *clk_name = clk_hw_get_name(hw); + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->ioctl(0, IOCTL_GET_PLL_FRAC_MODE, clk_id, 0, + ret_payload); + if (ret) + pr_warn_once("%s() PLL get frac mode failed for %s, ret = %d\n", + __func__, clk_name, ret); + + return ret_payload[1]; +} + +/** + * zynqmp_pll_set_mode() - Set the PLL mode + * @hw: Handle between common and hardware-specific interfaces + * @on: Flag to determine the mode + */ +static inline void zynqmp_pll_set_mode(struct clk_hw *hw, bool on) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + u32 clk_id = clk->clk_id; + const char *clk_name = clk_hw_get_name(hw); + int ret; + u32 mode; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + if (on) + mode = PLL_MODE_FRAC; + else + mode = PLL_MODE_INT; + + ret = eemi_ops->ioctl(0, IOCTL_SET_PLL_FRAC_MODE, clk_id, mode, NULL); + if (ret) + pr_warn_once("%s() PLL set frac mode failed for %s, ret = %d\n", + __func__, clk_name, ret); +} + +/** + * zynqmp_pll_round_rate() - Round a clock frequency + * @hw: Handle between common and hardware-specific interfaces + * @rate: Desired clock frequency + * @prate: Clock frequency of parent clock + * + * Return: Frequency closest to @rate the hardware can generate + */ +static long zynqmp_pll_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *prate) +{ + u32 fbdiv; + long rate_div, f; + + /* Enable the fractional mode if needed */ + rate_div = (rate * FRAC_DIV) / *prate; + f = rate_div % FRAC_DIV; + zynqmp_pll_set_mode(hw, !!f); + + if (zynqmp_pll_get_mode(hw) == PLL_MODE_FRAC) { + if (rate > PS_PLL_VCO_MAX) { + fbdiv = rate / PS_PLL_VCO_MAX; + rate = rate / (fbdiv + 1); + } + if (rate < PS_PLL_VCO_MIN) { + fbdiv = DIV_ROUND_UP(PS_PLL_VCO_MIN, rate); + rate = rate * fbdiv; + } + return rate; + } + + fbdiv = DIV_ROUND_CLOSEST(rate, *prate); + fbdiv = clamp_t(u32, fbdiv, PLL_FBDIV_MIN, PLL_FBDIV_MAX); + return *prate * fbdiv; +} + +/** + * zynqmp_pll_recalc_rate() - Recalculate clock frequency + * @hw: Handle between common and hardware-specific interfaces + * @parent_rate: Clock frequency of parent clock + * + * Return: Current clock frequency + */ +static unsigned long zynqmp_pll_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + u32 clk_id = clk->clk_id; + const char *clk_name = clk_hw_get_name(hw); + u32 fbdiv, data; + unsigned long rate, frac; + u32 ret_payload[PAYLOAD_ARG_CNT]; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_getdivider(clk_id, &fbdiv); + if (ret) + pr_warn_once("%s() get divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + + rate = parent_rate * fbdiv; + if (zynqmp_pll_get_mode(hw) == PLL_MODE_FRAC) { + eemi_ops->ioctl(0, IOCTL_GET_PLL_FRAC_DATA, clk_id, 0, + ret_payload); + data = ret_payload[1]; + frac = (parent_rate * data) / FRAC_DIV; + rate = rate + frac; + } + + return rate; +} + +/** + * zynqmp_pll_set_rate() - Set rate of PLL + * @hw: Handle between common and hardware-specific interfaces + * @rate: Frequency of clock to be set + * @parent_rate: Clock frequency of parent clock + * + * Set PLL divider to set desired rate. + * + * Returns: rate which is set on success else error code + */ +static int zynqmp_pll_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + u32 clk_id = clk->clk_id; + const char *clk_name = clk_hw_get_name(hw); + u32 fbdiv; + long rate_div, frac, m, f; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + if (zynqmp_pll_get_mode(hw) == PLL_MODE_FRAC) { + rate_div = (rate * FRAC_DIV) / parent_rate; + m = rate_div / FRAC_DIV; + f = rate_div % FRAC_DIV; + m = clamp_t(u32, m, (PLL_FBDIV_MIN), (PLL_FBDIV_MAX)); + rate = parent_rate * m; + frac = (parent_rate * f) / FRAC_DIV; + + ret = eemi_ops->clock_setdivider(clk_id, m); + if (ret) + pr_warn_once("%s() set divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + + eemi_ops->ioctl(0, IOCTL_SET_PLL_FRAC_DATA, clk_id, f, NULL); + + return rate + frac; + } + + fbdiv = DIV_ROUND_CLOSEST(rate, parent_rate); + fbdiv = clamp_t(u32, fbdiv, PLL_FBDIV_MIN, PLL_FBDIV_MAX); + ret = eemi_ops->clock_setdivider(clk_id, fbdiv); + if (ret) + pr_warn_once("%s() set divider failed for %s, ret = %d\n", + __func__, clk_name, ret); + + return parent_rate * fbdiv; +} + +/** + * zynqmp_pll_is_enabled() - Check if a clock is enabled + * @hw: Handle between common and hardware-specific interfaces + * + * Return: 1 if the clock is enabled, 0 otherwise + */ +static int zynqmp_pll_is_enabled(struct clk_hw *hw) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = clk->clk_id; + unsigned int state; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + ret = eemi_ops->clock_getstate(clk_id, &state); + if (ret) { + pr_warn_once("%s() clock get state failed for %s, ret = %d\n", + __func__, clk_name, ret); + return -EIO; + } + + return state ? 1 : 0; +} + +/** + * zynqmp_pll_enable() - Enable clock + * @hw: Handle between common and hardware-specific interfaces + * + * Return: 0 on success else error code + */ +static int zynqmp_pll_enable(struct clk_hw *hw) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = clk->clk_id; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + if (zynqmp_pll_is_enabled(hw)) + return 0; + + ret = eemi_ops->clock_enable(clk_id); + if (ret) + pr_warn_once("%s() clock enable failed for %s, ret = %d\n", + __func__, clk_name, ret); + + return ret; +} + +/** + * zynqmp_pll_disable() - Disable clock + * @hw: Handle between common and hardware-specific interfaces + */ +static void zynqmp_pll_disable(struct clk_hw *hw) +{ + struct zynqmp_pll *clk = to_zynqmp_pll(hw); + const char *clk_name = clk_hw_get_name(hw); + u32 clk_id = clk->clk_id; + int ret; + const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops(); + + if (!zynqmp_pll_is_enabled(hw)) + return; + + ret = eemi_ops->clock_disable(clk_id); + if (ret) + pr_warn_once("%s() clock disable failed for %s, ret = %d\n", + __func__, clk_name, ret); +} + +static const struct clk_ops zynqmp_pll_ops = { + .enable = zynqmp_pll_enable, + .disable = zynqmp_pll_disable, + .is_enabled = zynqmp_pll_is_enabled, + .round_rate = zynqmp_pll_round_rate, + .recalc_rate = zynqmp_pll_recalc_rate, + .set_rate = zynqmp_pll_set_rate, +}; + +/** + * zynqmp_clk_register_pll() - Register PLL with the clock framework + * @name: PLL name + * @clk_id: Clock ID + * @parents: Name of this clock's parents + * @num_parents: Number of parents + * @nodes: Clock topology node + * + * Return: clock hardware to the registered clock + */ +struct clk_hw *zynqmp_clk_register_pll(const char *name, u32 clk_id, + const char * const *parents, + u8 num_parents, + const struct clock_topology *nodes) +{ + struct zynqmp_pll *pll; + struct clk_hw *hw; + struct clk_init_data init; + int ret; + + init.name = name; + init.ops = &zynqmp_pll_ops; + init.flags = nodes->flag; + init.parent_names = parents; + init.num_parents = 1; + + pll = kzalloc(sizeof(*pll), GFP_KERNEL); + if (!pll) + return ERR_PTR(-ENOMEM); + + pll->hw.init = &init; + pll->clk_id = clk_id; + + hw = &pll->hw; + ret = clk_hw_register(NULL, hw); + if (ret) { + kfree(pll); + return ERR_PTR(ret); + } + + clk_hw_set_rate_range(hw, PS_PLL_VCO_MIN, PS_PLL_VCO_MAX); + if (ret < 0) + pr_err("%s:ERROR clk_set_rate_range failed %d\n", name, ret); + + return hw; +} diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 7a9db0861803..3c3c28eff56a 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,7 @@ enum pm_query_id { PM_QID_CLOCK_GET_FIXEDFACTOR_PARAMS, PM_QID_CLOCK_GET_PARENTS, PM_QID_CLOCK_GET_ATTRIBUTES, + PM_QID_CLOCK_GET_NUM_CLOCKS = 12, }; /** -- cgit v1.2.3-71-gd317 From f2e74abfaad446765ce0350aed1d9c5eed5b1b36 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:38 +0200 Subject: remoteproc: add release ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces a release ops in rproc_mem_entry structure to associate dedicated release mechanism to each memory entry descriptor in order to keep remoteproc core generic. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 23 +++++++++++++++++++++-- include/linux/remoteproc.h | 5 ++++- 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index ebadaad070a5..674f88d237b8 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -599,6 +599,24 @@ out: return ret; } +/** + * rproc_release_carveout() - release acquired carveout + * @rproc: rproc handle + * @mem: the memory entry to release + * + * This function releases specified memory entry @mem allocated via + * dma_alloc_coherent() function by @rproc. + */ +static int rproc_release_carveout(struct rproc *rproc, + struct rproc_mem_entry *mem) +{ + struct device *dev = &rproc->dev; + + /* clean up carveout allocations */ + dma_free_coherent(dev->parent, mem->len, mem->va, mem->dma); + return 0; +} + /** * rproc_handle_carveout() - handle phys contig memory allocation requests * @rproc: rproc handle @@ -733,6 +751,7 @@ static int rproc_handle_carveout(struct rproc *rproc, carveout->len = rsc->len; carveout->dma = dma; carveout->da = rsc->da; + carveout->release = rproc_release_carveout; list_add_tail(&carveout->node, &rproc->carveouts); @@ -920,8 +939,8 @@ static void rproc_resource_cleanup(struct rproc *rproc) /* clean up carveout allocations */ list_for_each_entry_safe(entry, tmp, &rproc->carveouts, node) { - dma_free_coherent(dev->parent, entry->len, entry->va, - entry->dma); + if (entry->release) + entry->release(rproc, entry); list_del(&entry->node); kfree(entry); } diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 75f9ca05b865..4116e92d4b3d 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -305,12 +305,15 @@ struct fw_rsc_vdev { struct fw_rsc_vdev_vring vring[0]; } __packed; +struct rproc; + /** * struct rproc_mem_entry - memory entry descriptor * @va: virtual address * @dma: dma address * @len: length, in bytes * @da: device address + * @release: release associated memory * @priv: associated data * @node: list node */ @@ -321,9 +324,9 @@ struct rproc_mem_entry { u32 da; void *priv; struct list_head node; + int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -struct rproc; struct firmware; /** -- cgit v1.2.3-71-gd317 From 3265230c5b05fe919291d09e266a8aedc85ebad0 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:39 +0200 Subject: remoteproc: add name in rproc_mem_entry struct Add name field in struct rproc_mem_entry. This new field will be used to match memory area requested in resource table with pre-registered carveout. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 1 + drivers/remoteproc/remoteproc_debugfs.c | 1 + include/linux/remoteproc.h | 2 ++ 3 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 674f88d237b8..a2d338fc8ddd 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -752,6 +752,7 @@ static int rproc_handle_carveout(struct rproc *rproc, carveout->dma = dma; carveout->da = rsc->da; carveout->release = rproc_release_carveout; + strlcpy(carveout->name, rsc->name, sizeof(carveout->name)); list_add_tail(&carveout->node, &rproc->carveouts); diff --git a/drivers/remoteproc/remoteproc_debugfs.c b/drivers/remoteproc/remoteproc_debugfs.c index a5c29f2764a3..e90135c64af0 100644 --- a/drivers/remoteproc/remoteproc_debugfs.c +++ b/drivers/remoteproc/remoteproc_debugfs.c @@ -260,6 +260,7 @@ static int rproc_carveouts_show(struct seq_file *seq, void *p) list_for_each_entry(carveout, &rproc->carveouts, node) { seq_puts(seq, "Carveout memory entry:\n"); + seq_printf(seq, "\tName: %s\n", carveout->name); seq_printf(seq, "\tVirtual address: %pK\n", carveout->va); seq_printf(seq, "\tDMA address: %pad\n", &carveout->dma); seq_printf(seq, "\tDevice address: 0x%x\n", carveout->da); diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 4116e92d4b3d..19908c930f47 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -315,6 +315,7 @@ struct rproc; * @da: device address * @release: release associated memory * @priv: associated data + * @name: associated memory region name (optional) * @node: list node */ struct rproc_mem_entry { @@ -323,6 +324,7 @@ struct rproc_mem_entry { int len; u32 da; void *priv; + char name[32]; struct list_head node; int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; -- cgit v1.2.3-71-gd317 From 72029c901a0244ca2e1eb09e1c453413a17f5787 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:40 +0200 Subject: remoteproc: add helper function to allocate and init rproc_mem_entry struct This patch introduces rproc_mem_entry_init helper function to simplify rproc_mem_entry structure allocation and filling by client. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 65 +++++++++++++++++++++++++++--------- include/linux/remoteproc.h | 6 ++++ 2 files changed, 55 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index a2d338fc8ddd..9decc598944d 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -639,7 +639,7 @@ static int rproc_handle_carveout(struct rproc *rproc, struct fw_rsc_carveout *rsc, int offset, int avail) { - struct rproc_mem_entry *carveout, *mapping; + struct rproc_mem_entry *carveout, *mapping = NULL; struct device *dev = &rproc->dev; dma_addr_t dma; void *va; @@ -659,16 +659,11 @@ static int rproc_handle_carveout(struct rproc *rproc, dev_dbg(dev, "carveout rsc: name: %s, da 0x%x, pa 0x%x, len 0x%x, flags 0x%x\n", rsc->name, rsc->da, rsc->pa, rsc->len, rsc->flags); - carveout = kzalloc(sizeof(*carveout), GFP_KERNEL); - if (!carveout) - return -ENOMEM; - va = dma_alloc_coherent(dev->parent, rsc->len, &dma, GFP_KERNEL); if (!va) { dev_err(dev->parent, "failed to allocate dma memory: len 0x%x\n", rsc->len); - ret = -ENOMEM; - goto free_carv; + return -ENOMEM; } dev_dbg(dev, "carveout va %pK, dma %pad, len 0x%x\n", @@ -747,27 +742,65 @@ static int rproc_handle_carveout(struct rproc *rproc, */ rsc->pa = (u32)rproc_va_to_pa(va); - carveout->va = va; - carveout->len = rsc->len; - carveout->dma = dma; - carveout->da = rsc->da; - carveout->release = rproc_release_carveout; - strlcpy(carveout->name, rsc->name, sizeof(carveout->name)); + carveout = rproc_mem_entry_init(dev, va, dma, rsc->len, rsc->da, + rproc_release_carveout, rsc->name); + if (!carveout) + goto free_carv; list_add_tail(&carveout->node, &rproc->carveouts); return 0; +free_carv: + kfree(carveout); free_mapping: kfree(mapping); dma_free: dma_free_coherent(dev->parent, rsc->len, va, dma); -free_carv: - kfree(carveout); return ret; } -/* +/** + * rproc_mem_entry_init() - allocate and initialize rproc_mem_entry struct + * @dev: pointer on device struct + * @va: virtual address + * @dma: dma address + * @len: memory carveout length + * @da: device address + * @release: memory carveout function + * @name: carveout name + * + * This function allocates a rproc_mem_entry struct and fill it with parameters + * provided by client. + */ +struct rproc_mem_entry * +rproc_mem_entry_init(struct device *dev, + void *va, dma_addr_t dma, int len, u32 da, + int (*release)(struct rproc *, struct rproc_mem_entry *), + const char *name, ...) +{ + struct rproc_mem_entry *mem; + va_list args; + + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return mem; + + mem->va = va; + mem->dma = dma; + mem->da = da; + mem->len = len; + mem->release = release; + + va_start(args, name); + vsnprintf(mem->name, sizeof(mem->name), name, args); + va_end(args); + + return mem; +} +EXPORT_SYMBOL(rproc_mem_entry_init); + +/** * A lookup table for resource handlers. The indices are defined in * enum fw_resource_type. */ diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 19908c930f47..9e2b84fa2efa 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,12 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +struct rproc_mem_entry * +rproc_mem_entry_init(struct device *dev, + void *va, dma_addr_t dma, int len, u32 da, + int (*release)(struct rproc *, struct rproc_mem_entry *), + const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3-71-gd317 From 15c0b0258e4f1c3c817f34d092d2cc6ff5178bdd Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:41 +0200 Subject: remoteproc: introduce rproc_add_carveout function This patch introduces a new API to allow platform driver to register platform specific carveout regions. Signed-off-by: Loic Pallardy Acked-by: Bjorn Andersson Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 16 +++++++++++++++- include/linux/remoteproc.h | 2 ++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 9decc598944d..db771e53f097 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -747,7 +747,7 @@ static int rproc_handle_carveout(struct rproc *rproc, if (!carveout) goto free_carv; - list_add_tail(&carveout->node, &rproc->carveouts); + rproc_add_carveout(rproc, carveout); return 0; @@ -760,6 +760,20 @@ dma_free: return ret; } +/** + * rproc_add_carveout() - register an allocated carveout region + * @rproc: rproc handle + * @mem: memory entry to register + * + * This function registers specified memory entry in @rproc carveouts list. + * Specified carveout should have been allocated before registering. + */ +void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem) +{ + list_add_tail(&mem->node, &rproc->carveouts); +} +EXPORT_SYMBOL(rproc_add_carveout); + /** * rproc_mem_entry_init() - allocate and initialize rproc_mem_entry struct * @dev: pointer on device struct diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 9e2b84fa2efa..8a350265d883 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -559,6 +559,8 @@ int rproc_add(struct rproc *rproc); int rproc_del(struct rproc *rproc); void rproc_free(struct rproc *rproc); +void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); + struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, -- cgit v1.2.3-71-gd317 From d7c51706d0956472b7c0530b1bf8fba32d82ee6b Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:43 +0200 Subject: remoteproc: add alloc ops in rproc_mem_entry struct Memory entry could be allocated in different ways (ioremap, dma_alloc_coherent, internal RAM allocator...). This patch introduces an alloc ops in rproc_mem_entry structure to associate dedicated allocation mechanism to each memory entry descriptor in order to do remote core agnostic from memory allocators. The introduction of this ops allows to perform allocation of all registered carveout at the same time, just before calling rproc_start(). It simplifies and makes uniform carveout management whatever origin. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 261 ++++++++++++++++++++++------------- include/linux/remoteproc.h | 7 + 2 files changed, 175 insertions(+), 93 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 800320d06cb8..9d17b3079506 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -642,74 +642,31 @@ out: } /** - * rproc_release_carveout() - release acquired carveout + * rproc_alloc_carveout() - allocated specified carveout * @rproc: rproc handle - * @mem: the memory entry to release - * - * This function releases specified memory entry @mem allocated via - * dma_alloc_coherent() function by @rproc. - */ -static int rproc_release_carveout(struct rproc *rproc, - struct rproc_mem_entry *mem) -{ - struct device *dev = &rproc->dev; - - /* clean up carveout allocations */ - dma_free_coherent(dev->parent, mem->len, mem->va, mem->dma); - return 0; -} - -/** - * rproc_handle_carveout() - handle phys contig memory allocation requests - * @rproc: rproc handle - * @rsc: the resource entry - * @avail: size of available data (for image validation) - * - * This function will handle firmware requests for allocation of physically - * contiguous memory regions. - * - * These request entries should come first in the firmware's resource table, - * as other firmware entries might request placing other data objects inside - * these memory regions (e.g. data/code segments, trace resource entries, ...). + * @mem: the memory entry to allocate * - * Allocating memory this way helps utilizing the reserved physical memory - * (e.g. CMA) more efficiently, and also minimizes the number of TLB entries - * needed to map it (in case @rproc is using an IOMMU). Reducing the TLB - * pressure is important; it may have a substantial impact on performance. + * This function allocate specified memory entry @mem using + * dma_alloc_coherent() as default allocator */ -static int rproc_handle_carveout(struct rproc *rproc, - struct fw_rsc_carveout *rsc, - int offset, int avail) +static int rproc_alloc_carveout(struct rproc *rproc, + struct rproc_mem_entry *mem) { - struct rproc_mem_entry *carveout, *mapping = NULL; + struct rproc_mem_entry *mapping = NULL; struct device *dev = &rproc->dev; dma_addr_t dma; void *va; int ret; - if (sizeof(*rsc) > avail) { - dev_err(dev, "carveout rsc is truncated\n"); - return -EINVAL; - } - - /* make sure reserved bytes are zeroes */ - if (rsc->reserved) { - dev_err(dev, "carveout rsc has non zero reserved bytes\n"); - return -EINVAL; - } - - dev_dbg(dev, "carveout rsc: name: %s, da 0x%x, pa 0x%x, len 0x%x, flags 0x%x\n", - rsc->name, rsc->da, rsc->pa, rsc->len, rsc->flags); - - va = dma_alloc_coherent(dev->parent, rsc->len, &dma, GFP_KERNEL); + va = dma_alloc_coherent(dev->parent, mem->len, &dma, GFP_KERNEL); if (!va) { dev_err(dev->parent, - "failed to allocate dma memory: len 0x%x\n", rsc->len); + "failed to allocate dma memory: len 0x%x\n", mem->len); return -ENOMEM; } dev_dbg(dev, "carveout va %pK, dma %pad, len 0x%x\n", - va, &dma, rsc->len); + va, &dma, mem->len); /* * Ok, this is non-standard. @@ -729,22 +686,22 @@ static int rproc_handle_carveout(struct rproc *rproc, * physical address in this case. */ - if (rsc->da != FW_RSC_ADDR_ANY && !rproc->domain) { - dev_err(dev->parent, - "Bad carveout rsc configuration\n"); - ret = -ENOMEM; - goto dma_free; - } + if (mem->da != FW_RSC_ADDR_ANY) { + if (!rproc->domain) { + dev_err(dev->parent, + "Bad carveout rsc configuration\n"); + ret = -ENOMEM; + goto dma_free; + } - if (rsc->da != FW_RSC_ADDR_ANY && rproc->domain) { mapping = kzalloc(sizeof(*mapping), GFP_KERNEL); if (!mapping) { ret = -ENOMEM; goto dma_free; } - ret = iommu_map(rproc->domain, rsc->da, dma, rsc->len, - rsc->flags); + ret = iommu_map(rproc->domain, mem->da, dma, mem->len, + mem->flags); if (ret) { dev_err(dev, "iommu_map failed: %d\n", ret); goto free_mapping; @@ -757,51 +714,101 @@ static int rproc_handle_carveout(struct rproc *rproc, * We can't trust the remote processor not to change the * resource table, so we must maintain this info independently. */ - mapping->da = rsc->da; - mapping->len = rsc->len; + mapping->da = mem->da; + mapping->len = mem->len; list_add_tail(&mapping->node, &rproc->mappings); dev_dbg(dev, "carveout mapped 0x%x to %pad\n", - rsc->da, &dma); + mem->da, &dma); + } else { + mem->da = (u32)dma; } - /* - * Some remote processors might need to know the pa - * even though they are behind an IOMMU. E.g., OMAP4's - * remote M3 processor needs this so it can control - * on-chip hardware accelerators that are not behind - * the IOMMU, and therefor must know the pa. - * - * Generally we don't want to expose physical addresses - * if we don't have to (remote processors are generally - * _not_ trusted), so we might want to do this only for - * remote processor that _must_ have this (e.g. OMAP4's - * dual M3 subsystem). - * - * Non-IOMMU processors might also want to have this info. - * In this case, the device address and the physical address - * are the same. - */ - rsc->pa = (u32)rproc_va_to_pa(va); - - carveout = rproc_mem_entry_init(dev, va, dma, rsc->len, rsc->da, - rproc_release_carveout, rsc->name); - if (!carveout) - goto free_carv; - - rproc_add_carveout(rproc, carveout); + mem->dma = (u32)dma; + mem->va = va; return 0; -free_carv: - kfree(carveout); free_mapping: kfree(mapping); dma_free: - dma_free_coherent(dev->parent, rsc->len, va, dma); + dma_free_coherent(dev->parent, mem->len, va, dma); return ret; } +/** + * rproc_release_carveout() - release acquired carveout + * @rproc: rproc handle + * @mem: the memory entry to release + * + * This function releases specified memory entry @mem allocated via + * rproc_alloc_carveout() function by @rproc. + */ +static int rproc_release_carveout(struct rproc *rproc, + struct rproc_mem_entry *mem) +{ + struct device *dev = &rproc->dev; + + /* clean up carveout allocations */ + dma_free_coherent(dev->parent, mem->len, mem->va, mem->dma); + return 0; +} + +/** + * rproc_handle_carveout() - handle phys contig memory allocation requests + * @rproc: rproc handle + * @rsc: the resource entry + * @avail: size of available data (for image validation) + * + * This function will handle firmware requests for allocation of physically + * contiguous memory regions. + * + * These request entries should come first in the firmware's resource table, + * as other firmware entries might request placing other data objects inside + * these memory regions (e.g. data/code segments, trace resource entries, ...). + * + * Allocating memory this way helps utilizing the reserved physical memory + * (e.g. CMA) more efficiently, and also minimizes the number of TLB entries + * needed to map it (in case @rproc is using an IOMMU). Reducing the TLB + * pressure is important; it may have a substantial impact on performance. + */ +static int rproc_handle_carveout(struct rproc *rproc, + struct fw_rsc_carveout *rsc, + int offset, int avail) +{ + struct rproc_mem_entry *carveout; + struct device *dev = &rproc->dev; + + if (sizeof(*rsc) > avail) { + dev_err(dev, "carveout rsc is truncated\n"); + return -EINVAL; + } + + /* make sure reserved bytes are zeroes */ + if (rsc->reserved) { + dev_err(dev, "carveout rsc has non zero reserved bytes\n"); + return -EINVAL; + } + + dev_dbg(dev, "carveout rsc: name: %s, da 0x%x, pa 0x%x, len 0x%x, flags 0x%x\n", + rsc->name, rsc->da, rsc->pa, rsc->len, rsc->flags); + + /* Register carveout in in list */ + carveout = rproc_mem_entry_init(dev, 0, 0, rsc->len, rsc->da, + rproc_alloc_carveout, + rproc_release_carveout, rsc->name); + if (!carveout) { + dev_err(dev, "Can't allocate memory entry structure\n"); + return -ENOMEM; + } + + carveout->flags = rsc->flags; + carveout->rsc_offset = offset; + rproc_add_carveout(rproc, carveout); + + return 0; +} + /** * rproc_add_carveout() - register an allocated carveout region * @rproc: rproc handle @@ -832,6 +839,7 @@ EXPORT_SYMBOL(rproc_add_carveout); struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, + int (*alloc)(struct rproc *, struct rproc_mem_entry *), int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...) { @@ -846,7 +854,9 @@ rproc_mem_entry_init(struct device *dev, mem->dma = dma; mem->da = da; mem->len = len; + mem->alloc = alloc; mem->release = release; + mem->rsc_offset = FW_RSC_ADDR_ANY; va_start(args, name); vsnprintf(mem->name, sizeof(mem->name), name, args); @@ -977,6 +987,63 @@ static void rproc_unprepare_subdevices(struct rproc *rproc) } } +/** + * rproc_alloc_registered_carveouts() - allocate all carveouts registered + * in the list + * @rproc: the remote processor handle + * + * This function parses registered carveout list, performs allocation + * if alloc() ops registered and updates resource table information + * if rsc_offset set. + * + * Return: 0 on success + */ +static int rproc_alloc_registered_carveouts(struct rproc *rproc) +{ + struct rproc_mem_entry *entry, *tmp; + struct fw_rsc_carveout *rsc; + struct device *dev = &rproc->dev; + int ret; + + list_for_each_entry_safe(entry, tmp, &rproc->carveouts, node) { + if (entry->alloc) { + ret = entry->alloc(rproc, entry); + if (ret) { + dev_err(dev, "Unable to allocate carveout %s: %d\n", + entry->name, ret); + return -ENOMEM; + } + } + + if (entry->rsc_offset != FW_RSC_ADDR_ANY) { + /* update resource table */ + rsc = (void *)rproc->table_ptr + entry->rsc_offset; + + /* + * Some remote processors might need to know the pa + * even though they are behind an IOMMU. E.g., OMAP4's + * remote M3 processor needs this so it can control + * on-chip hardware accelerators that are not behind + * the IOMMU, and therefor must know the pa. + * + * Generally we don't want to expose physical addresses + * if we don't have to (remote processors are generally + * _not_ trusted), so we might want to do this only for + * remote processor that _must_ have this (e.g. OMAP4's + * dual M3 subsystem). + * + * Non-IOMMU processors might also want to have this info. + * In this case, the device address and the physical address + * are the same. + */ + if (entry->va) + rsc->pa = (u32)rproc_va_to_pa(entry->va); + } + } + + return 0; +} + /** * rproc_coredump_cleanup() - clean up dump_segments list * @rproc: the remote processor handle @@ -1149,6 +1216,14 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) goto clean_up_resources; } + /* Allocate carveout resources associated to rproc */ + ret = rproc_alloc_registered_carveouts(rproc); + if (ret) { + dev_err(dev, "Failed to allocate associated carveouts: %d\n", + ret); + goto clean_up_resources; + } + ret = rproc_start(rproc, fw); if (ret) goto clean_up_resources; diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8a350265d883..d251c091303c 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -317,6 +317,9 @@ struct rproc; * @priv: associated data * @name: associated memory region name (optional) * @node: list node + * @rsc_offset: offset in resource table + * @flags: iommu protection flags + * @alloc: specific memory allocator function */ struct rproc_mem_entry { void *va; @@ -326,6 +329,9 @@ struct rproc_mem_entry { void *priv; char name[32]; struct list_head node; + u32 rsc_offset; + u32 flags; + int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -564,6 +570,7 @@ void rproc_add_carveout(struct rproc *rproc, struct rproc_mem_entry *mem); struct rproc_mem_entry * rproc_mem_entry_init(struct device *dev, void *va, dma_addr_t dma, int len, u32 da, + int (*alloc)(struct rproc *, struct rproc_mem_entry *), int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); -- cgit v1.2.3-71-gd317 From 1429cca1175f4cb64dd5d61ffd6037895a41d672 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:44 +0200 Subject: remoteproc: add helper function to allocate rproc_mem_entry from reserved memory This patch introduces rproc_res_mem_entry_init() helper function to allocate a rproc_mem_entry structure from a reserved memory region. In that case, rproc_mem_entry structure has no alloc and release ops. It will be used to assigned the specified reserved memory to any rproc sub device. Relation between rproc_mem_entry and rproc sub device will be done by name. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 37 ++++++++++++++++++++++++++++++++++++ include/linux/remoteproc.h | 6 ++++++ 2 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 9d17b3079506..d7a623b8801c 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -857,6 +857,7 @@ rproc_mem_entry_init(struct device *dev, mem->alloc = alloc; mem->release = release; mem->rsc_offset = FW_RSC_ADDR_ANY; + mem->of_resm_idx = -1; va_start(args, name); vsnprintf(mem->name, sizeof(mem->name), name, args); @@ -866,6 +867,42 @@ rproc_mem_entry_init(struct device *dev, } EXPORT_SYMBOL(rproc_mem_entry_init); +/** + * rproc_of_resm_mem_entry_init() - allocate and initialize rproc_mem_entry struct + * from a reserved memory phandle + * @dev: pointer on device struct + * @of_resm_idx: reserved memory phandle index in "memory-region" + * @len: memory carveout length + * @da: device address + * @name: carveout name + * + * This function allocates a rproc_mem_entry struct and fill it with parameters + * provided by client. + */ +struct rproc_mem_entry * +rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, int len, + u32 da, const char *name, ...) +{ + struct rproc_mem_entry *mem; + va_list args; + + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return mem; + + mem->da = da; + mem->len = len; + mem->rsc_offset = FW_RSC_ADDR_ANY; + mem->of_resm_idx = of_resm_idx; + + va_start(args, name); + vsnprintf(mem->name, sizeof(mem->name), name, args); + va_end(args); + + return mem; +} +EXPORT_SYMBOL(rproc_of_resm_mem_entry_init); + /** * A lookup table for resource handlers. The indices are defined in * enum fw_resource_type. diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d251c091303c..d4cabe8da507 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -319,6 +319,7 @@ struct rproc; * @node: list node * @rsc_offset: offset in resource table * @flags: iommu protection flags + * @of_resm_idx: reserved memory phandle index * @alloc: specific memory allocator function */ struct rproc_mem_entry { @@ -331,6 +332,7 @@ struct rproc_mem_entry { struct list_head node; u32 rsc_offset; u32 flags; + u32 of_resm_idx; int (*alloc)(struct rproc *rproc, struct rproc_mem_entry *mem); int (*release)(struct rproc *rproc, struct rproc_mem_entry *mem); }; @@ -574,6 +576,10 @@ rproc_mem_entry_init(struct device *dev, int (*release)(struct rproc *, struct rproc_mem_entry *), const char *name, ...); +struct rproc_mem_entry * +rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, int len, + u32 da, const char *name, ...); + int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); -- cgit v1.2.3-71-gd317 From df2fc43d09d3ee5ede82cab9299df5e78aa427b5 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 13 Sep 2018 11:17:23 +0200 Subject: list: introduce list_bulk_move_tail helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move all entries between @first and including @last before @head. This is useful for LRU lists where a whole block of entries should be moved to the end of the list. Used as a band aid in TTM, but better placed in the common list headers. Acked-by: Dave Airlie Signed-off-by: Christian König Reviewed-by: Huang Rui Reviewed-by: Junwei Zhang Signed-off-by: Alex Deucher --- drivers/gpu/drm/ttm/ttm_bo.c | 25 +++++-------------------- include/linux/list.h | 23 +++++++++++++++++++++++ 2 files changed, 28 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index b2a33bf1ef10..26b889f86670 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -247,20 +247,6 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); -static void ttm_list_move_bulk_tail(struct list_head *list, - struct list_head *first, - struct list_head *last) -{ - first->prev->next = last->next; - last->next->prev = first->prev; - - list->prev->next = first; - first->prev = list->prev; - - last->next = list; - list->prev = last; -} - void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk) { unsigned i; @@ -276,8 +262,8 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk) reservation_object_assert_held(pos->last->resv); man = &pos->first->bdev->man[TTM_PL_TT]; - ttm_list_move_bulk_tail(&man->lru[i], &pos->first->lru, - &pos->last->lru); + list_bulk_move_tail(&man->lru[i], &pos->first->lru, + &pos->last->lru); } for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { @@ -291,8 +277,8 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk) reservation_object_assert_held(pos->last->resv); man = &pos->first->bdev->man[TTM_PL_VRAM]; - ttm_list_move_bulk_tail(&man->lru[i], &pos->first->lru, - &pos->last->lru); + list_bulk_move_tail(&man->lru[i], &pos->first->lru, + &pos->last->lru); } for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { @@ -306,8 +292,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk) reservation_object_assert_held(pos->last->resv); lru = &pos->first->bdev->glob->swap_lru[i]; - ttm_list_move_bulk_tail(lru, &pos->first->swap, - &pos->last->swap); + list_bulk_move_tail(lru, &pos->first->swap, &pos->last->swap); } } EXPORT_SYMBOL(ttm_bo_bulk_move_lru_tail); diff --git a/include/linux/list.h b/include/linux/list.h index de04cc5ed536..edb7628e46ed 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -183,6 +183,29 @@ static inline void list_move_tail(struct list_head *list, list_add_tail(list, head); } +/** + * list_bulk_move_tail - move a subsection of a list to its tail + * @head: the head that will follow our entry + * @first: first entry to move + * @last: last entry to move, can be the same as first + * + * Move all entries between @first and including @last before @head. + * All three entries must belong to the same linked list. + */ +static inline void list_bulk_move_tail(struct list_head *head, + struct list_head *first, + struct list_head *last) +{ + first->prev->next = last->next; + last->next->prev = first->prev; + + head->prev->next = first; + first->prev = head->prev; + + last->next = head; + head->prev = last; +} + /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test -- cgit v1.2.3-71-gd317 From a6ca88b241d5e929e6e60b12ad8cd288f0ffa256 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 1 Oct 2018 22:36:36 -0700 Subject: trace_uprobe: support reference counter in fd-based uprobe This patch enables uprobes with reference counter in fd-based uprobe. Highest 32 bits of perf_event_attr.config is used to stored offset of the reference count (semaphore). Format information in /sys/bus/event_source/devices/uprobe/format/ is updated to reflect this new feature. Link: http://lkml.kernel.org/r/20181002053636.1896903-1-songliubraving@fb.com Cc: Oleg Nesterov Acked-by: Peter Zijlstra (Intel) Reviewed-and-tested-by: Ravi Bangoria Signed-off-by: Song Liu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 3 ++- kernel/events/core.c | 49 ++++++++++++++++++++++++++++++++--------- kernel/trace/trace_event_perf.c | 7 +++--- kernel/trace/trace_probe.h | 3 ++- kernel/trace/trace_uprobe.c | 4 +++- 5 files changed, 50 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 78a010e19ed4..4130a5497d40 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -575,7 +575,8 @@ extern int bpf_get_kprobe_info(const struct perf_event *event, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS -extern int perf_uprobe_init(struct perf_event *event, bool is_retprobe); +extern int perf_uprobe_init(struct perf_event *event, + unsigned long ref_ctr_offset, bool is_retprobe); extern void perf_uprobe_destroy(struct perf_event *event); extern int bpf_get_uprobe_info(const struct perf_event *event, u32 *fd_type, const char **filename, diff --git a/kernel/events/core.c b/kernel/events/core.c index c80549bf82c6..65b30773af3e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8368,30 +8368,39 @@ static struct pmu perf_tracepoint = { * * PERF_PROBE_CONFIG_IS_RETPROBE if set, create kretprobe/uretprobe * if not set, create kprobe/uprobe + * + * The following values specify a reference counter (or semaphore in the + * terminology of tools like dtrace, systemtap, etc.) Userspace Statically + * Defined Tracepoints (USDT). Currently, we use 40 bit for the offset. + * + * PERF_UPROBE_REF_CTR_OFFSET_BITS # of bits in config as th offset + * PERF_UPROBE_REF_CTR_OFFSET_SHIFT # of bits to shift left */ enum perf_probe_config { PERF_PROBE_CONFIG_IS_RETPROBE = 1U << 0, /* [k,u]retprobe */ + PERF_UPROBE_REF_CTR_OFFSET_BITS = 32, + PERF_UPROBE_REF_CTR_OFFSET_SHIFT = 64 - PERF_UPROBE_REF_CTR_OFFSET_BITS, }; PMU_FORMAT_ATTR(retprobe, "config:0"); +#endif -static struct attribute *probe_attrs[] = { +#ifdef CONFIG_KPROBE_EVENTS +static struct attribute *kprobe_attrs[] = { &format_attr_retprobe.attr, NULL, }; -static struct attribute_group probe_format_group = { +static struct attribute_group kprobe_format_group = { .name = "format", - .attrs = probe_attrs, + .attrs = kprobe_attrs, }; -static const struct attribute_group *probe_attr_groups[] = { - &probe_format_group, +static const struct attribute_group *kprobe_attr_groups[] = { + &kprobe_format_group, NULL, }; -#endif -#ifdef CONFIG_KPROBE_EVENTS static int perf_kprobe_event_init(struct perf_event *event); static struct pmu perf_kprobe = { .task_ctx_nr = perf_sw_context, @@ -8401,7 +8410,7 @@ static struct pmu perf_kprobe = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, - .attr_groups = probe_attr_groups, + .attr_groups = kprobe_attr_groups, }; static int perf_kprobe_event_init(struct perf_event *event) @@ -8433,6 +8442,24 @@ static int perf_kprobe_event_init(struct perf_event *event) #endif /* CONFIG_KPROBE_EVENTS */ #ifdef CONFIG_UPROBE_EVENTS +PMU_FORMAT_ATTR(ref_ctr_offset, "config:32-63"); + +static struct attribute *uprobe_attrs[] = { + &format_attr_retprobe.attr, + &format_attr_ref_ctr_offset.attr, + NULL, +}; + +static struct attribute_group uprobe_format_group = { + .name = "format", + .attrs = uprobe_attrs, +}; + +static const struct attribute_group *uprobe_attr_groups[] = { + &uprobe_format_group, + NULL, +}; + static int perf_uprobe_event_init(struct perf_event *event); static struct pmu perf_uprobe = { .task_ctx_nr = perf_sw_context, @@ -8442,12 +8469,13 @@ static struct pmu perf_uprobe = { .start = perf_swevent_start, .stop = perf_swevent_stop, .read = perf_swevent_read, - .attr_groups = probe_attr_groups, + .attr_groups = uprobe_attr_groups, }; static int perf_uprobe_event_init(struct perf_event *event) { int err; + unsigned long ref_ctr_offset; bool is_retprobe; if (event->attr.type != perf_uprobe.type) @@ -8463,7 +8491,8 @@ static int perf_uprobe_event_init(struct perf_event *event) return -EOPNOTSUPP; is_retprobe = event->attr.config & PERF_PROBE_CONFIG_IS_RETPROBE; - err = perf_uprobe_init(event, is_retprobe); + ref_ctr_offset = event->attr.config >> PERF_UPROBE_REF_CTR_OFFSET_SHIFT; + err = perf_uprobe_init(event, ref_ctr_offset, is_retprobe); if (err) return err; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 69a3fe926e8c..76217bbef815 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -290,7 +290,8 @@ void perf_kprobe_destroy(struct perf_event *p_event) #endif /* CONFIG_KPROBE_EVENTS */ #ifdef CONFIG_UPROBE_EVENTS -int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe) +int perf_uprobe_init(struct perf_event *p_event, + unsigned long ref_ctr_offset, bool is_retprobe) { int ret; char *path = NULL; @@ -312,8 +313,8 @@ int perf_uprobe_init(struct perf_event *p_event, bool is_retprobe) goto out; } - tp_event = create_local_trace_uprobe( - path, p_event->attr.probe_offset, is_retprobe); + tp_event = create_local_trace_uprobe(path, p_event->attr.probe_offset, + ref_ctr_offset, is_retprobe); if (IS_ERR(tp_event)) { ret = PTR_ERR(tp_event); goto out; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 5f52668e165d..03b10f3201a5 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -412,6 +412,7 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, extern void destroy_local_trace_kprobe(struct trace_event_call *event_call); extern struct trace_event_call * -create_local_trace_uprobe(char *name, unsigned long offs, bool is_return); +create_local_trace_uprobe(char *name, unsigned long offs, + unsigned long ref_ctr_offset, bool is_return); extern void destroy_local_trace_uprobe(struct trace_event_call *event_call); #endif diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 3a7c73c40007..d09638706fe0 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1405,7 +1405,8 @@ static int unregister_uprobe_event(struct trace_uprobe *tu) #ifdef CONFIG_PERF_EVENTS struct trace_event_call * -create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) +create_local_trace_uprobe(char *name, unsigned long offs, + unsigned long ref_ctr_offset, bool is_return) { struct trace_uprobe *tu; struct path path; @@ -1437,6 +1438,7 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) tu->offset = offs; tu->path = path; + tu->ref_ctr_offset = ref_ctr_offset; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu, &tu->tp.call); -- cgit v1.2.3-71-gd317 From 81b45683487a51b0f4d3b29d37f20d6d078544e4 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 26 Aug 2018 03:16:29 +0900 Subject: compiler.h: give up __compiletime_assert_fallback() __compiletime_assert_fallback() is supposed to stop building earlier by using the negative-array-size method in case the compiler does not support "error" attribute, but has never worked like that. You can simply try: BUILD_BUG_ON(1); GCC immediately terminates the build, but Clang does not report anything because Clang does not support the "error" attribute now. It will later fail at link time, but __compiletime_assert_fallback() is not working at least. The root cause is commit 1d6a0d19c855 ("bug.h: prevent double evaluation of `condition' in BUILD_BUG_ON"). Prior to that commit, BUILD_BUG_ON() was checked by the negative-array-size method *and* the link-time trick. Since that commit, the negative-array-size is not effective because '__cond' is no longer constant. As the comment in says, GCC (and Clang as well) only emits the error for obvious cases. When '__cond' is a variable, ((void)sizeof(char[1 - 2 * __cond])) ... is not obvious for the compiler to know the array size is negative. Reverting that commit would break BUILD_BUG() because negative-size-array is evaluated before the code is optimized out. Let's give up __compiletime_assert_fallback(). This commit does not change the current behavior since it just rips off the useless code. Signed-off-by: Masahiro Yamada Reviewed-by: Kees Cook Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook --- include/linux/compiler.h | 17 +---------------- 1 file changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 681d866efb1e..87c776c3ce73 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -314,29 +314,14 @@ static inline void *offset_to_ptr(const int *off) #endif #ifndef __compiletime_error # define __compiletime_error(message) -/* - * Sparse complains of variable sized arrays due to the temporary variable in - * __compiletime_assert. Unfortunately we can't just expand it out to make - * sparse see a constant array size without breaking compiletime_assert on old - * versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether. - */ -# ifndef __CHECKER__ -# define __compiletime_error_fallback(condition) \ - do { ((void)sizeof(char[1 - 2 * condition])); } while (0) -# endif -#endif -#ifndef __compiletime_error_fallback -# define __compiletime_error_fallback(condition) do { } while (0) #endif #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - int __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ - if (__cond) \ + if (!(condition)) \ prefix ## suffix(); \ - __compiletime_error_fallback(__cond); \ } while (0) #else # define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) -- cgit v1.2.3-71-gd317 From c6aed238b7a9b15a5c90a0c31f1d36577b5d2cbe Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Fri, 27 Jul 2018 15:14:47 +0200 Subject: remoteproc: modify vring allocation to rely on centralized carveout allocator Current version of rproc_alloc_vring function supports only dynamic vring allocation. This patch allows to allocate vrings based on memory region declatation. Vrings are now manage like memory carveouts, to communize memory management code in rproc_alloc_registered_carveouts(). Allocated buffer is retrieved in rp_find_vq() thanks to rproc_find_carveout_by_name() functions for. This patch sets vrings names to vdev"x"vring"y" with x vdev index in resource table and y vring index in vdev. This will be updated when name will be associated to vdev in firmware resource table. Signed-off-by: Loic Pallardy Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 61 +++++++++++++++++--------------- drivers/remoteproc/remoteproc_internal.h | 2 ++ drivers/remoteproc/remoteproc_virtio.c | 14 +++++++- include/linux/remoteproc.h | 6 ++-- 4 files changed, 51 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 5abcd27a29f3..f77a42f6a8aa 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -53,6 +53,11 @@ typedef int (*rproc_handle_resources_t)(struct rproc *rproc, typedef int (*rproc_handle_resource_t)(struct rproc *rproc, void *, int offset, int avail); +static int rproc_alloc_carveout(struct rproc *rproc, + struct rproc_mem_entry *mem); +static int rproc_release_carveout(struct rproc *rproc, + struct rproc_mem_entry *mem); + /* Unique indices for remoteproc devices */ static DEFINE_IDA(rproc_dev_index); @@ -312,21 +317,33 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) struct device *dev = &rproc->dev; struct rproc_vring *rvring = &rvdev->vring[i]; struct fw_rsc_vdev *rsc; - dma_addr_t dma; - void *va; int ret, size, notifyid; + struct rproc_mem_entry *mem; /* actual size of vring (in bytes) */ size = PAGE_ALIGN(vring_size(rvring->len, rvring->align)); - /* - * Allocate non-cacheable memory for the vring. In the future - * this call will also configure the IOMMU for us - */ - va = dma_alloc_coherent(dev->parent, size, &dma, GFP_KERNEL); - if (!va) { - dev_err(dev->parent, "dma_alloc_coherent failed\n"); - return -EINVAL; + rsc = (void *)rproc->table_ptr + rvdev->rsc_offset; + + /* Search for pre-registered carveout */ + mem = rproc_find_carveout_by_name(rproc, "vdev%dvring%d", rvdev->index, + i); + if (mem) { + if (rproc_check_carveout_da(rproc, mem, rsc->vring[i].da, size)) + return -ENOMEM; + } else { + /* Register carveout in in list */ + mem = rproc_mem_entry_init(dev, 0, 0, size, rsc->vring[i].da, + rproc_alloc_carveout, + rproc_release_carveout, + "vdev%dvring%d", + rvdev->index, i); + if (!mem) { + dev_err(dev, "Can't allocate memory entry structure\n"); + return -ENOMEM; + } + + rproc_add_carveout(rproc, mem); } /* @@ -337,7 +354,6 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) ret = idr_alloc(&rproc->notifyids, rvring, 0, 0, GFP_KERNEL); if (ret < 0) { dev_err(dev, "idr_alloc failed: %d\n", ret); - dma_free_coherent(dev->parent, size, va, dma); return ret; } notifyid = ret; @@ -346,21 +362,9 @@ int rproc_alloc_vring(struct rproc_vdev *rvdev, int i) if (notifyid > rproc->max_notifyid) rproc->max_notifyid = notifyid; - dev_dbg(dev, "vring%d: va %pK dma %pad size 0x%x idr %d\n", - i, va, &dma, size, notifyid); - - rvring->va = va; - rvring->dma = dma; rvring->notifyid = notifyid; - /* - * Let the rproc know the notifyid and da of this vring. - * Not all platforms use dma_alloc_coherent to automatically - * set up the iommu. In this case the device address (da) will - * hold the physical address and not the device address. - */ - rsc = (void *)rproc->table_ptr + rvdev->rsc_offset; - rsc->vring[i].da = dma; + /* Let the rproc know the notifyid of this vring.*/ rsc->vring[i].notifyid = notifyid; return 0; } @@ -392,12 +396,10 @@ rproc_parse_vring(struct rproc_vdev *rvdev, struct fw_rsc_vdev *rsc, int i) void rproc_free_vring(struct rproc_vring *rvring) { - int size = PAGE_ALIGN(vring_size(rvring->len, rvring->align)); struct rproc *rproc = rvring->rvdev->rproc; int idx = rvring->rvdev->vring - rvring; struct fw_rsc_vdev *rsc; - dma_free_coherent(rproc->dev.parent, size, rvring->va, rvring->dma); idr_remove(&rproc->notifyids, rvring->notifyid); /* reset resource entry info */ @@ -484,6 +486,7 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc, rvdev->id = rsc->id; rvdev->rproc = rproc; + rvdev->index = rproc->nb_vdev++; /* parse the vrings */ for (i = 0; i < rsc->num_of_vrings; i++) { @@ -528,9 +531,6 @@ void rproc_vdev_release(struct kref *ref) for (id = 0; id < ARRAY_SIZE(rvdev->vring); id++) { rvring = &rvdev->vring[id]; - if (!rvring->va) - continue; - rproc_free_vring(rvring); } @@ -1323,6 +1323,9 @@ static int rproc_fw_boot(struct rproc *rproc, const struct firmware *fw) /* reset max_notifyid */ rproc->max_notifyid = -1; + /* reset handled vdev */ + rproc->nb_vdev = 0; + /* handle fw resources which are required to boot rproc */ ret = rproc_handle_resources(rproc, rproc_loading_handlers); if (ret) { diff --git a/drivers/remoteproc/remoteproc_internal.h b/drivers/remoteproc/remoteproc_internal.h index 7570beb035b5..f6cad243d7ca 100644 --- a/drivers/remoteproc/remoteproc_internal.h +++ b/drivers/remoteproc/remoteproc_internal.h @@ -60,6 +60,8 @@ int rproc_elf_load_segments(struct rproc *rproc, const struct firmware *fw); int rproc_elf_load_rsc_table(struct rproc *rproc, const struct firmware *fw); struct resource_table *rproc_elf_find_loaded_rsc_table(struct rproc *rproc, const struct firmware *fw); +struct rproc_mem_entry * +rproc_find_carveout_by_name(struct rproc *rproc, const char *name, ...); static inline int rproc_fw_sanity_check(struct rproc *rproc, const struct firmware *fw) diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index bbecd44df7e8..de21f620b882 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -76,7 +76,9 @@ static struct virtqueue *rp_find_vq(struct virtio_device *vdev, struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); struct rproc *rproc = vdev_to_rproc(vdev); struct device *dev = &rproc->dev; + struct rproc_mem_entry *mem; struct rproc_vring *rvring; + struct fw_rsc_vdev *rsc; struct virtqueue *vq; void *addr; int len, size; @@ -88,8 +90,14 @@ static struct virtqueue *rp_find_vq(struct virtio_device *vdev, if (!name) return NULL; + /* Search allocated memory region by name */ + mem = rproc_find_carveout_by_name(rproc, "vdev%dvring%d", rvdev->index, + id); + if (!mem || !mem->va) + return ERR_PTR(-ENOMEM); + rvring = &rvdev->vring[id]; - addr = rvring->va; + addr = mem->va; len = rvring->len; /* zero vring */ @@ -114,6 +122,10 @@ static struct virtqueue *rp_find_vq(struct virtio_device *vdev, rvring->vq = vq; vq->priv = rvring; + /* Update vring in resource table */ + rsc = (void *)rproc->table_ptr + rvdev->rsc_offset; + rsc->vring[id].da = mem->da; + return vq; } diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index d4cabe8da507..8bb0cf0416f1 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -454,6 +454,7 @@ struct rproc_dump_segment { * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started * @dump_segments: list of segments in the firmware + * @nb_vdev: number of vdev currently handled by rproc */ struct rproc { struct list_head node; @@ -486,6 +487,7 @@ struct rproc { bool has_iommu; bool auto_boot; struct list_head dump_segments; + int nb_vdev; }; /** @@ -513,7 +515,6 @@ struct rproc_subdev { /** * struct rproc_vring - remoteproc vring state * @va: virtual address - * @dma: dma address * @len: length, in bytes * @da: device address * @align: vring alignment @@ -523,7 +524,6 @@ struct rproc_subdev { */ struct rproc_vring { void *va; - dma_addr_t dma; int len; u32 da; u32 align; @@ -542,6 +542,7 @@ struct rproc_vring { * @vdev: the virio device * @vring: the vrings for this vdev * @rsc_offset: offset of the vdev's resource entry + * @index: vdev position versus other vdev declared in resource table */ struct rproc_vdev { struct kref refcount; @@ -554,6 +555,7 @@ struct rproc_vdev { struct virtio_device vdev; struct rproc_vring vring[RVDEV_NUM_VRINGS]; u32 rsc_offset; + u32 index; }; struct rproc *rproc_get_by_phandle(phandle phandle); -- cgit v1.2.3-71-gd317 From 18127429a854e7607b859484880b8e26cee9ddab Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in set_mask_bits() macro Unprotected naming of local variables within the set_mask_bits() can easily lead to using the wrong scope. Noticed this when "set_mask_bits(&foo->bar, 0, mask)" behaved as no-op. Signed-off-by: Miklos Szeredi Fixes: 00a1a053ebe5 ("ext4: atomically set inode->i_flags in ext4_set_inode_flags()") Cc: Theodore Ts'o --- include/linux/bitops.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 7ddb1349394d..d18ee0e63c32 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -236,17 +236,17 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #ifdef __KERNEL__ #ifndef set_mask_bits -#define set_mask_bits(ptr, _mask, _bits) \ +#define set_mask_bits(ptr, mask, bits) \ ({ \ - const typeof(*ptr) mask = (_mask), bits = (_bits); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = (old & ~mask) | bits; \ - } while (cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = (old__ & ~mask__) | bits__; \ + } while (cmpxchg(ptr, old__, new__) != old__); \ \ - new; \ + new__; \ }) #endif -- cgit v1.2.3-71-gd317 From edfa87281f4fa1b78a21f6db999935a2faa2f6b8 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 15 Oct 2018 15:43:06 +0200 Subject: bitops: protect variables in bit_clear_unless() macro Unprotected naming of local variables within bit_clear_unless() can easily lead to using the wrong scope. Noticed this by code review after having hit this issue in set_mask_bits() Signed-off-by: Miklos Szeredi Fixes: 85ad1d13ee9b ("md: set MD_CHANGE_PENDING in a atomic region") Cc: Guoqing Jiang --- include/linux/bitops.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index d18ee0e63c32..705f7c442691 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -251,18 +251,18 @@ static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, #endif #ifndef bit_clear_unless -#define bit_clear_unless(ptr, _clear, _test) \ +#define bit_clear_unless(ptr, clear, test) \ ({ \ - const typeof(*ptr) clear = (_clear), test = (_test); \ - typeof(*ptr) old, new; \ + const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ + typeof(*(ptr)) old__, new__; \ \ do { \ - old = READ_ONCE(*ptr); \ - new = old & ~clear; \ - } while (!(old & test) && \ - cmpxchg(ptr, old, new) != old); \ + old__ = READ_ONCE(*(ptr)); \ + new__ = old__ & ~clear__; \ + } while (!(old__ & test__) && \ + cmpxchg(ptr, old__, new__) != old__); \ \ - !(old & test); \ + !(old__ & test__); \ }) #endif -- cgit v1.2.3-71-gd317 From 616e45df7c4aa71279c07cc803a1d51f43f89f37 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:54 +0800 Subject: clk: add new APIs to operate on all available clocks This patch introduces of_clk_bulk_get_all and clk_bulk_x_all APIs to users who just want to handle all available clocks from device tree without need to know the detailed clock information likes clock numbers and names. This is useful in writing some generic drivers to handle clock part. Cc: Stephen Boyd Cc: Masahiro Yamada Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- drivers/clk/clk-bulk.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/clk.h | 42 ++++++++++++++++++++++++++++++++++++++++- 2 files changed, 92 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c index 4460ac52199f..6a7118d4250a 100644 --- a/drivers/clk/clk-bulk.c +++ b/drivers/clk/clk-bulk.c @@ -17,9 +17,11 @@ */ #include +#include #include #include #include +#include static int __must_check of_clk_bulk_get(struct device_node *np, int num_clks, struct clk_bulk_data *clks) @@ -49,6 +51,32 @@ err: return ret; } +static int __must_check of_clk_bulk_get_all(struct device_node *np, + struct clk_bulk_data **clks) +{ + struct clk_bulk_data *clk_bulk; + int num_clks; + int ret; + + num_clks = of_clk_get_parent_count(np); + if (!num_clks) + return 0; + + clk_bulk = kmalloc_array(num_clks, sizeof(*clk_bulk), GFP_KERNEL); + if (!clk_bulk) + return -ENOMEM; + + ret = of_clk_bulk_get(np, num_clks, clk_bulk); + if (ret) { + kfree(clk_bulk); + return ret; + } + + *clks = clk_bulk; + + return num_clks; +} + void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) { while (--num_clks >= 0) { @@ -88,6 +116,29 @@ err: } EXPORT_SYMBOL(clk_bulk_get); +void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) +{ + if (IS_ERR_OR_NULL(clks)) + return; + + clk_bulk_put(num_clks, clks); + + kfree(clks); +} +EXPORT_SYMBOL(clk_bulk_put_all); + +int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + struct device_node *np = dev_of_node(dev); + + if (!np) + return 0; + + return of_clk_bulk_get_all(np, clks); +} +EXPORT_SYMBOL(clk_bulk_get_all); + #ifdef CONFIG_HAVE_CLK_PREPARE /** diff --git a/include/linux/clk.h b/include/linux/clk.h index 4f750c481b82..e9433c76757b 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -312,7 +312,26 @@ struct clk *clk_get(struct device *dev, const char *id); */ int __must_check clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); - +/** + * clk_bulk_get_all - lookup and obtain all available references to clock + * producer. + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * This helper function allows drivers to get all clk consumers in one + * operation. If any of the clk cannot be acquired then any clks + * that were obtained will be freed before returning to the caller. + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * Drivers must assume that the clock source is not enabled. + * + * clk_bulk_get should not be called from within interrupt context. + */ +int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_bulk_get - managed get multiple clk consumers * @dev: device for clock "consumer" @@ -487,6 +506,19 @@ void clk_put(struct clk *clk); */ void clk_bulk_put(int num_clks, struct clk_bulk_data *clks); +/** + * clk_bulk_put_all - "free" all the clock source + * @num_clks: the number of clk_bulk_data + * @clks: the clk_bulk_data table of consumer + * + * Note: drivers must ensure that all clk_bulk_enable calls made on this + * clock source are balanced by clk_bulk_disable calls prior to calling + * this function. + * + * clk_bulk_put_all should not be called from within interrupt context. + */ +void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks); + /** * devm_clk_put - "free" a managed clock source * @dev: device used to acquire the clock @@ -642,6 +674,12 @@ static inline int __must_check clk_bulk_get(struct device *dev, int num_clks, return 0; } +static inline int __must_check clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + return 0; +} + static inline struct clk *devm_clk_get(struct device *dev, const char *id) { return NULL; @@ -663,6 +701,8 @@ static inline void clk_put(struct clk *clk) {} static inline void clk_bulk_put(int num_clks, struct clk_bulk_data *clks) {} +static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {} + static inline void devm_clk_put(struct device *dev, struct clk *clk) {} -- cgit v1.2.3-71-gd317 From f08c2e2865f6f9b172f37d7bbf24716f9ebad553 Mon Sep 17 00:00:00 2001 From: Dong Aisheng Date: Fri, 31 Aug 2018 12:45:55 +0800 Subject: clk: add managed version of clk_bulk_get_all This patch introduces the managed version of clk_bulk_get_all. Cc: Michael Turquette Cc: Stephen Boyd Tested-by: Thor Thayer Signed-off-by: Dong Aisheng Signed-off-by: Stephen Boyd --- drivers/clk/clk-devres.c | 24 ++++++++++++++++++++++++ include/linux/clk.h | 23 +++++++++++++++++++++++ 2 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk-devres.c b/drivers/clk/clk-devres.c index d854e26a8ddb..12c87457eca1 100644 --- a/drivers/clk/clk-devres.c +++ b/drivers/clk/clk-devres.c @@ -70,6 +70,30 @@ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, } EXPORT_SYMBOL_GPL(devm_clk_bulk_get); +int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + struct clk_bulk_devres *devres; + int ret; + + devres = devres_alloc(devm_clk_bulk_release, + sizeof(*devres), GFP_KERNEL); + if (!devres) + return -ENOMEM; + + ret = clk_bulk_get_all(dev, &devres->clks); + if (ret > 0) { + *clks = devres->clks; + devres->num_clks = ret; + devres_add(dev, devres); + } else { + devres_free(devres); + } + + return ret; +} +EXPORT_SYMBOL_GPL(devm_clk_bulk_get_all); + static int devm_clk_match(struct device *dev, void *res, void *data) { struct clk **c = res; diff --git a/include/linux/clk.h b/include/linux/clk.h index e9433c76757b..c705271dc1f2 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -346,6 +346,22 @@ int __must_check clk_bulk_get_all(struct device *dev, */ int __must_check devm_clk_bulk_get(struct device *dev, int num_clks, struct clk_bulk_data *clks); +/** + * devm_clk_bulk_get_all - managed get multiple clk consumers + * @dev: device for clock "consumer" + * @clks: pointer to the clk_bulk_data table of consumer + * + * Returns a positive value for the number of clocks obtained while the + * clock references are stored in the clk_bulk_data table in @clks field. + * Returns 0 if there're none and a negative value if something failed. + * + * This helper function allows drivers to get several clk + * consumers in one operation with management, the clks will + * automatically be freed when the device is unbound. + */ + +int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks); /** * devm_clk_get - lookup and obtain a managed reference to a clock producer. @@ -691,6 +707,13 @@ static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clk return 0; } +static inline int __must_check devm_clk_bulk_get_all(struct device *dev, + struct clk_bulk_data **clks) +{ + + return 0; +} + static inline struct clk *devm_get_clk_from_child(struct device *dev, struct device_node *np, const char *con_id) { -- cgit v1.2.3-71-gd317 From fe0640eb30b7da261ae84d252ed9ed3c7e68dfd8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 10:22:21 -0700 Subject: compiler.h: update definition of unreachable() Fixes the objtool warning seen with Clang: arch/x86/mm/fault.o: warning: objtool: no_context()+0x220: unreachable instruction Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Josh noted that the fallback definition was meant to work around a pre-gcc-4.6 bug. GCC still needs to work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365, so compiler-gcc.h defines its own version of unreachable(). Clang and ICC can use this shared definition. Link: https://github.com/ClangBuiltLinux/linux/issues/204 Suggested-by: Andy Lutomirski Suggested-by: Josh Poimboeuf Tested-by: Nathan Chancellor Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b5fb034fa6fa..2e0b6322588b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -124,7 +124,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) +# define unreachable() do { \ + annotate_unreachable(); \ + __builtin_unreachable(); \ +} while (0) #endif /* -- cgit v1.2.3-71-gd317 From 1ff2fea5e30ca15752777441ecb64a169fe22e9e Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Mon, 15 Oct 2018 14:24:27 -0700 Subject: compiler-gcc: remove comment about gcc 4.5 from unreachable() Remove the comment about being unable to detect __builtin_unreachable. __builtin_unreachable was implemented in the GCC 4.5 timeframe. The kernel's minimum supported version of GCC is 4.6 since commit cafa0010cd51 ("Raise the minimum required gcc version to 4.6"). Commit cb984d101b30 ("compiler-gcc: integrate the various compiler-gcc[345].h files") shows that unreachable() had different guards based on GCC version. Suggested-by: Miguel Ojeda Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler-gcc.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cfac027e1625..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -96,10 +96,6 @@ * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ do { \ -- cgit v1.2.3-71-gd317 From 99c228a994ec8b1580c43631866fd2c5440f5bfd Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 18 Oct 2018 14:22:55 +0300 Subject: fs: group frequently accessed fields of struct super_block together Kernel test robot reported [1] a 6% performance regression in a concurrent unlink(2) workload on commit 60f7ed8c7c4d ("fsnotify: send path type events to group with super block marks"). The performance test was run with no fsnotify marks at all on the data set, so the only extra instructions added by the offending commit are tests of the super_block fields s_fsnotify_{marks,mask} and these tests happen on almost every single inode access. When adding those fields to the super_block struct, we did not give much thought of placing them on a hot cache lines (we just placed them at the end of the struct). Re-organize struct super_block to try and keep some frequently accessed fields on the same cache line. Move the frequently accessed fields s_fsnotify_{marks,mask} near the frequently accessed fields s_fs_info,s_time_gran, while filling a 64bit alignment hole after s_time_gran. Move the seldom accessed fields s_id,s_uuid,s_max_links,s_mode near the seldom accessed fields s_vfs_rename_mutex,s_subtype. Rong Chen confirmed that this patch solved the reported problem. [1] https://lkml.org/lkml/2018/9/30/206 Reported-by: kernel test robot Tested-by: kernel test robot Fixes: 1e6cb72399 ("fsnotify: add super block object type") Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- include/linux/fs.h | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c14801d0aa3..6da94deb957f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1393,17 +1393,26 @@ struct super_block { struct sb_writers s_writers; + /* + * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and + * s_fsnotify_marks together for cache efficiency. They are frequently + * accessed and rarely modified. + */ + void *s_fs_info; /* Filesystem private info */ + + /* Granularity of c/m/atime in ns (cannot be worse than a second) */ + u32 s_time_gran; +#ifdef CONFIG_FSNOTIFY + __u32 s_fsnotify_mask; + struct fsnotify_mark_connector __rcu *s_fsnotify_marks; +#endif + char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ - void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; fmode_t s_mode; - /* Granularity of c/m/atime in ns. - Cannot be worse than a second */ - u32 s_time_gran; - /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. @@ -1464,11 +1473,6 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ - -#ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; -#endif } __randomize_layout; /* Helper functions so that in most cases filesystems will -- cgit v1.2.3-71-gd317 From 3952105df4723abbd36b57e88c8dad42cf6c8b59 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:23 +0530 Subject: remoteproc: Introduce custom dump function for each remoteproc segment Introduce custom dump function and private data per remoteproc dump segment. The dump function is responsible for filling the device memory segment associated with coredump Signed-off-by: Sibi Sankar Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 18 +++++++++++------- include/linux/remoteproc.h | 6 ++++++ 2 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index f77a42f6a8aa..6bed40d01dbf 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1508,14 +1508,18 @@ static void rproc_coredump(struct rproc *rproc) phdr->p_flags = PF_R | PF_W | PF_X; phdr->p_align = 0; - ptr = rproc_da_to_va(rproc, segment->da, segment->size); - if (!ptr) { - dev_err(&rproc->dev, - "invalid coredump segment (%pad, %zu)\n", - &segment->da, segment->size); - memset(data + offset, 0xff, segment->size); + if (segment->dump) { + segment->dump(rproc, segment, data + offset); } else { - memcpy(data + offset, ptr, segment->size); + ptr = rproc_da_to_va(rproc, segment->da, segment->size); + if (!ptr) { + dev_err(&rproc->dev, + "invalid coredump segment (%pad, %zu)\n", + &segment->da, segment->size); + memset(data + offset, 0xff, segment->size); + } else { + memcpy(data + offset, ptr, segment->size); + } } offset += phdr->p_filesz; diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 8bb0cf0416f1..2d036adab7ff 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -412,6 +412,9 @@ enum rproc_crash_type { * @node: list node related to the rproc segment list * @da: device address of the segment * @size: size of the segment + * @priv: private data associated with the dump_segment + * @dump: custom dump function to fill device memory segment associated + * with coredump */ struct rproc_dump_segment { struct list_head node; @@ -419,6 +422,9 @@ struct rproc_dump_segment { dma_addr_t da; size_t size; + void *priv; + void (*dump)(struct rproc *rproc, struct rproc_dump_segment *segment, + void *dest); loff_t offset; }; -- cgit v1.2.3-71-gd317 From ab8f873bb90da7bbe40e2f41c92a4971c4f0dc76 Mon Sep 17 00:00:00 2001 From: Sibi Sankar Date: Wed, 17 Oct 2018 19:25:24 +0530 Subject: remoteproc: Add mechanism for custom dump function assignment This patch adds a mechanism for assigning each rproc dump segment with a custom dump function and private data. The dump function is to be called for each rproc segment during coredump if assigned. Signed-off-by: Sibi Sankar [bjorn: reordred arguments to rproc_coredump_add_custom_segment()] Signed-off-by: Bjorn Andersson --- drivers/remoteproc/remoteproc_core.c | 38 ++++++++++++++++++++++++++++++++++++ include/linux/remoteproc.h | 6 ++++++ 2 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 6bed40d01dbf..54ec38fc5dca 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1446,6 +1446,44 @@ int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size) } EXPORT_SYMBOL(rproc_coredump_add_segment); +/** + * rproc_coredump_add_custom_segment() - add custom coredump segment + * @rproc: handle of a remote processor + * @da: device address + * @size: size of segment + * @dumpfn: custom dump function called for each segment during coredump + * @priv: private data + * + * Add device memory to the list of segments to be included in the coredump + * and associate the segment with the given custom dump function and private + * data. + * + * Return: 0 on success, negative errno on error. + */ +int rproc_coredump_add_custom_segment(struct rproc *rproc, + dma_addr_t da, size_t size, + void (*dumpfn)(struct rproc *rproc, + struct rproc_dump_segment *segment, + void *dest), + void *priv) +{ + struct rproc_dump_segment *segment; + + segment = kzalloc(sizeof(*segment), GFP_KERNEL); + if (!segment) + return -ENOMEM; + + segment->da = da; + segment->size = size; + segment->priv = priv; + segment->dump = dumpfn; + + list_add_tail(&segment->node, &rproc->dump_segments); + + return 0; +} +EXPORT_SYMBOL(rproc_coredump_add_custom_segment); + /** * rproc_coredump() - perform coredump * @rproc: rproc handle diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 2d036adab7ff..507a2b524208 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -592,6 +592,12 @@ int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); +int rproc_coredump_add_custom_segment(struct rproc *rproc, + dma_addr_t da, size_t size, + void (*dumpfn)(struct rproc *rproc, + struct rproc_dump_segment *segment, + void *dest), + void *priv); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { -- cgit v1.2.3-71-gd317 From f8d5d0cc145cc21bfc56ef807dc28102aebbf228 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 16:30:10 -0500 Subject: xarray: Add definition of struct xarray This is a direct replacement for struct radix_tree_root. Some of the struct members have changed name; convert those, and use a #define so that radix_tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 28 ++++-------- include/linux/xarray.h | 70 +++++++++++++++++++++++++++++ lib/Makefile | 2 +- lib/idr.c | 4 +- lib/radix-tree.c | 75 ++++++++++++++++---------------- lib/xarray.c | 44 +++++++++++++++++++ tools/testing/radix-tree/Makefile | 5 ++- tools/testing/radix-tree/linux/bug.h | 1 + tools/testing/radix-tree/linux/kconfig.h | 1 + tools/testing/radix-tree/multiorder.c | 6 +-- tools/testing/radix-tree/test.c | 6 +-- tools/testing/radix-tree/xarray.c | 7 +++ 12 files changed, 181 insertions(+), 68 deletions(-) create mode 100644 lib/xarray.c create mode 100644 tools/testing/radix-tree/linux/kconfig.h create mode 100644 tools/testing/radix-tree/xarray.c (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 60f3d8eb2cb7..0b080bd88ab7 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -30,6 +30,9 @@ #include #include +/* Keep unconverted code working */ +#define radix_tree_root xarray + /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: @@ -92,36 +95,21 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The IDR tag is stored in the low bits of the GFP flags */ +/* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) -/* The top bits of gfp_mask are used to store the root tags */ +/* The top bits of xa_flags are used to store the root tags */ #define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) -struct radix_tree_root { - spinlock_t xa_lock; - gfp_t gfp_mask; - struct radix_tree_node __rcu *rnode; -}; - -#define RADIX_TREE_INIT(name, mask) { \ - .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ - .gfp_mask = (mask), \ - .rnode = NULL, \ -} +#define RADIX_TREE_INIT(name, mask) XARRAY_INIT(name, mask) #define RADIX_TREE(name, mask) \ struct radix_tree_root name = RADIX_TREE_INIT(name, mask) -#define INIT_RADIX_TREE(root, mask) \ -do { \ - spin_lock_init(&(root)->xa_lock); \ - (root)->gfp_mask = (mask); \ - (root)->rnode = NULL; \ -} while (0) +#define INIT_RADIX_TREE(root, mask) xa_init_flags(root, mask) static inline bool radix_tree_empty(const struct radix_tree_root *root) { - return root->rnode == NULL; + return root->xa_head == NULL; } /** diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4d1cd7a083e8..9122cf8bf52a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -10,6 +10,8 @@ */ #include +#include +#include #include #include @@ -153,6 +155,74 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * struct xarray - The anchor of the XArray. + * @xa_lock: Lock that protects the contents of the XArray. + * + * To use the xarray, define it statically or embed it in your data structure. + * It is a very small data structure, so it does not usually make sense to + * allocate it separately and keep a pointer to it in your data structure. + * + * You may use the xa_lock to protect your own data structures as well. + */ +/* + * If all of the entries in the array are NULL, @xa_head is a NULL pointer. + * If the only non-NULL entry in the array is at index 0, @xa_head is that + * entry. If any other entry in the array is non-NULL, @xa_head points + * to an @xa_node. + */ +struct xarray { + spinlock_t xa_lock; +/* private: The rest of the data structure is not to be used directly. */ + gfp_t xa_flags; + void __rcu * xa_head; +}; + +#define XARRAY_INIT(name, flags) { \ + .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ + .xa_flags = flags, \ + .xa_head = NULL, \ +} + +/** + * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. + * @name: A string that names your XArray. + * @flags: XA_FLAG values. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name and flags. It is + * equivalent to calling xa_init_flags() on the array, but it does the + * initialisation at compiletime instead of runtime. + */ +#define DEFINE_XARRAY_FLAGS(name, flags) \ + struct xarray name = XARRAY_INIT(name, flags) + +/** + * DEFINE_XARRAY() - Define an XArray. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of XArrays. It declares + * and initialises an empty XArray with the chosen name. It is equivalent + * to calling xa_init() on the array, but it does the initialisation at + * compiletime instead of runtime. + */ +#define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) + +void xa_init_flags(struct xarray *, gfp_t flags); + +/** + * xa_init() - Initialise an empty XArray. + * @xa: XArray. + * + * An empty XArray is full of NULL entries. + * + * Context: Any context. + */ +static inline void xa_init(struct xarray *xa) +{ + xa_init_flags(xa, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) diff --git a/lib/Makefile b/lib/Makefile index ca3f7ebb900d..057385f1f145 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -18,7 +18,7 @@ KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n lib-y := ctype.o string.o vsprintf.o cmdline.o \ - rbtree.o radix-tree.o timerqueue.o\ + rbtree.o radix-tree.o timerqueue.o xarray.o \ idr.o int_sqrt.o extable.o \ sha1.o chacha20.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ diff --git a/lib/idr.c b/lib/idr.c index 88419fbc5737..9a366b5be2c2 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -39,8 +39,8 @@ int idr_alloc_u32(struct idr *idr, void *ptr, u32 *nextid, unsigned int base = idr->idr_base; unsigned int id = *nextid; - if (WARN_ON_ONCE(!(idr->idr_rt.gfp_mask & ROOT_IS_IDR))) - idr->idr_rt.gfp_mask |= IDR_RT_MARKER; + if (WARN_ON_ONCE(!(idr->idr_rt.xa_flags & ROOT_IS_IDR))) + idr->idr_rt.xa_flags |= IDR_RT_MARKER; id = (id < base) ? 0 : id - base; radix_tree_iter_init(&iter, id); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 59b28111eabc..299d4bdba109 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -124,7 +124,7 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { - return root->gfp_mask & (__GFP_BITS_MASK & ~GFP_ZONEMASK); + return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, @@ -147,32 +147,32 @@ static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { - root->gfp_mask |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); + root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { - root->gfp_mask &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); + root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { - root->gfp_mask &= (1 << ROOT_TAG_SHIFT) - 1; + root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { - return (__force int)root->gfp_mask & (1 << (tag + ROOT_TAG_SHIFT)); + return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { - return (__force unsigned)root->gfp_mask >> ROOT_TAG_SHIFT; + return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { - return !!(root->gfp_mask & ROOT_IS_IDR); + return !!(root->xa_flags & ROOT_IS_IDR); } /* @@ -291,12 +291,12 @@ static void dump_node(struct radix_tree_node *node, unsigned long index) /* For debug */ static void radix_tree_dump(struct radix_tree_root *root) { - pr_debug("radix root: %p rnode %p tags %x\n", - root, root->rnode, - root->gfp_mask >> ROOT_TAG_SHIFT); - if (!radix_tree_is_internal_node(root->rnode)) + pr_debug("radix root: %p xa_head %p tags %x\n", + root, root->xa_head, + root->xa_flags >> ROOT_TAG_SHIFT); + if (!radix_tree_is_internal_node(root->xa_head)) return; - dump_node(entry_to_node(root->rnode), 0); + dump_node(entry_to_node(root->xa_head), 0); } static void dump_ida_node(void *entry, unsigned long index) @@ -340,9 +340,9 @@ static void dump_ida_node(void *entry, unsigned long index) static void ida_dump(struct ida *ida) { struct radix_tree_root *root = &ida->ida_rt; - pr_debug("ida: %p node %p free %d\n", ida, root->rnode, - root->gfp_mask >> ROOT_TAG_SHIFT); - dump_ida_node(root->rnode, 0); + pr_debug("ida: %p node %p free %d\n", ida, root->xa_head, + root->xa_flags >> ROOT_TAG_SHIFT); + dump_ida_node(root->xa_head, 0); } #endif @@ -576,7 +576,7 @@ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { - struct radix_tree_node *node = rcu_dereference_raw(root->rnode); + struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; @@ -605,7 +605,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; - entry = rcu_dereference_raw(root->rnode); + entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; @@ -633,7 +633,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { - /* Moving an exceptional root->rnode to a node */ + /* Moving an exceptional root->xa_head to a node */ node->exceptional = 1; } /* @@ -642,7 +642,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); - rcu_assign_pointer(root->rnode, entry); + rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: @@ -659,7 +659,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root, bool shrunk = false; for (;;) { - struct radix_tree_node *node = rcu_dereference_raw(root->rnode); + struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) @@ -695,9 +695,9 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root, * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new - * one (root->rnode) as far as dependent read barriers go. + * one (root->xa_head) as far as dependent read barriers go. */ - root->rnode = (void __rcu *)child; + root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); @@ -745,9 +745,8 @@ static bool delete_node(struct radix_tree_root *root, if (node->count) { if (node_to_entry(node) == - rcu_dereference_raw(root->rnode)) - deleted |= radix_tree_shrink(root, - update_node); + rcu_dereference_raw(root->xa_head)) + deleted |= radix_tree_shrink(root, update_node); return deleted; } @@ -762,7 +761,7 @@ static bool delete_node(struct radix_tree_root *root, */ if (!is_idr(root)) root_tag_clear_all(root); - root->rnode = NULL; + root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); @@ -787,7 +786,7 @@ static bool delete_node(struct radix_tree_root *root, * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are - * allocated and @root->rnode is used as a direct slot instead of + * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. @@ -797,7 +796,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; - void __rcu **slot = (void __rcu **)&root->rnode; + void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index | ((1UL << order) - 1); @@ -813,7 +812,7 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, if (error < 0) return error; shift = error; - child = rcu_dereference_raw(root->rnode); + child = rcu_dereference_raw(root->xa_head); } while (shift > order) { @@ -1004,7 +1003,7 @@ EXPORT_SYMBOL(__radix_tree_insert); * tree @root. * * Until there is more than one item in the tree, no nodes are - * allocated and @root->rnode is used as a direct slot instead of + * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, @@ -1017,7 +1016,7 @@ void *__radix_tree_lookup(const struct radix_tree_root *root, restart: parent = NULL; - slot = (void __rcu **)&root->rnode; + slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; @@ -1168,9 +1167,9 @@ void __radix_tree_replace(struct radix_tree_root *root, /* * This function supports replacing exceptional entries and * deleting entries, but that needs accounting against the - * node unless the slot is root->rnode. + * node unless the slot is root->xa_head. */ - WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->rnode) && + WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || exceptional)); replace_slot(slot, item, node, count, exceptional); @@ -1722,7 +1721,7 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, iter->tags = 1; iter->node = NULL; __set_iter_shift(iter, 0); - return (void __rcu **)&root->rnode; + return (void __rcu **)&root->xa_head; } do { @@ -2109,7 +2108,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root, unsigned long max) { struct radix_tree_node *node = NULL, *child; - void __rcu **slot = (void __rcu **)&root->rnode; + void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; @@ -2125,7 +2124,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root, if (error < 0) return ERR_PTR(error); shift = error; - child = rcu_dereference_raw(root->rnode); + child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; @@ -2190,10 +2189,10 @@ void __rcu **idr_get_free(struct radix_tree_root *root, */ void idr_destroy(struct idr *idr) { - struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.rnode); + struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); - idr->idr_rt.rnode = NULL; + idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); diff --git a/lib/xarray.c b/lib/xarray.c new file mode 100644 index 000000000000..862f4c64c754 --- /dev/null +++ b/lib/xarray.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * XArray implementation + * Copyright (c) 2017 Microsoft Corporation + * Author: Matthew Wilcox + */ + +#include +#include + +/* + * Coding conventions in this file: + * + * @xa is used to refer to the entire xarray. + * @xas is the 'xarray operation state'. It may be either a pointer to + * an xa_state, or an xa_state stored on the stack. This is an unfortunate + * ambiguity. + * @index is the index of the entry being operated on + * @mark is an xa_mark_t; a small number indicating one of the mark bits. + * @node refers to an xa_node; usually the primary one being operated on by + * this function. + * @offset is the index into the slots array inside an xa_node. + * @parent refers to the @xa_node closer to the head than @node. + * @entry refers to something stored in a slot in the xarray + */ + +/** + * xa_init_flags() - Initialise an empty XArray with flags. + * @xa: XArray. + * @flags: XA_FLAG values. + * + * If you need to initialise an XArray with special flags (eg you need + * to take the lock from interrupt context), use this function instead + * of xa_init(). + * + * Context: Any context. + */ +void xa_init_flags(struct xarray *xa, gfp_t flags) +{ + spin_lock_init(&xa->xa_lock); + xa->xa_flags = flags; + xa->xa_head = NULL; +} +EXPORT_SYMBOL(xa_init_flags); diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 12adcf9ffe86..c0cf1c79efd5 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder -CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o +CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o @@ -35,6 +35,7 @@ vpath %.c ../../lib $(OFILES): Makefile *.h */*.h generated/map-shift.h \ ../../include/linux/*.h \ ../../include/asm/*.h \ + ../../../include/linux/xarray.h \ ../../../include/linux/radix-tree.h \ ../../../include/linux/idr.h @@ -44,6 +45,8 @@ radix-tree.c: ../../../lib/radix-tree.c idr.c: ../../../lib/idr.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ +xarray.o: ../../../lib/xarray.c + generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ echo "#define XA_CHUNK_SHIFT $(SHIFT)" > \ diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h index 23b8ed52f8c8..03dc8a57eb99 100644 --- a/tools/testing/radix-tree/linux/bug.h +++ b/tools/testing/radix-tree/linux/bug.h @@ -1 +1,2 @@ +#include #include "asm/bug.h" diff --git a/tools/testing/radix-tree/linux/kconfig.h b/tools/testing/radix-tree/linux/kconfig.h new file mode 100644 index 000000000000..6c8675859913 --- /dev/null +++ b/tools/testing/radix-tree/linux/kconfig.h @@ -0,0 +1 @@ +#include "../../../../include/linux/kconfig.h" diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 2b4f4dba1882..080aea450430 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -192,13 +192,13 @@ static void multiorder_shrink(unsigned long index, int order) assert(item_insert_order(&tree, 0, order) == 0); - node = tree.rnode; + node = tree.xa_head; assert(item_insert(&tree, index) == 0); - assert(node != tree.rnode); + assert(node != tree.xa_head); assert(item_delete(&tree, index) != 0); - assert(node == tree.rnode); + assert(node == tree.xa_head); for (i = 0; i < max; i++) { struct item *item = item_lookup(&tree, i); diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 62de66c314b7..70ddf964d51c 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -281,7 +281,7 @@ static int verify_node(struct radix_tree_node *slot, unsigned int tag, void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag) { - struct radix_tree_node *node = root->rnode; + struct radix_tree_node *node = root->xa_head; if (!radix_tree_is_internal_node(node)) return; verify_node(node, tag, !!root_tag_get(root, tag)); @@ -311,13 +311,13 @@ void item_kill_tree(struct radix_tree_root *root) } } assert(radix_tree_gang_lookup(root, (void **)items, 0, 32) == 0); - assert(root->rnode == NULL); + assert(root->xa_head == NULL); } void tree_verify_min_height(struct radix_tree_root *root, int maxindex) { unsigned shift; - struct radix_tree_node *node = root->rnode; + struct radix_tree_node *node = root->xa_head; if (!radix_tree_is_internal_node(node)) { assert(maxindex == 0); return; diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c new file mode 100644 index 000000000000..9bbd667172a7 --- /dev/null +++ b/tools/testing/radix-tree/xarray.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * xarray.c: Userspace shim for XArray test-suite + * Copyright (c) 2018 Matthew Wilcox + */ + +#include "../../../lib/xarray.c" -- cgit v1.2.3-71-gd317 From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 9 Nov 2017 09:23:56 -0500 Subject: xarray: Define struct xa_node This is a direct replacement for struct radix_tree_node. A couple of struct members have changed name, so convert those. Use a #define so that radix tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 29 +++------------------ include/linux/xarray.h | 27 ++++++++++++++++++++ lib/radix-tree.c | 48 +++++++++++++++++------------------ mm/workingset.c | 16 ++++++------ tools/testing/radix-tree/multiorder.c | 30 +++++++++++----------- 5 files changed, 77 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 0b080bd88ab7..15388b7e38b9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -32,6 +32,7 @@ /* Keep unconverted code working */ #define radix_tree_root xarray +#define radix_tree_node xa_node /* * The bottom two bits of the slot determine how the remaining bits in the @@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr) /*** radix-tree API starts here ***/ -#define RADIX_TREE_MAX_TAGS 3 - #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) -#define RADIX_TREE_TAG_LONGS \ - ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_MAX_TAGS XA_MAX_MARKS +#define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) -/* - * @count is the count of every non-NULL element in the ->slots array - * whether that is a value entry, a retry entry, a user pointer, - * a sibling entry or a pointer to the next level of the tree. - * @exceptional is the count of every element in ->slots which is - * either a value entry or a sibling of a value entry. - */ -struct radix_tree_node { - unsigned char shift; /* Bits remaining in each slot */ - unsigned char offset; /* Slot offset in parent */ - unsigned char count; /* Total entry count */ - unsigned char exceptional; /* Exceptional entry count */ - struct radix_tree_node *parent; /* Used when ascending tree */ - struct radix_tree_root *root; /* The tree we belong to */ - union { - struct list_head private_list; /* For tree user */ - struct rcu_head rcu_head; /* Used when freeing node */ - }; - void __rcu *slots[RADIX_TREE_MAP_SIZE]; - unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; -}; - /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9122cf8bf52a..52141dfc5a90 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) +#define XA_MAX_MARKS 3 +#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) + +/* + * @count is the count of every non-NULL element in the ->slots array + * whether that is a value entry, a retry entry, a user pointer, + * a sibling entry or a pointer to the next level of the tree. + * @nr_values is the count of every element in ->slots which is + * either a value entry or a sibling of a value entry. + */ +struct xa_node { + unsigned char shift; /* Bits remaining in each slot */ + unsigned char offset; /* Slot offset in parent */ + unsigned char count; /* Total entry count */ + unsigned char nr_values; /* Value entry count */ + struct xa_node __rcu *parent; /* NULL at top of tree */ + struct xarray *array; /* The array we belong to */ + union { + struct list_head private_list; /* For tree user */ + struct rcu_head rcu_head; /* Used when freeing node */ + }; + void __rcu *slots[XA_CHUNK_SIZE]; + union { + unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; + unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; + }; +}; /* Private */ static inline bool xa_is_node(const void *entry) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 299d4bdba109..8a568cea1237 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -260,11 +260,11 @@ static void dump_node(struct radix_tree_node *node, unsigned long index) { unsigned long i; - pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d exceptional %d\n", + pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n", node, node->offset, index, index | node_maxindex(node), node->parent, node->tags[0][0], node->tags[1][0], node->tags[2][0], - node->shift, node->count, node->exceptional); + node->shift, node->count, node->nr_values); for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { unsigned long first = index | (i << node->shift); @@ -354,7 +354,7 @@ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, - unsigned int count, unsigned int exceptional) + unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; @@ -401,9 +401,9 @@ out: ret->shift = shift; ret->offset = offset; ret->count = count; - ret->exceptional = exceptional; + ret->nr_values = nr_values; ret->parent = parent; - ret->root = root; + ret->array = root; } return ret; } @@ -633,8 +633,8 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { - /* Moving an exceptional root->xa_head to a node */ - node->exceptional = 1; + /* Moving a value entry root->xa_head to a node */ + node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need @@ -928,12 +928,12 @@ static inline int insert_entries(struct radix_tree_node *node, if (xa_is_node(old)) radix_tree_free_nodes(old); if (xa_is_value(old)) - node->exceptional--; + node->nr_values--; } if (node) { node->count += n; if (xa_is_value(item)) - node->exceptional += n; + node->nr_values += n; } return n; } @@ -947,7 +947,7 @@ static inline int insert_entries(struct radix_tree_node *node, if (node) { node->count++; if (xa_is_value(item)) - node->exceptional++; + node->nr_values++; } return 1; } @@ -1083,7 +1083,7 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) EXPORT_SYMBOL(radix_tree_lookup); static inline void replace_sibling_entries(struct radix_tree_node *node, - void __rcu **slot, int count, int exceptional) + void __rcu **slot, int count, int values) { #ifdef CONFIG_RADIX_TREE_MULTIORDER unsigned offset = get_slot_offset(node, slot); @@ -1096,18 +1096,18 @@ static inline void replace_sibling_entries(struct radix_tree_node *node, node->slots[offset] = NULL; node->count--; } - node->exceptional += exceptional; + node->nr_values += values; } #endif } static void replace_slot(void __rcu **slot, void *item, - struct radix_tree_node *node, int count, int exceptional) + struct radix_tree_node *node, int count, int values) { - if (node && (count || exceptional)) { + if (node && (count || values)) { node->count += count; - node->exceptional += exceptional; - replace_sibling_entries(node, slot, count, exceptional); + node->nr_values += values; + replace_sibling_entries(node, slot, count, values); } rcu_assign_pointer(*slot, item); @@ -1161,17 +1161,17 @@ void __radix_tree_replace(struct radix_tree_root *root, radix_tree_update_node_t update_node) { void *old = rcu_dereference_raw(*slot); - int exceptional = !!xa_is_value(item) - !!xa_is_value(old); + int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* - * This function supports replacing exceptional entries and + * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && - (count || exceptional)); - replace_slot(slot, item, node, count, exceptional); + (count || values)); + replace_slot(slot, item, node, count, values); if (!node) return; @@ -1193,7 +1193,7 @@ void __radix_tree_replace(struct radix_tree_root *root, * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), - * regular entries, and exceptional entries, as that requires accounting + * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). @@ -1301,7 +1301,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY); } rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY); - parent->exceptional -= (end - offset); + parent->nr_values -= (end - offset); if (order == parent->shift) return 0; @@ -1961,7 +1961,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); - int exceptional = xa_is_value(old) ? -1 : 0; + int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; @@ -1971,7 +1971,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); - replace_slot(slot, NULL, node, -1, exceptional); + replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node, NULL); } diff --git a/mm/workingset.c b/mm/workingset.c index bb109b3afac2..c201cbb8c00f 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -349,7 +349,7 @@ void workingset_update_node(struct radix_tree_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ - if (node->count && node->count == node->exceptional) { + if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) list_lru_add(&shadow_nodes, &node->private_list); } else { @@ -428,8 +428,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * to reclaim, take the node off-LRU, and drop the lru_lock. */ - node = container_of(item, struct radix_tree_node, private_list); - mapping = container_of(node->root, struct address_space, i_pages); + node = container_of(item, struct xa_node, private_list); + mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { @@ -446,25 +446,25 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ - if (WARN_ON_ONCE(!node->exceptional)) + if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; - if (WARN_ON_ONCE(node->count != node->exceptional)) + if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) goto out_invalid; - if (WARN_ON_ONCE(!node->exceptional)) + if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(!mapping->nrexceptional)) goto out_invalid; node->slots[i] = NULL; - node->exceptional--; + node->nr_values--; node->count--; mapping->nrexceptional--; } } - if (WARN_ON_ONCE(node->exceptional)) + if (WARN_ON_ONCE(node->nr_values)) goto out_invalid; inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); __radix_tree_delete_node(&mapping->i_pages, node, diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 080aea450430..60786fa55302 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -393,7 +393,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) radix_tree_insert(&tree, 1 << order2, xa_mk_value(5)); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == xa_mk_value(5)); - assert(node->exceptional == 1); + assert(node->nr_values == 1); item2 = radix_tree_lookup(&tree, 0); free(item2); @@ -401,7 +401,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) radix_tree_join(&tree, 0, order1, item1); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == item1); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } @@ -409,7 +409,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) * This test revealed an accounting bug for value entries at one point. * Nodes were being freed back into the pool with an elevated exception count * by radix_tree_join() and then radix_tree_split() was failing to zero the - * count of exceptional entries. + * count of value entries. */ static void multiorder_join3(unsigned int order) { @@ -433,7 +433,7 @@ static void multiorder_join3(unsigned int order) } __radix_tree_lookup(&tree, 0, &node, NULL); - assert(node->exceptional == node->count); + assert(node->nr_values == node->count); item_kill_tree(&tree); } @@ -520,7 +520,7 @@ static void __multiorder_split2(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -530,7 +530,7 @@ static void __multiorder_split2(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item != xa_mk_value(5)); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } @@ -547,7 +547,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -556,7 +556,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(7)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); item_kill_tree(&tree); @@ -564,7 +564,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -577,13 +577,13 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); assert(item == xa_mk_value(7)); - assert(node->count == node->exceptional); + assert(node->count == node->nr_values); do { node = node->parent; if (!node) break; assert(node->count == 1); - assert(node->exceptional == 0); + assert(node->nr_values == 0); } while (1); item_kill_tree(&tree); @@ -611,15 +611,15 @@ static void multiorder_account(void) __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 0, &node, NULL); - assert(node->count == node->exceptional * 2); + assert(node->count == node->nr_values * 2); radix_tree_delete(&tree, 1 << 5); - assert(node->exceptional == 0); + assert(node->nr_values == 0); __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 1 << 5, &node, &slot); - assert(node->count == node->exceptional * 2); + assert(node->count == node->nr_values * 2); __radix_tree_replace(&tree, node, slot, NULL, NULL); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } -- cgit v1.2.3-71-gd317 From ad3d6c7263e368abdc151e1cc13dc78aa39cc7a7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 7 Nov 2017 14:57:46 -0500 Subject: xarray: Add XArray load operation The xa_load function brings with it a lot of infrastructure; xa_empty(), xa_is_err(), and large chunks of the XArray advanced API that are used to implement xa_load. As the test-suite demonstrates, it is possible to use the XArray functions on a radix tree. The radix tree functions depend on the GFP flags being stored in the root of the tree, so it's not possible to use the radix tree functions on an XArray. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 336 ++++++++++++++++++++++++++++++ lib/Kconfig.debug | 3 + lib/Makefile | 1 + lib/radix-tree.c | 43 ---- lib/test_xarray.c | 87 ++++++++ lib/xarray.c | 195 +++++++++++++++++ tools/include/linux/kernel.h | 1 + tools/testing/radix-tree/.gitignore | 1 + tools/testing/radix-tree/Makefile | 6 +- tools/testing/radix-tree/linux/kernel.h | 1 + tools/testing/radix-tree/linux/rcupdate.h | 2 + tools/testing/radix-tree/main.c | 1 + tools/testing/radix-tree/test.h | 1 + tools/testing/radix-tree/xarray.c | 28 +++ 14 files changed, 661 insertions(+), 45 deletions(-) create mode 100644 lib/test_xarray.c (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52141dfc5a90..a0df8217068c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include @@ -30,6 +32,10 @@ * * 0-62: Sibling entries * 256: Retry entry + * + * Errors are also represented as internal entries, but use the negative + * space (-4094 to -2). They're never stored in the slots array; only + * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) @@ -155,6 +161,42 @@ static inline bool xa_is_internal(const void *entry) return ((unsigned long)entry & 3) == 2; } +/** + * xa_is_err() - Report whether an XArray operation returned an error + * @entry: Result from calling an XArray function + * + * If an XArray operation cannot complete an operation, it will return + * a special value indicating an error. This function tells you + * whether an error occurred; xa_err() tells you which error occurred. + * + * Context: Any context. + * Return: %true if the entry indicates an error. + */ +static inline bool xa_is_err(const void *entry) +{ + return unlikely(xa_is_internal(entry)); +} + +/** + * xa_err() - Turn an XArray result into an errno. + * @entry: Result from calling an XArray function. + * + * If an XArray operation cannot complete an operation, it will return + * a special pointer value which encodes an errno. This function extracts + * the errno from the pointer value, or returns 0 if the pointer does not + * represent an errno. + * + * Context: Any context. + * Return: A negative errno or 0. + */ +static inline int xa_err(void *entry) +{ + /* xa_to_internal() would not do sign extension. */ + if (xa_is_err(entry)) + return (long)entry >> 2; + return 0; +} + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -209,6 +251,7 @@ struct xarray { #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) void xa_init_flags(struct xarray *, gfp_t flags); +void *xa_load(struct xarray *, unsigned long index); /** * xa_init() - Initialise an empty XArray. @@ -223,6 +266,18 @@ static inline void xa_init(struct xarray *xa) xa_init_flags(xa, 0); } +/** + * xa_empty() - Determine if an array has any present entries. + * @xa: XArray. + * + * Context: Any context. + * Return: %true if the array contains only NULL pointers. + */ +static inline bool xa_empty(const struct xarray *xa) +{ + return xa->xa_head == NULL; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -280,6 +335,65 @@ struct xa_node { }; }; +void xa_dump(const struct xarray *); +void xa_dump_node(const struct xa_node *); + +#ifdef XA_DEBUG +#define XA_BUG_ON(xa, x) do { \ + if (x) { \ + xa_dump(xa); \ + BUG(); \ + } \ + } while (0) +#define XA_NODE_BUG_ON(node, x) do { \ + if (x) { \ + if (node) xa_dump_node(node); \ + BUG(); \ + } \ + } while (0) +#else +#define XA_BUG_ON(xa, x) do { } while (0) +#define XA_NODE_BUG_ON(node, x) do { } while (0) +#endif + +/* Private */ +static inline void *xa_head(const struct xarray *xa) +{ + return rcu_dereference_check(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_head_locked(const struct xarray *xa) +{ + return rcu_dereference_protected(xa->xa_head, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_check(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline void *xa_entry_locked(const struct xarray *xa, + const struct xa_node *node, unsigned int offset) +{ + XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); + return rcu_dereference_protected(node->slots[offset], + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_to_node(const void *entry) +{ + return (struct xa_node *)((unsigned long)entry - 2); +} + /* Private */ static inline bool xa_is_node(const void *entry) { @@ -312,4 +426,226 @@ static inline bool xa_is_sibling(const void *entry) #define XA_RETRY_ENTRY xa_mk_internal(256) +/** + * xa_is_retry() - Is the entry a retry entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a retry entry. + */ +static inline bool xa_is_retry(const void *entry) +{ + return unlikely(entry == XA_RETRY_ENTRY); +} + +/** + * typedef xa_update_node_t - A callback function from the XArray. + * @node: The node which is being processed + * + * This function is called every time the XArray updates the count of + * present and value entries in a node. It allows advanced users to + * maintain the private_list in the node. + * + * Context: The xa_lock is held and interrupts may be disabled. + * Implementations should not drop the xa_lock, nor re-enable + * interrupts. + */ +typedef void (*xa_update_node_t)(struct xa_node *node); + +/* + * The xa_state is opaque to its users. It contains various different pieces + * of state involved in the current operation on the XArray. It should be + * declared on the stack and passed between the various internal routines. + * The various elements in it should not be accessed directly, but only + * through the provided accessor functions. The below documentation is for + * the benefit of those working on the code, not for users of the XArray. + * + * @xa_node usually points to the xa_node containing the slot we're operating + * on (and @xa_offset is the offset in the slots array). If there is a + * single entry in the array at index 0, there are no allocated xa_nodes to + * point to, and so we store %NULL in @xa_node. @xa_node is set to + * the value %XAS_RESTART if the xa_state is not walked to the correct + * position in the tree of nodes for this operation. If an error occurs + * during an operation, it is set to an %XAS_ERROR value. If we run off the + * end of the allocated nodes, it is set to %XAS_BOUNDS. + */ +struct xa_state { + struct xarray *xa; + unsigned long xa_index; + unsigned char xa_shift; + unsigned char xa_sibs; + unsigned char xa_offset; + unsigned char xa_pad; /* Helps gcc generate better code */ + struct xa_node *xa_node; + struct xa_node *xa_alloc; + xa_update_node_t xa_update; +}; + +/* + * We encode errnos in the xas->xa_node. If an error has happened, we need to + * drop the lock to fix it, and once we've done so the xa_state is invalid. + */ +#define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) +#define XAS_BOUNDS ((struct xa_node *)1UL) +#define XAS_RESTART ((struct xa_node *)3UL) + +#define __XA_STATE(array, index, shift, sibs) { \ + .xa = array, \ + .xa_index = index, \ + .xa_shift = shift, \ + .xa_sibs = sibs, \ + .xa_offset = 0, \ + .xa_pad = 0, \ + .xa_node = XAS_RESTART, \ + .xa_alloc = NULL, \ + .xa_update = NULL \ +} + +/** + * XA_STATE() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * + * Declare and initialise an xa_state on the stack. + */ +#define XA_STATE(name, array, index) \ + struct xa_state name = __XA_STATE(array, index, 0, 0) + +/** + * XA_STATE_ORDER() - Declare an XArray operation state. + * @name: Name of this operation state (usually xas). + * @array: Array to operate on. + * @index: Initial index of interest. + * @order: Order of entry. + * + * Declare and initialise an xa_state on the stack. This variant of + * XA_STATE() allows you to specify the 'order' of the element you + * want to operate on.` + */ +#define XA_STATE_ORDER(name, array, index, order) \ + struct xa_state name = __XA_STATE(array, \ + (index >> order) << order, \ + order - (order % XA_CHUNK_SHIFT), \ + (1U << (order % XA_CHUNK_SHIFT)) - 1) + +#define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) +#define xas_trylock(xas) xa_trylock((xas)->xa) +#define xas_lock(xas) xa_lock((xas)->xa) +#define xas_unlock(xas) xa_unlock((xas)->xa) +#define xas_lock_bh(xas) xa_lock_bh((xas)->xa) +#define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) +#define xas_lock_irq(xas) xa_lock_irq((xas)->xa) +#define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) +#define xas_lock_irqsave(xas, flags) \ + xa_lock_irqsave((xas)->xa, flags) +#define xas_unlock_irqrestore(xas, flags) \ + xa_unlock_irqrestore((xas)->xa, flags) + +/** + * xas_error() - Return an errno stored in the xa_state. + * @xas: XArray operation state. + * + * Return: 0 if no error has been noted. A negative errno if one has. + */ +static inline int xas_error(const struct xa_state *xas) +{ + return xa_err(xas->xa_node); +} + +/** + * xas_set_err() - Note an error in the xa_state. + * @xas: XArray operation state. + * @err: Negative error number. + * + * Only call this function with a negative @err; zero or positive errors + * will probably not behave the way you think they should. If you want + * to clear the error from an xa_state, use xas_reset(). + */ +static inline void xas_set_err(struct xa_state *xas, long err) +{ + xas->xa_node = XA_ERROR(err); +} + +/** + * xas_invalid() - Is the xas in a retry or error state? + * @xas: XArray operation state. + * + * Return: %true if the xas cannot be used for operations. + */ +static inline bool xas_invalid(const struct xa_state *xas) +{ + return (unsigned long)xas->xa_node & 3; +} + +/** + * xas_valid() - Is the xas a valid cursor into the array? + * @xas: XArray operation state. + * + * Return: %true if the xas can be used for operations. + */ +static inline bool xas_valid(const struct xa_state *xas) +{ + return !xas_invalid(xas); +} + +/** + * xas_reset() - Reset an XArray operation state. + * @xas: XArray operation state. + * + * Resets the error or walk state of the @xas so future walks of the + * array will start from the root. Use this if you have dropped the + * xarray lock and want to reuse the xa_state. + * + * Context: Any context. + */ +static inline void xas_reset(struct xa_state *xas) +{ + xas->xa_node = XAS_RESTART; +} + +/** + * xas_retry() - Retry the operation if appropriate. + * @xas: XArray operation state. + * @entry: Entry from xarray. + * + * The advanced functions may sometimes return an internal entry, such as + * a retry entry or a zero entry. This function sets up the @xas to restart + * the walk from the head of the array if needed. + * + * Context: Any context. + * Return: true if the operation needs to be retried. + */ +static inline bool xas_retry(struct xa_state *xas, const void *entry) +{ + if (!xa_is_retry(entry)) + return false; + xas_reset(xas); + return true; +} + +void *xas_load(struct xa_state *); + +/** + * xas_reload() - Refetch an entry from the xarray. + * @xas: XArray operation state. + * + * Use this function to check that a previously loaded entry still has + * the same value. This is useful for the lockless pagecache lookup where + * we walk the array with only the RCU lock to protect us, lock the page, + * then check that the page hasn't moved since we looked it up. + * + * The caller guarantees that @xas is still valid. If it may be in an + * error or restart state, call xas_load() instead. + * + * Return: The entry at this location in the xarray. + */ +static inline void *xas_reload(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (node) + return xa_entry(xas->xa, node, xas->xa_offset); + return xa_head(xas->xa); +} + #endif /* _LINUX_XARRAY_H */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4966c4fbe7f7..091155e12422 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1813,6 +1813,9 @@ config TEST_BITFIELD config TEST_UUID tristate "Test functions located in the uuid module at runtime" +config TEST_XARRAY + tristate "Test the XArray code at runtime" + config TEST_OVERFLOW tristate "Test check_*_overflow() functions at runtime" diff --git a/lib/Makefile b/lib/Makefile index 057385f1f145..e6f809556af5 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -68,6 +68,7 @@ obj-$(CONFIG_TEST_PRINTF) += test_printf.o obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o obj-$(CONFIG_TEST_UUID) += test_uuid.o +obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_PARMAN) += test_parman.o obj-$(CONFIG_TEST_KMOD) += test_kmod.o obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8a568cea1237..b8e961428484 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -256,49 +256,6 @@ static unsigned long next_index(unsigned long index, } #ifndef __KERNEL__ -static void dump_node(struct radix_tree_node *node, unsigned long index) -{ - unsigned long i; - - pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n", - node, node->offset, index, index | node_maxindex(node), - node->parent, - node->tags[0][0], node->tags[1][0], node->tags[2][0], - node->shift, node->count, node->nr_values); - - for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { - unsigned long first = index | (i << node->shift); - unsigned long last = first | ((1UL << node->shift) - 1); - void *entry = node->slots[i]; - if (!entry) - continue; - if (entry == RADIX_TREE_RETRY) { - pr_debug("radix retry offset %ld indices %lu-%lu parent %p\n", - i, first, last, node); - } else if (!radix_tree_is_internal_node(entry)) { - pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n", - entry, i, first, last, node); - } else if (xa_is_sibling(entry)) { - pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n", - entry, i, first, last, node, - node->slots[xa_to_sibling(entry)]); - } else { - dump_node(entry_to_node(entry), first); - } - } -} - -/* For debug */ -static void radix_tree_dump(struct radix_tree_root *root) -{ - pr_debug("radix root: %p xa_head %p tags %x\n", - root, root->xa_head, - root->xa_flags >> ROOT_TAG_SHIFT); - if (!radix_tree_is_internal_node(root->xa_head)) - return; - dump_node(entry_to_node(root->xa_head), 0); -} - static void dump_ida_node(void *entry, unsigned long index) { unsigned long i; diff --git a/lib/test_xarray.c b/lib/test_xarray.c new file mode 100644 index 000000000000..a7248b87617f --- /dev/null +++ b/lib/test_xarray.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * test_xarray.c: Test the XArray API + * Copyright (c) 2017-2018 Microsoft Corporation + * Author: Matthew Wilcox + */ + +#include +#include + +static unsigned int tests_run; +static unsigned int tests_passed; + +#ifndef XA_DEBUG +# ifdef __KERNEL__ +void xa_dump(const struct xarray *xa) { } +# endif +#undef XA_BUG_ON +#define XA_BUG_ON(xa, x) do { \ + tests_run++; \ + if (x) { \ + printk("BUG at %s:%d\n", __func__, __LINE__); \ + xa_dump(xa); \ + dump_stack(); \ + } else { \ + tests_passed++; \ + } \ +} while (0) +#endif + +static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + radix_tree_insert(xa, index, xa_mk_value(index)); + return NULL; +} + +static void xa_erase_index(struct xarray *xa, unsigned long index) +{ + radix_tree_delete(xa, index); +} + +static noinline void check_xa_load(struct xarray *xa) +{ + unsigned long i, j; + + for (i = 0; i < 1024; i++) { + for (j = 0; j < 1024; j++) { + void *entry = xa_load(xa, j); + if (j < i) + XA_BUG_ON(xa, xa_to_value(entry) != j); + else + XA_BUG_ON(xa, entry); + } + XA_BUG_ON(xa, xa_store_index(xa, i, GFP_KERNEL) != NULL); + } + + for (i = 0; i < 1024; i++) { + for (j = 0; j < 1024; j++) { + void *entry = xa_load(xa, j); + if (j >= i) + XA_BUG_ON(xa, xa_to_value(entry) != j); + else + XA_BUG_ON(xa, entry); + } + xa_erase_index(xa, i); + } + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static RADIX_TREE(array, GFP_KERNEL); + +static int xarray_checks(void) +{ + check_xa_load(&array); + + printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); + return (tests_run == tests_passed) ? 0 : -EINVAL; +} + +static void xarray_exit(void) +{ +} + +module_init(xarray_checks); +module_exit(xarray_exit); +MODULE_AUTHOR("Matthew Wilcox "); +MODULE_LICENSE("GPL"); diff --git a/lib/xarray.c b/lib/xarray.c index 862f4c64c754..19cfcbc69a68 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -24,6 +24,100 @@ * @entry refers to something stored in a slot in the xarray */ +/* extracts the offset within this node from the index */ +static unsigned int get_offset(unsigned long index, struct xa_node *node) +{ + return (index >> node->shift) & XA_CHUNK_MASK; +} + +/* move the index either forwards (find) or backwards (sibling slot) */ +static void xas_move_index(struct xa_state *xas, unsigned long offset) +{ + unsigned int shift = xas->xa_node->shift; + xas->xa_index &= ~XA_CHUNK_MASK << shift; + xas->xa_index += offset << shift; +} + +static void *set_bounds(struct xa_state *xas) +{ + xas->xa_node = XAS_BOUNDS; + return NULL; +} + +/* + * Starts a walk. If the @xas is already valid, we assume that it's on + * the right path and just return where we've got to. If we're in an + * error state, return NULL. If the index is outside the current scope + * of the xarray, return NULL without changing @xas->xa_node. Otherwise + * set @xas->xa_node to NULL and return the current head of the array. + */ +static void *xas_start(struct xa_state *xas) +{ + void *entry; + + if (xas_valid(xas)) + return xas_reload(xas); + if (xas_error(xas)) + return NULL; + + entry = xa_head(xas->xa); + if (!xa_is_node(entry)) { + if (xas->xa_index) + return set_bounds(xas); + } else { + if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) + return set_bounds(xas); + } + + xas->xa_node = NULL; + return entry; +} + +static void *xas_descend(struct xa_state *xas, struct xa_node *node) +{ + unsigned int offset = get_offset(xas->xa_index, node); + void *entry = xa_entry(xas->xa, node, offset); + + xas->xa_node = node; + if (xa_is_sibling(entry)) { + offset = xa_to_sibling(entry); + entry = xa_entry(xas->xa, node, offset); + } + + xas->xa_offset = offset; + return entry; +} + +/** + * xas_load() - Load an entry from the XArray (advanced). + * @xas: XArray operation state. + * + * Usually walks the @xas to the appropriate state to load the entry + * stored at xa_index. However, it will do nothing and return %NULL if + * @xas is in an error state. xas_load() will never expand the tree. + * + * If the xa_state is set up to operate on a multi-index entry, xas_load() + * may return %NULL or an internal entry, even if there are entries + * present within the range specified by @xas. + * + * Context: Any context. The caller should hold the xa_lock or the RCU lock. + * Return: Usually an entry in the XArray, but see description for exceptions. + */ +void *xas_load(struct xa_state *xas) +{ + void *entry = xas_start(xas); + + while (xa_is_node(entry)) { + struct xa_node *node = xa_to_node(entry); + + if (xas->xa_shift > node->shift) + break; + entry = xas_descend(xas, node); + } + return entry; +} +EXPORT_SYMBOL_GPL(xas_load); + /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. @@ -42,3 +136,104 @@ void xa_init_flags(struct xarray *xa, gfp_t flags) xa->xa_head = NULL; } EXPORT_SYMBOL(xa_init_flags); + +/** + * xa_load() - Load an entry from an XArray. + * @xa: XArray. + * @index: index into array. + * + * Context: Any context. Takes and releases the RCU lock. + * Return: The entry at @index in @xa. + */ +void *xa_load(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + void *entry; + + rcu_read_lock(); + do { + entry = xas_load(&xas); + } while (xas_retry(&xas, entry)); + rcu_read_unlock(); + + return entry; +} +EXPORT_SYMBOL(xa_load); + +#ifdef XA_DEBUG +void xa_dump_node(const struct xa_node *node) +{ + unsigned i, j; + + if (!node) + return; + if ((unsigned long)node & 3) { + pr_cont("node %px\n", node); + return; + } + + pr_cont("node %px %s %d parent %px shift %d count %d values %d " + "array %px list %px %px marks", + node, node->parent ? "offset" : "max", node->offset, + node->parent, node->shift, node->count, node->nr_values, + node->array, node->private_list.prev, node->private_list.next); + for (i = 0; i < XA_MAX_MARKS; i++) + for (j = 0; j < XA_MARK_LONGS; j++) + pr_cont(" %lx", node->marks[i][j]); + pr_cont("\n"); +} + +void xa_dump_index(unsigned long index, unsigned int shift) +{ + if (!shift) + pr_info("%lu: ", index); + else if (shift >= BITS_PER_LONG) + pr_info("0-%lu: ", ~0UL); + else + pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); +} + +void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) +{ + if (!entry) + return; + + xa_dump_index(index, shift); + + if (xa_is_node(entry)) { + if (shift == 0) { + pr_cont("%px\n", entry); + } else { + unsigned long i; + struct xa_node *node = xa_to_node(entry); + xa_dump_node(node); + for (i = 0; i < XA_CHUNK_SIZE; i++) + xa_dump_entry(node->slots[i], + index + (i << node->shift), node->shift); + } + } else if (xa_is_value(entry)) + pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), + xa_to_value(entry), entry); + else if (!xa_is_internal(entry)) + pr_cont("%px\n", entry); + else if (xa_is_retry(entry)) + pr_cont("retry (%ld)\n", xa_to_internal(entry)); + else if (xa_is_sibling(entry)) + pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); + else + pr_cont("UNKNOWN ENTRY (%px)\n", entry); +} + +void xa_dump(const struct xarray *xa) +{ + void *entry = xa->xa_head; + unsigned int shift = 0; + + pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, + xa->xa_flags, radix_tree_tagged(xa, 0), + radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2)); + if (xa_is_node(entry)) + shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; + xa_dump_entry(entry, 0, shift); +} +#endif diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 0ad884452c5c..6935ef94e77a 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -70,6 +70,7 @@ #define BUG_ON(cond) assert(!(cond)) #endif #endif +#define BUG() BUG_ON(1) #if __BYTE_ORDER == __BIG_ENDIAN #define cpu_to_le16 bswap_16 diff --git a/tools/testing/radix-tree/.gitignore b/tools/testing/radix-tree/.gitignore index d4706c0ffceb..3834899b6693 100644 --- a/tools/testing/radix-tree/.gitignore +++ b/tools/testing/radix-tree/.gitignore @@ -4,3 +4,4 @@ idr-test main multiorder radix-tree.c +xarray diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index c0cf1c79efd5..1379f1d78d0b 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -4,7 +4,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ -fsanitize=undefined LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu -TARGETS = main idr-test multiorder +TARGETS = main idr-test multiorder xarray CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o @@ -25,6 +25,8 @@ main: $(OFILES) idr-test.o: ../../../lib/test_ida.c idr-test: idr-test.o $(CORE_OFILES) +xarray: $(CORE_OFILES) + multiorder: multiorder.o $(CORE_OFILES) clean: @@ -45,7 +47,7 @@ radix-tree.c: ../../../lib/radix-tree.c idr.c: ../../../lib/idr.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ -xarray.o: ../../../lib/xarray.c +xarray.o: ../../../lib/xarray.c ../../../lib/test_xarray.c generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index 426f32f28547..5d06ac75a14d 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -14,6 +14,7 @@ #include "../../../include/linux/kconfig.h" #define printk printf +#define pr_info printk #define pr_debug printk #define pr_cont printk diff --git a/tools/testing/radix-tree/linux/rcupdate.h b/tools/testing/radix-tree/linux/rcupdate.h index 73ed33658203..fd280b070fdb 100644 --- a/tools/testing/radix-tree/linux/rcupdate.h +++ b/tools/testing/radix-tree/linux/rcupdate.h @@ -6,5 +6,7 @@ #define rcu_dereference_raw(p) rcu_dereference(p) #define rcu_dereference_protected(p, cond) rcu_dereference(p) +#define rcu_dereference_check(p, cond) rcu_dereference(p) +#define RCU_INIT_POINTER(p, v) (p) = (v) #endif diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index b741686e53d6..09deaf4f0959 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -365,6 +365,7 @@ int main(int argc, char **argv) rcu_register_thread(); radix_tree_init(); + xarray_tests(); regression1_test(); regression2_test(); regression3_test(); diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 92d901eacf49..e3dc7a16f09b 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -34,6 +34,7 @@ int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *, unsigned iftag, unsigned thentag); unsigned long find_item(struct radix_tree_root *, void *item); +void xarray_tests(void); void tag_check(void); void multiorder_checks(void); void iteration_test(unsigned order, unsigned duration); diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c index 9bbd667172a7..e61e43efe463 100644 --- a/tools/testing/radix-tree/xarray.c +++ b/tools/testing/radix-tree/xarray.c @@ -4,4 +4,32 @@ * Copyright (c) 2018 Matthew Wilcox */ +#define XA_DEBUG +#include "test.h" + +#define module_init(x) +#define module_exit(x) +#define MODULE_AUTHOR(x) +#define MODULE_LICENSE(x) +#define dump_stack() assert(0) + #include "../../../lib/xarray.c" +#undef XA_DEBUG +#include "../../../lib/test_xarray.c" + +void xarray_tests(void) +{ + xarray_checks(); + xarray_exit(); +} + +int __weak main(void) +{ + radix_tree_init(); + xarray_tests(); + radix_tree_cpu_dead(1); + rcu_barrier(); + if (nr_allocated) + printf("nr_allocated = %d\n", nr_allocated); + return 0; +} -- cgit v1.2.3-71-gd317 From 9b89a0355144685a787b0dc5bcf7bdd6f2d02968 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 09:34:31 -0500 Subject: xarray: Add XArray marks XArray marks are like the radix tree tags, only slightly more strongly typed. They are renamed in order to distinguish them from tagged pointers. This commit adds the basic get/set/clear operations. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 63 +++++++ lib/test_xarray.c | 34 ++++ lib/xarray.c | 232 +++++++++++++++++++++++++- tools/include/asm-generic/bitops.h | 1 + tools/include/asm-generic/bitops/atomic.h | 9 - tools/include/asm-generic/bitops/non-atomic.h | 109 ++++++++++++ tools/include/linux/spinlock.h | 10 +- 7 files changed, 445 insertions(+), 13 deletions(-) create mode 100644 tools/include/asm-generic/bitops/non-atomic.h (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a0df8217068c..2de504ae9ba4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -197,6 +198,20 @@ static inline int xa_err(void *entry) return 0; } +typedef unsigned __bitwise xa_mark_t; +#define XA_MARK_0 ((__force xa_mark_t)0U) +#define XA_MARK_1 ((__force xa_mark_t)1U) +#define XA_MARK_2 ((__force xa_mark_t)2U) +#define XA_PRESENT ((__force xa_mark_t)8U) +#define XA_MARK_MAX XA_MARK_2 + +/* + * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, + * and we remain compatible with that. + */ +#define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ + (__force unsigned)(mark))) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -252,6 +267,9 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_init() - Initialise an empty XArray. @@ -278,6 +296,19 @@ static inline bool xa_empty(const struct xarray *xa) return xa->xa_head == NULL; } +/** + * xa_marked() - Inquire whether any entry in this array has a mark set + * @xa: Array + * @mark: Mark value + * + * Context: Any context. + * Return: %true if any entry has this mark set. + */ +static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) +{ + return xa->xa_flags & XA_FLAGS_MARK(mark); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -290,6 +321,12 @@ static inline bool xa_empty(const struct xarray *xa) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +/* + * Versions of the normal API which require the caller to hold the xa_lock. + */ +void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); +void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -388,6 +425,22 @@ static inline void *xa_entry_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline struct xa_node *xa_parent(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_check(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + +/* Private */ +static inline struct xa_node *xa_parent_locked(const struct xarray *xa, + const struct xa_node *node) +{ + return rcu_dereference_protected(node->parent, + lockdep_is_held(&xa->xa_lock)); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -588,6 +641,12 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/* True if the pointer is something other than a node */ +static inline bool xas_not_node(struct xa_node *node) +{ + return ((unsigned long)node & 3) || !node; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -625,6 +684,10 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); +bool xas_get_mark(const struct xa_state *, xa_mark_t); +void xas_set_mark(const struct xa_state *, xa_mark_t); +void xas_clear_mark(const struct xa_state *, xa_mark_t); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. diff --git a/lib/test_xarray.c b/lib/test_xarray.c index a7248b87617f..f8b0e9ba80a4 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -67,11 +67,45 @@ static noinline void check_xa_load(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) +{ + /* NULL elements have no marks set */ + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); + xa_set_mark(xa, index, XA_MARK_0); + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); + + /* Storing a pointer will not make a mark appear */ + XA_BUG_ON(xa, xa_store_index(xa, index, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); + xa_set_mark(xa, index, XA_MARK_0); + XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0)); + + /* Setting one mark will not set another mark */ + XA_BUG_ON(xa, xa_get_mark(xa, index + 1, XA_MARK_0)); + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_1)); + + /* Storing NULL clears marks, and they can't be set again */ + xa_erase_index(xa, index); + XA_BUG_ON(xa, !xa_empty(xa)); + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); + xa_set_mark(xa, index, XA_MARK_0); + XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); +} + +static noinline void check_xa_mark(struct xarray *xa) +{ + unsigned long index; + + for (index = 0; index < 16384; index += 4) + check_xa_mark_1(xa, index); +} + static RADIX_TREE(array, GFP_KERNEL); static int xarray_checks(void) { check_xa_load(&array); + check_xa_mark(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index 19cfcbc69a68..aa86c47e532f 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -5,6 +5,7 @@ * Author: Matthew Wilcox */ +#include #include #include @@ -24,6 +25,48 @@ * @entry refers to something stored in a slot in the xarray */ +static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) +{ + if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) + xa->xa_flags |= XA_FLAGS_MARK(mark); +} + +static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) +{ + if (xa->xa_flags & XA_FLAGS_MARK(mark)) + xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); +} + +static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) +{ + return node->marks[(__force unsigned)mark]; +} + +static inline bool node_get_mark(struct xa_node *node, + unsigned int offset, xa_mark_t mark) +{ + return test_bit(offset, node_marks(node, mark)); +} + +/* returns true if the bit was set */ +static inline bool node_set_mark(struct xa_node *node, unsigned int offset, + xa_mark_t mark) +{ + return __test_and_set_bit(offset, node_marks(node, mark)); +} + +/* returns true if the bit was set */ +static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, + xa_mark_t mark) +{ + return __test_and_clear_bit(offset, node_marks(node, mark)); +} + +static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) +{ + return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); +} + /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { @@ -118,6 +161,85 @@ void *xas_load(struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_load); +/** + * xas_get_mark() - Returns the state of this mark. + * @xas: XArray operation state. + * @mark: Mark number. + * + * Return: true if the mark is set, false if the mark is clear or @xas + * is in an error state. + */ +bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) +{ + if (xas_invalid(xas)) + return false; + if (!xas->xa_node) + return xa_marked(xas->xa, mark); + return node_get_mark(xas->xa_node, xas->xa_offset, mark); +} +EXPORT_SYMBOL_GPL(xas_get_mark); + +/** + * xas_set_mark() - Sets the mark on this entry and its parents. + * @xas: XArray operation state. + * @mark: Mark number. + * + * Sets the specified mark on this entry, and walks up the tree setting it + * on all the ancestor entries. Does nothing if @xas has not been walked to + * an entry, or is in an error state. + */ +void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) +{ + struct xa_node *node = xas->xa_node; + unsigned int offset = xas->xa_offset; + + if (xas_invalid(xas)) + return; + + while (node) { + if (node_set_mark(node, offset, mark)) + return; + offset = node->offset; + node = xa_parent_locked(xas->xa, node); + } + + if (!xa_marked(xas->xa, mark)) + xa_mark_set(xas->xa, mark); +} +EXPORT_SYMBOL_GPL(xas_set_mark); + +/** + * xas_clear_mark() - Clears the mark on this entry and its parents. + * @xas: XArray operation state. + * @mark: Mark number. + * + * Clears the specified mark on this entry, and walks back to the head + * attempting to clear it on all the ancestor entries. Does nothing if + * @xas has not been walked to an entry, or is in an error state. + */ +void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) +{ + struct xa_node *node = xas->xa_node; + unsigned int offset = xas->xa_offset; + + if (xas_invalid(xas)) + return; + + while (node) { + if (!node_clear_mark(node, offset, mark)) + return; + if (node_any_mark(node, mark)) + return; + + offset = node->offset; + node = xa_parent_locked(xas->xa, node); + } + + if (xa_marked(xas->xa, mark)) + xa_mark_clear(xas->xa, mark); +} +EXPORT_SYMBOL_GPL(xas_clear_mark); + /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. @@ -160,6 +282,112 @@ void *xa_load(struct xarray *xa, unsigned long index) } EXPORT_SYMBOL(xa_load); +/** + * __xa_set_mark() - Set this mark on this entry while locked. + * @xa: XArray. + * @index: Index of entry. + * @mark: Mark number. + * + * Attempting to set a mark on a NULL entry does not succeed. + * + * Context: Any context. Expects xa_lock to be held on entry. + */ +void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) +{ + XA_STATE(xas, xa, index); + void *entry = xas_load(&xas); + + if (entry) + xas_set_mark(&xas, mark); +} +EXPORT_SYMBOL_GPL(__xa_set_mark); + +/** + * __xa_clear_mark() - Clear this mark on this entry while locked. + * @xa: XArray. + * @index: Index of entry. + * @mark: Mark number. + * + * Context: Any context. Expects xa_lock to be held on entry. + */ +void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) +{ + XA_STATE(xas, xa, index); + void *entry = xas_load(&xas); + + if (entry) + xas_clear_mark(&xas, mark); +} +EXPORT_SYMBOL_GPL(__xa_clear_mark); + +/** + * xa_get_mark() - Inquire whether this mark is set on this entry. + * @xa: XArray. + * @index: Index of entry. + * @mark: Mark number. + * + * This function uses the RCU read lock, so the result may be out of date + * by the time it returns. If you need the result to be stable, use a lock. + * + * Context: Any context. Takes and releases the RCU lock. + * Return: True if the entry at @index has this mark set, false if it doesn't. + */ +bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) +{ + XA_STATE(xas, xa, index); + void *entry; + + rcu_read_lock(); + entry = xas_start(&xas); + while (xas_get_mark(&xas, mark)) { + if (!xa_is_node(entry)) + goto found; + entry = xas_descend(&xas, xa_to_node(entry)); + } + rcu_read_unlock(); + return false; + found: + rcu_read_unlock(); + return true; +} +EXPORT_SYMBOL(xa_get_mark); + +/** + * xa_set_mark() - Set this mark on this entry. + * @xa: XArray. + * @index: Index of entry. + * @mark: Mark number. + * + * Attempting to set a mark on a NULL entry does not succeed. + * + * Context: Process context. Takes and releases the xa_lock. + */ +void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) +{ + xa_lock(xa); + __xa_set_mark(xa, index, mark); + xa_unlock(xa); +} +EXPORT_SYMBOL(xa_set_mark); + +/** + * xa_clear_mark() - Clear this mark on this entry. + * @xa: XArray. + * @index: Index of entry. + * @mark: Mark number. + * + * Clearing a mark always succeeds. + * + * Context: Process context. Takes and releases the xa_lock. + */ +void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) +{ + xa_lock(xa); + __xa_clear_mark(xa, index, mark); + xa_unlock(xa); +} +EXPORT_SYMBOL(xa_clear_mark); + #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { @@ -230,8 +458,8 @@ void xa_dump(const struct xarray *xa) unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, - xa->xa_flags, radix_tree_tagged(xa, 0), - radix_tree_tagged(xa, 1), radix_tree_tagged(xa, 2)); + xa->xa_flags, xa_marked(xa, XA_MARK_0), + xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h index 9bce3b56b5e7..5d2ab38965cc 100644 --- a/tools/include/asm-generic/bitops.h +++ b/tools/include/asm-generic/bitops.h @@ -27,5 +27,6 @@ #include #include +#include #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */ diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h index 21c41ccd1266..2f6ea28764a7 100644 --- a/tools/include/asm-generic/bitops/atomic.h +++ b/tools/include/asm-generic/bitops/atomic.h @@ -15,13 +15,4 @@ static inline void clear_bit(int nr, unsigned long *addr) addr[nr / __BITS_PER_LONG] &= ~(1UL << (nr % __BITS_PER_LONG)); } -static __always_inline int test_bit(unsigned int nr, const unsigned long *addr) -{ - return ((1UL << (nr % __BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / __BITS_PER_LONG])) != 0; -} - -#define __set_bit(nr, addr) set_bit(nr, addr) -#define __clear_bit(nr, addr) clear_bit(nr, addr) - #endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ */ diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h new file mode 100644 index 000000000000..7e10c4b50c5d --- /dev/null +++ b/tools/include/asm-generic/bitops/non-atomic.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ +#define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ + +#include + +/** + * __set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Unlike set_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static inline void __set_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p |= mask; +} + +static inline void __clear_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p &= ~mask; +} + +/** + * __change_bit - Toggle a bit in memory + * @nr: the bit to change + * @addr: the address to start counting from + * + * Unlike change_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static inline void __change_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p ^= mask; +} + +/** + * __test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old | mask; + return (old & mask) != 0; +} + +/** + * __test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old & ~mask; + return (old & mask) != 0; +} + +/* WARNING: non atomic and it can be reordered! */ +static inline int __test_and_change_bit(int nr, + volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old ^ mask; + return (old & mask) != 0; +} + +/** + * test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static inline int test_bit(int nr, const volatile unsigned long *addr) +{ + return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); +} + +#endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 1738c0391da4..622266b197d0 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -8,8 +8,14 @@ #define spinlock_t pthread_mutex_t #define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER #define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER -#define spin_lock_init(x) pthread_mutex_init(x, NULL) - +#define spin_lock_init(x) pthread_mutex_init(x, NULL) + +#define spin_lock(x) pthread_mutex_lock(x) +#define spin_unlock(x) pthread_mutex_unlock(x) +#define spin_lock_bh(x) pthread_mutex_lock(x) +#define spin_unlock_bh(x) pthread_mutex_unlock(x) +#define spin_lock_irq(x) pthread_mutex_lock(x) +#define spin_unlock_irq(x) pthread_mutex_unlock(x) #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) -- cgit v1.2.3-71-gd317 From 58d6ea3085f2e53714810a513c61629f6d2be0a6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:15:08 -0500 Subject: xarray: Add XArray unconditional store operations xa_store() differs from radix_tree_insert() in that it will overwrite an existing element in the array rather than returning an error. This is the behaviour which most users want, and those that want more complex behaviour generally want to use the xas family of routines anyway. For memory allocation, xa_store() will first attempt to request memory from the slab allocator; if memory is not immediately available, it will drop the xa_lock and allocate memory, keeping a pointer in the xa_state. It does not use the per-CPU cache, although those will continue to exist until all radix tree users are converted to the xarray. This patch also includes xa_erase() and __xa_erase() for a streamlined way to store NULL. Since there is no need to allocate memory in order to store a NULL in the XArray, we do not need to trouble the user with deciding what memory allocation flags to use. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 147 ++++++- lib/radix-tree.c | 4 +- lib/test_xarray.c | 177 +++++++- lib/xarray.c | 693 +++++++++++++++++++++++++++++++ tools/include/linux/bitmap.h | 1 + tools/include/linux/spinlock.h | 2 + tools/testing/radix-tree/Makefile | 2 +- tools/testing/radix-tree/bitmap.c | 23 + tools/testing/radix-tree/linux/kernel.h | 4 + tools/testing/radix-tree/linux/lockdep.h | 11 + 10 files changed, 1055 insertions(+), 9 deletions(-) create mode 100644 tools/testing/radix-tree/bitmap.c create mode 100644 tools/testing/radix-tree/linux/lockdep.h (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2de504ae9ba4..15eab63286ed 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,10 +205,17 @@ typedef unsigned __bitwise xa_mark_t; #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +enum xa_lock_type { + XA_LOCK_IRQ = 1, + XA_LOCK_BH = 2, +}; + /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ +#define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) +#define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) @@ -267,6 +274,7 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); +void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -309,6 +317,23 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } +/** + * xa_erase() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase(struct xarray *xa, unsigned long index) +{ + return xa_store(xa, index, NULL, 0); +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -322,11 +347,65 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_unlock_irqrestore(&(xa)->xa_lock, flags) /* - * Versions of the normal API which require the caller to hold the xa_lock. - */ + * Versions of the normal API which require the caller to hold the + * xa_lock. If the GFP flags allow it, they will drop the lock to + * allocate memory, then reacquire it afterwards. These functions + * may also re-enable interrupts if the XArray flags indicate the + * locking should be interrupt safe. + */ +void *__xa_erase(struct xarray *, unsigned long index); +void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * xa_erase_bh() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_bh(xa); + entry = __xa_erase(xa, index); + xa_unlock_bh(xa); + + return entry; +} + +/** + * xa_erase_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock_irq(xa); + entry = __xa_erase(xa, index); + xa_unlock_irq(xa); + + return entry; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* @@ -441,6 +520,12 @@ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, lockdep_is_held(&xa->xa_lock)); } +/* Private */ +static inline void *xa_mk_node(const struct xa_node *node) +{ + return (void *)((unsigned long)node | 2); +} + /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { @@ -647,6 +732,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents head-of-tree, RESTART or BOUNDS */ +static inline bool xas_top(struct xa_node *node) +{ + return node <= XAS_RESTART; +} + /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. @@ -683,10 +774,14 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) } void *xas_load(struct xa_state *); +void *xas_store(struct xa_state *, void *entry); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void xas_init_marks(const struct xa_state *); + +bool xas_nomem(struct xa_state *, gfp_t); /** * xas_reload() - Refetch an entry from the xarray. @@ -711,4 +806,52 @@ static inline void *xas_reload(struct xa_state *xas) return xa_head(xas->xa); } +/** + * xas_set() - Set up XArray operation state for a different index. + * @xas: XArray operation state. + * @index: New index into the XArray. + * + * Move the operation state to refer to a different index. This will + * have the effect of starting a walk from the top; see xas_next() + * to move to an adjacent index. + */ +static inline void xas_set(struct xa_state *xas, unsigned long index) +{ + xas->xa_index = index; + xas->xa_node = XAS_RESTART; +} + +/** + * xas_set_order() - Set up XArray operation state for a multislot entry. + * @xas: XArray operation state. + * @index: Target of the operation. + * @order: Entry occupies 2^@order indices. + */ +static inline void xas_set_order(struct xa_state *xas, unsigned long index, + unsigned int order) +{ +#ifdef CONFIG_XARRAY_MULTI + xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; + xas->xa_shift = order - (order % XA_CHUNK_SHIFT); + xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; + xas->xa_node = XAS_RESTART; +#else + BUG_ON(order > 0); + xas_set(xas, index); +#endif +} + +/** + * xas_set_update() - Set up XArray operation state for a callback. + * @xas: XArray operation state. + * @update: Function to call when updating a node. + * + * The XArray can notify a caller after it has updated an xa_node. + * This is advanced functionality and is only needed by the page cache. + */ +static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) +{ + xas->xa_update = update; +} + #endif /* _LINUX_XARRAY_H */ diff --git a/lib/radix-tree.c b/lib/radix-tree.c index b8e961428484..3479d93c32b9 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -47,7 +47,7 @@ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; /* * Radix tree node cache. */ -static struct kmem_cache *radix_tree_node_cachep; +struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has @@ -365,7 +365,7 @@ out: return ret; } -static void radix_tree_node_rcu_free(struct rcu_head *head) +void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index f8b0e9ba80a4..b711030fbc32 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -30,13 +30,49 @@ void xa_dump(const struct xarray *xa) { } static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) { - radix_tree_insert(xa, index, xa_mk_value(index)); - return NULL; + return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp); } static void xa_erase_index(struct xarray *xa, unsigned long index) { - radix_tree_delete(xa, index); + XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX)); + XA_BUG_ON(xa, xa_load(xa, index) != NULL); +} + +/* + * If anyone needs this, please move it to xarray.c. We have no current + * users outside the test suite because all current multislot users want + * to use the advanced API. + */ +static void *xa_store_order(struct xarray *xa, unsigned long index, + unsigned order, void *entry, gfp_t gfp) +{ + XA_STATE_ORDER(xas, xa, index, order); + void *curr; + + do { + xas_lock(&xas); + curr = xas_store(&xas, entry); + xas_unlock(&xas); + } while (xas_nomem(&xas, gfp)); + + return curr; +} + +static noinline void check_xa_err(struct xarray *xa) +{ + XA_BUG_ON(xa, xa_err(xa_store_index(xa, 0, GFP_NOWAIT)) != 0); + XA_BUG_ON(xa, xa_err(xa_erase(xa, 0)) != 0); +#ifndef __KERNEL__ + /* The kernel does not fail GFP_NOWAIT allocations */ + XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM); + XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_NOWAIT)) != -ENOMEM); +#endif + XA_BUG_ON(xa, xa_err(xa_store_index(xa, 1, GFP_KERNEL)) != 0); + XA_BUG_ON(xa, xa_err(xa_store(xa, 1, xa_mk_value(0), GFP_KERNEL)) != 0); + XA_BUG_ON(xa, xa_err(xa_erase(xa, 1)) != 0); +// kills the test-suite :-( +// XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL); } static noinline void check_xa_load(struct xarray *xa) @@ -69,6 +105,9 @@ static noinline void check_xa_load(struct xarray *xa) static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) { + unsigned int order; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 8 : 1; + /* NULL elements have no marks set */ XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); xa_set_mark(xa, index, XA_MARK_0); @@ -90,6 +129,37 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); xa_set_mark(xa, index, XA_MARK_0); XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); + + /* + * Storing a multi-index entry over entries with marks gives the + * entire entry the union of the marks + */ + BUG_ON((index % 4) != 0); + for (order = 2; order < max_order; order++) { + unsigned long base = round_down(index, 1UL << order); + unsigned long next = base + (1UL << order); + unsigned long i; + + XA_BUG_ON(xa, xa_store_index(xa, index + 1, GFP_KERNEL)); + xa_set_mark(xa, index + 1, XA_MARK_0); + XA_BUG_ON(xa, xa_store_index(xa, index + 2, GFP_KERNEL)); + xa_set_mark(xa, index + 2, XA_MARK_1); + XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL)); + xa_store_order(xa, index, order, xa_mk_value(index), + GFP_KERNEL); + for (i = base; i < next; i++) { + XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0)); + XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_1)); + XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_2)); + } + XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0)); + XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1)); + XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_2)); + xa_erase_index(xa, index); + xa_erase_index(xa, next); + XA_BUG_ON(xa, !xa_empty(xa)); + } + XA_BUG_ON(xa, !xa_empty(xa)); } static noinline void check_xa_mark(struct xarray *xa) @@ -100,12 +170,111 @@ static noinline void check_xa_mark(struct xarray *xa) check_xa_mark_1(xa, index); } -static RADIX_TREE(array, GFP_KERNEL); +static noinline void check_xa_shrink(struct xarray *xa) +{ + XA_STATE(xas, xa, 1); + struct xa_node *node; + + XA_BUG_ON(xa, !xa_empty(xa)); + XA_BUG_ON(xa, xa_store_index(xa, 0, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store_index(xa, 1, GFP_KERNEL) != NULL); + + /* + * Check that erasing the entry at 1 shrinks the tree and properly + * marks the node as being deleted. + */ + xas_lock(&xas); + XA_BUG_ON(xa, xas_load(&xas) != xa_mk_value(1)); + node = xas.xa_node; + XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != xa_mk_value(0)); + XA_BUG_ON(xa, xas_store(&xas, NULL) != xa_mk_value(1)); + XA_BUG_ON(xa, xa_load(xa, 1) != NULL); + XA_BUG_ON(xa, xas.xa_node != XAS_BOUNDS); + XA_BUG_ON(xa, xa_entry_locked(xa, node, 0) != XA_RETRY_ENTRY); + XA_BUG_ON(xa, xas_load(&xas) != NULL); + xas_unlock(&xas); + XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0)); + xa_erase_index(xa, 0); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_multi_store(struct xarray *xa) +{ +#ifdef CONFIG_XARRAY_MULTI + unsigned long i, j, k; + unsigned int max_order = (sizeof(long) == 4) ? 30 : 60; + + /* Loading from any position returns the same value */ + xa_store_order(xa, 0, 1, xa_mk_value(0), GFP_KERNEL); + XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0)); + XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0)); + XA_BUG_ON(xa, xa_load(xa, 2) != NULL); + rcu_read_lock(); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 2); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2); + rcu_read_unlock(); + + /* Storing adjacent to the value does not alter the value */ + xa_store(xa, 3, xa, GFP_KERNEL); + XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0)); + XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(0)); + XA_BUG_ON(xa, xa_load(xa, 2) != NULL); + rcu_read_lock(); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 3); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 2); + rcu_read_unlock(); + + /* Overwriting multiple indexes works */ + xa_store_order(xa, 0, 2, xa_mk_value(1), GFP_KERNEL); + XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(1)); + XA_BUG_ON(xa, xa_load(xa, 1) != xa_mk_value(1)); + XA_BUG_ON(xa, xa_load(xa, 2) != xa_mk_value(1)); + XA_BUG_ON(xa, xa_load(xa, 3) != xa_mk_value(1)); + XA_BUG_ON(xa, xa_load(xa, 4) != NULL); + rcu_read_lock(); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->count != 4); + XA_BUG_ON(xa, xa_to_node(xa_head(xa))->nr_values != 4); + rcu_read_unlock(); + + /* We can erase multiple values with a single store */ + xa_store_order(xa, 0, 63, NULL, GFP_KERNEL); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Even when the first slot is empty but the others aren't */ + xa_store_index(xa, 1, GFP_KERNEL); + xa_store_index(xa, 2, GFP_KERNEL); + xa_store_order(xa, 0, 2, NULL, GFP_KERNEL); + XA_BUG_ON(xa, !xa_empty(xa)); + + for (i = 0; i < max_order; i++) { + for (j = 0; j < max_order; j++) { + xa_store_order(xa, 0, i, xa_mk_value(i), GFP_KERNEL); + xa_store_order(xa, 0, j, xa_mk_value(j), GFP_KERNEL); + + for (k = 0; k < max_order; k++) { + void *entry = xa_load(xa, (1UL << k) - 1); + if ((i < k) && (j < k)) + XA_BUG_ON(xa, entry != NULL); + else + XA_BUG_ON(xa, entry != xa_mk_value(j)); + } + + xa_erase(xa, 0); + XA_BUG_ON(xa, !xa_empty(xa)); + } + } +#endif +} + +static DEFINE_XARRAY(array); static int xarray_checks(void) { + check_xa_err(&array); check_xa_load(&array); check_xa_mark(&array); + check_xa_shrink(&array); + check_multi_store(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index aa86c47e532f..4596a95ed9cd 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -7,6 +7,8 @@ #include #include +#include +#include #include /* @@ -25,6 +27,31 @@ * @entry refers to something stored in a slot in the xarray */ +static inline unsigned int xa_lock_type(const struct xarray *xa) +{ + return (__force unsigned int)xa->xa_flags & 3; +} + +static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) +{ + if (lock_type == XA_LOCK_IRQ) + xas_lock_irq(xas); + else if (lock_type == XA_LOCK_BH) + xas_lock_bh(xas); + else + xas_lock(xas); +} + +static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) +{ + if (lock_type == XA_LOCK_IRQ) + xas_unlock_irq(xas); + else if (lock_type == XA_LOCK_BH) + xas_unlock_bh(xas); + else + xas_unlock(xas); +} + static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) @@ -67,6 +94,34 @@ static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } +#define mark_inc(mark) do { \ + mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ +} while (0) + +/* + * xas_squash_marks() - Merge all marks to the first entry + * @xas: Array operation state. + * + * Set a mark on the first entry if any entry has it set. Clear marks on + * all sibling entries. + */ +static void xas_squash_marks(const struct xa_state *xas) +{ + unsigned int mark = 0; + unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; + + if (!xas->xa_sibs) + return; + + do { + unsigned long *marks = xas->xa_node->marks[mark]; + if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) + continue; + __set_bit(xas->xa_offset, marks); + bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); + } while (mark++ != (__force unsigned)XA_MARK_MAX); +} + /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { @@ -161,6 +216,516 @@ void *xas_load(struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_load); +/* Move the radix tree node cache here */ +extern struct kmem_cache *radix_tree_node_cachep; +extern void radix_tree_node_rcu_free(struct rcu_head *head); + +#define XA_RCU_FREE ((struct xarray *)1) + +static void xa_node_free(struct xa_node *node) +{ + XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); + node->array = XA_RCU_FREE; + call_rcu(&node->rcu_head, radix_tree_node_rcu_free); +} + +/* + * xas_destroy() - Free any resources allocated during the XArray operation. + * @xas: XArray operation state. + * + * This function is now internal-only. + */ +static void xas_destroy(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_alloc; + + if (!node) + return; + XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); + kmem_cache_free(radix_tree_node_cachep, node); + xas->xa_alloc = NULL; +} + +/** + * xas_nomem() - Allocate memory if needed. + * @xas: XArray operation state. + * @gfp: Memory allocation flags. + * + * If we need to add new nodes to the XArray, we try to allocate memory + * with GFP_NOWAIT while holding the lock, which will usually succeed. + * If it fails, @xas is flagged as needing memory to continue. The caller + * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, + * the caller should retry the operation. + * + * Forward progress is guaranteed as one node is allocated here and + * stored in the xa_state where it will be found by xas_alloc(). More + * nodes will likely be found in the slab allocator, but we do not tie + * them up here. + * + * Return: true if memory was needed, and was successfully allocated. + */ +bool xas_nomem(struct xa_state *xas, gfp_t gfp) +{ + if (xas->xa_node != XA_ERROR(-ENOMEM)) { + xas_destroy(xas); + return false; + } + xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); + if (!xas->xa_alloc) + return false; + XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); + xas->xa_node = XAS_RESTART; + return true; +} +EXPORT_SYMBOL_GPL(xas_nomem); + +/* + * __xas_nomem() - Drop locks and allocate memory if needed. + * @xas: XArray operation state. + * @gfp: Memory allocation flags. + * + * Internal variant of xas_nomem(). + * + * Return: true if memory was needed, and was successfully allocated. + */ +static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) + __must_hold(xas->xa->xa_lock) +{ + unsigned int lock_type = xa_lock_type(xas->xa); + + if (xas->xa_node != XA_ERROR(-ENOMEM)) { + xas_destroy(xas); + return false; + } + if (gfpflags_allow_blocking(gfp)) { + xas_unlock_type(xas, lock_type); + xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); + xas_lock_type(xas, lock_type); + } else { + xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); + } + if (!xas->xa_alloc) + return false; + XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); + xas->xa_node = XAS_RESTART; + return true; +} + +static void xas_update(struct xa_state *xas, struct xa_node *node) +{ + if (xas->xa_update) + xas->xa_update(node); + else + XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); +} + +static void *xas_alloc(struct xa_state *xas, unsigned int shift) +{ + struct xa_node *parent = xas->xa_node; + struct xa_node *node = xas->xa_alloc; + + if (xas_invalid(xas)) + return NULL; + + if (node) { + xas->xa_alloc = NULL; + } else { + node = kmem_cache_alloc(radix_tree_node_cachep, + GFP_NOWAIT | __GFP_NOWARN); + if (!node) { + xas_set_err(xas, -ENOMEM); + return NULL; + } + } + + if (parent) { + node->offset = xas->xa_offset; + parent->count++; + XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); + xas_update(xas, parent); + } + XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); + XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); + node->shift = shift; + node->count = 0; + node->nr_values = 0; + RCU_INIT_POINTER(node->parent, xas->xa_node); + node->array = xas->xa; + + return node; +} + +/* + * Use this to calculate the maximum index that will need to be created + * in order to add the entry described by @xas. Because we cannot store a + * multiple-index entry at index 0, the calculation is a little more complex + * than you might expect. + */ +static unsigned long xas_max(struct xa_state *xas) +{ + unsigned long max = xas->xa_index; + +#ifdef CONFIG_XARRAY_MULTI + if (xas->xa_shift || xas->xa_sibs) { + unsigned long mask; + mask = (((xas->xa_sibs + 1UL) << xas->xa_shift) - 1); + max |= mask; + if (mask == max) + max++; + } +#endif + + return max; +} + +/* The maximum index that can be contained in the array without expanding it */ +static unsigned long max_index(void *entry) +{ + if (!xa_is_node(entry)) + return 0; + return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; +} + +static void xas_shrink(struct xa_state *xas) +{ + struct xarray *xa = xas->xa; + struct xa_node *node = xas->xa_node; + + for (;;) { + void *entry; + + XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); + if (node->count != 1) + break; + entry = xa_entry_locked(xa, node, 0); + if (!entry) + break; + if (!xa_is_node(entry) && node->shift) + break; + xas->xa_node = XAS_BOUNDS; + + RCU_INIT_POINTER(xa->xa_head, entry); + + node->count = 0; + node->nr_values = 0; + if (!xa_is_node(entry)) + RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); + xas_update(xas, node); + xa_node_free(node); + if (!xa_is_node(entry)) + break; + node = xa_to_node(entry); + node->parent = NULL; + } +} + +/* + * xas_delete_node() - Attempt to delete an xa_node + * @xas: Array operation state. + * + * Attempts to delete the @xas->xa_node. This will fail if xa->node has + * a non-zero reference count. + */ +static void xas_delete_node(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + for (;;) { + struct xa_node *parent; + + XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); + if (node->count) + break; + + parent = xa_parent_locked(xas->xa, node); + xas->xa_node = parent; + xas->xa_offset = node->offset; + xa_node_free(node); + + if (!parent) { + xas->xa->xa_head = NULL; + xas->xa_node = XAS_BOUNDS; + return; + } + + parent->slots[xas->xa_offset] = NULL; + parent->count--; + XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); + node = parent; + xas_update(xas, node); + } + + if (!node->parent) + xas_shrink(xas); +} + +/** + * xas_free_nodes() - Free this node and all nodes that it references + * @xas: Array operation state. + * @top: Node to free + * + * This node has been removed from the tree. We must now free it and all + * of its subnodes. There may be RCU walkers with references into the tree, + * so we must replace all entries with retry markers. + */ +static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) +{ + unsigned int offset = 0; + struct xa_node *node = top; + + for (;;) { + void *entry = xa_entry_locked(xas->xa, node, offset); + + if (xa_is_node(entry)) { + node = xa_to_node(entry); + offset = 0; + continue; + } + if (entry) + RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); + offset++; + while (offset == XA_CHUNK_SIZE) { + struct xa_node *parent; + + parent = xa_parent_locked(xas->xa, node); + offset = node->offset + 1; + node->count = 0; + node->nr_values = 0; + xas_update(xas, node); + xa_node_free(node); + if (node == top) + return; + node = parent; + } + } +} + +/* + * xas_expand adds nodes to the head of the tree until it has reached + * sufficient height to be able to contain @xas->xa_index + */ +static int xas_expand(struct xa_state *xas, void *head) +{ + struct xarray *xa = xas->xa; + struct xa_node *node = NULL; + unsigned int shift = 0; + unsigned long max = xas_max(xas); + + if (!head) { + if (max == 0) + return 0; + while ((max >> shift) >= XA_CHUNK_SIZE) + shift += XA_CHUNK_SHIFT; + return shift + XA_CHUNK_SHIFT; + } else if (xa_is_node(head)) { + node = xa_to_node(head); + shift = node->shift + XA_CHUNK_SHIFT; + } + xas->xa_node = NULL; + + while (max > max_index(head)) { + xa_mark_t mark = 0; + + XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); + node = xas_alloc(xas, shift); + if (!node) + return -ENOMEM; + + node->count = 1; + if (xa_is_value(head)) + node->nr_values = 1; + RCU_INIT_POINTER(node->slots[0], head); + + /* Propagate the aggregated mark info to the new child */ + for (;;) { + if (xa_marked(xa, mark)) + node_set_mark(node, 0, mark); + if (mark == XA_MARK_MAX) + break; + mark_inc(mark); + } + + /* + * Now that the new node is fully initialised, we can add + * it to the tree + */ + if (xa_is_node(head)) { + xa_to_node(head)->offset = 0; + rcu_assign_pointer(xa_to_node(head)->parent, node); + } + head = xa_mk_node(node); + rcu_assign_pointer(xa->xa_head, head); + xas_update(xas, node); + + shift += XA_CHUNK_SHIFT; + } + + xas->xa_node = node; + return shift; +} + +/* + * xas_create() - Create a slot to store an entry in. + * @xas: XArray operation state. + * + * Most users will not need to call this function directly, as it is called + * by xas_store(). It is useful for doing conditional store operations + * (see the xa_cmpxchg() implementation for an example). + * + * Return: If the slot already existed, returns the contents of this slot. + * If the slot was newly created, returns NULL. If it failed to create the + * slot, returns NULL and indicates the error in @xas. + */ +static void *xas_create(struct xa_state *xas) +{ + struct xarray *xa = xas->xa; + void *entry; + void __rcu **slot; + struct xa_node *node = xas->xa_node; + int shift; + unsigned int order = xas->xa_shift; + + if (xas_top(node)) { + entry = xa_head_locked(xa); + xas->xa_node = NULL; + shift = xas_expand(xas, entry); + if (shift < 0) + return NULL; + entry = xa_head_locked(xa); + slot = &xa->xa_head; + } else if (xas_error(xas)) { + return NULL; + } else if (node) { + unsigned int offset = xas->xa_offset; + + shift = node->shift; + entry = xa_entry_locked(xa, node, offset); + slot = &node->slots[offset]; + } else { + shift = 0; + entry = xa_head_locked(xa); + slot = &xa->xa_head; + } + + while (shift > order) { + shift -= XA_CHUNK_SHIFT; + if (!entry) { + node = xas_alloc(xas, shift); + if (!node) + break; + rcu_assign_pointer(*slot, xa_mk_node(node)); + } else if (xa_is_node(entry)) { + node = xa_to_node(entry); + } else { + break; + } + entry = xas_descend(xas, node); + slot = &node->slots[xas->xa_offset]; + } + + return entry; +} + +static void update_node(struct xa_state *xas, struct xa_node *node, + int count, int values) +{ + if (!node || (!count && !values)) + return; + + node->count += count; + node->nr_values += values; + XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); + XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); + xas_update(xas, node); + if (count < 0) + xas_delete_node(xas); +} + +/** + * xas_store() - Store this entry in the XArray. + * @xas: XArray operation state. + * @entry: New entry. + * + * If @xas is operating on a multi-index entry, the entry returned by this + * function is essentially meaningless (it may be an internal entry or it + * may be %NULL, even if there are non-NULL entries at some of the indices + * covered by the range). This is not a problem for any current users, + * and can be changed if needed. + * + * Return: The old entry at this index. + */ +void *xas_store(struct xa_state *xas, void *entry) +{ + struct xa_node *node; + void __rcu **slot = &xas->xa->xa_head; + unsigned int offset, max; + int count = 0; + int values = 0; + void *first, *next; + bool value = xa_is_value(entry); + + if (entry) + first = xas_create(xas); + else + first = xas_load(xas); + + if (xas_invalid(xas)) + return first; + node = xas->xa_node; + if (node && (xas->xa_shift < node->shift)) + xas->xa_sibs = 0; + if ((first == entry) && !xas->xa_sibs) + return first; + + next = first; + offset = xas->xa_offset; + max = xas->xa_offset + xas->xa_sibs; + if (node) { + slot = &node->slots[offset]; + if (xas->xa_sibs) + xas_squash_marks(xas); + } + if (!entry) + xas_init_marks(xas); + + for (;;) { + /* + * Must clear the marks before setting the entry to NULL, + * otherwise xas_for_each_marked may find a NULL entry and + * stop early. rcu_assign_pointer contains a release barrier + * so the mark clearing will appear to happen before the + * entry is set to NULL. + */ + rcu_assign_pointer(*slot, entry); + if (xa_is_node(next)) + xas_free_nodes(xas, xa_to_node(next)); + if (!node) + break; + count += !next - !entry; + values += !xa_is_value(first) - !value; + if (entry) { + if (offset == max) + break; + if (!xa_is_sibling(entry)) + entry = xa_mk_sibling(xas->xa_offset); + } else { + if (offset == XA_CHUNK_MASK) + break; + } + next = xa_entry_locked(xas->xa, node, ++offset); + if (!xa_is_sibling(next)) { + if (!entry && (offset > max)) + break; + first = next; + } + slot++; + } + + update_node(xas, node, count, values); + return first; +} +EXPORT_SYMBOL_GPL(xas_store); + /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. @@ -240,6 +805,30 @@ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) } EXPORT_SYMBOL_GPL(xas_clear_mark); +/** + * xas_init_marks() - Initialise all marks for the entry + * @xas: Array operations state. + * + * Initialise all marks for the entry specified by @xas. If we're tracking + * free entries with a mark, we need to set it on all entries. All other + * marks are cleared. + * + * This implementation is not as efficient as it could be; we may walk + * up the tree multiple times. + */ +void xas_init_marks(const struct xa_state *xas) +{ + xa_mark_t mark = 0; + + for (;;) { + xas_clear_mark(xas, mark); + if (mark == XA_MARK_MAX) + break; + mark_inc(mark); + } +} +EXPORT_SYMBOL_GPL(xas_init_marks); + /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. @@ -253,9 +842,19 @@ EXPORT_SYMBOL_GPL(xas_clear_mark); */ void xa_init_flags(struct xarray *xa, gfp_t flags) { + unsigned int lock_type; + static struct lock_class_key xa_lock_irq; + static struct lock_class_key xa_lock_bh; + spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; + + lock_type = xa_lock_type(xa); + if (lock_type == XA_LOCK_IRQ) + lockdep_set_class(&xa->xa_lock, &xa_lock_irq); + else if (lock_type == XA_LOCK_BH) + lockdep_set_class(&xa->xa_lock, &xa_lock_bh); } EXPORT_SYMBOL(xa_init_flags); @@ -282,6 +881,100 @@ void *xa_load(struct xarray *xa, unsigned long index) } EXPORT_SYMBOL(xa_load); +static void *xas_result(struct xa_state *xas, void *curr) +{ + XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr)); + if (xas_error(xas)) + curr = xas->xa_node; + return curr; +} + +/** + * __xa_erase() - Erase this entry from the XArray while locked. + * @xa: XArray. + * @index: Index into array. + * + * If the entry at this index is a multi-index entry then all indices will + * be erased, and the entry will no longer be a multi-index entry. + * This function expects the xa_lock to be held on entry. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: The old entry at this index. + */ +void *__xa_erase(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + return xas_result(&xas, xas_store(&xas, NULL)); +} +EXPORT_SYMBOL_GPL(__xa_erase); + +/** + * xa_store() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * After this function returns, loads from this index will return @entry. + * Storing into an existing multislot entry updates the entry of every index. + * The marks associated with @index are unaffected unless @entry is %NULL. + * + * Context: Process context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry + * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation + * failed. + */ +void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + void *curr; + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return XA_ERROR(-EINVAL); + + do { + xas_lock(&xas); + curr = xas_store(&xas, entry); + xas_unlock(&xas); + } while (xas_nomem(&xas, gfp)); + + return xas_result(&xas, curr); +} +EXPORT_SYMBOL(xa_store); + +/** + * __xa_store() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * You must already be holding the xa_lock when calling this function. + * It will drop the lock if needed to allocate memory, and then reacquire + * it afterwards. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: The old entry at this index or xa_err() if an error happened. + */ +void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + void *curr; + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return XA_ERROR(-EINVAL); + + do { + curr = xas_store(&xas, entry); + } while (__xas_nomem(&xas, gfp)); + + return xas_result(&xas, curr); +} +EXPORT_SYMBOL(__xa_store); + /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index e63662db131b..05dca5c203f3 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -15,6 +15,7 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); +void bitmap_clear(unsigned long *map, unsigned int start, int len); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 622266b197d0..c934572d935c 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -37,4 +37,6 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) return true; } +#include + #endif diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 1379f1d78d0b..acf1afa01c5b 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -5,7 +5,7 @@ CFLAGS += -I. -I../../include -g -Og -Wall -D_LGPL_SOURCE -fsanitize=address \ LDFLAGS += -fsanitize=address -fsanitize=undefined LDLIBS+= -lpthread -lurcu TARGETS = main idr-test multiorder xarray -CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o +CORE_OFILES := xarray.o radix-tree.o idr.o linux.o test.o find_bit.o bitmap.o OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \ tag_check.o multiorder.o idr-test.o iteration_check.o benchmark.o diff --git a/tools/testing/radix-tree/bitmap.c b/tools/testing/radix-tree/bitmap.c new file mode 100644 index 000000000000..66ec4a24a203 --- /dev/null +++ b/tools/testing/radix-tree/bitmap.c @@ -0,0 +1,23 @@ +/* lib/bitmap.c pulls in at least two other files. */ + +#include + +void bitmap_clear(unsigned long *map, unsigned int start, int len) +{ + unsigned long *p = map + BIT_WORD(start); + const unsigned int size = start + len; + int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); + unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); + + while (len - bits_to_clear >= 0) { + *p &= ~mask_to_clear; + len -= bits_to_clear; + bits_to_clear = BITS_PER_LONG; + mask_to_clear = ~0UL; + p++; + } + if (len) { + mask_to_clear &= BITMAP_LAST_WORD_MASK(size); + *p &= ~mask_to_clear; + } +} diff --git a/tools/testing/radix-tree/linux/kernel.h b/tools/testing/radix-tree/linux/kernel.h index 5d06ac75a14d..4568248222ae 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -18,4 +18,8 @@ #define pr_debug printk #define pr_cont printk +#define __acquires(x) +#define __releases(x) +#define __must_hold(x) + #endif /* _KERNEL_H */ diff --git a/tools/testing/radix-tree/linux/lockdep.h b/tools/testing/radix-tree/linux/lockdep.h new file mode 100644 index 000000000000..565fccdfe6e9 --- /dev/null +++ b/tools/testing/radix-tree/linux/lockdep.h @@ -0,0 +1,11 @@ +#ifndef _LINUX_LOCKDEP_H +#define _LINUX_LOCKDEP_H +struct lock_class_key { + unsigned int a; +}; + +static inline void lockdep_set_class(spinlock_t *lock, + struct lock_class_key *key) +{ +} +#endif /* _LINUX_LOCKDEP_H */ -- cgit v1.2.3-71-gd317 From 41aec91f55985e7f14ee75fe2f6e7bcfff0d0fae Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 10 Nov 2017 15:34:55 -0500 Subject: xarray: Add XArray conditional store operations Like cmpxchg(), xa_cmpxchg will only store to the index if the current entry matches the old entry. It returns the current entry, which is usually more useful than the errno returned by radix_tree_insert(). For the users who really only want the errno, the xa_insert() wrapper provides a more convenient calling convention. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 60 ++++++++++++++++++++++++++++++++++++++++++ lib/test_xarray.c | 20 ++++++++++++++ lib/xarray.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 151 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 15eab63286ed..7f740f675b96 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -275,6 +275,8 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *xa_cmpxchg(struct xarray *, unsigned long index, + void *old, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -334,6 +336,34 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } +/** + * xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Process context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -355,9 +385,39 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, + void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +/** + * __xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use __xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int __xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. diff --git a/lib/test_xarray.c b/lib/test_xarray.c index b711030fbc32..fb472258b639 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -198,6 +198,25 @@ static noinline void check_xa_shrink(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_cmpxchg(struct xarray *xa) +{ + void *FIVE = xa_mk_value(5); + void *SIX = xa_mk_value(6); + void *LOTS = xa_mk_value(12345678); + + XA_BUG_ON(xa, !xa_empty(xa)); + XA_BUG_ON(xa, xa_store_index(xa, 12345678, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_insert(xa, 12345678, xa, GFP_KERNEL) != -EEXIST); + XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, SIX, FIVE, GFP_KERNEL) != LOTS); + XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, LOTS, FIVE, GFP_KERNEL) != LOTS); + XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, FIVE, LOTS, GFP_KERNEL) != FIVE); + XA_BUG_ON(xa, xa_cmpxchg(xa, 5, FIVE, NULL, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_cmpxchg(xa, 5, NULL, FIVE, GFP_KERNEL) != NULL); + xa_erase_index(xa, 12345678); + xa_erase_index(xa, 5); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_multi_store(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI @@ -274,6 +293,7 @@ static int xarray_checks(void) check_xa_load(&array); check_xa_mark(&array); check_xa_shrink(&array); + check_cmpxchg(&array); check_multi_store(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); diff --git a/lib/xarray.c b/lib/xarray.c index 4596a95ed9cd..2ba5a98ec618 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -975,6 +975,77 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) } EXPORT_SYMBOL(__xa_store); +/** + * xa_cmpxchg() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * If the entry at @index is the same as @old, replace it with @entry. + * If the return value is equal to @old, then the exchange was successful. + * + * Context: Process context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +void *xa_cmpxchg(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + void *curr; + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return XA_ERROR(-EINVAL); + + do { + xas_lock(&xas); + curr = xas_load(&xas); + if (curr == old) + xas_store(&xas, entry); + xas_unlock(&xas); + } while (xas_nomem(&xas, gfp)); + + return xas_result(&xas, curr); +} +EXPORT_SYMBOL(xa_cmpxchg); + +/** + * __xa_cmpxchg() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * You must already be holding the xa_lock when calling this function. + * It will drop the lock if needed to allocate memory, and then reacquire + * it afterwards. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: The old entry at this index or xa_err() if an error happened. + */ +void *__xa_cmpxchg(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + void *curr; + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return XA_ERROR(-EINVAL); + + do { + curr = xas_load(&xas); + if (curr == old) + xas_store(&xas, entry); + } while (__xas_nomem(&xas, gfp)); + + return xas_result(&xas, curr); +} +EXPORT_SYMBOL(__xa_cmpxchg); + /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. -- cgit v1.2.3-71-gd317 From b803b42823d0d9e8b6deccf01ffc2aba5d0738df Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 08:30:11 -0500 Subject: xarray: Add XArray iterators The xa_for_each iterator allows the user to efficiently walk a range of the array, executing the loop body once for each entry in that range that matches the filter. This commit also includes xa_find() and xa_find_after() which are helper functions for xa_for_each() but may also be useful in their own right. In the xas family of functions, we have xas_for_each(), xas_find(), xas_next_entry(), xas_for_each_tagged(), xas_find_tagged(), xas_next_tagged() and xas_pause(). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 165 ++++++++++++++++++++++++++++ lib/test_xarray.c | 183 +++++++++++++++++++++++++++++++ lib/xarray.c | 292 +++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 640 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7f740f675b96..66b10efa5a50 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -280,6 +280,10 @@ void *xa_cmpxchg(struct xarray *, unsigned long index, bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); +void *xa_find(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +void *xa_find_after(struct xarray *xa, unsigned long *index, + unsigned long max, xa_mark_t) __attribute__((nonnull(2))); /** * xa_init() - Initialise an empty XArray. @@ -364,6 +368,35 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_for_each() - Iterate over a portion of an XArray. + * @xa: XArray. + * @entry: Entry retrieved from array. + * @index: Index of @entry. + * @max: Maximum index to retrieve from array. + * @filter: Selection criterion. + * + * Initialise @index to the lowest index you want to retrieve from the + * array. During the iteration, @entry will have the value of the entry + * stored in @xa at @index. The iteration will skip all entries in the + * array which do not match @filter. You may modify @index during the + * iteration if you want to skip or reprocess indices. It is safe to modify + * the array during the iteration. At the end of the iteration, @entry will + * be set to NULL and @index will have a value less than or equal to max. + * + * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). xa_for_each() + * will spin if it hits a retry entry; if you intend to see retry entries, + * you should use the xas_for_each() iterator instead. The xas_for_each() + * iterator will expand into more inline code than xa_for_each(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each(xa, entry, index, max, filter) \ + for (entry = xa_find(xa, &index, max, filter); entry; \ + entry = xa_find_after(xa, &index, max, filter)) + #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) @@ -835,13 +868,16 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); +void *xas_find(struct xa_state *, unsigned long max); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); +void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); +void xas_pause(struct xa_state *); /** * xas_reload() - Refetch an entry from the xarray. @@ -914,4 +950,133 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +/** + * xas_next_entry() - Advance iterator to next present entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * + * xas_next_entry() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find(), and will call xas_find() + * for all the hard cases. + * + * Return: The next present entry after the one currently referred to by @xas. + */ +static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) +{ + struct xa_node *node = xas->xa_node; + void *entry; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) + return xas_find(xas, max); + + do { + if (unlikely(xas->xa_index >= max)) + return xas_find(xas, max); + if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) + return xas_find(xas, max); + entry = xa_entry(xas->xa, node, xas->xa_offset + 1); + if (unlikely(xa_is_internal(entry))) + return xas_find(xas, max); + xas->xa_offset++; + xas->xa_index++; + } while (!entry); + + return entry; +} + +/* Private */ +static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, + xa_mark_t mark) +{ + unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; + unsigned int offset = xas->xa_offset; + + if (advance) + offset++; + if (XA_CHUNK_SIZE == BITS_PER_LONG) { + if (offset < XA_CHUNK_SIZE) { + unsigned long data = *addr & (~0UL << offset); + if (data) + return __ffs(data); + } + return XA_CHUNK_SIZE; + } + + return find_next_bit(addr, XA_CHUNK_SIZE, offset); +} + +/** + * xas_next_marked() - Advance iterator to next marked entry. + * @xas: XArray operation state. + * @max: Highest index to return. + * @mark: Mark to search for. + * + * xas_next_marked() is an inline function to optimise xarray traversal for + * speed. It is equivalent to calling xas_find_marked(), and will call + * xas_find_marked() for all the hard cases. + * + * Return: The next marked entry after the one currently referred to by @xas. + */ +static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, + xa_mark_t mark) +{ + struct xa_node *node = xas->xa_node; + unsigned int offset; + + if (unlikely(xas_not_node(node) || node->shift)) + return xas_find_marked(xas, max, mark); + offset = xas_find_chunk(xas, true, mark); + xas->xa_offset = offset; + xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; + if (xas->xa_index > max) + return NULL; + if (offset == XA_CHUNK_SIZE) + return xas_find_marked(xas, max, mark); + return xa_entry(xas->xa, node, offset); +} + +/* + * If iterating while holding a lock, drop the lock and reschedule + * every %XA_CHECK_SCHED loops. + */ +enum { + XA_CHECK_SCHED = 4096, +}; + +/** + * xas_for_each() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * + * The loop body will be executed for each entry present in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each(xas, entry, max) \ + for (entry = xas_find(xas, max); entry; \ + entry = xas_next_entry(xas, max)) + +/** + * xas_for_each_marked() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * @max: Maximum index to retrieve from array. + * @mark: Mark to search for. + * + * The loop body will be executed for each marked entry in the xarray + * between the current xas position and @max. @entry will be set to + * the entry retrieved from the xarray. It is safe to delete entries + * from the array in the loop body. You should hold either the RCU lock + * or the xa_lock while iterating. If you need to drop the lock, call + * xas_pause() first. + */ +#define xas_for_each_marked(xas, entry, max, mark) \ + for (entry = xas_find_marked(xas, max, mark); entry; \ + entry = xas_next_marked(xas, max, mark)) + #endif /* _LINUX_XARRAY_H */ diff --git a/lib/test_xarray.c b/lib/test_xarray.c index fb472258b639..e3c2d4d00b15 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -75,6 +75,48 @@ static noinline void check_xa_err(struct xarray *xa) // XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL); } +static noinline void check_xas_retry(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + void *entry; + + xa_store_index(xa, 0, GFP_KERNEL); + xa_store_index(xa, 1, GFP_KERNEL); + + rcu_read_lock(); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_value(0)); + xa_erase_index(xa, 1); + XA_BUG_ON(xa, !xa_is_retry(xas_reload(&xas))); + XA_BUG_ON(xa, xas_retry(&xas, NULL)); + XA_BUG_ON(xa, xas_retry(&xas, xa_mk_value(0))); + xas_reset(&xas); + XA_BUG_ON(xa, xas.xa_node != XAS_RESTART); + XA_BUG_ON(xa, xas_next_entry(&xas, ULONG_MAX) != xa_mk_value(0)); + XA_BUG_ON(xa, xas.xa_node != NULL); + + XA_BUG_ON(xa, xa_store_index(xa, 1, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, !xa_is_internal(xas_reload(&xas))); + xas.xa_node = XAS_RESTART; + XA_BUG_ON(xa, xas_next_entry(&xas, ULONG_MAX) != xa_mk_value(0)); + rcu_read_unlock(); + + /* Make sure we can iterate through retry entries */ + xas_lock(&xas); + xas_set(&xas, 0); + xas_store(&xas, XA_RETRY_ENTRY); + xas_set(&xas, 1); + xas_store(&xas, XA_RETRY_ENTRY); + + xas_set(&xas, 0); + xas_for_each(&xas, entry, ULONG_MAX) { + xas_store(&xas, xa_mk_value(xas.xa_index)); + } + xas_unlock(&xas); + + xa_erase_index(xa, 0); + xa_erase_index(xa, 1); +} + static noinline void check_xa_load(struct xarray *xa) { unsigned long i, j; @@ -217,6 +259,44 @@ static noinline void check_cmpxchg(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_xas_erase(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + void *entry; + unsigned long i, j; + + for (i = 0; i < 200; i++) { + for (j = i; j < 2 * i + 17; j++) { + xas_set(&xas, j); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(j)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + } + + xas_set(&xas, ULONG_MAX); + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(0)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + xas_lock(&xas); + xas_store(&xas, NULL); + + xas_set(&xas, 0); + j = i; + xas_for_each(&xas, entry, ULONG_MAX) { + XA_BUG_ON(xa, entry != xa_mk_value(j)); + xas_store(&xas, NULL); + j++; + } + xas_unlock(&xas); + XA_BUG_ON(xa, !xa_empty(xa)); + } +} + static noinline void check_multi_store(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI @@ -285,16 +365,119 @@ static noinline void check_multi_store(struct xarray *xa) #endif } +static noinline void check_multi_find(struct xarray *xa) +{ +#ifdef CONFIG_XARRAY_MULTI + unsigned long index; + + xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL); + XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL); + + index = 0; + XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != + xa_mk_value(12)); + XA_BUG_ON(xa, index != 12); + index = 13; + XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != + xa_mk_value(12)); + XA_BUG_ON(xa, (index < 12) || (index >= 16)); + XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) != + xa_mk_value(16)); + XA_BUG_ON(xa, index != 16); + + xa_erase_index(xa, 12); + xa_erase_index(xa, 16); + XA_BUG_ON(xa, !xa_empty(xa)); +#endif +} + +static noinline void check_multi_find_2(struct xarray *xa) +{ + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 10 : 1; + unsigned int i, j; + void *entry; + + for (i = 0; i < max_order; i++) { + unsigned long index = 1UL << i; + for (j = 0; j < index; j++) { + XA_STATE(xas, xa, j + index); + xa_store_index(xa, index - 1, GFP_KERNEL); + xa_store_order(xa, index, i, xa_mk_value(index), + GFP_KERNEL); + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + xa_erase_index(xa, index); + } + rcu_read_unlock(); + xa_erase_index(xa, index - 1); + XA_BUG_ON(xa, !xa_empty(xa)); + } + } +} + +static noinline void check_find(struct xarray *xa) +{ + unsigned long i, j, k; + + XA_BUG_ON(xa, !xa_empty(xa)); + + /* + * Check xa_find with all pairs between 0 and 99 inclusive, + * starting at every index between 0 and 99 + */ + for (i = 0; i < 100; i++) { + XA_BUG_ON(xa, xa_store_index(xa, i, GFP_KERNEL) != NULL); + xa_set_mark(xa, i, XA_MARK_0); + for (j = 0; j < i; j++) { + XA_BUG_ON(xa, xa_store_index(xa, j, GFP_KERNEL) != + NULL); + xa_set_mark(xa, j, XA_MARK_0); + for (k = 0; k < 100; k++) { + unsigned long index = k; + void *entry = xa_find(xa, &index, ULONG_MAX, + XA_PRESENT); + if (k <= j) + XA_BUG_ON(xa, index != j); + else if (k <= i) + XA_BUG_ON(xa, index != i); + else + XA_BUG_ON(xa, entry != NULL); + + index = k; + entry = xa_find(xa, &index, ULONG_MAX, + XA_MARK_0); + if (k <= j) + XA_BUG_ON(xa, index != j); + else if (k <= i) + XA_BUG_ON(xa, index != i); + else + XA_BUG_ON(xa, entry != NULL); + } + xa_erase_index(xa, j); + XA_BUG_ON(xa, xa_get_mark(xa, j, XA_MARK_0)); + XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0)); + } + xa_erase_index(xa, i); + XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_0)); + } + XA_BUG_ON(xa, !xa_empty(xa)); + check_multi_find(xa); + check_multi_find_2(xa); +} + static DEFINE_XARRAY(array); static int xarray_checks(void) { check_xa_err(&array); + check_xas_retry(&array); check_xa_load(&array); check_xa_mark(&array); check_xa_shrink(&array); + check_xas_erase(&array); check_cmpxchg(&array); check_multi_store(&array); + check_find(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index 2ba5a98ec618..24494f42daa6 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -128,6 +128,11 @@ static unsigned int get_offset(unsigned long index, struct xa_node *node) return (index >> node->shift) & XA_CHUNK_MASK; } +static void xas_set_offset(struct xa_state *xas) +{ + xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); +} + /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { @@ -136,6 +141,12 @@ static void xas_move_index(struct xa_state *xas, unsigned long offset) xas->xa_index += offset << shift; } +static void xas_advance(struct xa_state *xas) +{ + xas->xa_offset++; + xas_move_index(xas, xas->xa_offset); +} + static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; @@ -829,6 +840,202 @@ void xas_init_marks(const struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_init_marks); +/** + * xas_pause() - Pause a walk to drop a lock. + * @xas: XArray operation state. + * + * Some users need to pause a walk and drop the lock they're holding in + * order to yield to a higher priority thread or carry out an operation + * on an entry. Those users should call this function before they drop + * the lock. It resets the @xas to be suitable for the next iteration + * of the loop after the user has reacquired the lock. If most entries + * found during a walk require you to call xas_pause(), the xa_for_each() + * iterator may be more appropriate. + * + * Note that xas_pause() only works for forward iteration. If a user needs + * to pause a reverse iteration, we will need a xas_pause_rev(). + */ +void xas_pause(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (xas_invalid(xas)) + return; + + if (node) { + unsigned int offset = xas->xa_offset; + while (++offset < XA_CHUNK_SIZE) { + if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) + break; + } + xas->xa_index += (offset - xas->xa_offset) << node->shift; + } else { + xas->xa_index++; + } + xas->xa_node = XAS_RESTART; +} +EXPORT_SYMBOL_GPL(xas_pause); + +/** + * xas_find() - Find the next present entry in the XArray. + * @xas: XArray operation state. + * @max: Highest index to return. + * + * If the @xas has not yet been walked to an entry, return the entry + * which has an index >= xas.xa_index. If it has been walked, the entry + * currently being pointed at has been processed, and so we move to the + * next entry. + * + * If no entry is found and the array is smaller than @max, the iterator + * is set to the smallest index not yet in the array. This allows @xas + * to be immediately passed to xas_store(). + * + * Return: The entry, if found, otherwise %NULL. + */ +void *xas_find(struct xa_state *xas, unsigned long max) +{ + void *entry; + + if (xas_error(xas)) + return NULL; + + if (!xas->xa_node) { + xas->xa_index = 1; + return set_bounds(xas); + } else if (xas_top(xas->xa_node)) { + entry = xas_load(xas); + if (entry || xas_not_node(xas->xa_node)) + return entry; + } else if (!xas->xa_node->shift && + xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { + xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; + } + + xas_advance(xas); + + while (xas->xa_node && (xas->xa_index <= max)) { + if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { + xas->xa_offset = xas->xa_node->offset + 1; + xas->xa_node = xa_parent(xas->xa, xas->xa_node); + continue; + } + + entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); + if (xa_is_node(entry)) { + xas->xa_node = xa_to_node(entry); + xas->xa_offset = 0; + continue; + } + if (entry && !xa_is_sibling(entry)) + return entry; + + xas_advance(xas); + } + + if (!xas->xa_node) + xas->xa_node = XAS_BOUNDS; + return NULL; +} +EXPORT_SYMBOL_GPL(xas_find); + +/** + * xas_find_marked() - Find the next marked entry in the XArray. + * @xas: XArray operation state. + * @max: Highest index to return. + * @mark: Mark number to search for. + * + * If the @xas has not yet been walked to an entry, return the marked entry + * which has an index >= xas.xa_index. If it has been walked, the entry + * currently being pointed at has been processed, and so we return the + * first marked entry with an index > xas.xa_index. + * + * If no marked entry is found and the array is smaller than @max, @xas is + * set to the bounds state and xas->xa_index is set to the smallest index + * not yet in the array. This allows @xas to be immediately passed to + * xas_store(). + * + * If no entry is found before @max is reached, @xas is set to the restart + * state. + * + * Return: The entry, if found, otherwise %NULL. + */ +void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) +{ + bool advance = true; + unsigned int offset; + void *entry; + + if (xas_error(xas)) + return NULL; + + if (!xas->xa_node) { + xas->xa_index = 1; + goto out; + } else if (xas_top(xas->xa_node)) { + advance = false; + entry = xa_head(xas->xa); + xas->xa_node = NULL; + if (xas->xa_index > max_index(entry)) + goto bounds; + if (!xa_is_node(entry)) { + if (xa_marked(xas->xa, mark)) + return entry; + xas->xa_index = 1; + goto out; + } + xas->xa_node = xa_to_node(entry); + xas->xa_offset = xas->xa_index >> xas->xa_node->shift; + } + + while (xas->xa_index <= max) { + if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { + xas->xa_offset = xas->xa_node->offset + 1; + xas->xa_node = xa_parent(xas->xa, xas->xa_node); + if (!xas->xa_node) + break; + advance = false; + continue; + } + + if (!advance) { + entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); + if (xa_is_sibling(entry)) { + xas->xa_offset = xa_to_sibling(entry); + xas_move_index(xas, xas->xa_offset); + } + } + + offset = xas_find_chunk(xas, advance, mark); + if (offset > xas->xa_offset) { + advance = false; + xas_move_index(xas, offset); + /* Mind the wrap */ + if ((xas->xa_index - 1) >= max) + goto max; + xas->xa_offset = offset; + if (offset == XA_CHUNK_SIZE) + continue; + } + + entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); + if (!xa_is_node(entry)) + return entry; + xas->xa_node = xa_to_node(entry); + xas_set_offset(xas); + } + +out: + if (!max) + goto max; +bounds: + xas->xa_node = XAS_BOUNDS; + return NULL; +max: + xas->xa_node = XAS_RESTART; + return NULL; +} +EXPORT_SYMBOL_GPL(xas_find_marked); + /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. @@ -1152,6 +1359,91 @@ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) } EXPORT_SYMBOL(xa_clear_mark); +/** + * xa_find() - Search the XArray for an entry. + * @xa: XArray. + * @indexp: Pointer to an index. + * @max: Maximum index to search to. + * @filter: Selection criterion. + * + * Finds the entry in @xa which matches the @filter, and has the lowest + * index that is at least @indexp and no more than @max. + * If an entry is found, @indexp is updated to be the index of the entry. + * This function is protected by the RCU read lock, so it may not find + * entries which are being simultaneously added. It will not return an + * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). + * + * Context: Any context. Takes and releases the RCU lock. + * Return: The entry, if found, otherwise %NULL. + */ +void *xa_find(struct xarray *xa, unsigned long *indexp, + unsigned long max, xa_mark_t filter) +{ + XA_STATE(xas, xa, *indexp); + void *entry; + + rcu_read_lock(); + do { + if ((__force unsigned int)filter < XA_MAX_MARKS) + entry = xas_find_marked(&xas, max, filter); + else + entry = xas_find(&xas, max); + } while (xas_retry(&xas, entry)); + rcu_read_unlock(); + + if (entry) + *indexp = xas.xa_index; + return entry; +} +EXPORT_SYMBOL(xa_find); + +/** + * xa_find_after() - Search the XArray for a present entry. + * @xa: XArray. + * @indexp: Pointer to an index. + * @max: Maximum index to search to. + * @filter: Selection criterion. + * + * Finds the entry in @xa which matches the @filter and has the lowest + * index that is above @indexp and no more than @max. + * If an entry is found, @indexp is updated to be the index of the entry. + * This function is protected by the RCU read lock, so it may miss entries + * which are being simultaneously added. It will not return an + * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). + * + * Context: Any context. Takes and releases the RCU lock. + * Return: The pointer, if found, otherwise %NULL. + */ +void *xa_find_after(struct xarray *xa, unsigned long *indexp, + unsigned long max, xa_mark_t filter) +{ + XA_STATE(xas, xa, *indexp + 1); + void *entry; + + rcu_read_lock(); + for (;;) { + if ((__force unsigned int)filter < XA_MAX_MARKS) + entry = xas_find_marked(&xas, max, filter); + else + entry = xas_find(&xas, max); + if (xas.xa_shift) { + if (xas.xa_index & ((1UL << xas.xa_shift) - 1)) + continue; + } else { + if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK)) + continue; + } + if (!xas_retry(&xas, entry)) + break; + } + rcu_read_unlock(); + + if (entry) + *indexp = xas.xa_index; + return entry; +} +EXPORT_SYMBOL(xa_find_after); + #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { -- cgit v1.2.3-71-gd317 From 80a0a1a9a3cde9b23851e8eb7160e2786549306a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 14 Nov 2017 16:42:22 -0500 Subject: xarray: Extract entries from an XArray The xa_extract function combines the functionality of radix_tree_gang_lookup() and radix_tree_gang_lookup_tagged(). It extracts entries matching the specified filter into a normal array. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 ++ lib/xarray.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 66b10efa5a50..82ceed981924 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -284,6 +284,8 @@ void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); +unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, + unsigned long max, unsigned int n, xa_mark_t); /** * xa_init() - Initialise an empty XArray. diff --git a/lib/xarray.c b/lib/xarray.c index 24494f42daa6..70e04810c8c2 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1444,6 +1444,86 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp, } EXPORT_SYMBOL(xa_find_after); +static unsigned int xas_extract_present(struct xa_state *xas, void **dst, + unsigned long max, unsigned int n) +{ + void *entry; + unsigned int i = 0; + + rcu_read_lock(); + xas_for_each(xas, entry, max) { + if (xas_retry(xas, entry)) + continue; + dst[i++] = entry; + if (i == n) + break; + } + rcu_read_unlock(); + + return i; +} + +static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, + unsigned long max, unsigned int n, xa_mark_t mark) +{ + void *entry; + unsigned int i = 0; + + rcu_read_lock(); + xas_for_each_marked(xas, entry, max, mark) { + if (xas_retry(xas, entry)) + continue; + dst[i++] = entry; + if (i == n) + break; + } + rcu_read_unlock(); + + return i; +} + +/** + * xa_extract() - Copy selected entries from the XArray into a normal array. + * @xa: The source XArray to copy from. + * @dst: The buffer to copy entries into. + * @start: The first index in the XArray eligible to be selected. + * @max: The last index in the XArray eligible to be selected. + * @n: The maximum number of entries to copy. + * @filter: Selection criterion. + * + * Copies up to @n entries that match @filter from the XArray. The + * copied entries will have indices between @start and @max, inclusive. + * + * The @filter may be an XArray mark value, in which case entries which are + * marked with that mark will be copied. It may also be %XA_PRESENT, in + * which case all entries which are not NULL will be copied. + * + * The entries returned may not represent a snapshot of the XArray at a + * moment in time. For example, if another thread stores to index 5, then + * index 10, calling xa_extract() may return the old contents of index 5 + * and the new contents of index 10. Indices not modified while this + * function is running will not be skipped. + * + * If you need stronger guarantees, holding the xa_lock across calls to this + * function will prevent concurrent modification. + * + * Context: Any context. Takes and releases the RCU lock. + * Return: The number of entries copied. + */ +unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, + unsigned long max, unsigned int n, xa_mark_t filter) +{ + XA_STATE(xas, xa, start); + + if (!n) + return 0; + + if ((__force unsigned int)filter < XA_MAX_MARKS) + return xas_extract_marked(&xas, dst, max, n, filter); + return xas_extract_present(&xas, dst, max, n); +} +EXPORT_SYMBOL(xa_extract); + #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { -- cgit v1.2.3-71-gd317 From 687149fca1f37c447e5d161e0a4a04cb2c880cb6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 08:16:34 -0500 Subject: xarray: Destroy an XArray This function frees all the internal memory allocated to the xarray and reinitialises it to be empty. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 1 + lib/test_xarray.c | 34 ++++++++++++++++++++++++++++++++++ lib/xarray.c | 28 ++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 82ceed981924..0a758fa3ed2c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,6 +286,7 @@ void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); +void xa_destroy(struct xarray *); /** * xa_init() - Initialise an empty XArray. diff --git a/lib/test_xarray.c b/lib/test_xarray.c index e3c2d4d00b15..a96f67caa1c2 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -465,6 +465,39 @@ static noinline void check_find(struct xarray *xa) check_multi_find_2(xa); } +static noinline void check_destroy(struct xarray *xa) +{ + unsigned long index; + + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Destroying an empty array is a no-op */ + xa_destroy(xa); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Destroying an array with a single entry */ + for (index = 0; index < 1000; index++) { + xa_store_index(xa, index, GFP_KERNEL); + XA_BUG_ON(xa, xa_empty(xa)); + xa_destroy(xa); + XA_BUG_ON(xa, !xa_empty(xa)); + } + + /* Destroying an array with a single entry at ULONG_MAX */ + xa_store(xa, ULONG_MAX, xa, GFP_KERNEL); + XA_BUG_ON(xa, xa_empty(xa)); + xa_destroy(xa); + XA_BUG_ON(xa, !xa_empty(xa)); + +#ifdef CONFIG_XARRAY_MULTI + /* Destroying an array with a multi-index entry */ + xa_store_order(xa, 1 << 11, 11, xa, GFP_KERNEL); + XA_BUG_ON(xa, xa_empty(xa)); + xa_destroy(xa); + XA_BUG_ON(xa, !xa_empty(xa)); +#endif +} + static DEFINE_XARRAY(array); static int xarray_checks(void) @@ -478,6 +511,7 @@ static int xarray_checks(void) check_cmpxchg(&array); check_multi_store(&array); check_find(&array); + check_destroy(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index 70e04810c8c2..057dbe0d3bf6 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1524,6 +1524,34 @@ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, } EXPORT_SYMBOL(xa_extract); +/** + * xa_destroy() - Free all internal data structures. + * @xa: XArray. + * + * After calling this function, the XArray is empty and has freed all memory + * allocated for its internal data structures. You are responsible for + * freeing the objects referenced by the XArray. + * + * Context: Any context. Takes and releases the xa_lock, interrupt-safe. + */ +void xa_destroy(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + unsigned long flags; + void *entry; + + xas.xa_node = NULL; + xas_lock_irqsave(&xas, flags); + entry = xa_head_locked(xa); + RCU_INIT_POINTER(xa->xa_head, NULL); + xas_init_marks(&xas); + /* lockdep checks we're still holding the lock in xas_free_nodes() */ + if (xa_is_node(entry)) + xas_free_nodes(&xas, xa_to_node(entry)); + xas_unlock_irqrestore(&xas, flags); +} +EXPORT_SYMBOL(xa_destroy); + #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { -- cgit v1.2.3-71-gd317 From 64d3e9a9e0cc51957d243dd2b0adc5d74ff5e128 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 00:06:52 -0500 Subject: xarray: Step through an XArray The xas_next and xas_prev functions move the xas index by one position, and adjust the rest of the iterator state to match it. This is more efficient than calling xas_set() as it keeps the iterator at the leaves of the tree instead of walking the iterator from the root each time. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 67 ++++++++++++++++++++++++++++ lib/test_xarray.c | 115 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/xarray.c | 74 +++++++++++++++++++++++++++++++ 3 files changed, 256 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0a758fa3ed2c..381f94a66762 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -828,6 +828,12 @@ static inline bool xas_not_node(struct xa_node *node) return ((unsigned long)node & 3) || !node; } +/* True if the node represents RESTART or an error */ +static inline bool xas_frozen(struct xa_node *node) +{ + return (unsigned long)node & 2; +} + /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { @@ -1082,4 +1088,65 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +void *__xas_next(struct xa_state *); +void *__xas_prev(struct xa_state *); + +/** + * xas_prev() - Move iterator to previous index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * subtracted from the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index 0, this function wraps + * around to %ULONG_MAX. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_prev(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == 0)) + return __xas_prev(xas); + + xas->xa_index--; + xas->xa_offset--; + return xa_entry(xas->xa, node, xas->xa_offset); +} + +/** + * xas_next() - Move state to next index. + * @xas: XArray operation state. + * + * If the @xas was in an error state, it will remain in an error state + * and this function will return %NULL. If the @xas has never been walked, + * it will have the effect of calling xas_load(). Otherwise one will be + * added to the index and the state will be walked to the correct + * location in the array for the next operation. + * + * If the iterator was referencing index %ULONG_MAX, this function wraps + * around to 0. + * + * Return: The entry at the new index. This may be %NULL or an internal + * entry. + */ +static inline void *xas_next(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + + if (unlikely(xas_not_node(node) || node->shift || + xas->xa_offset == XA_CHUNK_MASK)) + return __xas_next(xas); + + xas->xa_index++; + xas->xa_offset++; + return xa_entry(xas->xa, node, xas->xa_offset); +} + #endif /* _LINUX_XARRAY_H */ diff --git a/lib/test_xarray.c b/lib/test_xarray.c index a96f67caa1c2..85ef1882dd3c 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -465,6 +465,120 @@ static noinline void check_find(struct xarray *xa) check_multi_find_2(xa); } +static noinline void check_move_small(struct xarray *xa, unsigned long idx) +{ + XA_STATE(xas, xa, 0); + unsigned long i; + + xa_store_index(xa, 0, GFP_KERNEL); + xa_store_index(xa, idx, GFP_KERNEL); + + rcu_read_lock(); + for (i = 0; i < idx * 4; i++) { + void *entry = xas_next(&xas); + if (i <= idx) + XA_BUG_ON(xa, xas.xa_node == XAS_RESTART); + XA_BUG_ON(xa, xas.xa_index != i); + if (i == 0 || i == idx) + XA_BUG_ON(xa, entry != xa_mk_value(i)); + else + XA_BUG_ON(xa, entry != NULL); + } + xas_next(&xas); + XA_BUG_ON(xa, xas.xa_index != i); + + do { + void *entry = xas_prev(&xas); + i--; + if (i <= idx) + XA_BUG_ON(xa, xas.xa_node == XAS_RESTART); + XA_BUG_ON(xa, xas.xa_index != i); + if (i == 0 || i == idx) + XA_BUG_ON(xa, entry != xa_mk_value(i)); + else + XA_BUG_ON(xa, entry != NULL); + } while (i > 0); + + xas_set(&xas, ULONG_MAX); + XA_BUG_ON(xa, xas_next(&xas) != NULL); + XA_BUG_ON(xa, xas.xa_index != ULONG_MAX); + XA_BUG_ON(xa, xas_next(&xas) != xa_mk_value(0)); + XA_BUG_ON(xa, xas.xa_index != 0); + XA_BUG_ON(xa, xas_prev(&xas) != NULL); + XA_BUG_ON(xa, xas.xa_index != ULONG_MAX); + rcu_read_unlock(); + + xa_erase_index(xa, 0); + xa_erase_index(xa, idx); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_move(struct xarray *xa) +{ + XA_STATE(xas, xa, (1 << 16) - 1); + unsigned long i; + + for (i = 0; i < (1 << 16); i++) + XA_BUG_ON(xa, xa_store_index(xa, i, GFP_KERNEL) != NULL); + + rcu_read_lock(); + do { + void *entry = xas_prev(&xas); + i--; + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, i != xas.xa_index); + } while (i != 0); + + XA_BUG_ON(xa, xas_prev(&xas) != NULL); + XA_BUG_ON(xa, xas.xa_index != ULONG_MAX); + + do { + void *entry = xas_next(&xas); + XA_BUG_ON(xa, entry != xa_mk_value(i)); + XA_BUG_ON(xa, i != xas.xa_index); + i++; + } while (i < (1 << 16)); + rcu_read_unlock(); + + for (i = (1 << 8); i < (1 << 15); i++) + xa_erase_index(xa, i); + + i = xas.xa_index; + + rcu_read_lock(); + do { + void *entry = xas_prev(&xas); + i--; + if ((i < (1 << 8)) || (i >= (1 << 15))) + XA_BUG_ON(xa, entry != xa_mk_value(i)); + else + XA_BUG_ON(xa, entry != NULL); + XA_BUG_ON(xa, i != xas.xa_index); + } while (i != 0); + + XA_BUG_ON(xa, xas_prev(&xas) != NULL); + XA_BUG_ON(xa, xas.xa_index != ULONG_MAX); + + do { + void *entry = xas_next(&xas); + if ((i < (1 << 8)) || (i >= (1 << 15))) + XA_BUG_ON(xa, entry != xa_mk_value(i)); + else + XA_BUG_ON(xa, entry != NULL); + XA_BUG_ON(xa, i != xas.xa_index); + i++; + } while (i < (1 << 16)); + rcu_read_unlock(); + + xa_destroy(xa); + + for (i = 0; i < 16; i++) + check_move_small(xa, 1UL << i); + + for (i = 2; i < 16; i++) + check_move_small(xa, (1UL << i) - 1); +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -512,6 +626,7 @@ static int xarray_checks(void) check_multi_store(&array); check_find(&array); check_destroy(&array); + check_move(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index 057dbe0d3bf6..303c46579598 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -876,6 +876,80 @@ void xas_pause(struct xa_state *xas) } EXPORT_SYMBOL_GPL(xas_pause); +/* + * __xas_prev() - Find the previous entry in the XArray. + * @xas: XArray operation state. + * + * Helper function for xas_prev() which handles all the complex cases + * out of line. + */ +void *__xas_prev(struct xa_state *xas) +{ + void *entry; + + if (!xas_frozen(xas->xa_node)) + xas->xa_index--; + if (xas_not_node(xas->xa_node)) + return xas_load(xas); + + if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) + xas->xa_offset--; + + while (xas->xa_offset == 255) { + xas->xa_offset = xas->xa_node->offset - 1; + xas->xa_node = xa_parent(xas->xa, xas->xa_node); + if (!xas->xa_node) + return set_bounds(xas); + } + + for (;;) { + entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); + if (!xa_is_node(entry)) + return entry; + + xas->xa_node = xa_to_node(entry); + xas_set_offset(xas); + } +} +EXPORT_SYMBOL_GPL(__xas_prev); + +/* + * __xas_next() - Find the next entry in the XArray. + * @xas: XArray operation state. + * + * Helper function for xas_next() which handles all the complex cases + * out of line. + */ +void *__xas_next(struct xa_state *xas) +{ + void *entry; + + if (!xas_frozen(xas->xa_node)) + xas->xa_index++; + if (xas_not_node(xas->xa_node)) + return xas_load(xas); + + if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) + xas->xa_offset++; + + while (xas->xa_offset == XA_CHUNK_SIZE) { + xas->xa_offset = xas->xa_node->offset + 1; + xas->xa_node = xa_parent(xas->xa, xas->xa_node); + if (!xas->xa_node) + return set_bounds(xas); + } + + for (;;) { + entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); + if (!xa_is_node(entry)) + return entry; + + xas->xa_node = xa_to_node(entry); + xas_set_offset(xas); + } +} +EXPORT_SYMBOL_GPL(__xas_next); + /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. -- cgit v1.2.3-71-gd317 From 4e99d4e9579d3b950bf4b38d0d64eb1b9be78761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Jun 2018 22:46:02 -0400 Subject: xarray: Add xas_for_each_conflict This iterator iterates over each entry that is stored in the index or indices specified by the xa_state. This is intended for use for a conditional store of a multiindex entry, or to allow entries which are about to be removed from the xarray to be disposed of properly. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 17 +++++++++++++ lib/test_xarray.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++ lib/xarray.c | 61 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 146 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 381f94a66762..2664e718dbd3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -878,6 +878,7 @@ static inline bool xas_retry(struct xa_state *xas, const void *entry) void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); +void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); @@ -1088,6 +1089,22 @@ enum { for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) +/** + * xas_for_each_conflict() - Iterate over a range of an XArray. + * @xas: XArray operation state. + * @entry: Entry retrieved from the array. + * + * The loop body will be executed for each entry in the XArray that lies + * within the range specified by @xas. If the loop completes successfully, + * any entries that lie in this range will be replaced by @entry. The caller + * may break out of the loop; if they do so, the contents of the XArray will + * be unchanged. The operation may fail due to an out of memory condition. + * The caller may also call xa_set_err() to exit the loop while setting an + * error to record the reason. + */ +#define xas_for_each_conflict(xas, entry) \ + while ((entry = xas_find_conflict(xas))) + void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 85ef1882dd3c..8eba3de1baea 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -365,6 +365,73 @@ static noinline void check_multi_store(struct xarray *xa) #endif } +static noinline void __check_store_iter(struct xarray *xa, unsigned long start, + unsigned int order, unsigned int present) +{ + XA_STATE_ORDER(xas, xa, start, order); + void *entry; + unsigned int count = 0; + +retry: + xas_lock(&xas); + xas_for_each_conflict(&xas, entry) { + XA_BUG_ON(xa, !xa_is_value(entry)); + XA_BUG_ON(xa, entry < xa_mk_value(start)); + XA_BUG_ON(xa, entry > xa_mk_value(start + (1UL << order) - 1)); + count++; + } + xas_store(&xas, xa_mk_value(start)); + xas_unlock(&xas); + if (xas_nomem(&xas, GFP_KERNEL)) { + count = 0; + goto retry; + } + XA_BUG_ON(xa, xas_error(&xas)); + XA_BUG_ON(xa, count != present); + XA_BUG_ON(xa, xa_load(xa, start) != xa_mk_value(start)); + XA_BUG_ON(xa, xa_load(xa, start + (1UL << order) - 1) != + xa_mk_value(start)); + xa_erase_index(xa, start); +} + +static noinline void check_store_iter(struct xarray *xa) +{ + unsigned int i, j; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; + + for (i = 0; i < max_order; i++) { + unsigned int min = 1 << i; + unsigned int max = (2 << i) - 1; + __check_store_iter(xa, 0, i, 0); + XA_BUG_ON(xa, !xa_empty(xa)); + __check_store_iter(xa, min, i, 0); + XA_BUG_ON(xa, !xa_empty(xa)); + + xa_store_index(xa, min, GFP_KERNEL); + __check_store_iter(xa, min, i, 1); + XA_BUG_ON(xa, !xa_empty(xa)); + xa_store_index(xa, max, GFP_KERNEL); + __check_store_iter(xa, min, i, 1); + XA_BUG_ON(xa, !xa_empty(xa)); + + for (j = 0; j < min; j++) + xa_store_index(xa, j, GFP_KERNEL); + __check_store_iter(xa, 0, i, min); + XA_BUG_ON(xa, !xa_empty(xa)); + for (j = 0; j < min; j++) + xa_store_index(xa, min + j, GFP_KERNEL); + __check_store_iter(xa, min, i, min); + XA_BUG_ON(xa, !xa_empty(xa)); + } +#ifdef CONFIG_XARRAY_MULTI + xa_store_index(xa, 63, GFP_KERNEL); + xa_store_index(xa, 65, GFP_KERNEL); + __check_store_iter(xa, 64, 2, 1); + xa_erase_index(xa, 63); +#endif + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_multi_find(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI @@ -627,6 +694,7 @@ static int xarray_checks(void) check_find(&array); check_destroy(&array); check_move(&array); + check_store_iter(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; diff --git a/lib/xarray.c b/lib/xarray.c index 303c46579598..41f8ebc651f5 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1110,6 +1110,67 @@ max: } EXPORT_SYMBOL_GPL(xas_find_marked); +/** + * xas_find_conflict() - Find the next present entry in a range. + * @xas: XArray operation state. + * + * The @xas describes both a range and a position within that range. + * + * Context: Any context. Expects xa_lock to be held. + * Return: The next entry in the range covered by @xas or %NULL. + */ +void *xas_find_conflict(struct xa_state *xas) +{ + void *curr; + + if (xas_error(xas)) + return NULL; + + if (!xas->xa_node) + return NULL; + + if (xas_top(xas->xa_node)) { + curr = xas_start(xas); + if (!curr) + return NULL; + while (xa_is_node(curr)) { + struct xa_node *node = xa_to_node(curr); + curr = xas_descend(xas, node); + } + if (curr) + return curr; + } + + if (xas->xa_node->shift > xas->xa_shift) + return NULL; + + for (;;) { + if (xas->xa_node->shift == xas->xa_shift) { + if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) + break; + } else if (xas->xa_offset == XA_CHUNK_MASK) { + xas->xa_offset = xas->xa_node->offset; + xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); + if (!xas->xa_node) + break; + continue; + } + curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); + if (xa_is_sibling(curr)) + continue; + while (xa_is_node(curr)) { + xas->xa_node = xa_to_node(curr); + xas->xa_offset = 0; + curr = xa_entry_locked(xas->xa, xas->xa_node, 0); + } + if (curr) + return curr; + } + xas->xa_offset -= xas->xa_sibs; + return NULL; +} +EXPORT_SYMBOL_GPL(xas_find_conflict); + /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. -- cgit v1.2.3-71-gd317 From 2264f5132fe45571139727ebdeb78696b35d1506 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 00:11:48 -0500 Subject: xarray: Add xas_create_range This hopefully temporary function is useful for users who have not yet been converted to multi-index entries. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 13 ++++++ lib/test_xarray.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++ lib/xarray.c | 50 +++++++++++++++++++++ 3 files changed, 182 insertions(+) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 2664e718dbd3..deae17aa0ed7 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -822,6 +822,17 @@ static inline bool xas_valid(const struct xa_state *xas) return !xas_invalid(xas); } +/** + * xas_is_node() - Does the xas point to a node? + * @xas: XArray operation state. + * + * Return: %true if the xas currently references a node. + */ +static inline bool xas_is_node(const struct xa_state *xas) +{ + return xas_valid(xas) && xas->xa_node; +} + /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { @@ -889,6 +900,8 @@ void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); +void xas_create_range(struct xa_state *); + /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 8eba3de1baea..703370015d10 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -646,6 +646,124 @@ static noinline void check_move(struct xarray *xa) check_move_small(xa, (1UL << i) - 1); } +static noinline void xa_store_many_order(struct xarray *xa, + unsigned long index, unsigned order) +{ + XA_STATE_ORDER(xas, xa, index, order); + unsigned int i = 0; + + do { + xas_lock(&xas); + XA_BUG_ON(xa, xas_find_conflict(&xas)); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; + for (i = 0; i < (1U << order); i++) { + XA_BUG_ON(xa, xas_store(&xas, xa_mk_value(index + i))); + xas_next(&xas); + } +unlock: + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + XA_BUG_ON(xa, xas_error(&xas)); +} + +static noinline void check_create_range_1(struct xarray *xa, + unsigned long index, unsigned order) +{ + unsigned long i; + + xa_store_many_order(xa, index, order); + for (i = index; i < index + (1UL << order); i++) + xa_erase_index(xa, i); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_create_range_2(struct xarray *xa, unsigned order) +{ + unsigned long i; + unsigned long nr = 1UL << order; + + for (i = 0; i < nr * nr; i += nr) + xa_store_many_order(xa, i, order); + for (i = 0; i < nr * nr; i++) + xa_erase_index(xa, i); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_create_range_3(void) +{ + XA_STATE(xas, NULL, 0); + xas_set_err(&xas, -EEXIST); + xas_create_range(&xas); + XA_BUG_ON(NULL, xas_error(&xas) != -EEXIST); +} + +static noinline void check_create_range_4(struct xarray *xa, + unsigned long index, unsigned order) +{ + XA_STATE_ORDER(xas, xa, index, order); + unsigned long base = xas.xa_index; + unsigned long i = 0; + + xa_store_index(xa, index, GFP_KERNEL); + do { + xas_lock(&xas); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; + for (i = 0; i < (1UL << order); i++) { + void *old = xas_store(&xas, xa_mk_value(base + i)); + if (xas.xa_index == index) + XA_BUG_ON(xa, old != xa_mk_value(base + i)); + else + XA_BUG_ON(xa, old != NULL); + xas_next(&xas); + } +unlock: + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + XA_BUG_ON(xa, xas_error(&xas)); + + for (i = base; i < base + (1UL << order); i++) + xa_erase_index(xa, i); + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_create_range(struct xarray *xa) +{ + unsigned int order; + unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 12 : 1; + + for (order = 0; order < max_order; order++) { + check_create_range_1(xa, 0, order); + check_create_range_1(xa, 1U << order, order); + check_create_range_1(xa, 2U << order, order); + check_create_range_1(xa, 3U << order, order); + check_create_range_1(xa, 1U << 24, order); + if (order < 10) + check_create_range_2(xa, order); + + check_create_range_4(xa, 0, order); + check_create_range_4(xa, 1U << order, order); + check_create_range_4(xa, 2U << order, order); + check_create_range_4(xa, 3U << order, order); + check_create_range_4(xa, 1U << 24, order); + + check_create_range_4(xa, 1, order); + check_create_range_4(xa, (1U << order) + 1, order); + check_create_range_4(xa, (2U << order) + 1, order); + check_create_range_4(xa, (2U << order) - 1, order); + check_create_range_4(xa, (3U << order) + 1, order); + check_create_range_4(xa, (3U << order) - 1, order); + check_create_range_4(xa, (1U << 24) + 1, order); + } + + check_create_range_3(); +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -694,6 +812,7 @@ static int xarray_checks(void) check_find(&array); check_destroy(&array); check_move(&array); + check_create_range(&array); check_store_iter(&array); printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); diff --git a/lib/xarray.c b/lib/xarray.c index 41f8ebc651f5..ff37516fe832 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -637,6 +637,56 @@ static void *xas_create(struct xa_state *xas) return entry; } +/** + * xas_create_range() - Ensure that stores to this range will succeed + * @xas: XArray operation state. + * + * Creates all of the slots in the range covered by @xas. Sets @xas to + * create single-index entries and positions it at the beginning of the + * range. This is for the benefit of users which have not yet been + * converted to use multi-index entries. + */ +void xas_create_range(struct xa_state *xas) +{ + unsigned long index = xas->xa_index; + unsigned char shift = xas->xa_shift; + unsigned char sibs = xas->xa_sibs; + + xas->xa_index |= ((sibs + 1) << shift) - 1; + if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) + xas->xa_offset |= sibs; + xas->xa_shift = 0; + xas->xa_sibs = 0; + + for (;;) { + xas_create(xas); + if (xas_error(xas)) + goto restore; + if (xas->xa_index <= (index | XA_CHUNK_MASK)) + goto success; + xas->xa_index -= XA_CHUNK_SIZE; + + for (;;) { + struct xa_node *node = xas->xa_node; + xas->xa_node = xa_parent_locked(xas->xa, node); + xas->xa_offset = node->offset - 1; + if (node->offset != 0) + break; + } + } + +restore: + xas->xa_shift = shift; + xas->xa_sibs = sibs; + xas->xa_index = index; + return; +success: + xas->xa_index = index; + if (xas->xa_node) + xas_set_offset(xas); +} +EXPORT_SYMBOL_GPL(xas_create_range); + static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { -- cgit v1.2.3-71-gd317 From 9f14d4f1f1045f161fd4db8a8e194b7825c2874a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 1 Oct 2018 14:54:59 -0400 Subject: xarray: Add xa_reserve and xa_release This function reserves a slot in the XArray for users which need to acquire multiple locks before storing their entry in the tree and so cannot use a plain xa_store(). Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 6 +++++ include/linux/xarray.h | 34 ++++++++++++++++++++++++++-- lib/test_xarray.c | 40 +++++++++++++++++++++++++++++++++ lib/xarray.c | 47 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 125 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 4b101b4f3aa1..2b397da84bcd 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -293,6 +293,12 @@ to :c:func:`xas_retry`, and retry the operation if it returns ``true``. of this RCU period. You should restart the lookup from the head of the array. + * - Zero + - :c:func:`xa_is_zero` + - Zero entries appear as ``NULL`` through the Normal API, but occupy + an entry in the XArray which can be used to reserve the index for + future use. + Other internal entries may be added in the future. As far as possible, they will be handled by :c:func:`xas_retry`. diff --git a/include/linux/xarray.h b/include/linux/xarray.h index deae17aa0ed7..bed63d3cfea8 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -32,7 +32,8 @@ * The following internal entries have a special meaning: * * 0-62: Sibling entries - * 256: Retry entry + * 256: Zero entry + * 257: Retry entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only @@ -277,6 +278,7 @@ void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int xa_reserve(struct xarray *, unsigned long index, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -371,6 +373,20 @@ static inline int xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -658,7 +674,19 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(256) +#define XA_RETRY_ENTRY xa_mk_internal(257) + +/** + * xa_is_zero() - Is the entry a zero entry? + * @entry: Entry retrieved from the XArray + * + * Return: %true if the entry is a zero entry. + */ +static inline bool xa_is_zero(const void *entry) +{ + return unlikely(entry == XA_ZERO_ENTRY); +} /** * xa_is_retry() - Is the entry a retry entry? @@ -880,6 +908,8 @@ static inline void xas_reset(struct xa_state *xas) */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { + if (xa_is_zero(entry)) + return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 703370015d10..6aafd411a5c3 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -259,6 +259,45 @@ static noinline void check_cmpxchg(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_reserve(struct xarray *xa) +{ + void *entry; + unsigned long index = 0; + + /* An array with a reserved entry is not empty */ + XA_BUG_ON(xa, !xa_empty(xa)); + xa_reserve(xa, 12345678, GFP_KERNEL); + XA_BUG_ON(xa, xa_empty(xa)); + XA_BUG_ON(xa, xa_load(xa, 12345678)); + xa_release(xa, 12345678); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Releasing a used entry does nothing */ + xa_reserve(xa, 12345678, GFP_KERNEL); + XA_BUG_ON(xa, xa_store_index(xa, 12345678, GFP_NOWAIT) != NULL); + xa_release(xa, 12345678); + xa_erase_index(xa, 12345678); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* cmpxchg sees a reserved entry as NULL */ + xa_reserve(xa, 12345678, GFP_KERNEL); + XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, NULL, xa_mk_value(12345678), + GFP_NOWAIT) != NULL); + xa_release(xa, 12345678); + xa_erase_index(xa, 12345678); + XA_BUG_ON(xa, !xa_empty(xa)); + + /* Can iterate through a reserved entry */ + xa_store_index(xa, 5, GFP_KERNEL); + xa_reserve(xa, 6, GFP_KERNEL); + xa_store_index(xa, 7, GFP_KERNEL); + + xa_for_each(xa, entry, index, ULONG_MAX, XA_PRESENT) { + XA_BUG_ON(xa, index != 5 && index != 7); + } + xa_destroy(xa); +} + static noinline void check_xas_erase(struct xarray *xa) { XA_STATE(xas, xa, 0); @@ -808,6 +847,7 @@ static int xarray_checks(void) check_xa_shrink(&array); check_xas_erase(&array); check_cmpxchg(&array); + check_reserve(&array); check_multi_store(&array); check_find(&array); check_destroy(&array); diff --git a/lib/xarray.c b/lib/xarray.c index ff37516fe832..546461914282 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1266,6 +1266,8 @@ void *xa_load(struct xarray *xa, unsigned long index) rcu_read_lock(); do { entry = xas_load(&xas); + if (xa_is_zero(entry)) + entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); @@ -1275,6 +1277,8 @@ EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { + if (xa_is_zero(curr)) + return NULL; XA_NODE_BUG_ON(xas->xa_node, xa_is_internal(curr)); if (xas_error(xas)) curr = xas->xa_node; @@ -1394,6 +1398,8 @@ void *xa_cmpxchg(struct xarray *xa, unsigned long index, do { xas_lock(&xas); curr = xas_load(&xas); + if (curr == XA_ZERO_ENTRY) + curr = NULL; if (curr == old) xas_store(&xas, entry); xas_unlock(&xas); @@ -1430,6 +1436,8 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, do { curr = xas_load(&xas); + if (curr == XA_ZERO_ENTRY) + curr = NULL; if (curr == old) xas_store(&xas, entry); } while (__xas_nomem(&xas, gfp)); @@ -1438,6 +1446,43 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, } EXPORT_SYMBOL(__xa_cmpxchg); +/** + * xa_reserve() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * Ensures there is somewhere to store an entry at @index in the array. + * If there is already something stored at @index, this function does + * nothing. If there was nothing there, the entry is marked as reserved. + * Loads from @index will continue to see a %NULL pointer until a + * subsequent store to @index. + * + * If you do not use the entry that you have reserved, call xa_release() + * or xa_erase() to free any unnecessary memory. + * + * Context: Process context. Takes and releases the xa_lock, IRQ or BH safe + * if specified in XArray flags. May sleep if the @gfp flags permit. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + XA_STATE(xas, xa, index); + unsigned int lock_type = xa_lock_type(xa); + void *curr; + + do { + xas_lock_type(&xas, lock_type); + curr = xas_load(&xas); + if (!curr) + xas_store(&xas, XA_ZERO_ENTRY); + xas_unlock_type(&xas, lock_type); + } while (xas_nomem(&xas, gfp)); + + return xas_error(&xas); +} +EXPORT_SYMBOL(xa_reserve); + /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. @@ -1797,6 +1842,8 @@ void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); + else if (xa_is_zero(entry)) + pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } -- cgit v1.2.3-71-gd317 From 371c752dc66948714ee3b66c3306f3ff1ff71d2e Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 10:50:12 -0400 Subject: xarray: Track free entries in an XArray Add the optional ability to track which entries in an XArray are free and provide xa_alloc() to replace most of the functionality of the IDR. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 23 +++++++-- include/linux/xarray.h | 101 ++++++++++++++++++++++++++++++++++++++ lib/test_xarray.c | 61 +++++++++++++++++++++++ lib/xarray.c | 88 +++++++++++++++++++++++++++++++-- 4 files changed, 266 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 2b397da84bcd..463e4c798ec1 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -103,12 +103,25 @@ Finally, you can remove all entries from an XArray by calling to free the entries first. You can do this by iterating over all present entries in the XArray using the :c:func:`xa_for_each` iterator. +ID assignment +------------- + +You can call :c:func:`xa_alloc` to store the entry at any unused index +in the XArray. If you need to modify the array from interrupt context, +you can use :c:func:`xa_alloc_bh` or :c:func:`xa_alloc_irq` to disable +interrupts while allocating the ID. Unlike :c:func:`xa_store`, allocating +a ``NULL`` pointer does not delete an entry. Instead it reserves an +entry like :c:func:`xa_reserve` and you can release it using either +:c:func:`xa_erase` or :c:func:`xa_release`. To use ID assignment, the +XArray must be defined with :c:func:`DEFINE_XARRAY_ALLOC`, or initialised +by passing ``XA_FLAGS_ALLOC`` to :c:func:`xa_init_flags`, + Memory allocation ----------------- -The :c:func:`xa_store`, :c:func:`xa_cmpxchg`, :c:func:`xa_reserve` -and :c:func:`xa_insert` functions take a gfp_t parameter in case -the XArray needs to allocate memory to store this entry. +The :c:func:`xa_store`, :c:func:`xa_cmpxchg`, :c:func:`xa_alloc`, +:c:func:`xa_reserve` and :c:func:`xa_insert` functions take a gfp_t +parameter in case the XArray needs to allocate memory to store this entry. If the entry is being deleted, no memory allocation needs to be performed, and the GFP flags specified will be ignored. @@ -143,6 +156,9 @@ Takes xa_lock internally: * :c:func:`xa_erase_bh` * :c:func:`xa_erase_irq` * :c:func:`xa_cmpxchg` + * :c:func:`xa_alloc` + * :c:func:`xa_alloc_bh` + * :c:func:`xa_alloc_irq` * :c:func:`xa_destroy` * :c:func:`xa_set_mark` * :c:func:`xa_clear_mark` @@ -152,6 +168,7 @@ Assumes xa_lock held on entry: * :c:func:`__xa_insert` * :c:func:`__xa_erase` * :c:func:`__xa_cmpxchg` + * :c:func:`__xa_alloc` * :c:func:`__xa_set_mark` * :c:func:`__xa_clear_mark` diff --git a/include/linux/xarray.h b/include/linux/xarray.h index bed63d3cfea8..e0b57af52e9b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -205,6 +205,7 @@ typedef unsigned __bitwise xa_mark_t; #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 +#define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, @@ -217,9 +218,12 @@ enum xa_lock_type { */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) +#define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) +#define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) + /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. @@ -273,6 +277,15 @@ struct xarray { */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) +/** + * DEFINE_XARRAY_ALLOC() - Define an XArray which can allocate IDs. + * @name: A string that names your XArray. + * + * This is intended for file scope definitions of allocating XArrays. + * See also DEFINE_XARRAY(). + */ +#define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) + void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); @@ -439,6 +452,7 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -518,6 +532,93 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_alloc() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_alloc_bh() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_bh(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_alloc_irq() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, + gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_alloc(xa, id, max, entry, gfp); + xa_unlock_irq(xa); + + return err; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 6aafd411a5c3..a752e6a37e6f 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -33,6 +33,15 @@ static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) return xa_store(xa, index, xa_mk_value(index & LONG_MAX), gfp); } +static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + u32 id = 0; + + XA_BUG_ON(xa, xa_alloc(xa, &id, UINT_MAX, xa_mk_value(index & LONG_MAX), + gfp) != 0); + XA_BUG_ON(xa, id != index); +} + static void xa_erase_index(struct xarray *xa, unsigned long index) { XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_value(index & LONG_MAX)); @@ -404,6 +413,57 @@ static noinline void check_multi_store(struct xarray *xa) #endif } +static DEFINE_XARRAY_ALLOC(xa0); + +static noinline void check_xa_alloc(void) +{ + int i; + u32 id; + + /* An empty array should assign 0 to the first alloc */ + xa_alloc_index(&xa0, 0, GFP_KERNEL); + + /* Erasing it should make the array empty again */ + xa_erase_index(&xa0, 0); + XA_BUG_ON(&xa0, !xa_empty(&xa0)); + + /* And it should assign 0 again */ + xa_alloc_index(&xa0, 0, GFP_KERNEL); + + /* The next assigned ID should be 1 */ + xa_alloc_index(&xa0, 1, GFP_KERNEL); + xa_erase_index(&xa0, 1); + + /* Storing a value should mark it used */ + xa_store_index(&xa0, 1, GFP_KERNEL); + xa_alloc_index(&xa0, 2, GFP_KERNEL); + + /* If we then erase 0, it should be free */ + xa_erase_index(&xa0, 0); + xa_alloc_index(&xa0, 0, GFP_KERNEL); + + xa_erase_index(&xa0, 1); + xa_erase_index(&xa0, 2); + + for (i = 1; i < 5000; i++) { + xa_alloc_index(&xa0, i, GFP_KERNEL); + } + + xa_destroy(&xa0); + + id = 0xfffffffeU; + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + GFP_KERNEL) != 0); + XA_BUG_ON(&xa0, id != 0xfffffffeU); + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + GFP_KERNEL) != 0); + XA_BUG_ON(&xa0, id != 0xffffffffU); + XA_BUG_ON(&xa0, xa_alloc(&xa0, &id, UINT_MAX, xa_mk_value(0), + GFP_KERNEL) != -ENOSPC); + XA_BUG_ON(&xa0, id != 0xffffffffU); + xa_destroy(&xa0); +} + static noinline void __check_store_iter(struct xarray *xa, unsigned long start, unsigned int order, unsigned int present) { @@ -849,6 +909,7 @@ static int xarray_checks(void) check_cmpxchg(&array); check_reserve(&array); check_multi_store(&array); + check_xa_alloc(); check_find(&array); check_destroy(&array); check_move(&array); diff --git a/lib/xarray.c b/lib/xarray.c index 546461914282..9a0d49d4b5f0 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -52,6 +52,11 @@ static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) xas_unlock(xas); } +static inline bool xa_track_free(const struct xarray *xa) +{ + return xa->xa_flags & XA_FLAGS_TRACK_FREE; +} + static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) @@ -94,6 +99,11 @@ static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } +static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) +{ + bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); +} + #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) @@ -416,6 +426,8 @@ static void xas_shrink(struct xa_state *xas) xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); + if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) + xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; @@ -549,8 +561,15 @@ static int xas_expand(struct xa_state *xas, void *head) /* Propagate the aggregated mark info to the new child */ for (;;) { - if (xa_marked(xa, mark)) + if (xa_track_free(xa) && mark == XA_FREE_MARK) { + node_mark_all(node, XA_FREE_MARK); + if (!xa_marked(xa, XA_FREE_MARK)) { + node_clear_mark(node, 0, XA_FREE_MARK); + xa_mark_set(xa, XA_FREE_MARK); + } + } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); + } if (mark == XA_MARK_MAX) break; mark_inc(mark); @@ -624,6 +643,8 @@ static void *xas_create(struct xa_state *xas) node = xas_alloc(xas, shift); if (!node) break; + if (xa_track_free(xa)) + node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); @@ -882,7 +903,10 @@ void xas_init_marks(const struct xa_state *xas) xa_mark_t mark = 0; for (;;) { - xas_clear_mark(xas, mark); + if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) + xas_set_mark(xas, mark); + else + xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); @@ -1333,6 +1357,8 @@ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) do { xas_lock(&xas); curr = xas_store(&xas, entry); + if (xa_track_free(xa) && entry) + xas_clear_mark(&xas, XA_FREE_MARK); xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); @@ -1365,6 +1391,8 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) do { curr = xas_store(&xas, entry); + if (xa_track_free(xa) && entry) + xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); @@ -1400,8 +1428,11 @@ void *xa_cmpxchg(struct xarray *xa, unsigned long index, curr = xas_load(&xas); if (curr == XA_ZERO_ENTRY) curr = NULL; - if (curr == old) + if (curr == old) { xas_store(&xas, entry); + if (xa_track_free(xa) && entry) + xas_clear_mark(&xas, XA_FREE_MARK); + } xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); @@ -1438,8 +1469,11 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, curr = xas_load(&xas); if (curr == XA_ZERO_ENTRY) curr = NULL; - if (curr == old) + if (curr == old) { xas_store(&xas, entry); + if (xa_track_free(xa) && entry) + xas_clear_mark(&xas, XA_FREE_MARK); + } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); @@ -1483,6 +1517,52 @@ int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) } EXPORT_SYMBOL(xa_reserve); +/** + * __xa_alloc() - Find somewhere to store this entry in the XArray. + * @xa: XArray. + * @id: Pointer to ID. + * @max: Maximum ID to allocate (inclusive). + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Allocates an unused ID in the range specified by @id and @max. + * Updates the @id pointer with the index, then stores the entry at that + * index. A concurrent lookup will not see an uninitialised @id. + * + * Context: Any context. Expects xa_lock to be held on entry. May + * release and reacquire xa_lock if @gfp flags permit. + * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if + * there is no more space in the XArray. + */ +int __xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, 0); + int err; + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return -EINVAL; + if (WARN_ON_ONCE(!xa_track_free(xa))) + return -EINVAL; + + if (!entry) + entry = XA_ZERO_ENTRY; + + do { + xas.xa_index = *id; + xas_find_marked(&xas, max, XA_FREE_MARK); + if (xas.xa_node == XAS_RESTART) + xas_set_err(&xas, -ENOSPC); + xas_store(&xas, entry); + xas_clear_mark(&xas, XA_FREE_MARK); + } while (__xas_nomem(&xas, gfp)); + + err = xas_error(&xas); + if (!err) + *id = xas.xa_index; + return err; +} +EXPORT_SYMBOL(__xa_alloc); + /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. -- cgit v1.2.3-71-gd317 From f32f004cddf86d63a9c42994bbce9f4e2f07c9fa Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 4 Jul 2018 15:42:46 -0400 Subject: ida: Convert to XArray Use the XA_TRACK_FREE ability to track which entries have a free bit, similarly to how it uses the radix tree's IDR_FREE tag. This eliminates the per-cpu ida_bitmap preload, and fixes the memory consumption regression I introduced when making the IDR able to store any pointer. Signed-off-by: Matthew Wilcox --- include/linux/idr.h | 18 +- lib/idr.c | 379 +++++++++++++++++++----------------- lib/radix-tree.c | 71 ------- tools/testing/radix-tree/idr-test.c | 8 +- 4 files changed, 213 insertions(+), 263 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index 3ec8628ce17f..60daf34b625d 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -214,8 +214,7 @@ static inline void idr_preload_end(void) ++id, (entry) = idr_get_next((idr), &(id))) /* - * IDA - IDR based id allocator, use when translation from id to - * pointer isn't necessary. + * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) @@ -225,14 +224,14 @@ struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; -DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); - struct ida { - struct radix_tree_root ida_rt; + struct xarray xa; }; +#define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) + #define IDA_INIT(name) { \ - .ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT), \ + .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) @@ -292,7 +291,7 @@ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) static inline void ida_init(struct ida *ida) { - INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); + xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } #define ida_simple_get(ida, start, end, gfp) \ @@ -301,9 +300,6 @@ static inline void ida_init(struct ida *ida) static inline bool ida_is_empty(const struct ida *ida) { - return radix_tree_empty(&ida->ida_rt); + return xa_empty(&ida->xa); } - -/* in lib/radix-tree.c */ -int ida_pre_get(struct ida *ida, gfp_t gfp_mask); #endif /* __IDR_H__ */ diff --git a/lib/idr.c b/lib/idr.c index 9a366b5be2c2..3c20ad9b0463 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -6,8 +6,6 @@ #include #include -DEFINE_PER_CPU(struct ida_bitmap *, ida_bitmap); - /** * idr_alloc_u32() - Allocate an ID. * @idr: IDR handle. @@ -320,6 +318,9 @@ EXPORT_SYMBOL(idr_replace); * free the individual IDs in it. You can use ida_is_empty() to find * out whether the IDA has any IDs currently allocated. * + * The IDA handles its own locking. It is safe to call any of the IDA + * functions without synchronisation in your code. + * * IDs are currently limited to the range [0-INT_MAX]. If this is an awkward * limitation, it should be quite straightforward to raise the maximum. */ @@ -327,151 +328,197 @@ EXPORT_SYMBOL(idr_replace); /* * Developer's notes: * - * The IDA uses the functionality provided by the IDR & radix tree to store - * bitmaps in each entry. The IDR_FREE tag means there is at least one bit - * free, unlike the IDR where it means at least one entry is free. + * The IDA uses the functionality provided by the XArray to store bitmaps in + * each entry. The XA_FREE_MARK is only cleared when all bits in the bitmap + * have been set. * - * I considered telling the radix tree that each slot is an order-10 node - * and storing the bit numbers in the radix tree, but the radix tree can't - * allow a single multiorder entry at index 0, which would significantly - * increase memory consumption for the IDA. So instead we divide the index - * by the number of bits in the leaf bitmap before doing a radix tree lookup. + * I considered telling the XArray that each slot is an order-10 node + * and indexing by bit number, but the XArray can't allow a single multi-index + * entry in the head, which would significantly increase memory consumption + * for the IDA. So instead we divide the index by the number of bits in the + * leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given * leaf, instead of allocating a 128-byte bitmap, we store the bits - * directly in the entry. - * - * We allow the radix tree 'exceptional' count to get out of date. Nothing - * in the IDA nor the radix tree code checks it. If it becomes important - * to maintain an accurate exceptional count, switch the rcu_assign_pointer() - * calls to radix_tree_iter_replace() which will correct the exceptional - * count. - * - * The IDA always requires a lock to alloc/free. If we add a 'test_bit' + * as a value entry. Value entries never have the XA_FREE_MARK cleared + * because we can always convert them into a bitmap entry. + * + * It would be possible to optimise further; once we've run out of a + * single 128-byte bitmap, we currently switch to a 576-byte node, put + * the 128-byte bitmap in the first entry and then start allocating extra + * 128-byte entries. We could instead use the 512 bytes of the node's + * data as a bitmap before moving to that scheme. I do not believe this + * is a worthwhile optimisation; Rasmus Villemoes surveyed the current + * users of the IDA and almost none of them use more than 1024 entries. + * Those that do use more than the 8192 IDs that the 512 bytes would + * provide. + * + * The IDA always uses a lock to alloc/free. If we add a 'test_bit' * equivalent, it will still need locking. Going to RCU lookup would require * using RCU to free bitmaps, and that's not trivial without embedding an * RCU head in the bitmap, which adds a 2-pointer overhead to each 128-byte * bitmap, which is excessive. */ -#define IDA_MAX (0x80000000U / IDA_BITMAP_BITS - 1) - -static int ida_get_new_above(struct ida *ida, int start) +/** + * ida_alloc_range() - Allocate an unused ID. + * @ida: IDA handle. + * @min: Lowest ID to allocate. + * @max: Highest ID to allocate. + * @gfp: Memory allocation flags. + * + * Allocate an ID between @min and @max, inclusive. The allocated ID will + * not exceed %INT_MAX, even if @max is larger. + * + * Context: Any context. + * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, + * or %-ENOSPC if there are no free IDs. + */ +int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, + gfp_t gfp) { - struct radix_tree_root *root = &ida->ida_rt; - void __rcu **slot; - struct radix_tree_iter iter; - struct ida_bitmap *bitmap; - unsigned long index; - unsigned bit; - int new; - - index = start / IDA_BITMAP_BITS; - bit = start % IDA_BITMAP_BITS; - - slot = radix_tree_iter_init(&iter, index); - for (;;) { - if (slot) - slot = radix_tree_next_slot(slot, &iter, - RADIX_TREE_ITER_TAGGED); - if (!slot) { - slot = idr_get_free(root, &iter, GFP_NOWAIT, IDA_MAX); - if (IS_ERR(slot)) { - if (slot == ERR_PTR(-ENOMEM)) - return -EAGAIN; - return PTR_ERR(slot); + XA_STATE(xas, &ida->xa, min / IDA_BITMAP_BITS); + unsigned bit = min % IDA_BITMAP_BITS; + unsigned long flags; + struct ida_bitmap *bitmap, *alloc = NULL; + + if ((int)min < 0) + return -ENOSPC; + + if ((int)max < 0) + max = INT_MAX; + +retry: + xas_lock_irqsave(&xas, flags); +next: + bitmap = xas_find_marked(&xas, max / IDA_BITMAP_BITS, XA_FREE_MARK); + if (xas.xa_index > min / IDA_BITMAP_BITS) + bit = 0; + if (xas.xa_index * IDA_BITMAP_BITS + bit > max) + goto nospc; + + if (xa_is_value(bitmap)) { + unsigned long tmp = xa_to_value(bitmap); + + if (bit < BITS_PER_XA_VALUE) { + bit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, bit); + if (xas.xa_index * IDA_BITMAP_BITS + bit > max) + goto nospc; + if (bit < BITS_PER_XA_VALUE) { + tmp |= 1UL << bit; + xas_store(&xas, xa_mk_value(tmp)); + goto out; } } - if (iter.index > index) - bit = 0; - new = iter.index * IDA_BITMAP_BITS; - bitmap = rcu_dereference_raw(*slot); - if (xa_is_value(bitmap)) { - unsigned long tmp = xa_to_value(bitmap); - int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, - bit); - if (vbit < BITS_PER_XA_VALUE) { - tmp |= 1UL << vbit; - rcu_assign_pointer(*slot, xa_mk_value(tmp)); - return new + vbit; - } - bitmap = this_cpu_xchg(ida_bitmap, NULL); - if (!bitmap) - return -EAGAIN; - bitmap->bitmap[0] = tmp; - rcu_assign_pointer(*slot, bitmap); + bitmap = alloc; + if (!bitmap) + bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); + if (!bitmap) + goto alloc; + bitmap->bitmap[0] = tmp; + xas_store(&xas, bitmap); + if (xas_error(&xas)) { + bitmap->bitmap[0] = 0; + goto out; } + } - if (bitmap) { - bit = find_next_zero_bit(bitmap->bitmap, - IDA_BITMAP_BITS, bit); - new += bit; - if (new < 0) - return -ENOSPC; - if (bit == IDA_BITMAP_BITS) - continue; + if (bitmap) { + bit = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, bit); + if (xas.xa_index * IDA_BITMAP_BITS + bit > max) + goto nospc; + if (bit == IDA_BITMAP_BITS) + goto next; - __set_bit(bit, bitmap->bitmap); - if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) - radix_tree_iter_tag_clear(root, &iter, - IDR_FREE); + __set_bit(bit, bitmap->bitmap); + if (bitmap_full(bitmap->bitmap, IDA_BITMAP_BITS)) + xas_clear_mark(&xas, XA_FREE_MARK); + } else { + if (bit < BITS_PER_XA_VALUE) { + bitmap = xa_mk_value(1UL << bit); } else { - new += bit; - if (new < 0) - return -ENOSPC; - if (bit < BITS_PER_XA_VALUE) { - bitmap = xa_mk_value(1UL << bit); - } else { - bitmap = this_cpu_xchg(ida_bitmap, NULL); - if (!bitmap) - return -EAGAIN; - __set_bit(bit, bitmap->bitmap); - } - radix_tree_iter_replace(root, &iter, slot, bitmap); + bitmap = alloc; + if (!bitmap) + bitmap = kzalloc(sizeof(*bitmap), GFP_NOWAIT); + if (!bitmap) + goto alloc; + __set_bit(bit, bitmap->bitmap); } - - return new; + xas_store(&xas, bitmap); + } +out: + xas_unlock_irqrestore(&xas, flags); + if (xas_nomem(&xas, gfp)) { + xas.xa_index = min / IDA_BITMAP_BITS; + bit = min % IDA_BITMAP_BITS; + goto retry; } + if (bitmap != alloc) + kfree(alloc); + if (xas_error(&xas)) + return xas_error(&xas); + return xas.xa_index * IDA_BITMAP_BITS + bit; +alloc: + xas_unlock_irqrestore(&xas, flags); + alloc = kzalloc(sizeof(*bitmap), gfp); + if (!alloc) + return -ENOMEM; + xas_set(&xas, min / IDA_BITMAP_BITS); + bit = min % IDA_BITMAP_BITS; + goto retry; +nospc: + xas_unlock_irqrestore(&xas, flags); + return -ENOSPC; } +EXPORT_SYMBOL(ida_alloc_range); -static void ida_remove(struct ida *ida, int id) +/** + * ida_free() - Release an allocated ID. + * @ida: IDA handle. + * @id: Previously allocated ID. + * + * Context: Any context. + */ +void ida_free(struct ida *ida, unsigned int id) { - unsigned long index = id / IDA_BITMAP_BITS; - unsigned offset = id % IDA_BITMAP_BITS; + XA_STATE(xas, &ida->xa, id / IDA_BITMAP_BITS); + unsigned bit = id % IDA_BITMAP_BITS; struct ida_bitmap *bitmap; - unsigned long *btmp; - struct radix_tree_iter iter; - void __rcu **slot; + unsigned long flags; - slot = radix_tree_iter_lookup(&ida->ida_rt, &iter, index); - if (!slot) - goto err; + BUG_ON((int)id < 0); + + xas_lock_irqsave(&xas, flags); + bitmap = xas_load(&xas); - bitmap = rcu_dereference_raw(*slot); if (xa_is_value(bitmap)) { - btmp = (unsigned long *)slot; - offset += 1; /* Intimate knowledge of the value encoding */ - if (offset >= BITS_PER_LONG) + unsigned long v = xa_to_value(bitmap); + if (bit >= BITS_PER_XA_VALUE) + goto err; + if (!(v & (1UL << bit))) goto err; + v &= ~(1UL << bit); + if (!v) + goto delete; + xas_store(&xas, xa_mk_value(v)); } else { - btmp = bitmap->bitmap; - } - if (!test_bit(offset, btmp)) - goto err; - - __clear_bit(offset, btmp); - radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE); - if (xa_is_value(bitmap)) { - if (xa_to_value(rcu_dereference_raw(*slot)) == 0) - radix_tree_iter_delete(&ida->ida_rt, &iter, slot); - } else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) { - kfree(bitmap); - radix_tree_iter_delete(&ida->ida_rt, &iter, slot); + if (!test_bit(bit, bitmap->bitmap)) + goto err; + __clear_bit(bit, bitmap->bitmap); + xas_set_mark(&xas, XA_FREE_MARK); + if (bitmap_empty(bitmap->bitmap, IDA_BITMAP_BITS)) { + kfree(bitmap); +delete: + xas_store(&xas, NULL); + } } + xas_unlock_irqrestore(&xas, flags); return; err: + xas_unlock_irqrestore(&xas, flags); WARN(1, "ida_free called for id=%d which is not allocated.\n", id); } +EXPORT_SYMBOL(ida_free); /** * ida_destroy() - Free all IDs. @@ -486,80 +533,60 @@ static void ida_remove(struct ida *ida, int id) */ void ida_destroy(struct ida *ida) { + XA_STATE(xas, &ida->xa, 0); + struct ida_bitmap *bitmap; unsigned long flags; - struct radix_tree_iter iter; - void __rcu **slot; - xa_lock_irqsave(&ida->ida_rt, flags); - radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) { - struct ida_bitmap *bitmap = rcu_dereference_raw(*slot); + xas_lock_irqsave(&xas, flags); + xas_for_each(&xas, bitmap, ULONG_MAX) { if (!xa_is_value(bitmap)) kfree(bitmap); - radix_tree_iter_delete(&ida->ida_rt, &iter, slot); + xas_store(&xas, NULL); } - xa_unlock_irqrestore(&ida->ida_rt, flags); + xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(ida_destroy); -/** - * ida_alloc_range() - Allocate an unused ID. - * @ida: IDA handle. - * @min: Lowest ID to allocate. - * @max: Highest ID to allocate. - * @gfp: Memory allocation flags. - * - * Allocate an ID between @min and @max, inclusive. The allocated ID will - * not exceed %INT_MAX, even if @max is larger. - * - * Context: Any context. - * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, - * or %-ENOSPC if there are no free IDs. - */ -int ida_alloc_range(struct ida *ida, unsigned int min, unsigned int max, - gfp_t gfp) -{ - int id = 0; - unsigned long flags; - - if ((int)min < 0) - return -ENOSPC; +#ifndef __KERNEL__ +extern void xa_dump_index(unsigned long index, unsigned int shift); +#define IDA_CHUNK_SHIFT ilog2(IDA_BITMAP_BITS) - if ((int)max < 0) - max = INT_MAX; - -again: - xa_lock_irqsave(&ida->ida_rt, flags); - id = ida_get_new_above(ida, min); - if (id > (int)max) { - ida_remove(ida, id); - id = -ENOSPC; - } - xa_unlock_irqrestore(&ida->ida_rt, flags); +static void ida_dump_entry(void *entry, unsigned long index) +{ + unsigned long i; + + if (!entry) + return; + + if (xa_is_node(entry)) { + struct xa_node *node = xa_to_node(entry); + unsigned int shift = node->shift + IDA_CHUNK_SHIFT + + XA_CHUNK_SHIFT; + + xa_dump_index(index * IDA_BITMAP_BITS, shift); + xa_dump_node(node); + for (i = 0; i < XA_CHUNK_SIZE; i++) + ida_dump_entry(node->slots[i], + index | (i << node->shift)); + } else if (xa_is_value(entry)) { + xa_dump_index(index * IDA_BITMAP_BITS, ilog2(BITS_PER_LONG)); + pr_cont("value: data %lx [%px]\n", xa_to_value(entry), entry); + } else { + struct ida_bitmap *bitmap = entry; - if (unlikely(id == -EAGAIN)) { - if (!ida_pre_get(ida, gfp)) - return -ENOMEM; - goto again; + xa_dump_index(index * IDA_BITMAP_BITS, IDA_CHUNK_SHIFT); + pr_cont("bitmap: %p data", bitmap); + for (i = 0; i < IDA_BITMAP_LONGS; i++) + pr_cont(" %lx", bitmap->bitmap[i]); + pr_cont("\n"); } - - return id; } -EXPORT_SYMBOL(ida_alloc_range); -/** - * ida_free() - Release an allocated ID. - * @ida: IDA handle. - * @id: Previously allocated ID. - * - * Context: Any context. - */ -void ida_free(struct ida *ida, unsigned int id) +static void ida_dump(struct ida *ida) { - unsigned long flags; - - BUG_ON((int)id < 0); - xa_lock_irqsave(&ida->ida_rt, flags); - ida_remove(ida, id); - xa_unlock_irqrestore(&ida->ida_rt, flags); + struct xarray *xa = &ida->xa; + pr_debug("ida: %p node %p free %d\n", ida, xa->xa_head, + xa->xa_flags >> ROOT_TAG_SHIFT); + ida_dump_entry(xa->xa_head, 0); } -EXPORT_SYMBOL(ida_free); +#endif diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3479d93c32b9..68702061464f 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -255,54 +255,6 @@ static unsigned long next_index(unsigned long index, return (index & ~node_maxindex(node)) + (offset << node->shift); } -#ifndef __KERNEL__ -static void dump_ida_node(void *entry, unsigned long index) -{ - unsigned long i; - - if (!entry) - return; - - if (radix_tree_is_internal_node(entry)) { - struct radix_tree_node *node = entry_to_node(entry); - - pr_debug("ida node: %p offset %d indices %lu-%lu parent %p free %lx shift %d count %d\n", - node, node->offset, index * IDA_BITMAP_BITS, - ((index | node_maxindex(node)) + 1) * - IDA_BITMAP_BITS - 1, - node->parent, node->tags[0][0], node->shift, - node->count); - for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) - dump_ida_node(node->slots[i], - index | (i << node->shift)); - } else if (xa_is_value(entry)) { - pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n", - entry, (int)(index & RADIX_TREE_MAP_MASK), - index * IDA_BITMAP_BITS, - index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE, - xa_to_value(entry)); - } else { - struct ida_bitmap *bitmap = entry; - - pr_debug("ida btmp: %p offset %d indices %lu-%lu data", bitmap, - (int)(index & RADIX_TREE_MAP_MASK), - index * IDA_BITMAP_BITS, - (index + 1) * IDA_BITMAP_BITS - 1); - for (i = 0; i < IDA_BITMAP_LONGS; i++) - pr_cont(" %lx", bitmap->bitmap[i]); - pr_cont("\n"); - } -} - -static void ida_dump(struct ida *ida) -{ - struct radix_tree_root *root = &ida->ida_rt; - pr_debug("ida: %p node %p free %d\n", ida, root->xa_head, - root->xa_flags >> ROOT_TAG_SHIFT); - dump_ida_node(root->xa_head, 0); -} -#endif - /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. @@ -2039,27 +1991,6 @@ void idr_preload(gfp_t gfp_mask) } EXPORT_SYMBOL(idr_preload); -int ida_pre_get(struct ida *ida, gfp_t gfp) -{ - /* - * The IDA API has no preload_end() equivalent. Instead, - * ida_get_new() can return -EAGAIN, prompting the caller - * to return to the ida_pre_get() step. - */ - if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE)) - preempt_enable(); - - if (!this_cpu_read(ida_bitmap)) { - struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp); - if (!bitmap) - return 0; - if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap)) - kfree(bitmap); - } - - return 1; -} - void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) @@ -2201,8 +2132,6 @@ static int radix_tree_cpu_dead(unsigned int cpu) kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } - kfree(per_cpu(ida_bitmap, cpu)); - per_cpu(ida_bitmap, cpu) = NULL; return 0; } diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index a5a4494922a6..1b63bdb7688f 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -402,16 +402,15 @@ void ida_check_nomem(void) */ void ida_check_conv_user(void) { -#if 0 DEFINE_IDA(ida); unsigned long i; - radix_tree_cpu_dead(1); for (i = 0; i < 1000000; i++) { int id = ida_alloc(&ida, GFP_NOWAIT); if (id == -ENOMEM) { - IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) != - BITS_PER_XA_VALUE); + IDA_BUG_ON(&ida, ((i % IDA_BITMAP_BITS) != + BITS_PER_XA_VALUE) && + ((i % IDA_BITMAP_BITS) != 0)); id = ida_alloc(&ida, GFP_KERNEL); } else { IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) == @@ -420,7 +419,6 @@ void ida_check_conv_user(void) IDA_BUG_ON(&ida, id != i); } ida_destroy(&ida); -#endif } void ida_check_random(void) -- cgit v1.2.3-71-gd317 From eb797a8ee0ab4cd03df556980ce7bf167cadaa50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Mar 2018 22:46:03 -0500 Subject: page cache: Rearrange address_space Change i_pages from a radix_tree_root to an xarray, convert the documentation into kernel-doc format and change the order of the elements to pack them better on 64-bit systems. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 46 +++++++++++++++++++++++++++++++--------------- 1 file changed, 31 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c0b4a1c22ff..d126cad0f621 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,24 +403,40 @@ int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); +/** + * struct address_space - Contents of a cacheable, mappable object. + * @host: Owner, either the inode or the block_device. + * @i_pages: Cached pages. + * @gfp_mask: Memory allocation flags to use for allocating pages. + * @i_mmap_writable: Number of VM_SHARED mappings. + * @i_mmap: Tree of private and shared mappings. + * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. + * @nrpages: Number of page entries, protected by the i_pages lock. + * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. + * @writeback_index: Writeback starts here. + * @a_ops: Methods. + * @flags: Error bits and flags (AS_*). + * @wb_err: The most recent error which has occurred. + * @private_lock: For use by the owner of the address_space. + * @private_list: For use by the owner of the address_space. + * @private_data: For use by the owner of the address_space. + */ struct address_space { - struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root i_pages; /* cached pages */ - atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root_cached i_mmap; /* tree of private and shared mappings */ - struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by the i_pages lock */ - unsigned long nrpages; /* number of total pages */ - /* number of shadow or DAX exceptional entries */ + struct inode *host; + struct xarray i_pages; + gfp_t gfp_mask; + atomic_t i_mmap_writable; + struct rb_root_cached i_mmap; + struct rw_semaphore i_mmap_rwsem; + unsigned long nrpages; unsigned long nrexceptional; - pgoff_t writeback_index;/* writeback starts here */ - const struct address_space_operations *a_ops; /* methods */ - unsigned long flags; /* error bits */ - spinlock_t private_lock; /* for use by the address_space */ - gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* for use by the address_space */ - void *private_data; /* ditto */ + pgoff_t writeback_index; + const struct address_space_operations *a_ops; + unsigned long flags; errseq_t wb_err; + spinlock_t private_lock; + struct list_head private_list; + void *private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but -- cgit v1.2.3-71-gd317 From 0d3f92966629e536b0c5c2355c1ada8e21c245f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 21 Nov 2017 14:07:06 -0500 Subject: page cache: Convert hole search to XArray The page cache offers the ability to search for a miss in the previous or next N locations. Rather than teach the XArray about the page cache's definition of a miss, use xas_prev() and xas_next() to search the page array. This should be more efficient as it does not have to start the lookup from the top for each index. Signed-off-by: Matthew Wilcox --- fs/nfs/blocklayout/blocklayout.c | 2 +- include/linux/pagemap.h | 4 +- mm/filemap.c | 110 ++++++++++++++++++--------------------- mm/readahead.c | 4 +- 4 files changed, 55 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 06cb0c1d9aee..d3781cd983f6 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -896,7 +896,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (end != inode->i_mapping->nrpages) { rcu_read_lock(); - end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); + end = page_cache_next_miss(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b1bd2186e6d2..cf9ad413eee9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -241,9 +241,9 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) typedef int filler_t(void *, struct page *); -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 diff --git a/mm/filemap.c b/mm/filemap.c index 4de14e75c4ec..714d3d0f60f5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1326,86 +1326,76 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * page_cache_next_hole - find the next hole (not-present entry) - * @mapping: mapping - * @index: index - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the - * lowest indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= - * max_scan' will be true). In rare cases of index wrap-around, 0 will - * be returned. - * - * page_cache_next_hole may be called under rcu_read_lock. However, - * like radix_tree_gang_lookup, this will not atomically search a - * snapshot of the tree at a single point in time. For example, if a - * hole is created at index 5, then subsequently a hole is created at - * index 10, page_cache_next_hole covering both indexes may return 10 - * if called under rcu_read_lock. + * page_cache_next_miss() - Find the next gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the + * gap with the lowest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 5, then subsequently a gap is + * created at index 10, page_cache_next_miss covering both indices may + * return 10 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'return - index >= max_scan' will be true). + * In the rare case of index wrap-around, 0 will be returned. */ -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { - unsigned long i; + XA_STATE(xas, &mapping->i_pages, index); - for (i = 0; i < max_scan; i++) { - struct page *page; - - page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || xa_is_value(page)) + while (max_scan--) { + void *entry = xas_next(&xas); + if (!entry || xa_is_value(entry)) break; - index++; - if (index == 0) + if (xas.xa_index == 0) break; } - return index; + return xas.xa_index; } -EXPORT_SYMBOL(page_cache_next_hole); +EXPORT_SYMBOL(page_cache_next_miss); /** - * page_cache_prev_hole - find the prev hole (not-present entry) - * @mapping: mapping - * @index: index - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] for - * the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= - * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX - * will be returned. - * - * page_cache_prev_hole may be called under rcu_read_lock. However, - * like radix_tree_gang_lookup, this will not atomically search a - * snapshot of the tree at a single point in time. For example, if a - * hole is created at index 10, then subsequently a hole is created at - * index 5, page_cache_prev_hole covering both indexes may return 5 if - * called under rcu_read_lock. + * page_cache_prev_miss() - Find the next gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [max(index - max_scan + 1, 0), index] for the + * gap with the highest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 10, then subsequently a gap is + * created at index 5, page_cache_prev_miss() covering both indices may + * return 5 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'index - return >= max_scan' will be true). + * In the rare case of wrap-around, ULONG_MAX will be returned. */ -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { - unsigned long i; - - for (i = 0; i < max_scan; i++) { - struct page *page; + XA_STATE(xas, &mapping->i_pages, index); - page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || xa_is_value(page)) + while (max_scan--) { + void *entry = xas_prev(&xas); + if (!entry || xa_is_value(entry)) break; - index--; - if (index == ULONG_MAX) + if (xas.xa_index == ULONG_MAX) break; } - return index; + return xas.xa_index; } -EXPORT_SYMBOL(page_cache_prev_hole); +EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry diff --git a/mm/readahead.c b/mm/readahead.c index de657077d41d..fc4dd364b37a 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -336,7 +336,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = page_cache_prev_hole(mapping, offset - 1, max); + head = page_cache_prev_miss(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -425,7 +425,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = page_cache_next_hole(mapping, offset + 1, max_pages); + start = page_cache_next_miss(mapping, offset + 1, max_pages); rcu_read_unlock(); if (!start || start - offset > max_pages) -- cgit v1.2.3-71-gd317 From 74d609585d8bd6083bd9d75bc1fd2c0d3851bcc5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:01:45 -0500 Subject: page cache: Add and replace pages using the XArray Use the XArray APIs to add and replace pages in the page cache. This removes two uses of the radix tree preload API and is significantly shorter code. It also removes the last user of __radix_tree_create() outside radix-tree.c itself, so make it static. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 3 - include/linux/swap.h | 8 ++- lib/radix-tree.c | 6 +- mm/filemap.c | 139 +++++++++++++++++++-------------------------- 4 files changed, 66 insertions(+), 90 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 15388b7e38b9..d55de428a589 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,9 +231,6 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..6ea50cf41b4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -/* Do not use directly, use workingset_lookup_update */ -void workingset_update_node(struct radix_tree_node *node); +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + xas_set_update(xas, workingset_update_node); \ +} while (0) /* Returns workingset_update_node() if the mapping has shadow entries. */ #define workingset_lookup_update(mapping) \ diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 68702061464f..8a58051eb5b3 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -700,9 +700,9 @@ static bool delete_node(struct radix_tree_root *root, * * Returns -ENOMEM, or 0 for success. */ -int __radix_tree_create(struct radix_tree_root *root, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp) +static int __radix_tree_create(struct radix_tree_root *root, + unsigned long index, unsigned order, + struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; diff --git a/mm/filemap.c b/mm/filemap.c index 714d3d0f60f5..b63caebd1367 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -111,35 +111,6 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ -static int page_cache_tree_insert(struct address_space *mapping, - struct page *page, void **shadowp) -{ - struct radix_tree_node *node; - void **slot; - int error; - - error = __radix_tree_create(&mapping->i_pages, page->index, 0, - &node, &slot); - if (error) - return error; - if (*slot) { - void *p; - - p = radix_tree_deref_slot_protected(slot, - &mapping->i_pages.xa_lock); - if (!xa_is_value(p)) - return -EEXIST; - - mapping->nrexceptional--; - if (shadowp) - *shadowp = p; - } - __radix_tree_replace(&mapping->i_pages, node, slot, page, - workingset_lookup_update(mapping)); - mapping->nrpages++; - return 0; -} - static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { @@ -775,51 +746,44 @@ EXPORT_SYMBOL(file_write_and_wait_range); * locked. This function does not add the new page to the LRU, the * caller must do that. * - * The remove + add is atomic. The only way this function can fail is - * memory allocation failure. + * The remove + add is atomic. This function cannot fail. */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { - int error; + struct address_space *mapping = old->mapping; + void (*freepage)(struct page *) = mapping->a_ops->freepage; + pgoff_t offset = old->index; + XA_STATE(xas, &mapping->i_pages, offset); + unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); - error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK); - if (!error) { - struct address_space *mapping = old->mapping; - void (*freepage)(struct page *); - unsigned long flags; - - pgoff_t offset = old->index; - freepage = mapping->a_ops->freepage; + get_page(new); + new->mapping = mapping; + new->index = offset; - get_page(new); - new->mapping = mapping; - new->index = offset; + xas_lock_irqsave(&xas, flags); + xas_store(&xas, new); - xa_lock_irqsave(&mapping->i_pages, flags); - __delete_from_page_cache(old, NULL); - error = page_cache_tree_insert(mapping, new, NULL); - BUG_ON(error); - - /* - * hugetlb pages do not participate in page cache accounting. - */ - if (!PageHuge(new)) - __inc_node_page_state(new, NR_FILE_PAGES); - if (PageSwapBacked(new)) - __inc_node_page_state(new, NR_SHMEM); - xa_unlock_irqrestore(&mapping->i_pages, flags); - mem_cgroup_migrate(old, new); - radix_tree_preload_end(); - if (freepage) - freepage(old); - put_page(old); - } + old->mapping = NULL; + /* hugetlb pages do not participate in page cache accounting. */ + if (!PageHuge(old)) + __dec_node_page_state(new, NR_FILE_PAGES); + if (!PageHuge(new)) + __inc_node_page_state(new, NR_FILE_PAGES); + if (PageSwapBacked(old)) + __dec_node_page_state(new, NR_SHMEM); + if (PageSwapBacked(new)) + __inc_node_page_state(new, NR_SHMEM); + xas_unlock_irqrestore(&xas, flags); + mem_cgroup_migrate(old, new); + if (freepage) + freepage(old); + put_page(old); - return error; + return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); @@ -828,12 +792,15 @@ static int __add_to_page_cache_locked(struct page *page, pgoff_t offset, gfp_t gfp_mask, void **shadowp) { + XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); struct mem_cgroup *memcg; int error; + void *old; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); + mapping_set_update(&xas, mapping); if (!huge) { error = mem_cgroup_try_charge(page, current->mm, @@ -842,39 +809,47 @@ static int __add_to_page_cache_locked(struct page *page, return error; } - error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK); - if (error) { - if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); - return error; - } - get_page(page); page->mapping = mapping; page->index = offset; - xa_lock_irq(&mapping->i_pages); - error = page_cache_tree_insert(mapping, page, shadowp); - radix_tree_preload_end(); - if (unlikely(error)) - goto err_insert; + do { + xas_lock_irq(&xas); + old = xas_load(&xas); + if (old && !xa_is_value(old)) + xas_set_err(&xas, -EEXIST); + xas_store(&xas, page); + if (xas_error(&xas)) + goto unlock; + + if (xa_is_value(old)) { + mapping->nrexceptional--; + if (shadowp) + *shadowp = old; + } + mapping->nrpages++; + + /* hugetlb pages do not participate in page cache accounting */ + if (!huge) + __inc_node_page_state(page, NR_FILE_PAGES); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); + + if (xas_error(&xas)) + goto error; - /* hugetlb pages do not participate in page cache accounting. */ - if (!huge) - __inc_node_page_state(page, NR_FILE_PAGES); - xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); return 0; -err_insert: +error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); put_page(page); - return error; + return xas_error(&xas); } /** -- cgit v1.2.3-71-gd317 From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:00:33 -0400 Subject: page cache: Convert find_get_pages_contig to XArray There's no direct replacement for radix_tree_for_each_contig() in the XArray API as it's an unusual thing to do. Instead, open-code a loop using xas_next(). This removes the only user of radix_tree_for_each_contig() so delete the iterator from the API and the test suite code for it. Signed-off-by: Matthew Wilcox --- .clang-format | 1 - include/linux/radix-tree.h | 17 ----------- mm/filemap.c | 53 ++++++++++++++-------------------- tools/testing/radix-tree/regression3.c | 23 --------------- 4 files changed, 22 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/.clang-format b/.clang-format index 1d5da22e0ba5..e6080f5834a3 100644 --- a/.clang-format +++ b/.clang-format @@ -323,7 +323,6 @@ ForEachMacros: - 'protocol_for_each_card' - 'protocol_for_each_dev' - 'queue_for_each_hw_ctx' - - 'radix_tree_for_each_contig' - 'radix_tree_for_each_slot' - 'radix_tree_for_each_tagged' - 'rbtree_postorder_for_each_entry_safe' diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index d55de428a589..023e888e1163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) -/** - * radix_tree_for_each_contig - iterate over contiguous slots - * - * @slot: the void** variable for pointer to slot - * @root: the struct radix_tree_root pointer - * @iter: the struct radix_tree_iter pointer - * @start: iteration starting index - * - * @slot points to radix tree slot, @iter->index contains its index. - */ -#define radix_tree_for_each_contig(slot, root, iter, start) \ - for (slot = radix_tree_iter_init(iter, start) ; \ - slot || (slot = radix_tree_next_chunk(root, iter, \ - RADIX_TREE_ITER_CONTIG)) ; \ - slot = radix_tree_next_slot(slot, iter, \ - RADIX_TREE_ITER_CONTIG)) - /** * radix_tree_for_each_tagged - iterate over tagged slots * diff --git a/mm/filemap.c b/mm/filemap.c index b72c39fe61c2..089b67598100 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1721,57 +1721,43 @@ out: unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, index); + struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) { - struct page *head, *page; -repeat: - page = radix_tree_deref_slot(slot); - /* The hole, there no reason to continue */ - if (unlikely(!page)) - break; - - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Stop - * looking for contiguous pages. - */ + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + struct page *head; + if (xas_retry(&xas, page)) + continue; + /* + * If the entry has been swapped out, we can stop looking. + * No current caller is looking for DAX entries. + */ + if (xa_is_value(page)) break; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; /* * must check mapping and index after taking the ref. * otherwise we can get both false positives and false * negatives, which is just confusing to the caller. */ - if (page->mapping == NULL || page_to_pgoff(page) != iter.index) { + if (!page->mapping || page_to_pgoff(page) != xas.xa_index) { put_page(page); break; } @@ -1779,6 +1765,11 @@ repeat: pages[ret] = page; if (++ret == nr_pages) break; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } rcu_read_unlock(); return ret; diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c index ace2543c3eda..9f9a3b280f56 100644 --- a/tools/testing/radix-tree/regression3.c +++ b/tools/testing/radix-tree/regression3.c @@ -69,21 +69,6 @@ void regression3_test(void) continue; } } - radix_tree_delete(&root, 1); - - first = true; - radix_tree_for_each_contig(slot, &root, &iter, 0) { - printv(2, "contig %ld %p\n", iter.index, *slot); - if (first) { - radix_tree_insert(&root, 1, ptr); - first = false; - } - if (radix_tree_deref_retry(*slot)) { - printv(2, "retry at %ld\n", iter.index); - slot = radix_tree_iter_retry(&iter); - continue; - } - } radix_tree_for_each_slot(slot, &root, &iter, 0) { printv(2, "slot %ld %p\n", iter.index, *slot); @@ -93,14 +78,6 @@ void regression3_test(void) } } - radix_tree_for_each_contig(slot, &root, &iter, 0) { - printv(2, "contig %ld %p\n", iter.index, *slot); - if (!iter.index) { - printv(2, "next at %ld\n", iter.index); - slot = radix_tree_iter_resume(slot, &iter); - } - } - radix_tree_tag_set(&root, 0, 0); radix_tree_tag_set(&root, 1, 0); radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { -- cgit v1.2.3-71-gd317 From a6906972fe67fb6f73ba04088f7897227fd1cd8f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:12:54 -0400 Subject: page cache; Convert find_get_pages_range_tag to XArray The 'end' parameter of the xas_for_each iterator avoids a useless iteration at the end of the range. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 +-- mm/filemap.c | 68 +++++++++++++++++++------------------------------ 2 files changed, 28 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf9ad413eee9..c9bbb9a05764 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -363,10 +363,10 @@ static inline unsigned find_get_pages(struct address_space *mapping, unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, int tag, unsigned int nr_pages, + pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, diff --git a/mm/filemap.c b/mm/filemap.c index 089b67598100..0df28aa6411c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1789,74 +1789,58 @@ EXPORT_SYMBOL(find_get_pages_contig); * @tag. We update @index to index the next page for the traversal. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, *index); + struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) { - struct page *head, *page; - - if (iter.index > end) - break; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each_marked(&xas, page, end, tag) { + struct page *head; + if (xas_retry(&xas, page)) continue; - - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page. - * - * Those entries should never be tagged, but - * this tree walk is lockless and the tags are - * looked up in bulk, one radix tree node at a - * time, so there is a sizable window for page - * reclaim to evict a page we saw tagged. - * - * Skip over it. - */ + /* + * Shadow entries should never be tagged, but this iteration + * is lockless so there is a window for page reclaim to evict + * a page we saw tagged. Skip over it. + */ + if (xa_is_value(page)) continue; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; pages[ret] = page; if (++ret == nr_pages) { - *index = pages[ret - 1]->index + 1; + *index = page->index + 1; goto out; } + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } /* - * We come here when we got at @end. We take care to not overflow the + * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the - * iteration when there is page at index -1 but that is already broken - * anyway. + * iteration when there is a page at index -1 but that is already + * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; -- cgit v1.2.3-71-gd317 From c1901cd33cf407d77a181f8dd4ffff98041ef480 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 23:56:04 -0400 Subject: page cache: Convert find_get_entries_tag to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 2 +- mm/filemap.c | 54 ++++++++++++++++++++++--------------------------- 2 files changed, 25 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c9bbb9a05764..226f96f0dee0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -373,7 +373,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, nr_pages, pages); } unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, diff --git a/mm/filemap.c b/mm/filemap.c index 0df28aa6411c..35ae011971e1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1866,57 +1866,51 @@ EXPORT_SYMBOL(find_get_pages_range_tag); * @tag. */ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { - void **slot; + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; unsigned int ret = 0; - struct radix_tree_iter iter; if (!nr_entries) return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) { - struct page *head, *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each_marked(&xas, page, ULONG_MAX, tag) { + struct page *head; + if (xas_retry(&xas, page)) continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - - /* - * A shadow entry of a recently evicted page, a swap - * entry from shmem/tmpfs or a DAX entry. Return it - * without attempting to raise page count. - */ + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (xa_is_value(page)) goto export; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; + export: - indices[ret] = iter.index; + indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } rcu_read_unlock(); return ret; -- cgit v1.2.3-71-gd317 From ff9c745b81ff1e482167fd73558450e66ad43a33 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 11:41:23 -0500 Subject: mm: Convert page-writeback to XArray Includes moving mapping_tagged() to fs.h as a static inline, and changing it to return bool. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 17 +++++++------ mm/page-writeback.c | 72 +++++++++++++++++++---------------------------------- 2 files changed, 36 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index d126cad0f621..e10278e4db66 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -483,15 +483,18 @@ struct block_device { struct mutex bd_fsfreeze_mutex; } __randomize_layout; +/* XArray tags, for tagging dirty and writeback pages in the pagecache. */ +#define PAGECACHE_TAG_DIRTY XA_MARK_0 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 + /* - * Radix-tree tags, for tagging dirty and writeback pages within the pagecache - * radix trees + * Returns true if any of the pages in the mapping are marked with the tag. */ -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 - -int mapping_tagged(struct address_space *mapping, int tag); +static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +{ + return xa_marked(&mapping->i_pages, tag); +} static inline void i_mmap_lock_write(struct address_space *mapping) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 84ae9bf5858a..fc6e5743b0bf 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2097,34 +2097,25 @@ void __init page_writeback_init(void) * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ -/* - * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce the i_pages lock - * latency. - */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { -#define WRITEBACK_TAG_BATCH 4096 - unsigned long tagged = 0; - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, start); + unsigned int tagged = 0; + void *page; - xa_lock_irq(&mapping->i_pages); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, - PAGECACHE_TAG_DIRTY) { - if (iter.index > end) - break; - radix_tree_iter_tag_set(&mapping->i_pages, &iter, - PAGECACHE_TAG_TOWRITE); - tagged++; - if ((tagged % WRITEBACK_TAG_BATCH) != 0) + xas_lock_irq(&xas); + xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { + xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); + if (++tagged % XA_CHECK_SCHED) continue; - slot = radix_tree_iter_resume(slot, &iter); - xa_unlock_irq(&mapping->i_pages); + + xas_pause(&xas); + xas_unlock_irq(&xas); cond_resched(); - xa_lock_irq(&mapping->i_pages); + xas_lock_irq(&xas); } - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); @@ -2164,7 +2155,7 @@ int write_cache_pages(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { @@ -2445,7 +2436,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, /* * For address_spaces which do not use buffers. Just tag the page as dirty in - * its radix tree. + * the xarray. * * This is also used when a single buffer is being dirtied: we want to set the * page dirty in that case, but not all the buffers. This is a "bottom-up" @@ -2471,7 +2462,7 @@ int __set_page_dirty_nobuffers(struct page *page) BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->i_pages, page_index(page), + __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); @@ -2634,13 +2625,13 @@ EXPORT_SYMBOL(__cancel_dirty_page); * Returns true if the page was previously dirty. * * This is for preparing to put the page under writeout. We leave the page - * tagged as dirty in the radix tree so that a concurrent write-for-sync + * tagged as dirty in the xarray so that a concurrent write-for-sync * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage * implementation will run either set_page_writeback() or set_page_dirty(), - * at which stage we bring the page's dirty flag and radix-tree dirty tag + * at which stage we bring the page's dirty flag and xarray dirty tag * back into sync. * - * This incoherency between the page's dirty flag and radix-tree tag is + * This incoherency between the page's dirty flag and xarray tag is * unfortunate, but it only exists while the page is locked. */ int clear_page_dirty_for_io(struct page *page) @@ -2721,7 +2712,7 @@ int test_clear_page_writeback(struct page *page) xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { - radix_tree_tag_clear(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) { struct bdi_writeback *wb = inode_to_wb(inode); @@ -2761,11 +2752,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write) lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { + XA_STATE(xas, &mapping->i_pages, page_index(page)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; - xa_lock_irqsave(&mapping->i_pages, flags); + xas_lock_irqsave(&xas, flags); + xas_load(&xas); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; @@ -2773,8 +2766,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); - radix_tree_tag_set(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_WRITEBACK); + xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); @@ -2787,12 +2779,10 @@ int __test_set_page_writeback(struct page *page, bool keep_write) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_TOWRITE); - xa_unlock_irqrestore(&mapping->i_pages, flags); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); } else { ret = TestSetPageWriteback(page); } @@ -2806,16 +2796,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write) } EXPORT_SYMBOL(__test_set_page_writeback); -/* - * Return true if any of the pages in the mapping are marked with the - * passed tag. - */ -int mapping_tagged(struct address_space *mapping, int tag) -{ - return radix_tree_tagged(&mapping->i_pages, tag); -} -EXPORT_SYMBOL(mapping_tagged); - /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. -- cgit v1.2.3-71-gd317 From a97e7904c0806309fd77103005bb7820c3f1c5e4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Nov 2017 14:24:59 -0500 Subject: mm: Convert workingset to XArray We construct an XA_STATE and use it to delete the node with xas_store() rather than adding a special function for this unique use case. Includes a test that simulates this usage for the test suite. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 9 -------- lib/test_xarray.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/workingset.c | 51 +++++++++++++++++------------------------ 3 files changed, 86 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6ea50cf41b4c..112cebcf0402 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node); xas_set_update(xas, workingset_update_node); \ } while (0) -/* Returns workingset_update_node() if the mapping has shadow entries. */ -#define workingset_lookup_update(mapping) \ -({ \ - radix_tree_update_node_t __helper = workingset_update_node; \ - if (dax_mapping(mapping) || shmem_mapping(mapping)) \ - __helper = NULL; \ - __helper; \ -}) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index a752e6a37e6f..128c6489082f 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -863,6 +863,67 @@ static noinline void check_create_range(struct xarray *xa) check_create_range_3(); } +static LIST_HEAD(shadow_nodes); + +static void test_update_node(struct xa_node *node) +{ + if (node->count && node->count == node->nr_values) { + if (list_empty(&node->private_list)) + list_add(&shadow_nodes, &node->private_list); + } else { + if (!list_empty(&node->private_list)) + list_del_init(&node->private_list); + } +} + +static noinline void shadow_remove(struct xarray *xa) +{ + struct xa_node *node; + + xa_lock(xa); + while ((node = list_first_entry_or_null(&shadow_nodes, + struct xa_node, private_list))) { + XA_STATE(xas, node->array, 0); + XA_BUG_ON(xa, node->array != xa); + list_del_init(&node->private_list); + xas.xa_node = xa_parent_locked(node->array, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, test_update_node); + xas_store(&xas, NULL); + } + xa_unlock(xa); +} + +static noinline void check_workingset(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + xas_set_update(&xas, test_update_node); + + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(0)); + xas_next(&xas); + xas_store(&xas, xa_mk_value(1)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + xas_lock(&xas); + xas_next(&xas); + xas_store(&xas, &xas); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + + xas_store(&xas, xa_mk_value(2)); + xas_unlock(&xas); + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + shadow_remove(xa); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -916,6 +977,10 @@ static int xarray_checks(void) check_create_range(&array); check_store_iter(&array); + check_workingset(&array, 0); + check_workingset(&array, 64); + check_workingset(&array, 4096); + printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; } diff --git a/mm/workingset.c b/mm/workingset.c index c201cbb8c00f..5cfb29ec3fd9 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -148,7 +148,7 @@ * and activations is maintained (node->inactive_age). * * On eviction, a snapshot of this counter (along with some bits to - * identify the node) is stored in the now empty page cache radix tree + * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible @@ -162,7 +162,7 @@ /* * Eviction timestamps need to be able to cover the full range of - * actionable refaults. However, bits are tight in the radix tree + * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group @@ -339,7 +339,7 @@ out: static struct list_lru shadow_nodes; -void workingset_update_node(struct radix_tree_node *node) +void workingset_update_node(struct xa_node *node) { /* * Track non-empty nodes that contain only shadow entries; @@ -368,7 +368,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, nodes = list_lru_shrink_count(&shadow_nodes, sc); /* - * Approximate a reasonable limit for the radix tree nodes + * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. @@ -383,11 +383,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * - * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * - * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE + * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ if (sc->memcg) { cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, @@ -396,7 +396,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); } - max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3); + max_nodes = cache >> (XA_CHUNK_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; @@ -409,11 +409,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, - void *arg) + void *arg) __must_hold(lru_lock) { + struct xa_node *node = container_of(item, struct xa_node, private_list); + XA_STATE(xas, node->array, 0); struct address_space *mapping; - struct radix_tree_node *node; - unsigned int i; int ret; /* @@ -421,14 +421,13 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any - * address_space that has radix tree nodes on the LRU. + * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ - node = container_of(item, struct xa_node, private_list); mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ @@ -450,25 +449,17 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; - for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { - if (node->slots[i]) { - if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) - goto out_invalid; - if (WARN_ON_ONCE(!node->nr_values)) - goto out_invalid; - if (WARN_ON_ONCE(!mapping->nrexceptional)) - goto out_invalid; - node->slots[i] = NULL; - node->nr_values--; - node->count--; - mapping->nrexceptional--; - } - } - if (WARN_ON_ONCE(node->nr_values)) - goto out_invalid; + mapping->nrexceptional -= node->nr_values; + xas.xa_node = xa_parent_locked(&mapping->i_pages, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, workingset_update_node); + /* + * We could store a shadow entry here which was the minimum of the + * shadow entries we were tracking ... + */ + xas_store(&xas, NULL); inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); - __radix_tree_delete_node(&mapping->i_pages, node, - workingset_lookup_update(mapping)); out_invalid: xa_unlock_irq(&mapping->i_pages); -- cgit v1.2.3-71-gd317 From 4e17ec250fce0eba9b70a91c9622da2748a3ec50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 29 Nov 2017 08:32:39 -0500 Subject: mm: Convert delete_from_swap_cache to XArray Both callers of __delete_from_swap_cache have the swp_entry_t already, so pass that in to make constructing the XA_STATE easier. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 5 +++-- mm/swap_state.c | 24 ++++++++++-------------- mm/vmscan.c | 2 +- 3 files changed, 14 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 112cebcf0402..cb479bf5842e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -403,7 +403,7 @@ 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 *); +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 *); extern void free_pages_and_swap_cache(struct page **, int); @@ -557,7 +557,8 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page) +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry) { } diff --git a/mm/swap_state.c b/mm/swap_state.c index 850314c2c3ab..f393c994cc60 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -154,23 +154,22 @@ unlock: * This must be called only on pages that have * been verified to be in the swap cache. */ -void __delete_from_swap_cache(struct page *page) +void __delete_from_swap_cache(struct page *page, swp_entry_t entry) { - struct address_space *address_space; + struct address_space *address_space = swap_address_space(entry); int i, nr = hpage_nr_pages(page); - swp_entry_t entry; - pgoff_t idx; + pgoff_t idx = swp_offset(entry); + XA_STATE(xas, &address_space->i_pages, idx); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(PageWriteback(page), page); - entry.val = page_private(page); - address_space = swap_address_space(entry); - idx = swp_offset(entry); for (i = 0; i < nr; i++) { - radix_tree_delete(&address_space->i_pages, idx + i); + void *entry = xas_store(&xas, NULL); + VM_BUG_ON_PAGE(entry != page + i, entry); set_page_private(page + i, 0); + xas_next(&xas); } ClearPageSwapCache(page); address_space->nrpages -= nr; @@ -243,14 +242,11 @@ fail: */ void delete_from_swap_cache(struct page *page) { - swp_entry_t entry; - struct address_space *address_space; - - entry.val = page_private(page); + swp_entry_t entry = { .val = page_private(page) }; + struct address_space *address_space = swap_address_space(entry); - address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, entry); xa_unlock_irq(&address_space->i_pages); put_swap_page(page, entry); diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..80f731cf974e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -923,7 +923,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, swap); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { -- cgit v1.2.3-71-gd317 From 10bbd235859bf483f9a8a4ebe95463d700bae394 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Dec 2017 17:30:38 -0500 Subject: pagevec: Use xa_mark_t Removes sparse warnings. Signed-off-by: Matthew Wilcox --- fs/btrfs/extent_io.c | 4 ++-- fs/ext4/inode.c | 2 +- fs/f2fs/data.c | 2 +- fs/gfs2/aops.c | 2 +- include/linux/pagevec.h | 8 +++++--- mm/swap.c | 4 ++-- 6 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4dd6faab02bb..fc7ca7d991ad 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3778,7 +3778,7 @@ int btree_write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ int scanned = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { @@ -3903,7 +3903,7 @@ static int extent_write_cache_pages(struct address_space *mapping, pgoff_t done_index; int range_whole = 0; int scanned = 0; - int tag; + xa_mark_t tag; /* * We have to hold onto the inode so that ordered extents can do their diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d767e993591d..57bad3edfbed 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2613,7 +2613,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) long left = mpd->wbc->nr_to_write; pgoff_t index = mpd->first_page; pgoff_t end = mpd->last_page; - int tag; + xa_mark_t tag; int i, err = 0; int blkbits = mpd->inode->i_blkbits; ext4_lblk_t lblk; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 382c1ef9a9e4..5b760809eecc 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2003,7 +2003,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, pgoff_t last_idx = ULONG_MAX; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 31e8270d0b26..8afbb35559b9 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -366,7 +366,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 6dc456ac6136..081d934eda64 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -9,6 +9,8 @@ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H +#include + /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 @@ -40,12 +42,12 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag); + xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages); + xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, int tag) + struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } diff --git a/mm/swap.c b/mm/swap.c index 4c5c7fcc6e46..6861f3140a13 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1002,7 +1002,7 @@ EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag) + xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); @@ -1012,7 +1012,7 @@ EXPORT_SYMBOL(pagevec_lookup_range_tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages) + xa_mark_t tag, unsigned max_pages) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); -- cgit v1.2.3-71-gd317 From 7b8d046fba91d62beb8a8f78244aaa3c23a60cdd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 22:13:06 -0500 Subject: shmem: Convert shmem_alloc_hugepage to XArray xa_find() is a slightly easier API to use than radix_tree_gang_lookup_slot() because it contains its own RCU locking. This commit removes the last user of radix_tree_gang_lookup_slot() so remove the function too. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 +----- lib/radix-tree.c | 44 +------------------------------------------- mm/shmem.c | 14 ++++---------- 3 files changed, 6 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 023e888e1163..8a4280bc350f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -147,12 +147,11 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup - * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 8 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -263,9 +262,6 @@ void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8a58051eb5b3..2f9c0e45eeb7 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1097,7 +1097,7 @@ void __radix_tree_replace(struct radix_tree_root *root, * @slot: pointer to slot * @item: new item to store in the slot. * - * For use with radix_tree_lookup_slot(), radix_tree_gang_lookup_slot(), + * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * @@ -1731,48 +1731,6 @@ radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, } EXPORT_SYMBOL(radix_tree_gang_lookup); -/** - * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree - * @root: radix tree root - * @results: where the results of the lookup are placed - * @indices: where their indices should be placed (but usually NULL) - * @first_index: start the lookup from this key - * @max_items: place up to this many items at *results - * - * Performs an index-ascending scan of the tree for present items. Places - * their slots at *@results and returns the number of items which were - * placed at *@results. - * - * The implementation is naive. - * - * Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must - * be dereferenced with radix_tree_deref_slot, and if using only RCU - * protection, radix_tree_deref_slot may fail requiring a retry. - */ -unsigned int -radix_tree_gang_lookup_slot(const struct radix_tree_root *root, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items) -{ - struct radix_tree_iter iter; - void __rcu **slot; - unsigned int ret = 0; - - if (unlikely(!max_items)) - return 0; - - radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = slot; - if (indices) - indices[ret] = iter.index; - if (++ret == max_items) - break; - } - - return ret; -} -EXPORT_SYMBOL(radix_tree_gang_lookup_slot); - /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag diff --git a/mm/shmem.c b/mm/shmem.c index 8633bd3dc433..608c9252248f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1431,23 +1431,17 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; - struct inode *inode = &info->vfs_inode; - struct address_space *mapping = inode->i_mapping; - pgoff_t idx, hindex; - void __rcu **results; + struct address_space *mapping = info->vfs_inode.i_mapping; + pgoff_t hindex; struct page *page; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) return NULL; hindex = round_down(index, HPAGE_PMD_NR); - rcu_read_lock(); - if (radix_tree_gang_lookup_slot(&mapping->i_pages, &results, &idx, - hindex, 1) && idx < hindex + HPAGE_PMD_NR) { - rcu_read_unlock(); + if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, + XA_PRESENT)) return NULL; - } - rcu_read_unlock(); shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, -- cgit v1.2.3-71-gd317 From 1cf56f9d670b88b2e947a7ccdb8ba32e6477915d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:24:45 -0400 Subject: radix tree: Remove radix_tree_update_node_t The only user of this functionality was the workingset code, and it's now been converted to the XArray. Remove __radix_tree_delete_node() entirely as it was also only used by the workingset code. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 7 +----- lib/idr.c | 2 +- lib/radix-tree.c | 42 +++++++---------------------------- tools/testing/radix-tree/multiorder.c | 2 +- 4 files changed, 11 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 8a4280bc350f..7513d0df984b 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -242,17 +242,12 @@ void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, unsigned long index); -typedef void (*radix_tree_update_node_t)(struct radix_tree_node *); void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot, void *entry, - radix_tree_update_node_t update_node); + void __rcu **slot, void *entry); void radix_tree_iter_replace(struct radix_tree_root *, const struct radix_tree_iter *, void __rcu **slot, void *entry); void radix_tree_replace_slot(struct radix_tree_root *, void __rcu **slot, void *entry); -void __radix_tree_delete_node(struct radix_tree_root *, - struct radix_tree_node *, - radix_tree_update_node_t update_node); void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); diff --git a/lib/idr.c b/lib/idr.c index 3c20ad9b0463..cb1db9b8d3f6 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -297,7 +297,7 @@ void *idr_replace(struct idr *idr, void *ptr, unsigned long id) if (!slot || radix_tree_tag_get(&idr->idr_rt, id, IDR_FREE)) return ERR_PTR(-ENOENT); - __radix_tree_replace(&idr->idr_rt, node, slot, ptr, NULL); + __radix_tree_replace(&idr->idr_rt, node, slot, ptr); return entry; } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 2f9c0e45eeb7..c4c252185734 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -562,8 +562,7 @@ out: * radix_tree_shrink - shrink radix tree to minimum height * @root radix tree root */ -static inline bool radix_tree_shrink(struct radix_tree_root *root, - radix_tree_update_node_t update_node) +static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; @@ -631,8 +630,6 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root, node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; - if (update_node) - update_node(node); } WARN_ON_ONCE(!list_empty(&node->private_list)); @@ -644,8 +641,7 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root, } static bool delete_node(struct radix_tree_root *root, - struct radix_tree_node *node, - radix_tree_update_node_t update_node) + struct radix_tree_node *node) { bool deleted = false; @@ -655,7 +651,7 @@ static bool delete_node(struct radix_tree_root *root, if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) - deleted |= radix_tree_shrink(root, update_node); + deleted |= radix_tree_shrink(root); return deleted; } @@ -1059,15 +1055,13 @@ static int calculate_count(struct radix_tree_root *root, * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. - * @update_node: callback for changing leaf nodes * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, - void __rcu **slot, void *item, - radix_tree_update_node_t update_node) + void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); @@ -1085,10 +1079,7 @@ void __radix_tree_replace(struct radix_tree_root *root, if (!node) return; - if (update_node) - update_node(node); - - delete_node(root, node, update_node); + delete_node(root, node); } /** @@ -1110,7 +1101,7 @@ void __radix_tree_replace(struct radix_tree_root *root, void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { - __radix_tree_replace(root, NULL, slot, item, NULL); + __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); @@ -1127,7 +1118,7 @@ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { - __radix_tree_replace(root, iter->node, slot, item, NULL); + __radix_tree_replace(root, iter->node, slot, item); } #ifdef CONFIG_RADIX_TREE_MULTIORDER @@ -1807,23 +1798,6 @@ radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); -/** - * __radix_tree_delete_node - try to free node after clearing a slot - * @root: radix tree root - * @node: node containing @index - * @update_node: callback for changing leaf nodes - * - * After clearing the slot at @index in @node from radix tree - * rooted at @root, call this function to attempt freeing the - * node and shrinking the tree. - */ -void __radix_tree_delete_node(struct radix_tree_root *root, - struct radix_tree_node *node, - radix_tree_update_node_t update_node) -{ - delete_node(root, node, update_node); -} - static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { @@ -1839,7 +1813,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); - return node && delete_node(root, node, NULL); + return node && delete_node(root, node); } /** diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 60786fa55302..0e0ff26c9bcb 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -618,7 +618,7 @@ static void multiorder_account(void) __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 1 << 5, &node, &slot); assert(node->count == node->nr_values * 2); - __radix_tree_replace(&tree, node, slot, NULL, NULL); + __radix_tree_replace(&tree, node, slot, NULL); assert(node->nr_values == 0); item_kill_tree(&tree); -- cgit v1.2.3-71-gd317 From 2956c6644bfd9aab9f6b21a12e1bd75876d9dd73 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove split/join code radix_tree_split and radix_tree_join were never used upstream. Remove them; if they're needed in future they will be replaced by XArray equivalents. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 - lib/radix-tree.c | 171 +---------------------- tools/testing/radix-tree/benchmark.c | 91 ------------- tools/testing/radix-tree/multiorder.c | 247 ---------------------------------- 4 files changed, 2 insertions(+), 513 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7513d0df984b..44f9abdcb5ab 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -284,12 +284,6 @@ static inline void radix_tree_preload_end(void) preempt_enable(); } -int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); -int radix_tree_split(struct radix_tree_root *, unsigned long index, - unsigned new_order); -int radix_tree_join(struct radix_tree_root *, unsigned long index, - unsigned new_order, void *); - void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index c4c252185734..c52e0bef5264 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -415,28 +415,6 @@ int radix_tree_maybe_preload(gfp_t gfp_mask) } EXPORT_SYMBOL(radix_tree_maybe_preload); -#ifdef CONFIG_RADIX_TREE_MULTIORDER -/* - * Preload with enough objects to ensure that we can split a single entry - * of order @old_order into many entries of size @new_order - */ -int radix_tree_split_preload(unsigned int old_order, unsigned int new_order, - gfp_t gfp_mask) -{ - unsigned top = 1 << (old_order % RADIX_TREE_MAP_SHIFT); - unsigned layers = (old_order / RADIX_TREE_MAP_SHIFT) - - (new_order / RADIX_TREE_MAP_SHIFT); - unsigned nr = 0; - - WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); - BUG_ON(new_order >= old_order); - - while (layers--) - nr = nr * RADIX_TREE_MAP_SIZE + 1; - return __radix_tree_preload(gfp_mask, top * nr); -} -#endif - /* * The same as function above, but preload number of nodes required to insert * (1 << order) continuous naturally-aligned elements. @@ -1111,8 +1089,8 @@ EXPORT_SYMBOL(radix_tree_replace_slot); * @slot: pointer to slot * @item: new item to store in the slot. * - * For use with radix_tree_split() and radix_tree_for_each_slot(). - * Caller must hold tree write locked across split and replacement. + * For use with radix_tree_for_each_slot(). + * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, @@ -1121,151 +1099,6 @@ void radix_tree_iter_replace(struct radix_tree_root *root, __radix_tree_replace(root, iter->node, slot, item); } -#ifdef CONFIG_RADIX_TREE_MULTIORDER -/** - * radix_tree_join - replace multiple entries with one multiorder entry - * @root: radix tree root - * @index: an index inside the new entry - * @order: order of the new entry - * @item: new entry - * - * Call this function to replace several entries with one larger entry. - * The existing entries are presumed to not need freeing as a result of - * this call. - * - * The replacement entry will have all the tags set on it that were set - * on any of the entries it is replacing. - */ -int radix_tree_join(struct radix_tree_root *root, unsigned long index, - unsigned order, void *item) -{ - struct radix_tree_node *node; - void __rcu **slot; - int error; - - BUG_ON(radix_tree_is_internal_node(item)); - - error = __radix_tree_create(root, index, order, &node, &slot); - if (!error) - error = insert_entries(node, slot, item, order, true); - if (error > 0) - error = 0; - - return error; -} - -/** - * radix_tree_split - Split an entry into smaller entries - * @root: radix tree root - * @index: An index within the large entry - * @order: Order of new entries - * - * Call this function as the first step in replacing a multiorder entry - * with several entries of lower order. After this function returns, - * loop over the relevant portion of the tree using radix_tree_for_each_slot() - * and call radix_tree_iter_replace() to set up each new entry. - * - * The tags from this entry are replicated to all the new entries. - * - * The radix tree should be locked against modification during the entire - * replacement operation. Lock-free lookups will see RADIX_TREE_RETRY which - * should prompt RCU walkers to restart the lookup from the root. - */ -int radix_tree_split(struct radix_tree_root *root, unsigned long index, - unsigned order) -{ - struct radix_tree_node *parent, *node, *child; - void __rcu **slot; - unsigned int offset, end; - unsigned n, tag, tags = 0; - gfp_t gfp = root_gfp_mask(root); - - if (!__radix_tree_lookup(root, index, &parent, &slot)) - return -ENOENT; - if (!parent) - return -ENOENT; - - offset = get_slot_offset(parent, slot); - - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tag_get(parent, tag, offset)) - tags |= 1 << tag; - - for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) { - if (!xa_is_sibling(rcu_dereference_raw(parent->slots[end]))) - break; - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_set(parent, tag, end); - /* rcu_assign_pointer ensures tags are set before RETRY */ - rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY); - } - rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY); - parent->nr_values -= (end - offset); - - if (order == parent->shift) - return 0; - if (order > parent->shift) { - while (offset < end) - offset += insert_entries(parent, &parent->slots[offset], - RADIX_TREE_RETRY, order, true); - return 0; - } - - node = parent; - - for (;;) { - if (node->shift > order) { - child = radix_tree_node_alloc(gfp, node, root, - node->shift - RADIX_TREE_MAP_SHIFT, - offset, 0, 0); - if (!child) - goto nomem; - if (node != parent) { - node->count++; - rcu_assign_pointer(node->slots[offset], - node_to_entry(child)); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_set(node, tag, offset); - } - - node = child; - offset = 0; - continue; - } - - n = insert_entries(node, &node->slots[offset], - RADIX_TREE_RETRY, order, false); - BUG_ON(n > RADIX_TREE_MAP_SIZE); - - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_set(node, tag, offset); - offset += n; - - while (offset == RADIX_TREE_MAP_SIZE) { - if (node == parent) - break; - offset = node->offset; - child = node; - node = node->parent; - rcu_assign_pointer(node->slots[offset], - node_to_entry(child)); - offset++; - } - if ((node == parent) && (offset == end)) - return 0; - } - - nomem: - /* Shouldn't happen; did user forget to preload? */ - /* TODO: free all the allocated nodes */ - WARN_ON(1); - return -ENOMEM; -} -#endif - static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c index 99c40f3ed133..35741b9c2a4a 100644 --- a/tools/testing/radix-tree/benchmark.c +++ b/tools/testing/radix-tree/benchmark.c @@ -146,90 +146,6 @@ static void benchmark_size(unsigned long size, unsigned long step, int order) rcu_barrier(); } -static long long __benchmark_split(unsigned long index, - int old_order, int new_order) -{ - struct timespec start, finish; - long long nsec; - RADIX_TREE(tree, GFP_ATOMIC); - - item_insert_order(&tree, index, old_order); - - clock_gettime(CLOCK_MONOTONIC, &start); - radix_tree_split(&tree, index, new_order); - clock_gettime(CLOCK_MONOTONIC, &finish); - nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + - (finish.tv_nsec - start.tv_nsec); - - item_kill_tree(&tree); - - return nsec; - -} - -static void benchmark_split(unsigned long size, unsigned long step) -{ - int i, j, idx; - long long nsec = 0; - - - for (idx = 0; idx < size; idx += step) { - for (i = 3; i < 11; i++) { - for (j = 0; j < i; j++) { - nsec += __benchmark_split(idx, i, j); - } - } - } - - printv(2, "Size %8ld, step %8ld, split time %10lld ns\n", - size, step, nsec); - -} - -static long long __benchmark_join(unsigned long index, - unsigned order1, unsigned order2) -{ - unsigned long loc; - struct timespec start, finish; - long long nsec; - void *item, *item2 = item_create(index + 1, order1); - RADIX_TREE(tree, GFP_KERNEL); - - item_insert_order(&tree, index, order2); - item = radix_tree_lookup(&tree, index); - - clock_gettime(CLOCK_MONOTONIC, &start); - radix_tree_join(&tree, index + 1, order1, item2); - clock_gettime(CLOCK_MONOTONIC, &finish); - nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + - (finish.tv_nsec - start.tv_nsec); - - loc = find_item(&tree, item); - if (loc == -1) - free(item); - - item_kill_tree(&tree); - - return nsec; -} - -static void benchmark_join(unsigned long step) -{ - int i, j, idx; - long long nsec = 0; - - for (idx = 0; idx < 1 << 10; idx += step) { - for (i = 1; i < 15; i++) { - for (j = 0; j < i; j++) { - nsec += __benchmark_join(idx, i, j); - } - } - } - - printv(2, "Size %8d, step %8ld, join time %10lld ns\n", - 1 << 10, step, nsec); -} - void benchmark(void) { unsigned long size[] = {1 << 10, 1 << 20, 0}; @@ -247,11 +163,4 @@ void benchmark(void) for (c = 0; size[c]; c++) for (s = 0; step[s]; s++) benchmark_size(size[c], step[s] << 9, 9); - - for (c = 0; size[c]; c++) - for (s = 0; step[s]; s++) - benchmark_split(size[c], step[s]); - - for (s = 0; step[s]; s++) - benchmark_join(step[s]); } diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 0e0ff26c9bcb..221e042d1b89 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -356,251 +356,6 @@ void multiorder_tagged_iteration(void) item_kill_tree(&tree); } -/* - * Basic join checks: make sure we can't find an entry in the tree after - * a larger entry has replaced it - */ -static void multiorder_join1(unsigned long index, - unsigned order1, unsigned order2) -{ - unsigned long loc; - void *item, *item2 = item_create(index + 1, order1); - RADIX_TREE(tree, GFP_KERNEL); - - item_insert_order(&tree, index, order2); - item = radix_tree_lookup(&tree, index); - radix_tree_join(&tree, index + 1, order1, item2); - loc = find_item(&tree, item); - if (loc == -1) - free(item); - item = radix_tree_lookup(&tree, index + 1); - assert(item == item2); - item_kill_tree(&tree); -} - -/* - * Check that the accounting of value entries is handled correctly - * by joining a value entry to a normal pointer. - */ -static void multiorder_join2(unsigned order1, unsigned order2) -{ - RADIX_TREE(tree, GFP_KERNEL); - struct radix_tree_node *node; - void *item1 = item_create(0, order1); - void *item2; - - item_insert_order(&tree, 0, order2); - radix_tree_insert(&tree, 1 << order2, xa_mk_value(5)); - item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); - assert(item2 == xa_mk_value(5)); - assert(node->nr_values == 1); - - item2 = radix_tree_lookup(&tree, 0); - free(item2); - - radix_tree_join(&tree, 0, order1, item1); - item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); - assert(item2 == item1); - assert(node->nr_values == 0); - item_kill_tree(&tree); -} - -/* - * This test revealed an accounting bug for value entries at one point. - * Nodes were being freed back into the pool with an elevated exception count - * by radix_tree_join() and then radix_tree_split() was failing to zero the - * count of value entries. - */ -static void multiorder_join3(unsigned int order) -{ - RADIX_TREE(tree, GFP_KERNEL); - struct radix_tree_node *node; - void **slot; - struct radix_tree_iter iter; - unsigned long i; - - for (i = 0; i < (1 << order); i++) { - radix_tree_insert(&tree, i, xa_mk_value(5)); - } - - radix_tree_join(&tree, 0, order, xa_mk_value(7)); - rcu_barrier(); - - radix_tree_split(&tree, 0, 0); - - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5)); - } - - __radix_tree_lookup(&tree, 0, &node, NULL); - assert(node->nr_values == node->count); - - item_kill_tree(&tree); -} - -static void multiorder_join(void) -{ - int i, j, idx; - - for (idx = 0; idx < 1024; idx = idx * 2 + 3) { - for (i = 1; i < 15; i++) { - for (j = 0; j < i; j++) { - multiorder_join1(idx, i, j); - } - } - } - - for (i = 1; i < 15; i++) { - for (j = 0; j < i; j++) { - multiorder_join2(i, j); - } - } - - for (i = 3; i < 10; i++) { - multiorder_join3(i); - } -} - -static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) -{ - struct radix_tree_preload *rtp = &radix_tree_preloads; - if (rtp->nr != 0) - printv(2, "split(%u %u) remaining %u\n", old_order, new_order, - rtp->nr); - /* - * Can't check for equality here as some nodes may have been - * RCU-freed while we ran. But we should never finish with more - * nodes allocated since they should have all been preloaded. - */ - if (nr_allocated > alloc) - printv(2, "split(%u %u) allocated %u %u\n", old_order, new_order, - alloc, nr_allocated); -} - -static void __multiorder_split(int old_order, int new_order) -{ - RADIX_TREE(tree, GFP_ATOMIC); - void **slot; - struct radix_tree_iter iter; - unsigned alloc; - struct item *item; - - radix_tree_preload(GFP_KERNEL); - assert(item_insert_order(&tree, 0, old_order) == 0); - radix_tree_preload_end(); - - /* Wipe out the preloaded cache or it'll confuse check_mem() */ - radix_tree_cpu_dead(0); - - item = radix_tree_tag_set(&tree, 0, 2); - - radix_tree_split_preload(old_order, new_order, GFP_KERNEL); - alloc = nr_allocated; - radix_tree_split(&tree, 0, new_order); - check_mem(old_order, new_order, alloc); - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, - item_create(iter.index, new_order)); - } - radix_tree_preload_end(); - - item_kill_tree(&tree); - free(item); -} - -static void __multiorder_split2(int old_order, int new_order) -{ - RADIX_TREE(tree, GFP_KERNEL); - void **slot; - struct radix_tree_iter iter; - struct radix_tree_node *node; - void *item; - - __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); - - item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == xa_mk_value(5)); - assert(node->nr_values > 0); - - radix_tree_split(&tree, 0, new_order); - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, - item_create(iter.index, new_order)); - } - - item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item != xa_mk_value(5)); - assert(node->nr_values == 0); - - item_kill_tree(&tree); -} - -static void __multiorder_split3(int old_order, int new_order) -{ - RADIX_TREE(tree, GFP_KERNEL); - void **slot; - struct radix_tree_iter iter; - struct radix_tree_node *node; - void *item; - - __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); - - item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == xa_mk_value(5)); - assert(node->nr_values > 0); - - radix_tree_split(&tree, 0, new_order); - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7)); - } - - item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == xa_mk_value(7)); - assert(node->nr_values > 0); - - item_kill_tree(&tree); - - __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); - - item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == xa_mk_value(5)); - assert(node->nr_values > 0); - - radix_tree_split(&tree, 0, new_order); - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - if (iter.index == (1 << new_order)) - radix_tree_iter_replace(&tree, &iter, slot, - xa_mk_value(7)); - else - radix_tree_iter_replace(&tree, &iter, slot, NULL); - } - - item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); - assert(item == xa_mk_value(7)); - assert(node->count == node->nr_values); - do { - node = node->parent; - if (!node) - break; - assert(node->count == 1); - assert(node->nr_values == 0); - } while (1); - - item_kill_tree(&tree); -} - -static void multiorder_split(void) -{ - int i, j; - - for (i = 3; i < 11; i++) - for (j = 0; j < i; j++) { - __multiorder_split(i, j); - __multiorder_split2(i, j); - __multiorder_split3(i, j); - } -} - static void multiorder_account(void) { RADIX_TREE(tree, GFP_KERNEL); @@ -702,8 +457,6 @@ void multiorder_checks(void) multiorder_tag_tests(); multiorder_iteration(); multiorder_tagged_iteration(); - multiorder_join(); - multiorder_split(); multiorder_account(); multiorder_iteration_race(); -- cgit v1.2.3-71-gd317 From 8cf2f98411e3a0865026a1061af637161b16d32b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 19 May 2018 16:47:47 -0400 Subject: radix tree: Remove radix_tree_maybe_preload_order This function was only used by the page cache which is now converted to the XArray. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 1 - lib/radix-tree.c | 74 ---------------------------------------------- 2 files changed, 75 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 44f9abdcb5ab..664d50c5c2ff 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -259,7 +259,6 @@ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); -int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index c52e0bef5264..b57ddc3dbbbd 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -41,9 +41,6 @@ #include -/* Number of nodes in fully populated tree of given height */ -static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; - /* * Radix tree node cache. */ @@ -415,51 +412,6 @@ int radix_tree_maybe_preload(gfp_t gfp_mask) } EXPORT_SYMBOL(radix_tree_maybe_preload); -/* - * The same as function above, but preload number of nodes required to insert - * (1 << order) continuous naturally-aligned elements. - */ -int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) -{ - unsigned long nr_subtrees; - int nr_nodes, subtree_height; - - /* Preloading doesn't help anything with this gfp mask, skip it */ - if (!gfpflags_allow_blocking(gfp_mask)) { - preempt_disable(); - return 0; - } - - /* - * Calculate number and height of fully populated subtrees it takes to - * store (1 << order) elements. - */ - nr_subtrees = 1 << order; - for (subtree_height = 0; nr_subtrees > RADIX_TREE_MAP_SIZE; - subtree_height++) - nr_subtrees >>= RADIX_TREE_MAP_SHIFT; - - /* - * The worst case is zero height tree with a single item at index 0 and - * then inserting items starting at ULONG_MAX - (1 << order). - * - * This requires RADIX_TREE_MAX_PATH nodes to build branch from root to - * 0-index item. - */ - nr_nodes = RADIX_TREE_MAX_PATH; - - /* Plus branch to fully populated subtrees. */ - nr_nodes += RADIX_TREE_MAX_PATH - subtree_height; - - /* Root node is shared. */ - nr_nodes--; - - /* Plus nodes required to build subtrees. */ - nr_nodes += nr_subtrees * height_to_maxnodes[subtree_height]; - - return __radix_tree_preload(gfp_mask, nr_nodes); -} - static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { @@ -1859,31 +1811,6 @@ radix_tree_node_ctor(void *arg) INIT_LIST_HEAD(&node->private_list); } -static __init unsigned long __maxindex(unsigned int height) -{ - unsigned int width = height * RADIX_TREE_MAP_SHIFT; - int shift = RADIX_TREE_INDEX_BITS - width; - - if (shift < 0) - return ~0UL; - if (shift >= BITS_PER_LONG) - return 0UL; - return ~0UL >> shift; -} - -static __init void radix_tree_init_maxnodes(void) -{ - unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1]; - unsigned int i, j; - - for (i = 0; i < ARRAY_SIZE(height_to_maxindex); i++) - height_to_maxindex[i] = __maxindex(i); - for (i = 0; i < ARRAY_SIZE(height_to_maxnodes); i++) { - for (j = i; j > 0; j--) - height_to_maxnodes[i] += height_to_maxindex[j - 1] + 1; - } -} - static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; @@ -1911,7 +1838,6 @@ void __init radix_tree_init(void) sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); - radix_tree_init_maxnodes(); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); -- cgit v1.2.3-71-gd317 From adb9d9c4ccb1ff0bf1d376e65f36aa5573c75c1a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 9 Apr 2018 16:52:21 -0400 Subject: radix tree: Remove radix_tree_clear_tags The page cache was the only user of this interface and it has now been converted to the XArray. Transform the test into a test of xas_init_marks(). Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- lib/radix-tree.c | 13 ------------ lib/test_xarray.c | 40 ++++++++++++++++++++++++++++++++++++ tools/testing/radix-tree/tag_check.c | 29 -------------------------- 4 files changed, 40 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 664d50c5c2ff..7b009af3bb1e 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -252,8 +252,6 @@ void radix_tree_iter_delete(struct radix_tree_root *, struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, - void __rcu **slot); unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index b57ddc3dbbbd..e92f2b6ae9c5 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1670,19 +1670,6 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) } EXPORT_SYMBOL(radix_tree_delete); -void radix_tree_clear_tags(struct radix_tree_root *root, - struct radix_tree_node *node, - void __rcu **slot) -{ - if (node) { - unsigned int tag, offset = get_slot_offset(node, slot); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - node_tag_clear(root, node, tag, offset); - } else { - root_tag_clear_all(root); - } -} - /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 815daffdd8c9..ca86141641cb 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -213,12 +213,52 @@ static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_xa_mark_2(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + unsigned long index; + unsigned int count = 0; + void *entry; + + xa_store_index(xa, 0, GFP_KERNEL); + xa_set_mark(xa, 0, XA_MARK_0); + xas_lock(&xas); + xas_load(&xas); + xas_init_marks(&xas); + xas_unlock(&xas); + XA_BUG_ON(xa, !xa_get_mark(xa, 0, XA_MARK_0) == 0); + + for (index = 3500; index < 4500; index++) { + xa_store_index(xa, index, GFP_KERNEL); + xa_set_mark(xa, index, XA_MARK_0); + } + + xas_reset(&xas); + rcu_read_lock(); + xas_for_each_marked(&xas, entry, ULONG_MAX, XA_MARK_0) + count++; + rcu_read_unlock(); + XA_BUG_ON(xa, count != 1000); + + xas_lock(&xas); + xas_for_each(&xas, entry, ULONG_MAX) { + xas_init_marks(&xas); + XA_BUG_ON(xa, !xa_get_mark(xa, xas.xa_index, XA_MARK_0)); + XA_BUG_ON(xa, !xas_get_mark(&xas, XA_MARK_0)); + } + xas_unlock(&xas); + + xa_destroy(xa); +} + static noinline void check_xa_mark(struct xarray *xa) { unsigned long index; for (index = 0; index < 16384; index += 4) check_xa_mark_1(xa, index); + + check_xa_mark_2(xa); } static noinline void check_xa_shrink(struct xarray *xa) diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index 543181e4847b..56a42f1c5ab0 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -331,34 +331,6 @@ static void single_check(void) item_kill_tree(&tree); } -void radix_tree_clear_tags_test(void) -{ - unsigned long index; - struct radix_tree_node *node; - struct radix_tree_iter iter; - void **slot; - - RADIX_TREE(tree, GFP_KERNEL); - - item_insert(&tree, 0); - item_tag_set(&tree, 0, 0); - __radix_tree_lookup(&tree, 0, &node, &slot); - radix_tree_clear_tags(&tree, node, slot); - assert(item_tag_get(&tree, 0, 0) == 0); - - for (index = 0; index < 1000; index++) { - item_insert(&tree, index); - item_tag_set(&tree, index, 0); - } - - radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_clear_tags(&tree, iter.node, slot); - assert(item_tag_get(&tree, iter.index, 0) == 0); - } - - item_kill_tree(&tree); -} - void tag_check(void) { single_check(); @@ -376,5 +348,4 @@ void tag_check(void) thrash_tags(); rcu_barrier(); printv(2, "after thrash_tags: %d allocated\n", nr_allocated); - radix_tree_clear_tags_test(); } -- cgit v1.2.3-71-gd317 From 372266ba0267803564824b1c09f1bb7f3f3fc761 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 18 Aug 2018 07:09:22 -0400 Subject: radix tree test suite: Convert tag_tagged_items to XArray The tag_tagged_items() function is supposed to test the page-writeback tagging code. Since that has been converted to the XArray, there's not much point in testing the radix tree's tagging code. This requires using the pthread mutex embedded in the xarray instead of an external lock, so remove the pthread mutexes which protect xarrays/radix trees. Also remove radix_tree_iter_tag_set() as this was the last user. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 2 -- lib/radix-tree.c | 12 ---------- tools/testing/radix-tree/iteration_check.c | 16 ++++++------- tools/testing/radix-tree/main.c | 4 ++-- tools/testing/radix-tree/multiorder.c | 12 +++++----- tools/testing/radix-tree/regression1.c | 17 +++++++------- tools/testing/radix-tree/regression2.c | 8 +++---- tools/testing/radix-tree/tag_check.c | 4 ++-- tools/testing/radix-tree/test.c | 37 ++++++++++++------------------ tools/testing/radix-tree/test.h | 5 ++-- 10 files changed, 46 insertions(+), 71 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 7b009af3bb1e..9a1460488163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -264,8 +264,6 @@ void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *, - const struct radix_tree_iter *iter, unsigned int tag); void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, diff --git a/lib/radix-tree.c b/lib/radix-tree.c index e92f2b6ae9c5..f107dd2698e3 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1108,18 +1108,6 @@ void *radix_tree_tag_set(struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_tag_set); -/** - * radix_tree_iter_tag_set - set a tag on the current iterator entry - * @root: radix tree root - * @iter: iterator state - * @tag: tag to set - */ -void radix_tree_iter_tag_set(struct radix_tree_root *root, - const struct radix_tree_iter *iter, unsigned int tag) -{ - node_tag_set(root, iter->node, tag, iter_offset(iter)); -} - static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c index a92bab513701..d047327bb9ef 100644 --- a/tools/testing/radix-tree/iteration_check.c +++ b/tools/testing/radix-tree/iteration_check.c @@ -18,10 +18,9 @@ #define NUM_THREADS 5 #define MAX_IDX 100 -#define TAG 0 -#define NEW_TAG 1 +#define TAG XA_MARK_0 +#define NEW_TAG XA_MARK_1 -static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER; static pthread_t threads[NUM_THREADS]; static unsigned int seeds[3]; static RADIX_TREE(tree, GFP_KERNEL); @@ -38,7 +37,7 @@ static void *add_entries_fn(void *arg) int order; for (pgoff = 0; pgoff < MAX_IDX; pgoff++) { - pthread_mutex_lock(&tree_lock); + xa_lock(&tree); for (order = max_order; order >= 0; order--) { if (item_insert_order(&tree, pgoff, order) == 0) { @@ -46,7 +45,7 @@ static void *add_entries_fn(void *arg) break; } } - pthread_mutex_unlock(&tree_lock); + xa_unlock(&tree); } } @@ -150,9 +149,9 @@ static void *remove_entries_fn(void *arg) pgoff = rand_r(&seeds[2]) % MAX_IDX; - pthread_mutex_lock(&tree_lock); + xa_lock(&tree); item_delete(&tree, pgoff); - pthread_mutex_unlock(&tree_lock); + xa_unlock(&tree); } rcu_unregister_thread(); @@ -165,8 +164,7 @@ static void *tag_entries_fn(void *arg) rcu_register_thread(); while (!test_complete) { - tag_tagged_items(&tree, &tree_lock, 0, MAX_IDX, 10, TAG, - NEW_TAG); + tag_tagged_items(&tree, 0, MAX_IDX, 10, TAG, NEW_TAG); } rcu_unregister_thread(); return NULL; diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index 79589ea570ab..77a44c54998f 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -214,7 +214,7 @@ void copy_tag_check(void) } // printf("\ncopying tags...\n"); - tagged = tag_tagged_items(&tree, NULL, start, end, ITEMS, 0, 1); + tagged = tag_tagged_items(&tree, start, end, ITEMS, XA_MARK_0, XA_MARK_1); // printf("checking copied tags\n"); assert(tagged == count); @@ -223,7 +223,7 @@ void copy_tag_check(void) /* Copy tags in several rounds */ // printf("\ncopying tags...\n"); tmp = rand() % (count / 10 + 2); - tagged = tag_tagged_items(&tree, NULL, start, end, tmp, 0, 2); + tagged = tag_tagged_items(&tree, start, end, tmp, XA_MARK_0, XA_MARK_2); assert(tagged == count); // printf("%lu %lu %lu\n", tagged, tmp, count); diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 221e042d1b89..0436554a099a 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -59,7 +59,7 @@ static void __multiorder_tag_test(int index, int order) assert(!radix_tree_tag_get(&tree, i, 1)); } - assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 1); + assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 1); assert(radix_tree_tag_clear(&tree, index, 0)); for_each_index(i, base, order) { @@ -87,7 +87,7 @@ static void __multiorder_tag_test2(unsigned order, unsigned long index2) assert(radix_tree_tag_set(&tree, 0, 0)); assert(radix_tree_tag_set(&tree, index2, 0)); - assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 2); + assert(tag_tagged_items(&tree, 0, ~0UL, 10, XA_MARK_0, XA_MARK_1) == 2); item_kill_tree(&tree); } @@ -318,8 +318,8 @@ void multiorder_tagged_iteration(void) } } - assert(tag_tagged_items(&tree, NULL, 0, ~0UL, TAG_ENTRIES, 1, 2) == - TAG_ENTRIES); + assert(tag_tagged_items(&tree, 0, ~0UL, TAG_ENTRIES, XA_MARK_1, + XA_MARK_2) == TAG_ENTRIES); for (j = 0; j < 256; j++) { int mask, k; @@ -345,8 +345,8 @@ void multiorder_tagged_iteration(void) } } - assert(tag_tagged_items(&tree, NULL, 1, ~0UL, MT_NUM_ENTRIES * 2, 1, 0) - == TAG_ENTRIES); + assert(tag_tagged_items(&tree, 1, ~0UL, MT_NUM_ENTRIES * 2, XA_MARK_1, + XA_MARK_0) == TAG_ENTRIES); i = 0; radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) { assert(iter.index == tag_index[i]); diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index b4a4a7168986..a61c7bcbc72d 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -44,7 +44,6 @@ #include "regression.h" static RADIX_TREE(mt_tree, GFP_KERNEL); -static pthread_mutex_t mt_lock = PTHREAD_MUTEX_INITIALIZER; struct page { pthread_mutex_t lock; @@ -126,29 +125,29 @@ static void *regression1_fn(void *arg) struct page *p; p = page_alloc(0); - pthread_mutex_lock(&mt_lock); + xa_lock(&mt_tree); radix_tree_insert(&mt_tree, 0, p); - pthread_mutex_unlock(&mt_lock); + xa_unlock(&mt_tree); p = page_alloc(1); - pthread_mutex_lock(&mt_lock); + xa_lock(&mt_tree); radix_tree_insert(&mt_tree, 1, p); - pthread_mutex_unlock(&mt_lock); + xa_unlock(&mt_tree); - pthread_mutex_lock(&mt_lock); + xa_lock(&mt_tree); p = radix_tree_delete(&mt_tree, 1); pthread_mutex_lock(&p->lock); p->count--; pthread_mutex_unlock(&p->lock); - pthread_mutex_unlock(&mt_lock); + xa_unlock(&mt_tree); page_free(p); - pthread_mutex_lock(&mt_lock); + xa_lock(&mt_tree); p = radix_tree_delete(&mt_tree, 0); pthread_mutex_lock(&p->lock); p->count--; pthread_mutex_unlock(&p->lock); - pthread_mutex_unlock(&mt_lock); + xa_unlock(&mt_tree); page_free(p); } } else { diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c index 424b91c77831..f2c7e640a919 100644 --- a/tools/testing/radix-tree/regression2.c +++ b/tools/testing/radix-tree/regression2.c @@ -53,9 +53,9 @@ #include "regression.h" #include "test.h" -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 +#define PAGECACHE_TAG_DIRTY XA_MARK_0 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 static RADIX_TREE(mt_tree, GFP_KERNEL); unsigned long page_count = 0; @@ -92,7 +92,7 @@ void regression2_test(void) /* 1. */ start = 0; end = max_slots - 2; - tag_tagged_items(&mt_tree, NULL, start, end, 1, + tag_tagged_items(&mt_tree, start, end, 1, PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE); /* 2. */ diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index 56a42f1c5ab0..f898957b1a19 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -24,7 +24,7 @@ __simple_checks(struct radix_tree_root *tree, unsigned long index, int tag) item_tag_set(tree, index, tag); ret = item_tag_get(tree, index, tag); assert(ret != 0); - ret = tag_tagged_items(tree, NULL, first, ~0UL, 10, tag, !tag); + ret = tag_tagged_items(tree, first, ~0UL, 10, tag, !tag); assert(ret == 1); ret = item_tag_get(tree, index, !tag); assert(ret != 0); @@ -321,7 +321,7 @@ static void single_check(void) assert(ret == 0); verify_tag_consistency(&tree, 0); verify_tag_consistency(&tree, 1); - ret = tag_tagged_items(&tree, NULL, first, 10, 10, 0, 1); + ret = tag_tagged_items(&tree, first, 10, 10, XA_MARK_0, XA_MARK_1); assert(ret == 1); ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 1); assert(ret == 1); diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 470419bfd49d..d70adcd03d35 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -176,35 +176,28 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start, } /* Use the same pattern as tag_pages_for_writeback() in mm/page-writeback.c */ -int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock, - unsigned long start, unsigned long end, unsigned batch, - unsigned iftag, unsigned thentag) +int tag_tagged_items(struct xarray *xa, unsigned long start, unsigned long end, + unsigned batch, xa_mark_t iftag, xa_mark_t thentag) { - unsigned long tagged = 0; - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, xa, start); + unsigned int tagged = 0; + struct item *item; if (batch == 0) batch = 1; - if (lock) - pthread_mutex_lock(lock); - radix_tree_for_each_tagged(slot, root, &iter, start, iftag) { - if (iter.index > end) - break; - radix_tree_iter_tag_set(root, &iter, thentag); - tagged++; - if ((tagged % batch) != 0) + xas_lock_irq(&xas); + xas_for_each_marked(&xas, item, end, iftag) { + xas_set_mark(&xas, thentag); + if (++tagged % batch) continue; - slot = radix_tree_iter_resume(slot, &iter); - if (lock) { - pthread_mutex_unlock(lock); - rcu_barrier(); - pthread_mutex_lock(lock); - } + + xas_pause(&xas); + xas_unlock_irq(&xas); + rcu_barrier(); + xas_lock_irq(&xas); } - if (lock) - pthread_mutex_unlock(lock); + xas_unlock_irq(&xas); return tagged; } diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 9532c18c6cb1..100e9a456f91 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -29,9 +29,8 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start, unsigned long nr, int chunk); void item_kill_tree(struct radix_tree_root *root); -int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *, - unsigned long start, unsigned long end, unsigned batch, - unsigned iftag, unsigned thentag); +int tag_tagged_items(struct xarray *, unsigned long start, unsigned long end, + unsigned batch, xa_mark_t iftag, xa_mark_t thentag); void xarray_tests(void); void tag_check(void); -- cgit v1.2.3-71-gd317 From 0e9446c35a80931044b6d8d2d74a9cabd248539f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 15 Aug 2018 14:13:29 -0400 Subject: xarray: Add range store functionality This version of xa_store_range() really only supports load and store. Our only user only needs basic load and store functionality, so there's no need to do the extra work to support marking and overlapping stores correctly yet. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 8 ++++ include/linux/xarray.h | 2 + lib/test_xarray.c | 34 ++++++++++++++ lib/xarray.c | 97 ++++++++++++++++++++++++++++++++++++++- 4 files changed, 139 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 463e4c798ec1..a4e705108f42 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -98,6 +98,13 @@ the XArray by calling :c:func:`xa_for_each`. You may prefer to use :c:func:`xa_find` or :c:func:`xa_find_after` to move to the next present entry in the XArray. +Calling :c:func:`xa_store_range` stores the same entry in a range +of indices. If you do this, some of the other operations will behave +in a slightly odd way. For example, marking the entry at one index +may result in the entry being marked at some, but not all of the other +indices. Storing into one index may result in the entry retrieved by +some, but not all of the other indices changing. + Finally, you can remove all entries from an XArray by calling :c:func:`xa_destroy`. If the XArray entries are pointers, you may wish to free the entries first. You can do this by iterating over all present @@ -156,6 +163,7 @@ Takes xa_lock internally: * :c:func:`xa_erase_bh` * :c:func:`xa_erase_irq` * :c:func:`xa_cmpxchg` + * :c:func:`xa_store_range` * :c:func:`xa_alloc` * :c:func:`xa_alloc_bh` * :c:func:`xa_alloc_irq` diff --git a/include/linux/xarray.h b/include/linux/xarray.h index e0b57af52e9b..d9514928ddac 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -292,6 +292,8 @@ void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int xa_reserve(struct xarray *, unsigned long index, gfp_t); +void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, + void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 0f06a93b4d0e..aa47754150ce 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1039,6 +1039,39 @@ static noinline void check_create_range(struct xarray *xa) check_create_range_3(); } +static noinline void __check_store_range(struct xarray *xa, unsigned long first, + unsigned long last) +{ +#ifdef CONFIG_XARRAY_MULTI + xa_store_range(xa, first, last, xa_mk_value(first), GFP_KERNEL); + + XA_BUG_ON(xa, xa_load(xa, first) != xa_mk_value(first)); + XA_BUG_ON(xa, xa_load(xa, last) != xa_mk_value(first)); + XA_BUG_ON(xa, xa_load(xa, first - 1) != NULL); + XA_BUG_ON(xa, xa_load(xa, last + 1) != NULL); + + xa_store_range(xa, first, last, NULL, GFP_KERNEL); +#endif + + XA_BUG_ON(xa, !xa_empty(xa)); +} + +static noinline void check_store_range(struct xarray *xa) +{ + unsigned long i, j; + + for (i = 0; i < 128; i++) { + for (j = i; j < 128; j++) { + __check_store_range(xa, i, j); + __check_store_range(xa, 128 + i, 128 + j); + __check_store_range(xa, 4095 + i, 4095 + j); + __check_store_range(xa, 4096 + i, 4096 + j); + __check_store_range(xa, 123456 + i, 123456 + j); + __check_store_range(xa, UINT_MAX + i, UINT_MAX + j); + } + } +} + static LIST_HEAD(shadow_nodes); static void test_update_node(struct xa_node *node) @@ -1184,6 +1217,7 @@ static int xarray_checks(void) check_destroy(&array); check_move(&array); check_create_range(&array); + check_store_range(&array); check_store_iter(&array); check_workingset(&array, 0); diff --git a/lib/xarray.c b/lib/xarray.c index 9a0d49d4b5f0..8b176f009c08 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -376,6 +376,14 @@ static void *xas_alloc(struct xa_state *xas, unsigned int shift) return node; } +#ifdef CONFIG_XARRAY_MULTI +/* Returns the number of indices covered by a given xa_state */ +static unsigned long xas_size(const struct xa_state *xas) +{ + return (xas->xa_sibs + 1UL) << xas->xa_shift; +} +#endif + /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a @@ -388,8 +396,7 @@ static unsigned long xas_max(struct xa_state *xas) #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { - unsigned long mask; - mask = (((xas->xa_sibs + 1UL) << xas->xa_shift) - 1); + unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; @@ -1517,6 +1524,92 @@ int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) } EXPORT_SYMBOL(xa_reserve); +#ifdef CONFIG_XARRAY_MULTI +static void xas_set_range(struct xa_state *xas, unsigned long first, + unsigned long last) +{ + unsigned int shift = 0; + unsigned long sibs = last - first; + unsigned int offset = XA_CHUNK_MASK; + + xas_set(xas, first); + + while ((first & XA_CHUNK_MASK) == 0) { + if (sibs < XA_CHUNK_MASK) + break; + if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) + break; + shift += XA_CHUNK_SHIFT; + if (offset == XA_CHUNK_MASK) + offset = sibs & XA_CHUNK_MASK; + sibs >>= XA_CHUNK_SHIFT; + first >>= XA_CHUNK_SHIFT; + } + + offset = first & XA_CHUNK_MASK; + if (offset + sibs > XA_CHUNK_MASK) + sibs = XA_CHUNK_MASK - offset; + if ((((first + sibs + 1) << shift) - 1) > last) + sibs -= 1; + + xas->xa_shift = shift; + xas->xa_sibs = sibs; +} + +/** + * xa_store_range() - Store this entry at a range of indices in the XArray. + * @xa: XArray. + * @first: First index to affect. + * @last: Last index to affect. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * After this function returns, loads from any index between @first and @last, + * inclusive will return @entry. + * Storing into an existing multislot entry updates the entry of every index. + * The marks associated with @index are unaffected unless @entry is %NULL. + * + * Context: Process context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in + * an XArray, or xa_err(-ENOMEM) if memory allocation failed. + */ +void *xa_store_range(struct xarray *xa, unsigned long first, + unsigned long last, void *entry, gfp_t gfp) +{ + XA_STATE(xas, xa, 0); + + if (WARN_ON_ONCE(xa_is_internal(entry))) + return XA_ERROR(-EINVAL); + if (last < first) + return XA_ERROR(-EINVAL); + + do { + xas_lock(&xas); + if (entry) { + unsigned int order = (last == ~0UL) ? 64 : + ilog2(last + 1); + xas_set_order(&xas, last, order); + xas_create(&xas); + if (xas_error(&xas)) + goto unlock; + } + do { + xas_set_range(&xas, first, last); + xas_store(&xas, entry); + if (xas_error(&xas)) + goto unlock; + first += xas_size(&xas); + } while (first <= last); +unlock: + xas_unlock(&xas); + } while (xas_nomem(&xas, gfp)); + + return xas_result(&xas, NULL); +} +EXPORT_SYMBOL(xa_store_range); +#endif /* CONFIG_XARRAY_MULTI */ + /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. -- cgit v1.2.3-71-gd317 From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 22 Sep 2018 16:14:30 -0400 Subject: radix tree: Remove multiorder support All users have now been converted to the XArray. Removing the support reduces code size and ensures new users will use the XArray instead. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 40 +---- lib/Kconfig | 4 - lib/radix-tree.c | 215 ++------------------------ mm/Kconfig | 4 +- tools/testing/radix-tree/generated/autoconf.h | 1 - 5 files changed, 19 insertions(+), 245 deletions(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9a1460488163..06c4c7a6c09c 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root) * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot - * @shift: shift for the node that holds our slots * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is @@ -110,20 +109,8 @@ struct radix_tree_iter { unsigned long next_index; unsigned long tags; struct radix_tree_node *node; -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned int shift; -#endif }; -static inline unsigned int iter_shift(const struct radix_tree_iter *iter) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - return iter->shift; -#else - return 0; -#endif -} - /** * Radix-tree synchronization * @@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_insert(struct radix_tree_root *, unsigned long index, - unsigned order, void *); -static inline int radix_tree_insert(struct radix_tree_root *root, - unsigned long index, void *entry) -{ - return __radix_tree_insert(root, index, 0, entry); -} +int radix_tree_insert(struct radix_tree_root *, unsigned long index, + void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); @@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { - return iter->index + (slots << iter_shift(iter)); + return iter->index + slots; } /** @@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { - return (iter->next_index - iter->index) >> iter_shift(iter); -} - -#ifdef CONFIG_RADIX_TREE_MULTIORDER -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags); -#else -/* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - return slot; + return iter->next_index - iter->index; } -#endif /** * radix_tree_next_slot - find next slot in chunk @@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, return NULL; found: - if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) - return __radix_tree_next_slot(slot, iter, flags); return slot; } diff --git a/lib/Kconfig b/lib/Kconfig index 40bfa6ccd294..a9965f4af4dd 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -405,10 +405,6 @@ config XARRAY_MULTI Support entries which occupy multiple consecutive indices in the XArray. -config RADIX_TREE_MULTIORDER - bool - select XARRAY_MULTI - config ASSOCIATIVE_ARRAY bool help diff --git a/lib/radix-tree.c b/lib/radix-tree.c index f107dd2698e3..1106bb6aa01e 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -110,11 +110,6 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); - if (xa_is_sibling(entry)) { - offset = xa_to_sibling(entry); - entry = rcu_dereference_raw(parent->slots[offset]); - } - *nodep = (void *)entry; return offset; } @@ -229,7 +224,7 @@ radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, static unsigned int iter_offset(const struct radix_tree_iter *iter) { - return (iter->index >> iter_shift(iter)) & RADIX_TREE_MAP_MASK; + return iter->index & RADIX_TREE_MAP_MASK; } /* @@ -506,16 +501,13 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root) /* * The candidate node has more than one child, or its child - * is not at the leftmost slot, or the child is a multiorder - * entry, we cannot shrink. + * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; - if (!radix_tree_is_internal_node(child) && node->shift) - break; /* * For an IDR, we must not shrink entry 0 into the root in @@ -613,7 +605,6 @@ static bool delete_node(struct radix_tree_root *root, * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key - * @order: index occupies 2^order aligned slots * @nodep: returns node * @slotp: returns slot * @@ -627,21 +618,19 @@ static bool delete_node(struct radix_tree_root *root, * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, - unsigned long index, unsigned order, - struct radix_tree_node **nodep, void __rcu ***slotp) + unsigned long index, struct radix_tree_node **nodep, + void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; - unsigned long max = index | ((1UL << order) - 1); + unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ - if (order > 0 && max == ((1UL << order) - 1)) - max++; if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) @@ -650,7 +639,7 @@ static int __radix_tree_create(struct radix_tree_root *root, child = rcu_dereference_raw(root->xa_head); } - while (shift > order) { + while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ @@ -711,70 +700,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) } } -#ifdef CONFIG_RADIX_TREE_MULTIORDER -static inline int insert_entries(struct radix_tree_node *node, - void __rcu **slot, void *item, unsigned order, bool replace) -{ - void *sibling; - unsigned i, n, tag, offset, tags = 0; - - if (node) { - if (order > node->shift) - n = 1 << (order - node->shift); - else - n = 1; - offset = get_slot_offset(node, slot); - } else { - n = 1; - offset = 0; - } - - if (n > 1) { - offset = offset & ~(n - 1); - slot = &node->slots[offset]; - } - sibling = xa_mk_sibling(offset); - - for (i = 0; i < n; i++) { - if (slot[i]) { - if (replace) { - node->count--; - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tag_get(node, tag, offset + i)) - tags |= 1 << tag; - } else - return -EEXIST; - } - } - - for (i = 0; i < n; i++) { - struct radix_tree_node *old = rcu_dereference_raw(slot[i]); - if (i) { - rcu_assign_pointer(slot[i], sibling); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_clear(node, tag, offset + i); - } else { - rcu_assign_pointer(slot[i], item); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_set(node, tag, offset); - } - if (xa_is_node(old)) - radix_tree_free_nodes(old); - if (xa_is_value(old)) - node->nr_values--; - } - if (node) { - node->count += n; - if (xa_is_value(item)) - node->nr_values += n; - } - return n; -} -#else static inline int insert_entries(struct radix_tree_node *node, - void __rcu **slot, void *item, unsigned order, bool replace) + void __rcu **slot, void *item, bool replace) { if (*slot) return -EEXIST; @@ -786,19 +713,17 @@ static inline int insert_entries(struct radix_tree_node *node, } return 1; } -#endif /** * __radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key - * @order: key covers the 2^order indices around index * @item: item to insert * * Insert an item into the radix tree at position @index. */ -int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, - unsigned order, void *item) +int radix_tree_insert(struct radix_tree_root *root, unsigned long index, + void *item) { struct radix_tree_node *node; void __rcu **slot; @@ -806,11 +731,11 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, BUG_ON(radix_tree_is_internal_node(item)); - error = __radix_tree_create(root, index, order, &node, &slot); + error = __radix_tree_create(root, index, &node, &slot); if (error) return error; - error = insert_entries(node, slot, item, order, false); + error = insert_entries(node, slot, item, false); if (error < 0) return error; @@ -825,7 +750,7 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, return 0; } -EXPORT_SYMBOL(__radix_tree_insert); +EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree @@ -917,32 +842,12 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) } EXPORT_SYMBOL(radix_tree_lookup); -static inline void replace_sibling_entries(struct radix_tree_node *node, - void __rcu **slot, int count, int values) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned offset = get_slot_offset(node, slot); - void *ptr = xa_mk_sibling(offset); - - while (++offset < RADIX_TREE_MAP_SIZE) { - if (rcu_dereference_raw(node->slots[offset]) != ptr) - break; - if (count < 0) { - node->slots[offset] = NULL; - node->count--; - } - node->nr_values += values; - } -#endif -} - static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; - replace_sibling_entries(node, slot, count, values); } rcu_assign_pointer(*slot, item); @@ -1223,14 +1128,6 @@ int radix_tree_tag_get(const struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_tag_get); -static inline void __set_iter_shift(struct radix_tree_iter *iter, - unsigned int shift) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - iter->shift = shift; -#endif -} - /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, @@ -1257,92 +1154,11 @@ static void set_iter_tags(struct radix_tree_iter *iter, } } -#ifdef CONFIG_RADIX_TREE_MULTIORDER -static void __rcu **skip_siblings(struct radix_tree_node **nodep, - void __rcu **slot, struct radix_tree_iter *iter) -{ - while (iter->index < iter->next_index) { - *nodep = rcu_dereference_raw(*slot); - if (*nodep && !xa_is_sibling(*nodep)) - return slot; - slot++; - iter->index = __radix_tree_iter_add(iter, 1); - iter->tags >>= 1; - } - - *nodep = NULL; - return NULL; -} - -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; - struct radix_tree_node *node; - - slot = skip_siblings(&node, slot, iter); - - while (radix_tree_is_internal_node(node)) { - unsigned offset; - unsigned long next_index; - - if (node == RADIX_TREE_RETRY) - return slot; - node = entry_to_node(node); - iter->node = node; - iter->shift = node->shift; - - if (flags & RADIX_TREE_ITER_TAGGED) { - offset = radix_tree_find_next_bit(node, tag, 0); - if (offset == RADIX_TREE_MAP_SIZE) - return NULL; - slot = &node->slots[offset]; - iter->index = __radix_tree_iter_add(iter, offset); - set_iter_tags(iter, node, offset, tag); - node = rcu_dereference_raw(*slot); - } else { - offset = 0; - slot = &node->slots[0]; - for (;;) { - node = rcu_dereference_raw(*slot); - if (node) - break; - slot++; - offset++; - if (offset == RADIX_TREE_MAP_SIZE) - return NULL; - } - iter->index = __radix_tree_iter_add(iter, offset); - } - if ((flags & RADIX_TREE_ITER_CONTIG) && (offset > 0)) - goto none; - next_index = (iter->index | shift_maxindex(iter->shift)) + 1; - if (next_index < iter->next_index) - iter->next_index = next_index; - } - - return slot; - none: - iter->next_index = 0; - return NULL; -} -EXPORT_SYMBOL(__radix_tree_next_slot); -#else -static void __rcu **skip_siblings(struct radix_tree_node **nodep, - void __rcu **slot, struct radix_tree_iter *iter) -{ - return slot; -} -#endif - void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - struct radix_tree_node *node; - slot++; iter->index = __radix_tree_iter_add(iter, 1); - skip_siblings(&node, slot, iter); iter->next_index = iter->index; iter->tags = 0; return NULL; @@ -1393,7 +1209,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; - __set_iter_shift(iter, 0); return (void __rcu **)&root->xa_head; } @@ -1414,8 +1229,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); - if (xa_is_sibling(slot)) - continue; if (slot) break; } @@ -1436,10 +1249,9 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ - iter->index = (index &~ node_maxindex(node)) | (offset << node->shift); + iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; - __set_iter_shift(iter, node->shift); if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); @@ -1750,7 +1562,6 @@ void __rcu **idr_get_free(struct radix_tree_root *root, else iter->next_index = 1; iter->node = node; - __set_iter_shift(iter, shift); set_iter_tags(iter, node, offset, IDR_FREE); return slot; diff --git a/mm/Kconfig b/mm/Kconfig index de64ea658716..02301a89089e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -379,7 +379,7 @@ config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE select COMPACTION - select RADIX_TREE_MULTIORDER + select XARRAY_MULTI help Transparent Hugepages allows the kernel to use huge pages and huge tlb transparently to the applications whenever possible. @@ -671,7 +671,7 @@ config ZONE_DEVICE depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP depends on ARCH_HAS_ZONE_DEVICE - select RADIX_TREE_MULTIORDER + select XARRAY_MULTI help Device memory hotplug support allows for establishing pmem, diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h index ca8e03ad19ac..2218b3cc184e 100644 --- a/tools/testing/radix-tree/generated/autoconf.h +++ b/tools/testing/radix-tree/generated/autoconf.h @@ -1,2 +1 @@ -#define CONFIG_RADIX_TREE_MULTIORDER 1 #define CONFIG_XARRAY_MULTI 1 -- cgit v1.2.3-71-gd317 From 94e6992bb560be8bffb47f287194adf070b57695 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 18:03:16 +0200 Subject: libceph: bump CEPH_MSG_MAX_DATA_LEN If the read is large enough, we end up spinning in the messenger: libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error libceph: osd0 192.168.122.1:6801 io error This is a receive side limit, so only reads were affected. Cc: stable@vger.kernel.org Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 49c93b9308d7..68bb09c29ce8 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -81,7 +81,13 @@ struct ceph_options { #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) -#define CEPH_MSG_MAX_DATA_LEN (16*1024*1024) + +/* + * Handle the largest possible rbd object in one message. + * There is no limit on the size of cephfs objects, but it has to obey + * rsize and wsize mount options anyway. + */ +#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024) #define CEPH_AUTH_NAME_DEFAULT "guest" -- cgit v1.2.3-71-gd317 From 24639ce56040a8ea890ad8836068c1ad8bd177c7 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 26 Sep 2018 19:12:07 +0200 Subject: libceph: osd_req_op_cls_init() doesn't need to take opcode Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 3 +-- include/linux/ceph/osd_client.h | 5 ++--- net/ceph/osd_client.c | 9 ++++----- 3 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f2fe692dda40..9cc7ee3b427f 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2374,8 +2374,7 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes) if (!obj_req->osd_req) return -ENOMEM; - ret = osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd", - "copyup"); + ret = osd_req_op_cls_init(obj_req->osd_req, 0, "rbd", "copyup"); if (ret) return ret; diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 02096da01845..f3e828460c91 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -444,9 +444,8 @@ extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); -extern int osd_req_op_cls_init(struct ceph_osd_request *osd_req, - unsigned int which, u16 opcode, - const char *class, const char *method); +int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, + const char *class, const char *method); extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, u16 opcode, const char *name, const void *value, size_t size, u8 cmp_op, u8 cmp_mode); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 60934bd8796c..a871b234cd90 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -767,15 +767,14 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req, EXPORT_SYMBOL(osd_req_op_extent_dup_last); int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, - u16 opcode, const char *class, const char *method) + const char *class, const char *method) { - struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which, - opcode, 0); + struct ceph_osd_req_op *op; struct ceph_pagelist *pagelist; size_t payload_len = 0; size_t size; - BUG_ON(opcode != CEPH_OSD_OP_CALL); + op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0); pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS); if (!pagelist) @@ -4962,7 +4961,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, if (ret) goto out_put_req; - ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method); + ret = osd_req_op_cls_init(req, 0, class, method); if (ret) goto out_put_req; -- cgit v1.2.3-71-gd317 From 33165d472310262d8c79c7e4d1a17dc60cea7e35 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 28 Sep 2018 15:38:34 +0200 Subject: libceph: introduce ceph_pagelist_alloc() struct ceph_pagelist cannot be embedded into anything else because it has its own refcount. Merge allocation and initialization together. Signed-off-by: Ilya Dryomov --- fs/ceph/acl.c | 3 +-- fs/ceph/mds_client.c | 3 +-- fs/ceph/xattr.c | 3 +-- include/linux/ceph/pagelist.h | 11 +---------- net/ceph/osd_client.c | 14 ++++---------- net/ceph/pagelist.c | 20 ++++++++++++++++++++ 6 files changed, 28 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 8a9b562ae4ca..5f0103f40079 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -206,10 +206,9 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL); if (!tmp_buf) goto out_err; - pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_KERNEL); + pagelist = ceph_pagelist_alloc(GFP_KERNEL); if (!pagelist) goto out_err; - ceph_pagelist_init(pagelist); err = ceph_pagelist_reserve(pagelist, PAGE_SIZE); if (err) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index bc43c822426a..580a79b9a91f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3126,10 +3126,9 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, pr_info("mds%d reconnect start\n", mds); - pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS); + pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) goto fail_nopagelist; - ceph_pagelist_init(pagelist); reply = ceph_msg_new(CEPH_MSG_CLIENT_RECONNECT, 0, GFP_NOFS, false); if (!reply) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 5cc8b94f8206..316f6ad10644 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -951,11 +951,10 @@ static int ceph_sync_setxattr(struct inode *inode, const char *name, if (size > 0) { /* copy value into pagelist */ - pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS); + pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; - ceph_pagelist_init(pagelist); err = ceph_pagelist_append(pagelist, value, size); if (err) goto out; diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h index d0223364349f..5dead8486fd8 100644 --- a/include/linux/ceph/pagelist.h +++ b/include/linux/ceph/pagelist.h @@ -23,16 +23,7 @@ struct ceph_pagelist_cursor { size_t room; /* room remaining to reset to */ }; -static inline void ceph_pagelist_init(struct ceph_pagelist *pl) -{ - INIT_LIST_HEAD(&pl->head); - pl->mapped_tail = NULL; - pl->length = 0; - pl->room = 0; - INIT_LIST_HEAD(&pl->free_list); - pl->num_pages_free = 0; - refcount_set(&pl->refcnt, 1); -} +struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags); extern void ceph_pagelist_release(struct ceph_pagelist *pl); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index a871b234cd90..db2ebc9e5f1f 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -776,12 +776,10 @@ int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which, op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0); - pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS); + pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; - ceph_pagelist_init(pagelist); - op->cls.class_name = class; size = strlen(class); BUG_ON(size > (size_t) U8_MAX); @@ -814,12 +812,10 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which, BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR); - pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS); + pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!pagelist) return -ENOMEM; - ceph_pagelist_init(pagelist); - payload_len = strlen(name); op->xattr.name_len = payload_len; ceph_pagelist_append(pagelist, name, payload_len); @@ -4598,11 +4594,10 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which, op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0); - pl = kmalloc(sizeof(*pl), GFP_NOIO); + pl = ceph_pagelist_alloc(GFP_NOIO); if (!pl) return -ENOMEM; - ceph_pagelist_init(pl); ret = ceph_pagelist_encode_64(pl, notify_id); ret |= ceph_pagelist_encode_64(pl, cookie); if (payload) { @@ -4669,11 +4664,10 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); op->notify.cookie = cookie; - pl = kmalloc(sizeof(*pl), GFP_NOIO); + pl = ceph_pagelist_alloc(GFP_NOIO); if (!pl) return -ENOMEM; - ceph_pagelist_init(pl); ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ ret |= ceph_pagelist_encode_32(pl, timeout); ret |= ceph_pagelist_encode_32(pl, payload_len); diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c index 2ea0564771d2..65e34f78b05d 100644 --- a/net/ceph/pagelist.c +++ b/net/ceph/pagelist.c @@ -6,6 +6,26 @@ #include #include +struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags) +{ + struct ceph_pagelist *pl; + + pl = kmalloc(sizeof(*pl), gfp_flags); + if (!pl) + return NULL; + + INIT_LIST_HEAD(&pl->head); + pl->mapped_tail = NULL; + pl->length = 0; + pl->room = 0; + INIT_LIST_HEAD(&pl->free_list); + pl->num_pages_free = 0; + refcount_set(&pl->refcnt, 1); + + return pl; +} +EXPORT_SYMBOL(ceph_pagelist_alloc); + static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl) { if (pl->mapped_tail) { -- cgit v1.2.3-71-gd317 From 0d9c1ab3be4c0187663096a6a084421d0a1e45c6 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 15 Oct 2018 17:38:23 +0200 Subject: libceph: preallocate message data items Currently message data items are allocated with ceph_msg_data_create() in setup_request_data() inside send_request(). send_request() has never been allowed to fail, so each allocation is followed by a BUG_ON: data = ceph_msg_data_create(...); BUG_ON(!data); It's been this way since support for multiple message data items was added in commit 6644ed7b7e04 ("libceph: make message data be a pointer") in 3.10. There is no reason to delay the allocation of message data items until the last possible moment and we certainly don't need a linked list of them as they are only ever appended to the end and never erased. Make ceph_msg_new2() take max_data_items and adapt the rest of the code. Reported-by: Jerry Lee Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 4 +- include/linux/ceph/messenger.h | 24 ++-------- include/linux/ceph/msgpool.h | 11 +++-- net/ceph/messenger.c | 106 +++++++++++++++-------------------------- net/ceph/msgpool.c | 25 ++++++---- net/ceph/osd_client.c | 102 +++++++++++++++++++++++++++++++++------ 6 files changed, 157 insertions(+), 115 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 97de674ea377..67a9aeb2f4ec 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2071,7 +2071,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, if (req->r_old_dentry_drop) len += req->r_old_dentry->d_name.len; - msg = ceph_msg_new(CEPH_MSG_CLIENT_REQUEST, len, GFP_NOFS, false); + msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false); if (!msg) { msg = ERR_PTR(-ENOMEM); goto out_free2; @@ -3129,7 +3129,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, if (!pagelist) goto fail_nopagelist; - reply = ceph_msg_new(CEPH_MSG_CLIENT_RECONNECT, 0, GFP_NOFS, false); + reply = ceph_msg_new2(CEPH_MSG_CLIENT_RECONNECT, 0, 1, GFP_NOFS, false); if (!reply) goto fail_nomsg; diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index fc2b4491ee0a..800a2128d411 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -82,22 +82,6 @@ enum ceph_msg_data_type { CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */ }; -static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) -{ - switch (type) { - case CEPH_MSG_DATA_NONE: - case CEPH_MSG_DATA_PAGES: - case CEPH_MSG_DATA_PAGELIST: -#ifdef CONFIG_BLOCK - case CEPH_MSG_DATA_BIO: -#endif /* CONFIG_BLOCK */ - case CEPH_MSG_DATA_BVECS: - return true; - default: - return false; - } -} - #ifdef CONFIG_BLOCK struct ceph_bio_iter { @@ -181,7 +165,6 @@ struct ceph_bvec_iter { } while (0) struct ceph_msg_data { - struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK @@ -202,7 +185,6 @@ struct ceph_msg_data { struct ceph_msg_data_cursor { size_t total_resid; /* across all data items */ - struct list_head *data_head; /* = &ceph_msg->data */ struct ceph_msg_data *data; /* current data item */ size_t resid; /* bytes not yet consumed */ @@ -240,7 +222,9 @@ struct ceph_msg { struct ceph_buffer *middle; size_t data_length; - struct list_head data; + struct ceph_msg_data *data; + int num_data_items; + int max_data_items; struct ceph_msg_data_cursor cursor; struct ceph_connection *con; @@ -381,6 +365,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, void ceph_msg_data_add_bvecs(struct ceph_msg *msg, struct ceph_bvec_iter *bvec_pos); +struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, + gfp_t flags, bool can_fail); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); diff --git a/include/linux/ceph/msgpool.h b/include/linux/ceph/msgpool.h index 76c98a512758..729cdf700eae 100644 --- a/include/linux/ceph/msgpool.h +++ b/include/linux/ceph/msgpool.h @@ -13,14 +13,15 @@ struct ceph_msgpool { mempool_t *pool; int type; /* preallocated message type */ int front_len; /* preallocated payload size */ + int max_data_items; }; -extern int ceph_msgpool_init(struct ceph_msgpool *pool, int type, - int front_len, int size, bool blocking, - const char *name); +int ceph_msgpool_init(struct ceph_msgpool *pool, int type, + int front_len, int max_data_items, int size, + const char *name); extern void ceph_msgpool_destroy(struct ceph_msgpool *pool); -extern struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *, - int front_len); +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items); extern void ceph_msgpool_put(struct ceph_msgpool *, struct ceph_msg *); #endif diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 76684edc43ef..88e35830198c 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -156,7 +156,6 @@ static bool con_flag_test_and_set(struct ceph_connection *con, /* Slab caches for frequently-allocated structures */ static struct kmem_cache *ceph_msg_cache; -static struct kmem_cache *ceph_msg_data_cache; /* static tag bytes (protocol control messages) */ static char tag_msg = CEPH_MSGR_TAG_MSG; @@ -235,23 +234,11 @@ static int ceph_msgr_slab_init(void) if (!ceph_msg_cache) return -ENOMEM; - BUG_ON(ceph_msg_data_cache); - ceph_msg_data_cache = KMEM_CACHE(ceph_msg_data, 0); - if (ceph_msg_data_cache) - return 0; - - kmem_cache_destroy(ceph_msg_cache); - ceph_msg_cache = NULL; - - return -ENOMEM; + return 0; } static void ceph_msgr_slab_exit(void) { - BUG_ON(!ceph_msg_data_cache); - kmem_cache_destroy(ceph_msg_data_cache); - ceph_msg_data_cache = NULL; - BUG_ON(!ceph_msg_cache); kmem_cache_destroy(ceph_msg_cache); ceph_msg_cache = NULL; @@ -1141,16 +1128,13 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor) static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length) { struct ceph_msg_data_cursor *cursor = &msg->cursor; - struct ceph_msg_data *data; BUG_ON(!length); BUG_ON(length > msg->data_length); - BUG_ON(list_empty(&msg->data)); + BUG_ON(!msg->num_data_items); - cursor->data_head = &msg->data; cursor->total_resid = length; - data = list_first_entry(&msg->data, struct ceph_msg_data, links); - cursor->data = data; + cursor->data = msg->data; __ceph_msg_data_cursor_init(cursor); } @@ -1231,8 +1215,7 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, if (!cursor->resid && cursor->total_resid) { WARN_ON(!cursor->last_piece); - BUG_ON(list_is_last(&cursor->data->links, cursor->data_head)); - cursor->data = list_next_entry(cursor->data, links); + cursor->data++; __ceph_msg_data_cursor_init(cursor); new_piece = true; } @@ -1248,9 +1231,6 @@ static size_t sizeof_footer(struct ceph_connection *con) static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { - BUG_ON(!msg); - BUG_ON(!data_len); - /* Initialize data cursor */ ceph_msg_data_cursor_init(msg, (size_t)data_len); @@ -1590,7 +1570,7 @@ static int write_partial_message_data(struct ceph_connection *con) dout("%s %p msg %p\n", __func__, con, msg); - if (list_empty(&msg->data)) + if (!msg->num_data_items) return -EINVAL; /* @@ -2347,8 +2327,7 @@ static int read_partial_msg_data(struct ceph_connection *con) u32 crc = 0; int ret; - BUG_ON(!msg); - if (list_empty(&msg->data)) + if (!msg->num_data_items) return -EIO; if (do_datacrc) @@ -3256,32 +3235,16 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con, return false; } -static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type) +static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg) { - struct ceph_msg_data *data; - - if (WARN_ON(!ceph_msg_data_type_valid(type))) - return NULL; - - data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS); - if (!data) - return NULL; - - data->type = type; - INIT_LIST_HEAD(&data->links); - - return data; + BUG_ON(msg->num_data_items >= msg->max_data_items); + return &msg->data[msg->num_data_items++]; } static void ceph_msg_data_destroy(struct ceph_msg_data *data) { - if (!data) - return; - - WARN_ON(!list_empty(&data->links)); if (data->type == CEPH_MSG_DATA_PAGELIST) ceph_pagelist_release(data->pagelist); - kmem_cache_free(ceph_msg_data_cache, data); } void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, @@ -3292,13 +3255,12 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, BUG_ON(!pages); BUG_ON(!length); - data = ceph_msg_data_create(CEPH_MSG_DATA_PAGES); - BUG_ON(!data); + data = ceph_msg_data_add(msg); + data->type = CEPH_MSG_DATA_PAGES; data->pages = pages; data->length = length; data->alignment = alignment & ~PAGE_MASK; - list_add_tail(&data->links, &msg->data); msg->data_length += length; } EXPORT_SYMBOL(ceph_msg_data_add_pages); @@ -3311,12 +3273,11 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg, BUG_ON(!pagelist); BUG_ON(!pagelist->length); - data = ceph_msg_data_create(CEPH_MSG_DATA_PAGELIST); - BUG_ON(!data); + data = ceph_msg_data_add(msg); + data->type = CEPH_MSG_DATA_PAGELIST; refcount_inc(&pagelist->refcnt); data->pagelist = pagelist; - list_add_tail(&data->links, &msg->data); msg->data_length += pagelist->length; } EXPORT_SYMBOL(ceph_msg_data_add_pagelist); @@ -3327,12 +3288,11 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, { struct ceph_msg_data *data; - data = ceph_msg_data_create(CEPH_MSG_DATA_BIO); - BUG_ON(!data); + data = ceph_msg_data_add(msg); + data->type = CEPH_MSG_DATA_BIO; data->bio_pos = *bio_pos; data->bio_length = length; - list_add_tail(&data->links, &msg->data); msg->data_length += length; } EXPORT_SYMBOL(ceph_msg_data_add_bio); @@ -3343,11 +3303,10 @@ void ceph_msg_data_add_bvecs(struct ceph_msg *msg, { struct ceph_msg_data *data; - data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS); - BUG_ON(!data); + data = ceph_msg_data_add(msg); + data->type = CEPH_MSG_DATA_BVECS; data->bvec_pos = *bvec_pos; - list_add_tail(&data->links, &msg->data); msg->data_length += bvec_pos->iter.bi_size; } EXPORT_SYMBOL(ceph_msg_data_add_bvecs); @@ -3356,8 +3315,8 @@ EXPORT_SYMBOL(ceph_msg_data_add_bvecs); * construct a new message with given type, size * the new msg has a ref count of 1. */ -struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, - bool can_fail) +struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, + gfp_t flags, bool can_fail) { struct ceph_msg *m; @@ -3371,7 +3330,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, INIT_LIST_HEAD(&m->list_head); kref_init(&m->kref); - INIT_LIST_HEAD(&m->data); /* front */ if (front_len) { @@ -3386,6 +3344,15 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, } m->front_alloc_len = m->front.iov_len = front_len; + if (max_data_items) { + m->data = kmalloc_array(max_data_items, sizeof(*m->data), + flags); + if (!m->data) + goto out2; + + m->max_data_items = max_data_items; + } + dout("ceph_msg_new %p front %d\n", m, front_len); return m; @@ -3402,6 +3369,13 @@ out: } return NULL; } +EXPORT_SYMBOL(ceph_msg_new2); + +struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, + bool can_fail) +{ + return ceph_msg_new2(type, front_len, 0, flags, can_fail); +} EXPORT_SYMBOL(ceph_msg_new); /* @@ -3497,13 +3471,14 @@ static void ceph_msg_free(struct ceph_msg *m) { dout("%s %p\n", __func__, m); kvfree(m->front.iov_base); + kfree(m->data); kmem_cache_free(ceph_msg_cache, m); } static void ceph_msg_release(struct kref *kref) { struct ceph_msg *m = container_of(kref, struct ceph_msg, kref); - struct ceph_msg_data *data, *next; + int i; dout("%s %p\n", __func__, m); WARN_ON(!list_empty(&m->list_head)); @@ -3516,11 +3491,8 @@ static void ceph_msg_release(struct kref *kref) m->middle = NULL; } - list_for_each_entry_safe(data, next, &m->data, links) { - list_del_init(&data->links); - ceph_msg_data_destroy(data); - } - m->data_length = 0; + for (i = 0; i < m->num_data_items; i++) + ceph_msg_data_destroy(&m->data[i]); if (m->pool) ceph_msgpool_put(m->pool, m); diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c index 3dddc074f0d7..e3ecb80cd182 100644 --- a/net/ceph/msgpool.c +++ b/net/ceph/msgpool.c @@ -14,7 +14,8 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg) struct ceph_msgpool *pool = arg; struct ceph_msg *msg; - msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true); + msg = ceph_msg_new2(pool->type, pool->front_len, pool->max_data_items, + gfp_mask, true); if (!msg) { dout("msgpool_alloc %s failed\n", pool->name); } else { @@ -35,11 +36,13 @@ static void msgpool_free(void *element, void *arg) } int ceph_msgpool_init(struct ceph_msgpool *pool, int type, - int front_len, int size, bool blocking, const char *name) + int front_len, int max_data_items, int size, + const char *name) { dout("msgpool %s init\n", name); pool->type = type; pool->front_len = front_len; + pool->max_data_items = max_data_items; pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool); if (!pool->pool) return -ENOMEM; @@ -53,18 +56,21 @@ void ceph_msgpool_destroy(struct ceph_msgpool *pool) mempool_destroy(pool->pool); } -struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, - int front_len) +struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len, + int max_data_items) { struct ceph_msg *msg; - if (front_len > pool->front_len) { - dout("msgpool_get %s need front %d, pool size is %d\n", - pool->name, front_len, pool->front_len); + if (front_len > pool->front_len || + max_data_items > pool->max_data_items) { + pr_warn_ratelimited("%s need %d/%d, pool %s has %d/%d\n", + __func__, front_len, max_data_items, pool->name, + pool->front_len, pool->max_data_items); WARN_ON_ONCE(1); /* try to alloc a fresh message */ - return ceph_msg_new(pool->type, front_len, GFP_NOFS, false); + return ceph_msg_new2(pool->type, front_len, max_data_items, + GFP_NOFS, false); } msg = mempool_alloc(pool->pool, GFP_NOFS); @@ -80,6 +86,9 @@ void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg) msg->front.iov_len = pool->front_len; msg->hdr.front_len = cpu_to_le32(pool->front_len); + msg->data_length = 0; + msg->num_data_items = 0; + kref_init(&msg->kref); /* retake single ref */ mempool_free(msg, pool->pool); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 7ac7f21ff317..cf0bd2cce848 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -614,12 +614,15 @@ static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc) return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0); } -int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) +static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp, + int num_request_data_items, + int num_reply_data_items) { struct ceph_osd_client *osdc = req->r_osdc; struct ceph_msg *msg; int msg_size; + WARN_ON(req->r_request || req->r_reply); WARN_ON(ceph_oid_empty(&req->r_base_oid)); WARN_ON(ceph_oloc_empty(&req->r_base_oloc)); @@ -641,9 +644,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) msg_size += 4 + 8; /* retry_attempt, features */ if (req->r_mempool) - msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size); + msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size, + num_request_data_items); else - msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true); + msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size, + num_request_data_items, gfp, true); if (!msg) return -ENOMEM; @@ -656,9 +661,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) msg_size += req->r_num_ops * sizeof(struct ceph_osd_op); if (req->r_mempool) - msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size); + msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size, + num_reply_data_items); else - msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true); + msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size, + num_reply_data_items, gfp, true); if (!msg) return -ENOMEM; @@ -666,7 +673,6 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) return 0; } -EXPORT_SYMBOL(ceph_osdc_alloc_messages); static bool osd_req_opcode_valid(u16 opcode) { @@ -679,6 +685,64 @@ __CEPH_FORALL_OSD_OPS(GENERATE_CASE) } } +static void get_num_data_items(struct ceph_osd_request *req, + int *num_request_data_items, + int *num_reply_data_items) +{ + struct ceph_osd_req_op *op; + + *num_request_data_items = 0; + *num_reply_data_items = 0; + + for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) { + switch (op->op) { + /* request */ + case CEPH_OSD_OP_WRITE: + case CEPH_OSD_OP_WRITEFULL: + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_CMPXATTR: + case CEPH_OSD_OP_NOTIFY_ACK: + *num_request_data_items += 1; + break; + + /* reply */ + case CEPH_OSD_OP_STAT: + case CEPH_OSD_OP_READ: + case CEPH_OSD_OP_LIST_WATCHERS: + *num_reply_data_items += 1; + break; + + /* both */ + case CEPH_OSD_OP_NOTIFY: + *num_request_data_items += 1; + *num_reply_data_items += 1; + break; + case CEPH_OSD_OP_CALL: + *num_request_data_items += 2; + *num_reply_data_items += 1; + break; + + default: + WARN_ON(!osd_req_opcode_valid(op->op)); + break; + } + } +} + +/* + * oid, oloc and OSD op opcode(s) must be filled in before this function + * is called. + */ +int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp) +{ + int num_request_data_items, num_reply_data_items; + + get_num_data_items(req, &num_request_data_items, &num_reply_data_items); + return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items, + num_reply_data_items); +} +EXPORT_SYMBOL(ceph_osdc_alloc_messages); + /* * This is an osd op init function for opcodes that have no data or * other information associated with them. It also serves as a @@ -1035,7 +1099,15 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, if (flags & CEPH_OSD_FLAG_WRITE) req->r_data_offset = off; - r = ceph_osdc_alloc_messages(req, GFP_NOFS); + if (num_ops > 1) + /* + * This is a special case for ceph_writepages_start(), but it + * also covers ceph_uninline_data(). If more multi-op request + * use cases emerge, we will need a separate helper. + */ + r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0); + else + r = ceph_osdc_alloc_messages(req, GFP_NOFS); if (r) goto fail; @@ -1842,13 +1914,16 @@ static bool should_plug_request(struct ceph_osd_request *req) return true; } +/* + * Keep get_num_data_items() in sync with this function. + */ static void setup_request_data(struct ceph_osd_request *req, struct ceph_msg *msg) { u32 data_len = 0; int i; - if (!list_empty(&msg->data)) + if (msg->num_data_items) return; WARN_ON(msg->data_length); @@ -4325,9 +4400,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc, lreq->notify_id, notify_id); } else if (!completion_done(&lreq->notify_finish_wait)) { struct ceph_msg_data *data = - list_first_entry_or_null(&msg->data, - struct ceph_msg_data, - links); + msg->num_data_items ? &msg->data[0] : NULL; if (data) { if (lreq->preply_pages) { @@ -5036,11 +5109,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client) goto out_map; err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP, - PAGE_SIZE, 10, true, "osd_op"); + PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op"); if (err < 0) goto out_mempool; err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY, - PAGE_SIZE, 10, true, "osd_op_reply"); + PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, + "osd_op_reply"); if (err < 0) goto out_msgpool; @@ -5310,7 +5384,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) u32 front_len = le32_to_cpu(hdr->front_len); u32 data_len = le32_to_cpu(hdr->data_len); - m = ceph_msg_new(type, front_len, GFP_NOIO, false); + m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false); if (!m) return NULL; -- cgit v1.2.3-71-gd317 From 23ddf9bea900b4ce39e5707e1ddf66062cfe6d91 Mon Sep 17 00:00:00 2001 From: Luis Henriques Date: Mon, 15 Oct 2018 16:45:58 +0100 Subject: libceph: support the RADOS copy-from operation Add support for performing remote object copies using the 'copy-from' operation. [ Add COPY_FROM to get_num_data_items(). ] Signed-off-by: Luis Henriques Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 17 ++++++++ include/linux/ceph/rados.h | 28 +++++++++++++ net/ceph/osd_client.c | 90 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index f3e828460c91..7a2af5034278 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -136,6 +136,13 @@ struct ceph_osd_req_op { u64 expected_object_size; u64 expected_write_size; } alloc_hint; + struct { + u64 snapid; + u64 src_version; + u8 flags; + u32 src_fadvise_flags; + struct ceph_osd_data osd_data; + } copy_from; }; }; @@ -510,6 +517,16 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct timespec64 *mtime, struct page **pages, int nr_pages); +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 dst_fadvise_flags, + u8 copy_from_flags); + /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index f1988387c5ad..3eb0e55665b4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -410,6 +410,14 @@ enum { enum { CEPH_OSD_OP_FLAG_EXCL = 1, /* EXCL object create */ CEPH_OSD_OP_FLAG_FAILOK = 2, /* continue despite failure */ + CEPH_OSD_OP_FLAG_FADVISE_RANDOM = 0x4, /* the op is random */ + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL = 0x8, /* the op is sequential */ + CEPH_OSD_OP_FLAG_FADVISE_WILLNEED = 0x10,/* data will be accessed in + the near future */ + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED = 0x20,/* data will not be accessed + in the near future */ + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE = 0x40,/* data will be accessed only + once by this client */ }; #define EOLDSNAPC ERESTART /* ORDERSNAP flag set; writer has old snapc*/ @@ -431,6 +439,15 @@ enum { CEPH_OSD_CMPXATTR_MODE_U64 = 2 }; +enum { + CEPH_OSD_COPY_FROM_FLAG_FLUSH = 1, /* part of a flush operation */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_OVERLAY = 2, /* ignore pool overlay */ + CEPH_OSD_COPY_FROM_FLAG_IGNORE_CACHE = 4, /* ignore osd cache logic */ + CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to + * cloneid */ + CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */ +}; + enum { CEPH_OSD_WATCH_OP_UNWATCH = 0, CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1, @@ -497,6 +514,17 @@ struct ceph_osd_op { __le64 expected_object_size; __le64 expected_write_size; } __attribute__ ((packed)) alloc_hint; + struct { + __le64 snapid; + __le64 src_version; + __u8 flags; /* CEPH_OSD_COPY_FROM_FLAG_* */ + /* + * CEPH_OSD_OP_FLAG_FADVISE_*: fadvise flags + * for src object, flags for dest object are in + * ceph_osd_op::flags. + */ + __le32 src_fadvise_flags; + } __attribute__ ((packed)) copy_from; }; __le32 payload_len; } __attribute__ ((packed)); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index a0148de51cc6..d23a9f81f3d7 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -410,6 +410,9 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req, case CEPH_OSD_OP_LIST_WATCHERS: ceph_osd_data_release(&op->list_watchers.response_data); break; + case CEPH_OSD_OP_COPY_FROM: + ceph_osd_data_release(&op->copy_from.osd_data); + break; default: break; } @@ -702,6 +705,7 @@ static void get_num_data_items(struct ceph_osd_request *req, case CEPH_OSD_OP_SETXATTR: case CEPH_OSD_OP_CMPXATTR: case CEPH_OSD_OP_NOTIFY_ACK: + case CEPH_OSD_OP_COPY_FROM: *num_request_data_items += 1; break; @@ -1016,6 +1020,14 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst, case CEPH_OSD_OP_CREATE: case CEPH_OSD_OP_DELETE: break; + case CEPH_OSD_OP_COPY_FROM: + dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid); + dst->copy_from.src_version = + cpu_to_le64(src->copy_from.src_version); + dst->copy_from.flags = src->copy_from.flags; + dst->copy_from.src_fadvise_flags = + cpu_to_le32(src->copy_from.src_fadvise_flags); + break; default: pr_err("unsupported osd opcode %s\n", ceph_osd_op_name(src->op)); @@ -1947,6 +1959,10 @@ static void setup_request_data(struct ceph_osd_request *req) ceph_osdc_msg_data_add(request_msg, &op->notify_ack.request_data); break; + case CEPH_OSD_OP_COPY_FROM: + ceph_osdc_msg_data_add(request_msg, + &op->copy_from.osd_data); + break; /* reply */ case CEPH_OSD_OP_STAT: @@ -5255,6 +5271,80 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, } EXPORT_SYMBOL(ceph_osdc_writepages); +static int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u8 copy_from_flags) +{ + struct ceph_osd_req_op *op; + struct page **pages; + void *p, *end; + + pages = ceph_alloc_page_vector(1, GFP_KERNEL); + if (IS_ERR(pages)) + return PTR_ERR(pages); + + op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags); + op->copy_from.snapid = src_snapid; + op->copy_from.src_version = src_version; + op->copy_from.flags = copy_from_flags; + op->copy_from.src_fadvise_flags = src_fadvise_flags; + + p = page_address(pages[0]); + end = p + PAGE_SIZE; + ceph_encode_string(&p, end, src_oid->name, src_oid->name_len); + encode_oloc(&p, end, src_oloc); + op->indata_len = PAGE_SIZE - (end - p); + + ceph_osd_data_pages_init(&op->copy_from.osd_data, pages, + op->indata_len, 0, false, true); + return 0; +} + +int ceph_osdc_copy_from(struct ceph_osd_client *osdc, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 dst_fadvise_flags, + u8 copy_from_flags) +{ + struct ceph_osd_request *req; + int ret; + + req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->r_flags = CEPH_OSD_FLAG_WRITE; + + ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); + ceph_oid_copy(&req->r_t.base_oid, dst_oid); + + ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid, + src_oloc, src_fadvise_flags, + dst_fadvise_flags, copy_from_flags); + if (ret) + goto out; + + ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); + if (ret) + goto out; + + ceph_osdc_start_request(osdc, req, false); + ret = ceph_osdc_wait_request(osdc, req); + +out: + ceph_osdc_put_request(req); + return ret; +} +EXPORT_SYMBOL(ceph_osdc_copy_from); + int __init ceph_osdc_setup(void) { size_t size = sizeof(struct ceph_osd_request) + -- cgit v1.2.3-71-gd317 From 00e23707442a75b404392cef1405ab4fd498de6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 22 Oct 2018 13:07:28 +0100 Subject: iov_iter: Use accessor function Use accessor functions to access an iterator's type and direction. This allows for the possibility of using some other method of determining the type of iterator than if-chains with bitwise-AND conditions. Signed-off-by: David Howells --- block/bio.c | 2 +- fs/block_dev.c | 2 +- fs/ceph/file.c | 2 +- fs/cifs/file.c | 4 ++-- fs/cifs/misc.c | 2 +- fs/cifs/smbdirect.c | 17 ++++++++++++---- fs/direct-io.c | 2 +- fs/fuse/file.c | 2 +- fs/iomap.c | 2 +- include/linux/uio.h | 48 +++++++++++++++++++++++++++++-------------- lib/iov_iter.c | 56 +++++++++++++++++++++++++-------------------------- mm/filemap.c | 2 +- net/9p/trans_virtio.c | 2 +- net/tls/tls_sw.c | 4 ++-- 14 files changed, 87 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 0093bed81c0e..c55f36bbe12a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1255,7 +1255,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, /* * success */ - if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) || + if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) || (map_data && map_data->from_user)) { ret = bio_copy_from_iter(bio, iter); if (ret) diff --git a/fs/block_dev.c b/fs/block_dev.c index 38b8ce05cbc7..a80b4f0ee7c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -349,7 +349,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) dio->size = 0; dio->multi_bio = false; - dio->should_dirty = is_read && (iter->type == ITER_IOVEC); + dio->should_dirty = is_read && iter_is_iovec(iter); blk_start_plug(&plug); for (;;) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 92ab20433682..524ecc95b04d 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -658,7 +658,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, if (ret < 0) return ret; - if (unlikely(to->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(to))) { size_t page_off; ret = iov_iter_get_pages_alloc(to, &pages, len, &page_off); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8d41ca7bfcf1..dcdbcb6f09f8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2990,7 +2990,7 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter) size_t copy = min_t(size_t, remaining, PAGE_SIZE); size_t written; - if (unlikely(iter->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(iter))) { void *addr = kmap_atomic(page); written = copy_to_iter(addr, copy, iter); @@ -3302,7 +3302,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) if (!is_sync_kiocb(iocb)) ctx->iocb = iocb; - if (to->type == ITER_IOVEC) + if (iter_is_iovec(to)) ctx->should_dirty = true; rc = setup_aio_ctx_iter(ctx, to, READ); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 6926685e513c..7b5b960a04b8 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -786,7 +786,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) struct page **pages = NULL; struct bio_vec *bv = NULL; - if (iter->type & ITER_KVEC) { + if (iov_iter_is_kvec(iter)) { memcpy(&ctx->iter, iter, sizeof(struct iov_iter)); ctx->len = count; iov_iter_advance(iter, count); diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 5fdb9a509a97..5b05bf255268 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2054,14 +2054,22 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) info->smbd_recv_pending++; - switch (msg->msg_iter.type) { - case READ | ITER_KVEC: + if (iov_iter_rw(&msg->msg_iter) == WRITE) { + /* It's a bug in upper layer to get there */ + cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n", + iov_iter_rw(&msg->msg_iter)); + rc = -EINVAL; + goto out; + } + + switch (iov_iter_type(&msg->msg_iter)) { + case ITER_KVEC: buf = msg->msg_iter.kvec->iov_base; to_read = msg->msg_iter.kvec->iov_len; rc = smbd_recv_buf(info, buf, to_read); break; - case READ | ITER_BVEC: + case ITER_BVEC: page = msg->msg_iter.bvec->bv_page; page_offset = msg->msg_iter.bvec->bv_offset; to_read = msg->msg_iter.bvec->bv_len; @@ -2071,10 +2079,11 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) default: /* It's a bug in upper layer to get there */ cifs_dbg(VFS, "CIFS: invalid msg type %d\n", - msg->msg_iter.type); + iov_iter_type(&msg->msg_iter)); rc = -EINVAL; } +out: info->smbd_recv_pending--; wake_up(&info->wait_smbd_recv_pending); diff --git a/fs/direct-io.c b/fs/direct-io.c index 093fb54cd316..722d17c88edb 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1313,7 +1313,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; - dio->should_dirty = (iter->type == ITER_IOVEC); + dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 32d0b883e74f..c9ccd45156dc 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1271,7 +1271,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, ssize_t ret = 0; /* Special case for kernel I/O: can copy directly into the buffer */ - if (ii->type & ITER_KVEC) { + if (iov_iter_is_kvec(ii)) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); diff --git a/fs/iomap.c b/fs/iomap.c index ec15cf2ec696..2c53400aa802 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1795,7 +1795,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (pos >= dio->i_size) goto out_free_dio; - if (iter->type == ITER_IOVEC) + if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ) dio->flags |= IOMAP_DIO_DIRTY; } else { flags |= IOMAP_WRITE; diff --git a/include/linux/uio.h b/include/linux/uio.h index 422b1c01ee0d..fcabc959c794 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,7 +21,7 @@ struct kvec { size_t iov_len; }; -enum { +enum iter_type { ITER_IOVEC = 0, ITER_KVEC = 2, ITER_BVEC = 4, @@ -47,6 +47,36 @@ struct iov_iter { }; }; +static inline enum iter_type iov_iter_type(const struct iov_iter *i) +{ + return i->type & ~(READ | WRITE); +} + +static inline bool iter_is_iovec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_IOVEC; +} + +static inline bool iov_iter_is_kvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_KVEC; +} + +static inline bool iov_iter_is_bvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_BVEC; +} + +static inline bool iov_iter_is_pipe(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_PIPE; +} + +static inline unsigned char iov_iter_rw(const struct iov_iter *i) +{ + return i->type & (READ | WRITE); +} + /* * Total number of bytes covered by an iovec. * @@ -74,7 +104,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) } #define iov_for_each(iov, iter, start) \ - if (!((start).type & (ITER_BVEC | ITER_PIPE))) \ + if (iov_iter_type(start) == ITER_IOVEC || \ + iov_iter_type(start) == ITER_KVEC) \ for (iter = (start); \ (iter).count && \ ((iov = iov_iter_iovec(&(iter))), 1); \ @@ -202,19 +233,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i) return i->count; } -static inline bool iter_is_iovec(const struct iov_iter *i) -{ - return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE)); -} - -/* - * Get one of READ or WRITE out of iter->type without any other flags OR'd in - * with it. - * - * The ?: is just for type safety. - */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) - /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 8be175df3075..42d39116a556 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -558,7 +558,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -658,7 +658,7 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -692,7 +692,7 @@ EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -712,7 +712,7 @@ EXPORT_SYMBOL(_copy_from_iter); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -739,7 +739,7 @@ EXPORT_SYMBOL(_copy_from_iter_full); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -773,7 +773,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache); size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -794,7 +794,7 @@ EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -836,7 +836,7 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; - } else if (likely(!(i->type & ITER_PIPE))) + } else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); @@ -848,7 +848,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -888,7 +888,7 @@ static size_t pipe_zero(size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), @@ -908,7 +908,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, kunmap_atomic(kaddr); return 0; } - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; @@ -972,7 +972,7 @@ static void pipe_advance(struct iov_iter *i, size_t size) void iov_iter_advance(struct iov_iter *i, size_t size) { - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { pipe_advance(i, size); return; } @@ -987,7 +987,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; int idx = i->idx; size_t off = i->iov_offset; @@ -1016,7 +1016,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) return; } unroll -= i->iov_offset; - if (i->type & ITER_BVEC) { + if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; @@ -1049,11 +1049,11 @@ EXPORT_SYMBOL(iov_iter_revert); */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; - else if (i->type & ITER_BVEC) + else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); @@ -1106,7 +1106,7 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx])) return size | i->iov_offset; return size; @@ -1125,7 +1125,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return ~0U; } @@ -1193,7 +1193,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; @@ -1205,7 +1205,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, len = maxpages * PAGE_SIZE; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages); if (unlikely(res < 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; @@ -1270,7 +1270,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; @@ -1283,7 +1283,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, p = get_pages_array(n); if (!p) return -ENOMEM; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p); if (unlikely(res < 0)) { kvfree(p); return res; @@ -1313,7 +1313,7 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -1355,7 +1355,7 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -1400,7 +1400,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); /* for now */ return 0; } @@ -1443,7 +1443,7 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) if (!size) return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; size_t off; int idx; @@ -1481,11 +1481,11 @@ EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; - if (unlikely(new->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } - if (new->type & ITER_BVEC) + if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..bdeee0168ea7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2122,7 +2122,7 @@ find_page: !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ - if (unlikely(iter->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 7728b0acde09..4d7d2070e9c8 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -322,7 +322,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, if (!iov_iter_count(data)) return 0; - if (!(data->type & ITER_KVEC)) { + if (iov_iter_is_kvec(data)) { int n; /* * We allow only p9_max_pages pinned. We wait for the diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index a525fc4c2a4b..ad64b9c8b600 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; unsigned char record_type = TLS_RECORD_TYPE_DATA; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); size_t try_to_copy, copied = 0; struct sk_msg *msg_pl, *msg_en; @@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk, bool cmsg = false; int target, err = 0; long timeo; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); int num_async = 0; flags |= nonblock; -- cgit v1.2.3-71-gd317 From aa563d7bca6e882ec2bdae24603c8f016401a144 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Separate type from direction and use accessor functions In the iov_iter struct, separate the iterator type from the iterator direction and use accessor functions to access them in most places. Convert a bunch of places to use switch-statements to access them rather then chains of bitwise-AND statements. This makes it easier to add further iterator types. Also, this can be more efficient as to implement a switch of small contiguous integers, the compiler can use ~50% fewer compare instructions than it has to use bitwise-and instructions. Further, cease passing the iterator type into the iterator setup function. The iterator function can set that itself. Only the direction is required. Signed-off-by: David Howells --- drivers/block/drbd/drbd_main.c | 2 +- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/loop.c | 9 ++++----- drivers/block/nbd.c | 12 +++++------- drivers/fsi/fsi-sbefifo.c | 4 ++-- drivers/isdn/mISDN/l1oip_core.c | 3 +-- drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 +++--- drivers/nvme/target/io-cmd-file.c | 2 +- drivers/target/iscsi/iscsi_target_util.c | 6 ++---- drivers/target/target_core_file.c | 6 +++--- drivers/usb/usbip/usbip_common.c | 2 +- drivers/xen/pvcalls-back.c | 8 ++++---- fs/9p/vfs_addr.c | 4 ++-- fs/9p/vfs_dir.c | 2 +- fs/9p/xattr.c | 4 ++-- fs/afs/rxrpc.c | 15 +++++++-------- fs/ceph/file.c | 5 ++--- fs/cifs/connect.c | 4 ++-- fs/cifs/misc.c | 2 +- fs/cifs/smb2ops.c | 4 ++-- fs/cifs/transport.c | 8 +++----- fs/dlm/lowcomms.c | 2 +- fs/nfsd/vfs.c | 4 ++-- fs/ocfs2/cluster/tcp.c | 2 +- fs/orangefs/inode.c | 2 +- fs/splice.c | 7 +++---- include/linux/uio.h | 10 +++++----- lib/iov_iter.c | 28 +++++++++++++++------------- mm/page_io.c | 2 +- net/9p/client.c | 2 +- net/bluetooth/6lowpan.c | 2 +- net/bluetooth/a2mp.c | 2 +- net/bluetooth/smp.c | 2 +- net/ceph/messenger.c | 6 +++--- net/netfilter/ipvs/ip_vs_sync.c | 2 +- net/smc/smc_clc.c | 4 ++-- net/socket.c | 6 +++--- net/sunrpc/svcsock.c | 2 +- net/tipc/topsrv.c | 2 +- net/tls/tls_device.c | 4 ++-- 40 files changed, 96 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index ef8212a4b73e..ded9735d44af 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1856,7 +1856,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, /* THINK if (signal_pending) return ... ? */ - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size); if (sock == connection->data.socket) { rcu_read_lock(); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 75f6b47169e6..fcc70642b004 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -516,7 +516,7 @@ static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flag struct msghdr msg = { .msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL) }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); return sock_recvmsg(sock, &msg, msg.msg_flags); } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ea9debf59b22..cb0cc8685076 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -268,7 +268,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -346,7 +346,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, ssize_t len; rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len); + iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; @@ -387,7 +387,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, b.bv_offset = 0; b.bv_len = bvec.bv_len; - iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len); + iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; @@ -554,8 +554,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, ITER_BVEC | rw, bvec, - segments, blk_rq_bytes(rq)); + iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 14a51254c3db..4d4d6129ff66 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -473,7 +473,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); switch (req_op(req)) { case REQ_OP_DISCARD: @@ -564,8 +564,7 @@ send_pages: dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", req, bvec.bv_len); - iov_iter_bvec(&from, ITER_BVEC | WRITE, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&from, WRITE, &bvec, 1, bvec.bv_len); if (skip) { if (skip >= iov_iter_count(&from)) { skip -= iov_iter_count(&from); @@ -624,7 +623,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) int ret = 0; reply.magic = 0; - iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); + iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply)); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { if (!nbd_disconnected(config)) @@ -678,8 +677,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { - iov_iter_bvec(&to, ITER_BVEC | READ, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", @@ -1073,7 +1071,7 @@ static void send_disconnects(struct nbd_device *nbd) for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret <= 0) diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c index ae861342626e..d92f5b87c251 100644 --- a/drivers/fsi/fsi-sbefifo.c +++ b/drivers/fsi/fsi-sbefifo.c @@ -638,7 +638,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo) } ffdc_iov.iov_base = ffdc; ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE; - iov_iter_kvec(&ffdc_iter, WRITE | ITER_KVEC, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); + iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); cmd[0] = cpu_to_be32(2); cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC); rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter); @@ -735,7 +735,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, rbytes = (*resp_len) * sizeof(__be32); resp_iov.iov_base = response; resp_iov.iov_len = rbytes; - iov_iter_kvec(&resp_iter, WRITE | ITER_KVEC, &resp_iov, 1, rbytes); + iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes); /* Perform the command */ mutex_lock(&sbefifo->lock); diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index b05022f94f18..072bb5e36c18 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -718,8 +718,7 @@ l1oip_socket_thread(void *data) printk(KERN_DEBUG "%s: socket created and open\n", __func__); while (!signal_pending(current)) { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, - recvbuf_size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, recvbuf_size); recvlen = sock_recvmsg(socket, &msg, 0); if (recvlen > 0) { l1oip_socket_parse(hc, &sin_rx, recvbuf, recvlen); diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index bd52f29b4a4e..264f4ed8eef2 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -3030,7 +3030,7 @@ ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&from, WRITE, &v, 1, buf_size); qp_lock(qpair); @@ -3074,7 +3074,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); @@ -3119,7 +3119,7 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 81a9dc5290a8..97f282eca3c2 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -101,7 +101,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, rw = READ; } - iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count); + iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count); iocb->ki_pos = pos; iocb->ki_filp = req->ns->file; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 49be1e41290c..991482576417 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1258,8 +1258,7 @@ static int iscsit_do_rx_data( return -1; memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, - count->iov, count->iov_count, data); + iov_iter_kvec(&msg.msg_iter, READ, count->iov, count->iov_count, data); while (msg_data_left(&msg)) { rx_loop = sock_recvmsg(conn->sock, &msg, MSG_WAITALL); @@ -1315,8 +1314,7 @@ int tx_data( memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, - iov, iov_count, data); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, iov_count, data); while (msg_data_left(&msg)) { int tx_loop = sock_sendmsg(conn->sock, &msg); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 16751ae55d7b..49b110d1b972 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -303,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC | is_write, bvec, sgl_nents, len); + iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); aio_cmd->cmd = cmd; aio_cmd->len = len; @@ -353,7 +353,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, sgl_nents, len); + iov_iter_bvec(&iter, READ, bvec, sgl_nents, len); if (is_write) ret = vfs_iter_write(fd, &iter, &pos, 0); else @@ -490,7 +490,7 @@ fd_execute_write_same(struct se_cmd *cmd) len += se_dev->dev_attrib.block_size; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, nolb, len); + iov_iter_bvec(&iter, READ, bvec, nolb, len); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); kfree(bvec); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 9756752c0681..45da3e01c7b0 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -309,7 +309,7 @@ int usbip_recv(struct socket *sock, void *buf, int size) if (!sock || !buf || !size) return -EINVAL; - iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); usbip_dbg_xmit("enter\n"); diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index b1092fbefa63..2e5d845b5091 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -137,13 +137,13 @@ static void pvcalls_conn_back_read(void *opaque) if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 1, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted); } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 2, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted); } atomic_set(&map->read, 0); @@ -195,13 +195,13 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size); } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 2, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size); } atomic_set(&map->write, 0); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index e1cbdfdb7c68..0bcbcc20f769 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -65,7 +65,7 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) if (retval == 0) return retval; - iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bvec, 1, PAGE_SIZE); retval = p9_client_read(fid, page_offset(page), &to, &err); if (err) { @@ -175,7 +175,7 @@ static int v9fs_vfs_writepage_locked(struct page *page) bvec.bv_page = page; bvec.bv_offset = 0; bvec.bv_len = len; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len); + iov_iter_bvec(&from, WRITE, &bvec, 1, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index b0405d6aac85..d5db3c968a03 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -133,7 +133,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) if (rdir->tail == rdir->head) { struct iov_iter to; int n; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen); + iov_iter_kvec(&to, READ, &kvec, 1, buflen); n = p9_client_read(file->private_data, ctx->pos, &to, &err); if (err) diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 352abc39e891..ac8ff8ca4c11 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -32,7 +32,7 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, struct iov_iter to; int err; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size); + iov_iter_kvec(&to, READ, &kvec, 1, buffer_size); attr_fid = p9_client_xattrwalk(fid, name, &attr_size); if (IS_ERR(attr_fid)) { @@ -107,7 +107,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, struct iov_iter from; int retval, err; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len); + iov_iter_kvec(&from, WRITE, &kvec, 1, value_len); p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n", name, value_len, flags); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 77a83790a31f..639c16882e93 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -286,7 +286,7 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, offset = 0; } - iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes); + iov_iter_bvec(&msg->msg_iter, WRITE, bv, nr, bytes); } /* @@ -401,8 +401,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, - call->request_size); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = MSG_WAITALL | (call->send_pages ? MSG_MORE : 0); @@ -432,7 +431,7 @@ error_do_abort: rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); } else { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, READ, NULL, 0, 0); rxrpc_kernel_recv_data(call->net->socket, rxcall, &msg.msg_iter, false, &call->abort_code, &call->service_id); @@ -468,7 +467,7 @@ static void afs_deliver_to_call(struct afs_call *call) if (state == AFS_CALL_SV_AWAIT_ACK) { struct iov_iter iter; - iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&iter, READ, NULL, 0, 0); ret = rxrpc_kernel_recv_data(call->net->socket, call->rxcall, &iter, false, &remote_abort, @@ -825,7 +824,7 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, WRITE, NULL, 0, 0); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -864,7 +863,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -905,7 +904,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, iov.iov_base = buf + call->offset; iov.iov_len = count - call->offset; - iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset); + iov_iter_kvec(&iter, READ, &iov, 1, count - call->offset); ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter, want_more, &remote_abort, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 524ecc95b04d..5dd433aa9b23 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -821,7 +821,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) aio_req->total_len = rc + zlen; } - iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs, + iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs, osd_data->num_bvecs, osd_data->bvec_pos.iter.bi_size); iov_iter_advance(&i, rc); @@ -1044,8 +1044,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, int zlen = min_t(size_t, len - ret, size - pos - ret); - iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages, - len); + iov_iter_bvec(&i, READ, bvecs, num_pages, len); iov_iter_advance(&i, ret); iov_iter_zero(zlen, &i); ret += zlen; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 52d71b64c0c6..11bcd2fb90b1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -588,7 +588,7 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, { struct msghdr smb_msg; struct kvec iov = {.iov_base = buf, .iov_len = to_read}; - iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read); + iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } @@ -600,7 +600,7 @@ cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, struct msghdr smb_msg; struct bio_vec bv = { .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; - iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read); + iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 7b5b960a04b8..10cff44832d8 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -857,7 +857,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) ctx->bv = bv; ctx->len = saved_len - count; ctx->npages = npages; - iov_iter_bvec(&ctx->iter, ITER_BVEC | rw, ctx->bv, npages, ctx->len); + iov_iter_bvec(&ctx->iter, rw, ctx->bv, npages, ctx->len); return 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 89985a0a6819..26f8a65b8722 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2962,13 +2962,13 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, return 0; } - iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len); + iov_iter_bvec(&iter, WRITE, bvec, npages, data_len); } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ WARN_ONCE(npages > 0, "read data can be either in buf or in pages"); iov.iov_base = buf + data_offset; iov.iov_len = data_len; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len); + iov_iter_kvec(&iter, WRITE, &iov, 1, data_len); } else { /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b48f43963da6..146b618802a5 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -307,8 +307,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, .iov_base = &rfc1002_marker, .iov_len = 4 }; - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov, - 1, 4); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, &hiov, 1, 4); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) goto uncork; @@ -329,8 +328,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, size += iov[i].iov_len; } - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, - iov, n_vec, size); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, iov, n_vec, size); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) @@ -346,7 +344,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, rqst_page_get_length(&rqst[j], i, &bvec.bv_len, &bvec.bv_offset); - iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, + iov_iter_bvec(&smb_msg.msg_iter, WRITE, &bvec, 1, bvec.bv_len); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index a5e4a221435c..76976d6e50f9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -674,7 +674,7 @@ static int receive_from_sock(struct connection *con) nvec = 2; } len = iov[0].iov_len + iov[1].iov_len; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nvec, len); + iov_iter_kvec(&msg.msg_iter, READ, iov, nvec, len); r = ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT | MSG_NOSIGNAL); if (ret <= 0) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b53e76391e52..8b90f5480904 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -923,7 +923,7 @@ __be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, int host_err; trace_nfsd_read_vector(rqstp, fhp, offset, *count); - iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count); + iov_iter_kvec(&iter, READ, vec, vlen, *count); host_err = vfs_iter_read(file, &iter, &offset, 0); return nfsd_finish_read(rqstp, fhp, file, offset, count, host_err); } @@ -999,7 +999,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (stable && !use_wgather) flags |= RWF_SYNC; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt); + iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) goto out_nfserr; diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 7d9eea7d4a87..e9f236af1927 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -916,7 +916,7 @@ static int o2net_recv_tcp_msg(struct socket *sock, void *data, size_t len) { struct kvec vec = { .iov_len = len, .iov_base = data, }; struct msghdr msg = { .msg_flags = MSG_DONTWAIT, }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, len); return sock_recvmsg(sock, &msg, MSG_DONTWAIT); } diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 31932879b716..136a8bdc1d91 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -25,7 +25,7 @@ static int read_one_page(struct page *page) struct iov_iter to; struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE}; - iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bv, 1, PAGE_SIZE); gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpage called with page %p\n", diff --git a/fs/splice.c b/fs/splice.c index b3daa971f597..3553f1956508 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -301,7 +301,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct kiocb kiocb; int idx, ret; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); + iov_iter_pipe(&to, READ, pipe, len); idx = to.idx; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; @@ -386,7 +386,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, */ offset = *ppos & ~PAGE_MASK; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset); + iov_iter_pipe(&to, READ, pipe, len + offset); res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base); if (res <= 0) @@ -745,8 +745,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, left -= this_len; } - iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n, - sd.total_len - left); + iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left); ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; diff --git a/include/linux/uio.h b/include/linux/uio.h index fcabc959c794..3d8f1acc142c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -29,7 +29,7 @@ enum iter_type { }; struct iov_iter { - int type; + unsigned int type; size_t iov_offset; size_t count; union { @@ -212,13 +212,13 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); -void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 42d39116a556..c42b928b15ef 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -428,17 +428,19 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); -void iov_iter_init(struct iov_iter *i, int direction, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { + WARN_ON(direction & ~(READ | WRITE)); + direction &= READ | WRITE; + /* It will get better. Eventually... */ if (uaccess_kernel()) { - direction |= ITER_KVEC; - i->type = direction; + i->type = ITER_KVEC | direction; i->kvec = (struct kvec *)iov; } else { - i->type = direction; + i->type = ITER_IOVEC | direction; i->iov = iov; } i->nr_segs = nr_segs; @@ -1060,12 +1062,12 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_single_seg_count); -void iov_iter_kvec(struct iov_iter *i, int direction, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_KVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_KVEC | (direction & (READ | WRITE)); i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1073,12 +1075,12 @@ void iov_iter_kvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_kvec); -void iov_iter_bvec(struct iov_iter *i, int direction, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_BVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_BVEC | (direction & (READ | WRITE)); i->bvec = bvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1086,13 +1088,13 @@ void iov_iter_bvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_bvec); -void iov_iter_pipe(struct iov_iter *i, int direction, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { - BUG_ON(direction != ITER_PIPE); + BUG_ON(direction != READ); WARN_ON(pipe->nrbufs == pipe->buffers); - i->type = direction; + i->type = ITER_PIPE | READ; i->pipe = pipe; i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); i->iov_offset = 0; diff --git a/mm/page_io.c b/mm/page_io.c index aafd19ec1db4..86de453a60cf 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, }; struct iov_iter from; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); diff --git a/net/9p/client.c b/net/9p/client.c index deae53a7dffc..a9cd1401bd09 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2070,7 +2070,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) struct kvec kv = {.iov_base = data, .iov_len = count}; struct iov_iter to; - iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count); + iov_iter_kvec(&to, READ, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, (unsigned long long) offset, count); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4e2576fc0c59..828e87fe8027 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, iv.iov_len = skb->len; memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len); err = l2cap_chan_send(chan, &msg, skb->len); if (err > 0) { diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 51c2cf2d8923..58fc6333d412 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len); l2cap_chan_send(chan, &msg, total_len); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a1c1b7e8a45c..c822e626761b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len); + iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len); l2cap_chan_send(chan, &msg, 1 + len); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0a187196aeed..e493ff77b378 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -526,7 +526,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) if (!buf) msg.msg_flags |= MSG_TRUNC; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -545,7 +545,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int r; BUG_ON(page_offset + length > PAGE_SIZE); - iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length); + iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -607,7 +607,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, else msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size); + iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size); ret = sock_sendmsg(sock, &msg); if (ret == -EAGAIN) ret = 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d4020c5e831d..2526be6b3d90 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) EnterFunction(7); /* Receive a packet */ - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 52241d679cc9..89c3a8c7859a 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, */ krflags = MSG_PEEK | MSG_WAITALL; smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, sizeof(struct smc_clc_msg_hdr)); len = sock_recvmsg(smc->clcsock, &msg, krflags); if (signal_pending(current)) { @@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { diff --git a/net/socket.c b/net/socket.c index b68801c7d0ab..fae408abea54 100644 --- a/net/socket.c +++ b/net/socket.c @@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg); int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); @@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } @@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, mm_segment_t oldfs = get_fs(); int result; - iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, READ, vec, num, size); set_fs(KERNEL_DS); result = sock_recvmsg(sock, msg, flags); set_fs(oldfs); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5445145e639c..0b46ec0bf74e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -338,7 +338,7 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, rqstp->rq_xprt_hlen = 0; clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen); + iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen); len = sock_recvmsg(svsk->sk_sock, &msg, msg.msg_flags); /* If we read a full record, then assume there may be more * data to read (stream based sockets only!) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d8956f7daac4..afa02eeec403 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) iov.iov_base = &s; iov.iov_len = sizeof(s); msg.msg_name = NULL; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len); ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 276edbc04f38..d753e362d2d9 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, iov.iov_base = kaddr + offset; iov.iov_len = size; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); rc = tls_push_data(sk, &msg_iter, size, flags, TLS_RECORD_TYPE_DATA); kunmap(page); @@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter msg_iter; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0); return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } -- cgit v1.2.3-71-gd317 From 9ea9ce0427aab02a2fd88fc608267cf6952119f1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Add I/O discard iterator Add a new iterator, ITER_DISCARD, that can only be used in READ mode and just discards any data copied to it. This is useful in a network filesystem for discarding any unwanted data sent by a server. Signed-off-by: David Howells --- include/linux/uio.h | 7 +++++++ lib/iov_iter.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 55 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 3d8f1acc142c..55ce99ddb912 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -26,6 +26,7 @@ enum iter_type { ITER_KVEC = 2, ITER_BVEC = 4, ITER_PIPE = 8, + ITER_DISCARD = 16, }; struct iov_iter { @@ -72,6 +73,11 @@ static inline bool iov_iter_is_pipe(const struct iov_iter *i) return iov_iter_type(i) == ITER_PIPE; } +static inline bool iov_iter_is_discard(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_DISCARD; +} + static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); @@ -220,6 +226,7 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_ unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, diff --git a/lib/iov_iter.c b/lib/iov_iter.c index c42b928b15ef..7ebccb5c1637 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -83,6 +83,7 @@ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ + } else if (unlikely(i->type & ITER_DISCARD)) { \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -114,6 +115,8 @@ } \ i->nr_segs -= kvec - i->kvec; \ i->kvec = kvec; \ + } else if (unlikely(i->type & ITER_DISCARD)) { \ + skip += n; \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -838,7 +841,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; - } else if (likely(!iov_iter_is_pipe(i))) + } else if (unlikely(iov_iter_is_discard(i))) + return bytes; + else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); @@ -850,7 +855,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } @@ -910,7 +915,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, kunmap_atomic(kaddr); return 0; } - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; @@ -978,6 +983,10 @@ void iov_iter_advance(struct iov_iter *i, size_t size) pipe_advance(i, size); return; } + if (unlikely(iov_iter_is_discard(i))) { + i->count -= size; + return; + } iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -1013,6 +1022,8 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) pipe_truncate(i); return; } + if (unlikely(iov_iter_is_discard(i))) + return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; @@ -1055,6 +1066,8 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; + if (unlikely(iov_iter_is_discard(i))) + return i->count; else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else @@ -1103,6 +1116,24 @@ void iov_iter_pipe(struct iov_iter *i, unsigned int direction, } EXPORT_SYMBOL(iov_iter_pipe); +/** + * iov_iter_discard - Initialise an I/O iterator that discards data + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator that just discards everything that's written to it. + * It's only available as a READ iterator. + */ +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) +{ + BUG_ON(direction != READ); + i->type = ITER_DISCARD | READ; + i->count = count; + i->iov_offset = 0; +} +EXPORT_SYMBOL(iov_iter_discard); + unsigned long iov_iter_alignment(const struct iov_iter *i) { unsigned long res = 0; @@ -1127,7 +1158,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return ~0U; } @@ -1197,6 +1228,9 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); + if (unlikely(iov_iter_is_discard(i))) + return -EFAULT; + iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); @@ -1274,6 +1308,9 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); + if (unlikely(iov_iter_is_discard(i))) + return -EFAULT; + iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); @@ -1315,7 +1352,7 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } @@ -1357,7 +1394,7 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return false; } @@ -1402,7 +1439,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(iov_iter_is_pipe(i))) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } @@ -1444,6 +1481,8 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) if (!size) return 0; + if (unlikely(iov_iter_is_discard(i))) + return 0; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; @@ -1487,6 +1526,8 @@ const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) WARN_ON(1); return NULL; } + if (unlikely(iov_iter_is_discard(new))) + return NULL; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), -- cgit v1.2.3-71-gd317 From 721fb6fbfd2132164c2e8777cc837f9b2c1794dc Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 17 Oct 2018 13:07:05 +0200 Subject: fsnotify: Fix busy inodes during unmount Detaching of mark connector from fsnotify_put_mark() can race with unmounting of the filesystem like: CPU1 CPU2 fsnotify_put_mark() spin_lock(&conn->lock); ... inode = fsnotify_detach_connector_from_object(conn) spin_unlock(&conn->lock); generic_shutdown_super() fsnotify_unmount_inodes() sees connector detached for inode -> nothing to do evict_inode() barfs on pending inode reference iput(inode); Resulting in "Busy inodes after unmount" message and possible kernel oops. Make fsnotify_unmount_inodes() properly wait for outstanding inode references from detached connectors. Note that the accounting of outstanding inode references in the superblock can cause some cacheline contention on the counter. OTOH it happens only during deletion of the last notification mark from an inode (or during unlinking of watched inode) and that is not too bad. I have measured time to create & delete inotify watch 100000 times from 64 processes in parallel (each process having its own inotify group and its own file on a shared superblock) on a 64 CPU machine. Average and standard deviation of 15 runs look like: Avg Stddev Vanilla 9.817400 0.276165 Fixed 9.710467 0.228294 So there's no statistically significant difference. Fixes: 6b3f05d24d35 ("fsnotify: Detach mark from object list when last reference is dropped") CC: stable@vger.kernel.org Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 3 +++ fs/notify/mark.c | 39 +++++++++++++++++++++++++++++++-------- include/linux/fs.h | 3 +++ 3 files changed, 37 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 875975504409..2172ba516c61 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -96,6 +96,9 @@ static void fsnotify_unmount_inodes(struct super_block *sb) if (iput_inode) iput(iput_inode); + /* Wait for outstanding inode references from connectors */ + wait_var_event(&sb->s_fsnotify_inode_refs, + !atomic_long_read(&sb->s_fsnotify_inode_refs)); } void fsnotify_sb_delete(struct super_block *sb) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index b5172ccb2e60..d2dd16cb5989 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -181,17 +181,20 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work) } } -static struct inode *fsnotify_detach_connector_from_object( - struct fsnotify_mark_connector *conn) +static void *fsnotify_detach_connector_from_object( + struct fsnotify_mark_connector *conn, + unsigned int *type) { struct inode *inode = NULL; + *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; + atomic_long_inc(&inode->i_sb->s_fsnotify_inode_refs); } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { @@ -215,10 +218,29 @@ static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) fsnotify_put_group(group); } +/* Drop object reference originally held by a connector */ +static void fsnotify_drop_object(unsigned int type, void *objp) +{ + struct inode *inode; + struct super_block *sb; + + if (!objp) + return; + /* Currently only inode references are passed to be dropped */ + if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) + return; + inode = objp; + sb = inode->i_sb; + iput(inode); + if (atomic_long_dec_and_test(&sb->s_fsnotify_inode_refs)) + wake_up_var(&sb->s_fsnotify_inode_refs); +} + void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn; - struct inode *inode = NULL; + void *objp = NULL; + unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ @@ -238,7 +260,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) conn = mark->connector; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { - inode = fsnotify_detach_connector_from_object(conn); + objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { __fsnotify_recalc_mask(conn); @@ -246,7 +268,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) mark->connector = NULL; spin_unlock(&conn->lock); - iput(inode); + fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); @@ -713,7 +735,8 @@ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; - struct inode *inode; + void *objp; + unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) @@ -739,11 +762,11 @@ void fsnotify_destroy_marks(fsnotify_connp_t *connp) * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ - inode = fsnotify_detach_connector_from_object(conn); + objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); - iput(inode); + fsnotify_drop_object(type, objp); } /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 6da94deb957f..00b23b21e78a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1437,6 +1437,9 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; + /* Pending fsnotify inode refs */ + atomic_long_t s_fsnotify_inode_refs; + /* Being remounted read-only */ int s_readonly_remount; -- cgit v1.2.3-71-gd317 From a7fe5190c03f8137ef08db84a58dd4daf2c4785d Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 4 Oct 2018 14:04:03 +0200 Subject: cpuidle: menu: Remove get_loadavg() from the performance multiplier The function get_loadavg() returns almost always zero. To be more precise, statistically speaking for a total of 1023379 times passing in the function, the load is equal to zero 1020728 times, greater than 100, 610 times, the remaining is between 0 and 5. In 2011, the get_loadavg() was removed from the Android tree because of the above [1]. At this time, the load was: unsigned long this_cpu_load(void) { struct rq *this = this_rq(); return this->cpu_load[0]; } In 2014, the code was changed by commit 372ba8cb46b2 (cpuidle: menu: Lookup CPU runqueues less) and the load is: void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) { struct rq *rq = this_rq(); *nr_waiters = atomic_read(&rq->nr_iowait); *load = rq->load.weight; } with the same result. Both measurements show using the load in this code path does no matter anymore. Removing it. [1] https://android.googlesource.com/kernel/common/+/4dedd9f124703207895777ac6e91dacde0f7cc17 Signed-off-by: Daniel Lezcano Acked-by: Mel Gorman Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/governors/menu.c | 25 ++++++------------------- include/linux/sched/stat.h | 1 - kernel/sched/core.c | 7 ------- 3 files changed, 6 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 575a68f31761..76df4f947f07 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -134,11 +134,6 @@ struct menu_device { #define LOAD_INT(x) ((x) >> FSHIFT) #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) -static inline int get_loadavg(unsigned long load) -{ - return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; -} - static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters) { int bucket = 0; @@ -172,18 +167,10 @@ static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters * to be, the higher this multiplier, and thus the higher * the barrier to go to an expensive C state. */ -static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned long load) +static inline int performance_multiplier(unsigned long nr_iowaiters) { - int mult = 1; - - /* for higher loadavg, we are more reluctant */ - - mult += 2 * get_loadavg(load); - - /* for IO wait tasks (per cpu!) we add 5x each */ - mult += 10 * nr_iowaiters; - - return mult; + /* for IO wait tasks (per cpu!) we add 10x each */ + return 1 + 10 * nr_iowaiters; } static DEFINE_PER_CPU(struct menu_device, menu_devices); @@ -301,7 +288,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, int idx; unsigned int interactivity_req; unsigned int predicted_us; - unsigned long nr_iowaiters, cpu_load; + unsigned long nr_iowaiters; ktime_t delta_next; if (data->needs_update) { @@ -312,7 +299,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, /* determine the expected residency time, round up */ data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); - get_iowait_load(&nr_iowaiters, &cpu_load); + nr_iowaiters = nr_iowait_cpu(dev->cpu); data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); if (unlikely(drv->state_count <= 1 || latency_req == 0) || @@ -356,7 +343,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * Use the performance multiplier and the user-configurable * latency_req to determine the maximum exit latency. */ - interactivity_req = predicted_us / performance_multiplier(nr_iowaiters, cpu_load); + interactivity_req = predicted_us / performance_multiplier(nr_iowaiters); if (latency_req > interactivity_req) latency_req = interactivity_req; } diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h index 04f1321d14c4..f30954cc059d 100644 --- a/include/linux/sched/stat.h +++ b/include/linux/sched/stat.h @@ -20,7 +20,6 @@ extern unsigned long nr_running(void); extern bool single_task_running(void); extern unsigned long nr_iowait(void); extern unsigned long nr_iowait_cpu(int cpu); -extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); static inline int sched_info_on(void) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9245c56b8f5f..c8d5c279be14 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2887,13 +2887,6 @@ unsigned long nr_iowait_cpu(int cpu) return atomic_read(&cpu_rq(cpu)->nr_iowait); } -void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) -{ - struct rq *rq = this_rq(); - *nr_waiters = atomic_read(&rq->nr_iowait); - *load = rq->load.weight; -} - /* * IO-wait accounting, and how its mostly bollocks (on SMP). * -- cgit v1.2.3-71-gd317 From ede95a63b5e84ddeea6b0c473b36ab8bfd8c6ce3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 23 Oct 2018 01:11:04 +0200 Subject: bpf: add bpf_jit_limit knob to restrict unpriv allocations Rick reported that the BPF JIT could potentially fill the entire module space with BPF programs from unprivileged users which would prevent later attempts to load normal kernel modules or privileged BPF programs, for example. If JIT was enabled but unsuccessful to generate the image, then before commit 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") we would always fall back to the BPF interpreter. Nowadays in the case where the CONFIG_BPF_JIT_ALWAYS_ON could be set, then the load will abort with a failure since the BPF interpreter was compiled out. Add a global limit and enforce it for unprivileged users such that in case of BPF interpreter compiled out we fail once the limit has been reached or we fall back to BPF interpreter earlier w/o using module mem if latter was compiled in. In a next step, fair share among unprivileged users can be resolved in particular for the case where we would fail hard once limit is reached. Fixes: 290af86629b2 ("bpf: introduce BPF_JIT_ALWAYS_ON config") Fixes: 0a14842f5a3c ("net: filter: Just In Time compiler for x86-64") Co-Developed-by: Rick Edgecombe Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Cc: Eric Dumazet Cc: Jann Horn Cc: Kees Cook Cc: LKML Signed-off-by: Alexei Starovoitov --- Documentation/sysctl/net.txt | 8 ++++++++ include/linux/filter.h | 1 + kernel/bpf/core.c | 49 +++++++++++++++++++++++++++++++++++++++++--- net/core/sysctl_net_core.c | 10 +++++++-- 4 files changed, 63 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 9ecde517728c..2793d4eac55f 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -92,6 +92,14 @@ Values : 0 - disable JIT kallsyms export (default value) 1 - enable JIT kallsyms export for privileged users only +bpf_jit_limit +------------- + +This enforces a global limit for memory allocations to the BPF JIT +compiler in order to reject unprivileged JIT requests once it has +been surpassed. bpf_jit_limit contains the value of the global limit +in bytes. + dev_weight -------------- diff --git a/include/linux/filter.h b/include/linux/filter.h index 91b4c934f02e..de629b706d1d 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -854,6 +854,7 @@ bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; +extern int bpf_jit_limit; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7c7eeea8cffc..6377225b2082 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,10 +365,13 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) } #ifdef CONFIG_BPF_JIT +# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000) + /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; +int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -577,27 +580,64 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; } +static atomic_long_t bpf_jit_current; + +#if defined(MODULES_VADDR) +static int __init bpf_jit_charge_init(void) +{ + /* Only used as heuristic here to derive limit. */ + bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2, + PAGE_SIZE), INT_MAX); + return 0; +} +pure_initcall(bpf_jit_charge_init); +#endif + +static int bpf_jit_charge_modmem(u32 pages) +{ + if (atomic_long_add_return(pages, &bpf_jit_current) > + (bpf_jit_limit >> PAGE_SHIFT)) { + if (!capable(CAP_SYS_ADMIN)) { + atomic_long_sub(pages, &bpf_jit_current); + return -EPERM; + } + } + + return 0; +} + +static void bpf_jit_uncharge_modmem(u32 pages) +{ + atomic_long_sub(pages, &bpf_jit_current); +} + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; - unsigned int size, hole, start; + u32 size, hole, start, pages; /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); + pages = size / PAGE_SIZE; + + if (bpf_jit_charge_modmem(pages)) + return NULL; hdr = module_alloc(size); - if (hdr == NULL) + if (!hdr) { + bpf_jit_uncharge_modmem(pages); return NULL; + } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); - hdr->pages = size / PAGE_SIZE; + hdr->pages = pages; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -610,7 +650,10 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { + u32 pages = hdr->pages; + module_memfree(hdr); + bpf_jit_uncharge_modmem(pages); } /* This symbol is only overridden by archs that have different diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b1a2c5e38530..37b4667128a3 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -279,7 +279,6 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } -# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -290,7 +289,6 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } -# endif #endif static struct ctl_table net_core_table[] = { @@ -397,6 +395,14 @@ static struct ctl_table net_core_table[] = { .extra2 = &one, }, # endif + { + .procname = "bpf_jit_limit", + .data = &bpf_jit_limit, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax_bpf_restricted, + .extra1 = &one, + }, #endif { .procname = "netdev_tstamp_prequeue", -- cgit v1.2.3-71-gd317 From 70025f84e5b79627a6739533c4fe7cef5b605886 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 9 Oct 2018 17:46:51 +0100 Subject: KEYS: Provide key type operations for asymmetric key ops [ver #2] Provide five new operations in the key_type struct that can be used to provide access to asymmetric key operations. These will be implemented for the asymmetric key type in a later patch and may refer to a key retained in RAM by the kernel or a key retained in crypto hardware. int (*asym_query)(const struct kernel_pkey_params *params, struct kernel_pkey_query *info); int (*asym_eds_op)(struct kernel_pkey_params *params, const void *in, void *out); int (*asym_verify_signature)(struct kernel_pkey_params *params, const void *in, const void *in2); Since encrypt, decrypt and sign are identical in their interfaces, they're rolled together in the asym_eds_op() operation and there's an operation ID in the params argument to distinguish them. Verify is different in that we supply the data and the signature instead and get an error value (or 0) as the only result on the expectation that this may well be how a hardware crypto device may work. Signed-off-by: David Howells Tested-by: Marcel Holtmann Reviewed-by: Marcel Holtmann Reviewed-by: Denis Kenzior Tested-by: Denis Kenzior Signed-off-by: James Morris --- Documentation/security/keys/core.rst | 106 +++++++++++++++++++++++++++++++++++ include/linux/key-type.h | 11 ++++ include/linux/keyctl.h | 46 +++++++++++++++ include/uapi/linux/keyctl.h | 5 ++ 4 files changed, 168 insertions(+) create mode 100644 include/linux/keyctl.h (limited to 'include/linux') diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index 9ce7256c6edb..c144978479d5 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -1483,6 +1483,112 @@ The structure has a number of fields, some of which are mandatory: attempted key link operation. If there is no match, -EINVAL is returned. + * ``int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out);`` + ``int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2);`` + + These methods are optional. If provided the first allows a key to be + used to encrypt, decrypt or sign a blob of data, and the second allows a + key to verify a signature. + + In all cases, the following information is provided in the params block:: + + struct kernel_pkey_params { + struct key *key; + const char *encoding; + const char *hash_algo; + char *info; + __u32 in_len; + union { + __u32 out_len; + __u32 in2_len; + }; + enum kernel_pkey_operation op : 8; + }; + + This includes the key to be used; a string indicating the encoding to use + (for instance, "pkcs1" may be used with an RSA key to indicate + RSASSA-PKCS1-v1.5 or RSAES-PKCS1-v1.5 encoding or "raw" if no encoding); + the name of the hash algorithm used to generate the data for a signature + (if appropriate); the sizes of the input and output (or second input) + buffers; and the ID of the operation to be performed. + + For a given operation ID, the input and output buffers are used as + follows:: + + Operation ID in,in_len out,out_len in2,in2_len + ======================= =============== =============== =============== + kernel_pkey_encrypt Raw data Encrypted data - + kernel_pkey_decrypt Encrypted data Raw data - + kernel_pkey_sign Raw data Signature - + kernel_pkey_verify Raw data - Signature + + asym_eds_op() deals with encryption, decryption and signature creation as + specified by params->op. Note that params->op is also set for + asym_verify_signature(). + + Encrypting and signature creation both take raw data in the input buffer + and return the encrypted result in the output buffer. Padding may have + been added if an encoding was set. In the case of signature creation, + depending on the encoding, the padding created may need to indicate the + digest algorithm - the name of which should be supplied in hash_algo. + + Decryption takes encrypted data in the input buffer and returns the raw + data in the output buffer. Padding will get checked and stripped off if + an encoding was set. + + Verification takes raw data in the input buffer and the signature in the + second input buffer and checks that the one matches the other. Padding + will be validated. Depending on the encoding, the digest algorithm used + to generate the raw data may need to be indicated in hash_algo. + + If successful, asym_eds_op() should return the number of bytes written + into the output buffer. asym_verify_signature() should return 0. + + A variety of errors may be returned, including EOPNOTSUPP if the operation + is not supported; EKEYREJECTED if verification fails; ENOPKG if the + required crypto isn't available. + + + * ``int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info);`` + + This method is optional. If provided it allows information about the + public or asymmetric key held in the key to be determined. + + The parameter block is as for asym_eds_op() and co. but in_len and out_len + are unused. The encoding and hash_algo fields should be used to reduce + the returned buffer/data sizes as appropriate. + + If successful, the following information is filled in:: + + struct kernel_pkey_query { + __u32 supported_ops; + __u32 key_size; + __u16 max_data_size; + __u16 max_sig_size; + __u16 max_enc_size; + __u16 max_dec_size; + }; + + The supported_ops field will contain a bitmask indicating what operations + are supported by the key, including encryption of a blob, decryption of a + blob, signing a blob and verifying the signature on a blob. The following + constants are defined for this:: + + KEYCTL_SUPPORTS_{ENCRYPT,DECRYPT,SIGN,VERIFY} + + The key_size field is the size of the key in bits. max_data_size and + max_sig_size are the maximum raw data and signature sizes for creation and + verification of a signature; max_enc_size and max_dec_size are the maximum + raw data and signature sizes for encryption and decryption. The + max_*_size fields are measured in bytes. + + If successful, 0 will be returned. If the key doesn't support this, + EOPNOTSUPP will be returned. + + Request-Key Callback Service ============================ diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 05d8fb5a06c4..bc9af551fc83 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -17,6 +17,9 @@ #ifdef CONFIG_KEYS +struct kernel_pkey_query; +struct kernel_pkey_params; + /* * key under-construction record * - passed to the request_key actor if supplied @@ -155,6 +158,14 @@ struct key_type { */ struct key_restriction *(*lookup_restriction)(const char *params); + /* Asymmetric key accessor functions. */ + int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); + int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2); + /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h new file mode 100644 index 000000000000..c7c48c79ce0e --- /dev/null +++ b/include/linux/keyctl.h @@ -0,0 +1,46 @@ +/* keyctl kernel bits + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef __LINUX_KEYCTL_H +#define __LINUX_KEYCTL_H + +#include + +struct kernel_pkey_query { + __u32 supported_ops; /* Which ops are supported */ + __u32 key_size; /* Size of the key in bits */ + __u16 max_data_size; /* Maximum size of raw data to sign in bytes */ + __u16 max_sig_size; /* Maximum size of signature in bytes */ + __u16 max_enc_size; /* Maximum size of encrypted blob in bytes */ + __u16 max_dec_size; /* Maximum size of decrypted blob in bytes */ +}; + +enum kernel_pkey_operation { + kernel_pkey_encrypt, + kernel_pkey_decrypt, + kernel_pkey_sign, + kernel_pkey_verify, +}; + +struct kernel_pkey_params { + struct key *key; + const char *encoding; /* Encoding (eg. "oaep" or "raw" for none) */ + const char *hash_algo; /* Digest algorithm used (eg. "sha1") or NULL if N/A */ + char *info; /* Modified info string to be released later */ + __u32 in_len; /* Input data size */ + union { + __u32 out_len; /* Output buffer size (enc/dec/sign) */ + __u32 in2_len; /* 2nd input data size (verify) */ + }; + enum kernel_pkey_operation op : 8; +}; + +#endif /* __LINUX_KEYCTL_H */ diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index 0f3cb13db8e9..1d1e9f2877af 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -82,4 +82,9 @@ struct keyctl_kdf_params { __u32 __spare[8]; }; +#define KEYCTL_SUPPORTS_ENCRYPT 0x01 +#define KEYCTL_SUPPORTS_DECRYPT 0x02 +#define KEYCTL_SUPPORTS_SIGN 0x04 +#define KEYCTL_SUPPORTS_VERIFY 0x08 + #endif /* _LINUX_KEYCTL_H */ -- cgit v1.2.3-71-gd317 From ae74136b4bb64440a55117e12065b8c282ab6c1a Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 3 Oct 2018 12:01:22 -0400 Subject: SUNRPC: Allow cache lookups to use RCU protection rather than the r/w spinlock Instead of the reader/writer spinlock, allow cache lookups to use RCU for looking up entries. This is more efficient since modifications can occur while other entries are being looked up. Note that for now, we keep the reader/writer spinlock until all users have been converted to use RCU-safe freeing of their cache entries. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 12 ++++++ net/sunrpc/cache.c | 93 +++++++++++++++++++++++++++++++++++++------- 2 files changed, 91 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 40d2822f0e2f..cf3e17ee2786 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -167,6 +167,9 @@ extern const struct file_operations cache_file_operations_pipefs; extern const struct file_operations content_file_operations_pipefs; extern const struct file_operations cache_flush_operations_pipefs; +extern struct cache_head * +sunrpc_cache_lookup_rcu(struct cache_detail *detail, + struct cache_head *key, int hash); extern struct cache_head * sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash); @@ -186,6 +189,12 @@ static inline struct cache_head *cache_get(struct cache_head *h) return h; } +static inline struct cache_head *cache_get_rcu(struct cache_head *h) +{ + if (kref_get_unless_zero(&h->ref)) + return h; + return NULL; +} static inline void cache_put(struct cache_head *h, struct cache_detail *cd) { @@ -227,6 +236,9 @@ extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); extern void *cache_seq_start(struct seq_file *file, loff_t *pos); extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop(struct seq_file *file, void *p); +extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); +extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); +extern void cache_seq_stop_rcu(struct seq_file *file, void *p); extern void qword_add(char **bpp, int *lp, char *str); extern void qword_addhex(char **bpp, int *lp, char *buf, int blen); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index aa8e62d61f4d..7593afed9036 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -54,6 +54,27 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } +static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail, + struct cache_head *key, + int hash) +{ + struct hlist_head *head = &detail->hash_table[hash]; + struct cache_head *tmp; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp, head, cache_list) { + if (detail->match(tmp, key)) { + if (cache_is_expired(detail, tmp)) + continue; + tmp = cache_get_rcu(tmp); + rcu_read_unlock(); + return tmp; + } + } + rcu_read_unlock(); + return NULL; +} + static struct cache_head *sunrpc_cache_find(struct cache_detail *detail, struct cache_head *key, int hash) { @@ -61,7 +82,6 @@ static struct cache_head *sunrpc_cache_find(struct cache_detail *detail, struct cache_head *tmp; read_lock(&detail->hash_lock); - hlist_for_each_entry(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) @@ -96,10 +116,10 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, write_lock(&detail->hash_lock); /* check if entry appeared while we slept */ - hlist_for_each_entry(tmp, head, cache_list) { + hlist_for_each_entry_rcu(tmp, head, cache_list) { if (detail->match(tmp, key)) { if (cache_is_expired(detail, tmp)) { - hlist_del_init(&tmp->cache_list); + hlist_del_init_rcu(&tmp->cache_list); detail->entries --; freeme = tmp; break; @@ -111,7 +131,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, } } - hlist_add_head(&new->cache_list, head); + hlist_add_head_rcu(&new->cache_list, head); detail->entries++; cache_get(new); write_unlock(&detail->hash_lock); @@ -121,6 +141,19 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, return new; } +struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail, + struct cache_head *key, int hash) +{ + struct cache_head *ret; + + ret = sunrpc_cache_find_rcu(detail, key, hash); + if (ret) + return ret; + /* Didn't find anything, insert an empty entry */ + return sunrpc_cache_add_entry(detail, key, hash); +} +EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu); + struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, struct cache_head *key, int hash) { @@ -134,6 +167,7 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, } EXPORT_SYMBOL_GPL(sunrpc_cache_lookup); + static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch); static void cache_fresh_locked(struct cache_head *head, time_t expiry, @@ -450,7 +484,7 @@ static int cache_clean(void) if (!cache_is_expired(current_detail, ch)) continue; - hlist_del_init(&ch->cache_list); + hlist_del_init_rcu(&ch->cache_list); current_detail->entries--; rv = 1; break; @@ -521,7 +555,7 @@ void cache_purge(struct cache_detail *detail) for (i = 0; i < detail->hash_size; i++) { head = &detail->hash_table[i]; hlist_for_each_entry_safe(ch, tmp, head, cache_list) { - hlist_del_init(&ch->cache_list); + hlist_del_init_rcu(&ch->cache_list); detail->entries--; set_bit(CACHE_CLEANED, &ch->flags); @@ -1306,21 +1340,19 @@ EXPORT_SYMBOL_GPL(qword_get); * get a header, then pass each real item in the cache */ -void *cache_seq_start(struct seq_file *m, loff_t *pos) - __acquires(cd->hash_lock) +static void *__cache_seq_start(struct seq_file *m, loff_t *pos) { loff_t n = *pos; unsigned int hash, entry; struct cache_head *ch; struct cache_detail *cd = m->private; - read_lock(&cd->hash_lock); if (!n--) return SEQ_START_TOKEN; hash = n >> 32; entry = n & ((1LL<<32) - 1); - hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list) + hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list) if (!entry--) return ch; n &= ~((1LL<<32) - 1); @@ -1332,9 +1364,19 @@ void *cache_seq_start(struct seq_file *m, loff_t *pos) if (hash >= cd->hash_size) return NULL; *pos = n+1; - return hlist_entry_safe(cd->hash_table[hash].first, + return hlist_entry_safe(rcu_dereference_raw( + hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); } + +void *cache_seq_start(struct seq_file *m, loff_t *pos) + __acquires(cd->hash_lock) +{ + struct cache_detail *cd = m->private; + + read_lock(&cd->hash_lock); + return __cache_seq_start(m, pos); +} EXPORT_SYMBOL_GPL(cache_seq_start); void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) @@ -1350,7 +1392,8 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) *pos += 1LL<<32; } else { ++*pos; - return hlist_entry_safe(ch->cache_list.next, + return hlist_entry_safe(rcu_dereference_raw( + hlist_next_rcu(&ch->cache_list)), struct cache_head, cache_list); } *pos &= ~((1LL<<32) - 1); @@ -1362,7 +1405,8 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) if (hash >= cd->hash_size) return NULL; ++*pos; - return hlist_entry_safe(cd->hash_table[hash].first, + return hlist_entry_safe(rcu_dereference_raw( + hlist_first_rcu(&cd->hash_table[hash])), struct cache_head, cache_list); } EXPORT_SYMBOL_GPL(cache_seq_next); @@ -1375,6 +1419,27 @@ void cache_seq_stop(struct seq_file *m, void *p) } EXPORT_SYMBOL_GPL(cache_seq_stop); +void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos) + __acquires(RCU) +{ + rcu_read_lock(); + return __cache_seq_start(m, pos); +} +EXPORT_SYMBOL_GPL(cache_seq_start_rcu); + +void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos) +{ + return cache_seq_next(file, p, pos); +} +EXPORT_SYMBOL_GPL(cache_seq_next_rcu); + +void cache_seq_stop_rcu(struct seq_file *m, void *p) + __releases(RCU) +{ + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(cache_seq_stop_rcu); + static int c_show(struct seq_file *m, void *p) { struct cache_head *cp = p; @@ -1863,7 +1928,7 @@ void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h) { write_lock(&cd->hash_lock); if (!hlist_unhashed(&h->cache_list)){ - hlist_del_init(&h->cache_list); + hlist_del_init_rcu(&h->cache_list); cd->entries--; write_unlock(&cd->hash_lock); cache_put(h, cd); -- cgit v1.2.3-71-gd317 From d48cf356a13073853f19be6ca5ebbecfc2762ebe Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:51 -0400 Subject: SUNRPC: Remove non-RCU protected lookup Clean up the cache code by removing the non-RCU protected lookup. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- Documentation/filesystems/nfs/rpc-cache.txt | 6 +-- include/linux/sunrpc/cache.h | 6 --- net/sunrpc/cache.c | 61 ++--------------------------- 3 files changed, 7 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/nfs/rpc-cache.txt b/Documentation/filesystems/nfs/rpc-cache.txt index ebcaaee21616..c4dac829db0f 100644 --- a/Documentation/filesystems/nfs/rpc-cache.txt +++ b/Documentation/filesystems/nfs/rpc-cache.txt @@ -84,7 +84,7 @@ Creating a Cache A message from user space has arrived to fill out a cache entry. It is in 'buf' of length 'len'. cache_parse should parse this, find the item in the - cache with sunrpc_cache_lookup, and update the item + cache with sunrpc_cache_lookup_rcu, and update the item with sunrpc_cache_update. @@ -95,7 +95,7 @@ Creating a Cache Using a cache ------------- -To find a value in a cache, call sunrpc_cache_lookup passing a pointer +To find a value in a cache, call sunrpc_cache_lookup_rcu passing a pointer to the cache_head in a sample item with the 'key' fields filled in. This will be passed to ->match to identify the target entry. If no entry is found, a new entry will be create, added to the cache, and @@ -116,7 +116,7 @@ item does become valid, the deferred copy of the request will be revisited (->revisit). It is expected that this method will reschedule the request for processing. -The value returned by sunrpc_cache_lookup can also be passed to +The value returned by sunrpc_cache_lookup_rcu can also be passed to sunrpc_cache_update to set the content for the item. A second item is passed which should hold the content. If the item found by _lookup has valid data, then it is discarded and a new item is created. This diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index cf3e17ee2786..c3d67e893430 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -171,9 +171,6 @@ extern struct cache_head * sunrpc_cache_lookup_rcu(struct cache_detail *detail, struct cache_head *key, int hash); extern struct cache_head * -sunrpc_cache_lookup(struct cache_detail *detail, - struct cache_head *key, int hash); -extern struct cache_head * sunrpc_cache_update(struct cache_detail *detail, struct cache_head *new, struct cache_head *old, int hash); @@ -233,9 +230,6 @@ extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); /* Must store cache_detail in seq_file->private if using next three functions */ -extern void *cache_seq_start(struct seq_file *file, loff_t *pos); -extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos); -extern void cache_seq_stop(struct seq_file *file, void *p); extern void *cache_seq_start_rcu(struct seq_file *file, loff_t *pos); extern void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos); extern void cache_seq_stop_rcu(struct seq_file *file, void *p); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 7593afed9036..593cf8607414 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -75,27 +75,6 @@ static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail, return NULL; } -static struct cache_head *sunrpc_cache_find(struct cache_detail *detail, - struct cache_head *key, int hash) -{ - struct hlist_head *head = &detail->hash_table[hash]; - struct cache_head *tmp; - - read_lock(&detail->hash_lock); - hlist_for_each_entry(tmp, head, cache_list) { - if (detail->match(tmp, key)) { - if (cache_is_expired(detail, tmp)) - /* This entry is expired, we will discard it. */ - break; - cache_get(tmp); - read_unlock(&detail->hash_lock); - return tmp; - } - } - read_unlock(&detail->hash_lock); - return NULL; -} - static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, struct cache_head *key, int hash) @@ -154,20 +133,6 @@ struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail, } EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu); -struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail, - struct cache_head *key, int hash) -{ - struct cache_head *ret; - - ret = sunrpc_cache_find(detail, key, hash); - if (ret) - return ret; - /* Didn't find anything, insert an empty entry */ - return sunrpc_cache_add_entry(detail, key, hash); -} -EXPORT_SYMBOL_GPL(sunrpc_cache_lookup); - - static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch); static void cache_fresh_locked(struct cache_head *head, time_t expiry, @@ -1369,17 +1334,7 @@ static void *__cache_seq_start(struct seq_file *m, loff_t *pos) struct cache_head, cache_list); } -void *cache_seq_start(struct seq_file *m, loff_t *pos) - __acquires(cd->hash_lock) -{ - struct cache_detail *cd = m->private; - - read_lock(&cd->hash_lock); - return __cache_seq_start(m, pos); -} -EXPORT_SYMBOL_GPL(cache_seq_start); - -void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) +static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); @@ -1411,14 +1366,6 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos) } EXPORT_SYMBOL_GPL(cache_seq_next); -void cache_seq_stop(struct seq_file *m, void *p) - __releases(cd->hash_lock) -{ - struct cache_detail *cd = m->private; - read_unlock(&cd->hash_lock); -} -EXPORT_SYMBOL_GPL(cache_seq_stop); - void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos) __acquires(RCU) { @@ -1466,9 +1413,9 @@ static int c_show(struct seq_file *m, void *p) } static const struct seq_operations cache_content_op = { - .start = cache_seq_start, - .next = cache_seq_next, - .stop = cache_seq_stop, + .start = cache_seq_start_rcu, + .next = cache_seq_next_rcu, + .stop = cache_seq_stop_rcu, .show = c_show, }; -- cgit v1.2.3-71-gd317 From 1863d77f15da0addcd293a1719fa5d3ef8cde3ca Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 1 Oct 2018 10:41:52 -0400 Subject: SUNRPC: Replace the cache_detail->hash_lock with a regular spinlock Now that the reader functions are all RCU protected, use a regular spinlock rather than a reader/writer lock. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/cache.h | 2 +- net/sunrpc/cache.c | 46 ++++++++++++++++++++++---------------------- 2 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index c3d67e893430..5a3e95017fc6 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -67,7 +67,7 @@ struct cache_detail { struct module * owner; int hash_size; struct hlist_head * hash_table; - rwlock_t hash_lock; + spinlock_t hash_lock; char *name; void (*cache_put)(struct kref *); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 593cf8607414..f96345b1180e 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -92,7 +92,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, cache_init(new, detail); detail->init(new, key); - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); /* check if entry appeared while we slept */ hlist_for_each_entry_rcu(tmp, head, cache_list) { @@ -104,7 +104,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, break; } cache_get(tmp); - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); cache_put(new, detail); return tmp; } @@ -113,7 +113,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, hlist_add_head_rcu(&new->cache_list, head); detail->entries++; cache_get(new); - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); if (freeme) cache_put(freeme, detail); @@ -167,18 +167,18 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, struct cache_head *tmp; if (!test_bit(CACHE_VALID, &old->flags)) { - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); if (!test_bit(CACHE_VALID, &old->flags)) { if (test_bit(CACHE_NEGATIVE, &new->flags)) set_bit(CACHE_NEGATIVE, &old->flags); else detail->update(old, new); cache_fresh_locked(old, new->expiry_time, detail); - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); cache_fresh_unlocked(old, detail); return old; } - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); } /* We need to insert a new entry */ tmp = detail->alloc(); @@ -189,7 +189,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, cache_init(tmp, detail); detail->init(tmp, old); - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); if (test_bit(CACHE_NEGATIVE, &new->flags)) set_bit(CACHE_NEGATIVE, &tmp->flags); else @@ -199,7 +199,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail, cache_get(tmp); cache_fresh_locked(tmp, new->expiry_time, detail); cache_fresh_locked(old, 0, detail); - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); cache_fresh_unlocked(tmp, detail); cache_fresh_unlocked(old, detail); cache_put(old, detail); @@ -239,7 +239,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h { int rv; - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); rv = cache_is_valid(h); if (rv == -EAGAIN) { set_bit(CACHE_NEGATIVE, &h->flags); @@ -247,7 +247,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h detail); rv = -ENOENT; } - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); cache_fresh_unlocked(h, detail); return rv; } @@ -357,7 +357,7 @@ static struct delayed_work cache_cleaner; void sunrpc_init_cache_detail(struct cache_detail *cd) { - rwlock_init(&cd->hash_lock); + spin_lock_init(&cd->hash_lock); INIT_LIST_HEAD(&cd->queue); spin_lock(&cache_list_lock); cd->nextcheck = 0; @@ -377,11 +377,11 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd) { cache_purge(cd); spin_lock(&cache_list_lock); - write_lock(&cd->hash_lock); + spin_lock(&cd->hash_lock); if (current_detail == cd) current_detail = NULL; list_del_init(&cd->others); - write_unlock(&cd->hash_lock); + spin_unlock(&cd->hash_lock); spin_unlock(&cache_list_lock); if (list_empty(&cache_list)) { /* module must be being unloaded so its safe to kill the worker */ @@ -438,7 +438,7 @@ static int cache_clean(void) struct hlist_head *head; struct hlist_node *tmp; - write_lock(¤t_detail->hash_lock); + spin_lock(¤t_detail->hash_lock); /* Ok, now to clean this strand */ @@ -455,7 +455,7 @@ static int cache_clean(void) break; } - write_unlock(¤t_detail->hash_lock); + spin_unlock(¤t_detail->hash_lock); d = current_detail; if (!ch) current_index ++; @@ -510,9 +510,9 @@ void cache_purge(struct cache_detail *detail) struct hlist_node *tmp = NULL; int i = 0; - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); if (!detail->entries) { - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); return; } @@ -524,13 +524,13 @@ void cache_purge(struct cache_detail *detail) detail->entries--; set_bit(CACHE_CLEANED, &ch->flags); - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); cache_fresh_unlocked(ch, detail); cache_put(ch, detail); - write_lock(&detail->hash_lock); + spin_lock(&detail->hash_lock); } } - write_unlock(&detail->hash_lock); + spin_unlock(&detail->hash_lock); } EXPORT_SYMBOL_GPL(cache_purge); @@ -1873,13 +1873,13 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs); void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h) { - write_lock(&cd->hash_lock); + spin_lock(&cd->hash_lock); if (!hlist_unhashed(&h->cache_list)){ hlist_del_init_rcu(&h->cache_list); cd->entries--; - write_unlock(&cd->hash_lock); + spin_unlock(&cd->hash_lock); cache_put(h, cd); } else - write_unlock(&cd->hash_lock); + spin_unlock(&cd->hash_lock); } EXPORT_SYMBOL_GPL(sunrpc_cache_unhash); -- cgit v1.2.3-71-gd317 From 3ae2cefb613b00d613677c05ffa384b4f660f468 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 1 Oct 2018 14:16:11 -0400 Subject: svcrdma: Increase the default connection credit limit Reduce queuing on clients by allowing more credits by default. 64 is the default NFSv4.1 slot table size on Linux clients. This size prevents the credit limit from putting RPC requests to sleep again after they have already slept waiting for a session slot. Signed-off-by: Chuck Lever Reviewed-by: Sagi Grimberg Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_rdma.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fd78f78df5c6..e6e26918504c 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -113,13 +113,14 @@ struct svcxprt_rdma { /* sc_flags */ #define RDMAXPRT_CONN_PENDING 3 -#define RPCRDMA_LISTEN_BACKLOG 10 -#define RPCRDMA_MAX_REQUESTS 32 - -/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our - * current NFSv4.1 implementation supports one backchannel slot. +/* + * Default connection parameters */ -#define RPCRDMA_MAX_BC_REQUESTS 2 +enum { + RPCRDMA_LISTEN_BACKLOG = 10, + RPCRDMA_MAX_REQUESTS = 64, + RPCRDMA_MAX_BC_REQUESTS = 2, +}; #define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -- cgit v1.2.3-71-gd317 From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:31 +1100 Subject: vfs: check file ranges before cloning files Move the file range checks from vfs_clone_file_prep into a separate generic_remap_checks function so that all the checks are collected in a central location. This forms the basis for adding more checks from generic_write_checks that will make cloning's input checking more consistent with write input checking. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- fs/ocfs2/refcounttree.c | 2 +- fs/read_write.c | 55 ++++++++++----------------------------- fs/xfs/xfs_reflink.c | 2 +- include/linux/fs.h | 9 ++++--- mm/filemap.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 90 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7a5ee145c733..19e03936c5e1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4850,7 +4850,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, &len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/fs/read_write.c b/fs/read_write.c index 260797b01851..d6e8e242a15f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1717,13 +1717,12 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) * Returns: 0 for "nothing to clone", 1 for "something to clone", or * the usual negative error code. */ -int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe) +int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *len, bool is_dedupe) { - loff_t bs = inode_out->i_sb->s_blocksize; - loff_t blen; - loff_t isize; + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; @@ -1740,10 +1739,10 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; - isize = i_size_read(inode_in); - /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { + loff_t isize = i_size_read(inode_in); + if (is_dedupe || pos_in == isize) return 0; if (pos_in > isize) @@ -1751,36 +1750,11 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, *len = isize - pos_in; } - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + *len < pos_in || pos_out + *len < pos_out || - pos_in + *len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + *len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + *len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = *len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode) { - if (pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - } + /* Check that we don't violate system file offset limits. */ + ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, + is_dedupe); + if (ret) + return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); @@ -1813,7 +1787,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, return 1; } -EXPORT_SYMBOL(vfs_clone_file_prep_inodes); +EXPORT_SYMBOL(vfs_clone_file_prep); int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) @@ -1851,9 +1825,6 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - if (pos_in + len > i_size_read(inode_in)) - return -EINVAL; - ret = file_in->f_op->clone_file_range(file_in, pos_in, file_out, pos_out, len); if (!ret) { diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 42ea7bab9144..281d5f53f2ec 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1326,7 +1326,7 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); 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 *); diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..47e6bfd45a91 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2974,6 +2974,75 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) } EXPORT_SYMBOL(generic_write_checks); +/* + * Performs necessary checks before doing a clone. + * + * Can adjust amount of bytes to clone. + * Returns appropriate error code that caller should return or + * zero in case the clone should be allowed. + */ +int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *req_count, bool is_dedupe) +{ + struct inode *inode_in = file_in->f_mapping->host; + struct inode *inode_out = file_out->f_mapping->host; + uint64_t count = *req_count; + uint64_t bcount; + loff_t size_in, size_out; + loff_t bs = inode_out->i_sb->s_blocksize; + + /* The start of both ranges must be aligned to an fs block. */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) + return -EINVAL; + + /* Ensure offsets don't wrap. */ + if (pos_in + count < pos_in || pos_out + count < pos_out) + return -EINVAL; + + size_in = i_size_read(inode_in); + size_out = i_size_read(inode_out); + + /* Dedupe requires both ranges to be within EOF. */ + if (is_dedupe && + (pos_in >= size_in || pos_in + count > size_in || + pos_out >= size_out || pos_out + count > size_out)) + return -EINVAL; + + /* Ensure the infile range is within the infile. */ + if (pos_in >= size_in) + return -EINVAL; + count = min(count, size_in - (uint64_t)pos_in); + + /* + * If the user wanted us to link to the infile's EOF, round up to the + * next block boundary for this check. + * + * Otherwise, make sure the count is also block-aligned, having + * already confirmed the starting offsets' block alignment. + */ + if (pos_in + count == size_in) { + bcount = ALIGN(size_in, bs) - pos_in; + } else { + if (!IS_ALIGNED(count, bs)) + return -EINVAL; + + bcount = count; + } + + /* Don't allow overlapped cloning within the same file. */ + if (inode_in == inode_out && + pos_out + bcount > pos_in && + pos_out < pos_in + bcount) + return -EINVAL; + + /* For now we don't support changing the length. */ + if (*req_count != count) + return -EINVAL; + + return 0; +} + int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) -- cgit v1.2.3-71-gd317 From a83ab01a62e61616ebb8b97f90f568c1214dc10d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:08 +1100 Subject: vfs: rename vfs_clone_file_prep to be more descriptive The vfs_clone_file_prep is a generic function to be called by filesystem implementations only. Rename the prefix to generic_ and make it more clear that it applies to remap operations, not just clones. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- fs/ocfs2/refcounttree.c | 2 +- fs/read_write.c | 8 ++++---- fs/xfs/xfs_reflink.c | 2 +- include/linux/fs.h | 6 +++--- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 19e03936c5e1..36c56dfbe485 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4850,7 +4850,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) goto out_unlock; - ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, &len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/fs/read_write.c b/fs/read_write.c index f5395d8da741..aca75a97a695 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1745,9 +1745,9 @@ static int generic_remap_check_len(struct inode *inode_in, * Returns: 0 for "nothing to clone", 1 for "something to clone", or * the usual negative error code. */ -int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 *len, bool is_dedupe) +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *len, bool is_dedupe) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -1822,7 +1822,7 @@ int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, return 1; } -EXPORT_SYMBOL(vfs_clone_file_prep); +EXPORT_SYMBOL(generic_remap_file_range_prep); int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 281d5f53f2ec..a7757a128a78 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1326,7 +1326,7 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/include/linux/fs.h b/include/linux/fs.h index ba93a6e7dac4..55729e1c2e75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); +extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3-71-gd317 From 2e5dfc99f2e61c42083ba742395e7a7b353513d1 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:21 +1100 Subject: vfs: combine the clone and dedupe into a single remap_file_range Combine the clone_file_range and dedupe_file_range operations into a single remap_file_range file operation dispatch since they're fundamentally the same operation. The differences between the two can be made in the prep functions. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- Documentation/filesystems/porting | 5 +++++ Documentation/filesystems/vfs.txt | 20 +++++++++++------ fs/btrfs/ctree.h | 8 +++---- fs/btrfs/file.c | 3 +-- fs/btrfs/ioctl.c | 45 ++++++++++++++++++++------------------- fs/cifs/cifsfs.c | 22 +++++++++++-------- fs/nfs/nfs4file.c | 10 ++++++--- fs/ocfs2/file.c | 24 +++++++-------------- fs/overlayfs/file.c | 30 +++++++++++++++----------- fs/read_write.c | 18 ++++++++-------- fs/xfs/xfs_file.c | 23 ++++++-------------- include/linux/fs.h | 25 ++++++++++++++++++---- 12 files changed, 127 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 7b7b845c490a..e6d4466268dd 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -622,3 +622,8 @@ in your dentry operations instead. alloc_file_clone(file, flags, ops) does not affect any caller's references. On success you get a new struct file sharing the mount/dentry with the original, on failure - ERR_PTR(). +-- +[mandatory] + ->clone_file_range() and ->dedupe_file_range have been replaced with + ->remap_file_range(). See Documentation/filesystems/vfs.txt for more + information. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index a6c6a8af48a2..6f5babfee27b 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -883,8 +883,9 @@ struct file_operations { unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); }; @@ -960,11 +961,16 @@ otherwise noted. copy_file_range: called by the copy_file_range(2) system call. - clone_file_range: called by the ioctl(2) system call for FICLONERANGE and - FICLONE commands. - - dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE - command. + remap_file_range: called by the ioctl(2) system call for FICLONERANGE and + FICLONE and FIDEDUPERANGE commands to remap file ranges. An + implementation should remap len bytes at pos_in of the source file into + the dest file at pos_out. Implementations must handle callers passing + in len == 0; this means "remap to the end of the source file". The + return value should be zero if all bytes were remapped, or the usual + negative error code if the remapping did not succeed completely. + The remap_flags parameter accepts REMAP_FILE_* flags. If + REMAP_FILE_DEDUP is set then the implementation must only remap if the + requested file ranges have identical contents. fadvise: possibly called by the fadvise64() system call. diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2cddfe7806a4..124a05662fc2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3218,9 +3218,6 @@ void btrfs_get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space); void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_balance_args *bargs); -int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff, - struct file *dst_file, loff_t dst_loff, - u64 olen); /* file.c */ int __init btrfs_auto_defrag_init(void); @@ -3250,8 +3247,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); -int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); +int btrfs_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len, + unsigned int remap_flags); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 2be00e873e92..9a963f061393 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3269,8 +3269,7 @@ const struct file_operations btrfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, #endif - .clone_file_range = btrfs_clone_file_range, - .dedupe_file_range = btrfs_dedupe_file_range, + .remap_file_range = btrfs_remap_file_range, }; void __cold btrfs_auto_defrag_exit(void) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d60b6caf09e8..bfd99c66723e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3627,26 +3627,6 @@ out_unlock: return ret; } -int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff, - struct file *dst_file, loff_t dst_loff, - u64 olen) -{ - struct inode *src = file_inode(src_file); - struct inode *dst = file_inode(dst_file); - u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; - - if (WARN_ON_ONCE(bs < PAGE_SIZE)) { - /* - * Btrfs does not support blocksize < page_size. As a - * result, btrfs_cmp_data() won't correctly handle - * this situation without an update. - */ - return -EINVAL; - } - - return btrfs_extent_same(src, src_loff, olen, dst, dst_loff); -} - static int clone_finish_inode_update(struct btrfs_trans_handle *trans, struct inode *inode, u64 endoff, @@ -4348,9 +4328,30 @@ out_unlock: return ret; } -int btrfs_clone_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len) +int btrfs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len, + unsigned int remap_flags) { + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + + if (remap_flags & REMAP_FILE_DEDUP) { + struct inode *src = file_inode(src_file); + struct inode *dst = file_inode(dst_file); + u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; + + if (WARN_ON_ONCE(bs < PAGE_SIZE)) { + /* + * Btrfs does not support blocksize < page_size. As a + * result, btrfs_cmp_data() won't correctly handle + * this situation without an update. + */ + return -EINVAL; + } + + return btrfs_extent_same(src, off, len, dst, destoff); + } + return btrfs_clone_files(dst_file, src_file, off, len, destoff); } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 7065426b3280..e8144d0dcde2 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -975,8 +975,9 @@ const struct inode_operations cifs_symlink_inode_ops = { .listxattr = cifs_listxattr, }; -static int cifs_clone_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len) +static int cifs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, u64 len, + unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); @@ -986,6 +987,9 @@ static int cifs_clone_file_range(struct file *src_file, loff_t off, unsigned int xid; int rc; + if (remap_flags & ~REMAP_FILE_ADVISORY) + return -EINVAL; + cifs_dbg(FYI, "clone range\n"); xid = get_xid(); @@ -1134,7 +1138,7 @@ const struct file_operations cifs_file_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1153,7 +1157,7 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1172,7 +1176,7 @@ const struct file_operations cifs_file_direct_ops = { .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1191,7 +1195,7 @@ const struct file_operations cifs_file_nobrl_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1209,7 +1213,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1227,7 +1231,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1239,7 +1243,7 @@ const struct file_operations cifs_dir_ops = { .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = generic_file_llseek, .fsync = cifs_dir_fsync, }; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 4288a6ecaf75..ae5780ce41dc 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -180,8 +180,9 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_allocate(filep, offset, len); } -static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, - struct file *dst_file, loff_t dst_off, u64 count) +static int nfs42_remap_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, u64 count, + unsigned int remap_flags) { struct inode *dst_inode = file_inode(dst_file); struct nfs_server *server = NFS_SERVER(dst_inode); @@ -190,6 +191,9 @@ static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, bool same_inode = false; int ret; + if (remap_flags & ~REMAP_FILE_ADVISORY) + return -EINVAL; + /* check alignment w.r.t. clone_blksize */ ret = -EINVAL; if (bs) { @@ -262,7 +266,7 @@ const struct file_operations nfs4_file_operations = { .copy_file_range = nfs4_copy_file_range, .llseek = nfs4_file_llseek, .fallocate = nfs42_fallocate, - .clone_file_range = nfs42_clone_file_range, + .remap_file_range = nfs42_remap_file_range, #else .llseek = nfs_file_llseek, #endif diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9fa35cb6f6e0..0b757a24567c 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2527,24 +2527,18 @@ out: return offset; } -static int ocfs2_file_clone_range(struct file *file_in, +static int ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len) + u64 len, + unsigned int remap_flags) { - return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, false); -} + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; -static int ocfs2_file_dedupe_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) -{ return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, true); + len, remap_flags & REMAP_FILE_DEDUP); } const struct inode_operations ocfs2_file_iops = { @@ -2586,8 +2580,7 @@ const struct file_operations ocfs2_fops = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, - .clone_file_range = ocfs2_file_clone_range, - .dedupe_file_range = ocfs2_file_dedupe_range, + .remap_file_range = ocfs2_remap_file_range, }; const struct file_operations ocfs2_dops = { @@ -2633,8 +2626,7 @@ const struct file_operations ocfs2_fops_no_plocks = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, - .clone_file_range = ocfs2_file_clone_range, - .dedupe_file_range = ocfs2_file_dedupe_range, + .remap_file_range = ocfs2_remap_file_range, }; const struct file_operations ocfs2_dops_no_plocks = { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 986313da0c88..fffb36fd5920 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -489,26 +489,31 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in, OVL_COPY); } -static int ovl_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +static int ovl_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags) { - return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0, - OVL_CLONE); -} + enum ovl_copyop op; + + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + + if (remap_flags & REMAP_FILE_DEDUP) + op = OVL_DEDUPE; + else + op = OVL_CLONE; -static int ovl_dedupe_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) -{ /* * Don't copy up because of a dedupe request, this wouldn't make sense * most of the time (data would be duplicated instead of deduplicated). */ - if (!ovl_inode_upper(file_inode(file_in)) || - !ovl_inode_upper(file_inode(file_out))) + if (op == OVL_DEDUPE && + (!ovl_inode_upper(file_inode(file_in)) || + !ovl_inode_upper(file_inode(file_out)))) return -EPERM; return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0, - OVL_DEDUPE); + op); } const struct file_operations ovl_file_operations = { @@ -525,6 +530,5 @@ const struct file_operations ovl_file_operations = { .compat_ioctl = ovl_compat_ioctl, .copy_file_range = ovl_copy_file_range, - .clone_file_range = ovl_clone_file_range, - .dedupe_file_range = ovl_dedupe_file_range, + .remap_file_range = ovl_remap_file_range, }; diff --git a/fs/read_write.c b/fs/read_write.c index 734c5661fb69..766bdcb381f3 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1588,9 +1588,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * Try cloning first, this is supported by more file systems, and * more efficient if both clone and copy are supported (e.g. NFS). */ - if (file_in->f_op->clone_file_range) { - ret = file_in->f_op->clone_file_range(file_in, pos_in, - file_out, pos_out, len); + if (file_in->f_op->remap_file_range) { + ret = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, len, 0); if (ret == 0) { ret = len; goto done; @@ -1849,7 +1849,7 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, (file_out->f_flags & O_APPEND)) return -EBADF; - if (!file_in->f_op->clone_file_range) + if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; ret = remap_verify_area(file_in, pos_in, len, false); @@ -1860,8 +1860,8 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - ret = file_in->f_op->clone_file_range(file_in, pos_in, - file_out, pos_out, len); + ret = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, len, 0); if (!ret) { fsnotify_access(file_in); fsnotify_modify(file_out); @@ -2006,7 +2006,7 @@ int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, goto out_drop_write; ret = -EINVAL; - if (!dst_file->f_op->dedupe_file_range) + if (!dst_file->f_op->remap_file_range) goto out_drop_write; if (len == 0) { @@ -2014,8 +2014,8 @@ int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, goto out_drop_write; } - ret = dst_file->f_op->dedupe_file_range(src_file, src_pos, - dst_file, dst_pos, len); + ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, + dst_pos, len, REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 61a5ad2600e8..2ad94d508f80 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -920,27 +920,19 @@ out_unlock: } STATIC int -xfs_file_clone_range( +xfs_file_remap_range( struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len) + u64 len, + unsigned int remap_flags) { - return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, false); -} + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; -STATIC int -xfs_file_dedupe_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) -{ return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, true); + len, remap_flags & REMAP_FILE_DEDUP); } STATIC int @@ -1175,8 +1167,7 @@ const struct file_operations xfs_file_operations = { .fsync = xfs_file_fsync, .get_unmapped_area = thp_get_unmapped_area, .fallocate = xfs_file_fallocate, - .clone_file_range = xfs_file_clone_range, - .dedupe_file_range = xfs_file_dedupe_range, + .remap_file_range = xfs_file_remap_range, }; const struct file_operations xfs_dir_file_operations = { diff --git a/include/linux/fs.h b/include/linux/fs.h index 55729e1c2e75..888cef35c7d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1721,6 +1721,24 @@ struct block_device_operations; #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) +/* + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.txt for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + */ +#define REMAP_FILE_DEDUP (1 << 0) + +/* + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. + * There are no flags yet, but subsequent commits will add some. + */ +#define REMAP_FILE_ADVISORY (0) struct iov_iter; @@ -1759,10 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); + int (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; -- cgit v1.2.3-71-gd317 From a91ae49bbaf43910edb09e03fedf26b23875bd52 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:28 +1100 Subject: vfs: pass remap flags to generic_remap_file_range_prep Plumb the remap flags through the filesystem from the vfs function dispatcher all the way to the prep function to prepare for behavior changes in subsequent patches. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/ocfs2/file.c | 2 +- fs/ocfs2/refcounttree.c | 4 ++-- fs/ocfs2/refcounttree.h | 2 +- fs/read_write.c | 14 +++++++------- fs/xfs/xfs_file.c | 2 +- fs/xfs/xfs_reflink.c | 21 +++++++++++---------- fs/xfs/xfs_reflink.h | 3 ++- include/linux/fs.h | 2 +- 8 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0b757a24567c..9809b0e5746f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2538,7 +2538,7 @@ static int ocfs2_remap_file_range(struct file *file_in, return -EINVAL; return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, remap_flags & REMAP_FILE_DEDUP); + len, remap_flags); } const struct inode_operations ocfs2_file_iops = { diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 36c56dfbe485..df9781567ec0 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4825,7 +4825,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, struct file *file_out, loff_t pos_out, u64 len, - bool is_dedupe) + unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -4851,7 +4851,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, goto out_unlock; ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - &len, is_dedupe); + &len, remap_flags); if (ret <= 0) goto out_unlock; diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index 4af55bf4b35b..d2c5f526edff 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -120,6 +120,6 @@ int ocfs2_reflink_remap_range(struct file *file_in, struct file *file_out, loff_t pos_out, u64 len, - bool is_dedupe); + unsigned int remap_flags); #endif /* OCFS2_REFCOUNTTREE_H */ diff --git a/fs/read_write.c b/fs/read_write.c index 766bdcb381f3..201381689284 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1722,14 +1722,14 @@ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, u64 *len, - bool is_dedupe) + unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; if ((*len & blkmask) == 0) return 0; - if (is_dedupe) + if (remap_flags & REMAP_FILE_DEDUP) *len &= ~blkmask; else if (pos_out + *len < i_size_read(inode_out)) return -EINVAL; @@ -1747,7 +1747,7 @@ static int generic_remap_check_len(struct inode *inode_in, */ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, bool is_dedupe) + u64 *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -1771,7 +1771,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, if (*len == 0) { loff_t isize = i_size_read(inode_in); - if (is_dedupe || pos_in == isize) + if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; @@ -1782,7 +1782,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, - is_dedupe); + (remap_flags & REMAP_FILE_DEDUP)); if (ret) return ret; @@ -1804,7 +1804,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, /* * Check that the extents are the same. */ - if (is_dedupe) { + if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; ret = vfs_dedupe_file_range_compare(inode_in, pos_in, @@ -1816,7 +1816,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, } ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, - is_dedupe); + remap_flags); if (ret) return ret; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 2ad94d508f80..20314eb4677a 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -932,7 +932,7 @@ xfs_file_remap_range( return -EINVAL; return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, remap_flags & REMAP_FILE_DEDUP); + len, remap_flags); } STATIC int diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index a7757a128a78..29aab196ce7e 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -921,13 +921,14 @@ xfs_reflink_update_dest( struct xfs_inode *dest, xfs_off_t newlen, xfs_extlen_t cowextsize, - bool is_dedupe) + unsigned int remap_flags) { struct xfs_mount *mp = dest->i_mount; struct xfs_trans *tp; int error; - if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) + if ((remap_flags & REMAP_FILE_DEDUP) && + newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) return 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); @@ -948,7 +949,7 @@ xfs_reflink_update_dest( dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; } - if (!is_dedupe) { + if (!(remap_flags & REMAP_FILE_DEDUP)) { xfs_trans_ichgtime(tp, dest, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); } @@ -1296,7 +1297,7 @@ xfs_reflink_remap_prep( struct file *file_out, loff_t pos_out, u64 *len, - bool is_dedupe) + unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct xfs_inode *src = XFS_I(inode_in); @@ -1327,7 +1328,7 @@ xfs_reflink_remap_prep( goto out_unlock; ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, - len, is_dedupe); + len, remap_flags); if (ret <= 0) goto out_unlock; @@ -1336,7 +1337,7 @@ xfs_reflink_remap_prep( * from the source file so we don't try to dedupe the partial * EOF block. */ - if (is_dedupe) { + if (remap_flags & REMAP_FILE_DEDUP) { *len &= ~blkmask; } else if (*len & blkmask) { /* @@ -1372,7 +1373,7 @@ xfs_reflink_remap_prep( PAGE_ALIGN(pos_out + *len) - 1); /* If we're altering the file contents... */ - if (!is_dedupe) { + if (!(remap_flags & REMAP_FILE_DEDUP)) { /* * ...update the timestamps (which will grab the ilock again * from xfs_fs_dirty_inode, so we have to call it before we @@ -1410,7 +1411,7 @@ xfs_reflink_remap_range( struct file *file_out, loff_t pos_out, u64 len, - bool is_dedupe) + unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct xfs_inode *src = XFS_I(inode_in); @@ -1430,7 +1431,7 @@ xfs_reflink_remap_range( /* Prepare and then clone file data. */ ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out, - &len, is_dedupe); + &len, remap_flags); if (ret <= 0) return ret; @@ -1457,7 +1458,7 @@ xfs_reflink_remap_range( cowextsize = src->i_d.di_cowextsize; ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, - is_dedupe); + remap_flags); out_unlock: xfs_reflink_remap_unlock(file_in, file_out); diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index c585ad9552b2..6f82d628bf17 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -28,7 +28,8 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); + struct file *file_out, loff_t pos_out, u64 len, + unsigned int remap_flags); extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *has_shared); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, diff --git a/include/linux/fs.h b/include/linux/fs.h index 888cef35c7d7..631c28ce1436 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1844,7 +1844,7 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, bool is_dedupe); + u64 *count, unsigned int remap_flags); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, -- cgit v1.2.3-71-gd317 From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:34 +1100 Subject: vfs: pass remap flags to generic_remap_checks Pass the same remap flags to generic_remap_checks for consistency. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/read_write.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index 201381689284..ebcbfc4f2907 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1782,7 +1782,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, - (remap_flags & REMAP_FILE_DEDUP)); + remap_flags); if (ret) return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index 631c28ce1436..c5435ca81132 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int remap_flags); 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 *); diff --git a/mm/filemap.c b/mm/filemap.c index 84b7301e41a0..410dc58f7b16 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks); */ int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *req_count, bool is_dedupe) + uint64_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; @@ -3016,7 +3016,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ - if (is_dedupe && + if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; -- cgit v1.2.3-71-gd317 From 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:49 +1100 Subject: vfs: make remap_file_range functions take and return bytes completed Change the remap_file_range functions to take a number of bytes to operate upon and return the number of bytes they operated on. This is a requirement for allowing fs implementations to return short clone/dedupe results to the user, which will enable us to obey resource limits in a graceful manner. A subsequent patch will enable copy_file_range to signal to the ->clone_file_range implementation that it can handle a short length, which will be returned in the function's return value. For now the short return is not implemented anywhere so the behavior won't change -- either copy_file_range manages to clone the entire range or it tries an alternative. Neither clone ioctl can take advantage of this, alas. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- Documentation/filesystems/vfs.txt | 10 ++++---- fs/btrfs/ctree.h | 6 ++--- fs/btrfs/ioctl.c | 13 +++++++---- fs/cifs/cifsfs.c | 6 ++--- fs/ioctl.c | 10 +++++++- fs/nfs/nfs4file.c | 6 ++--- fs/nfsd/vfs.c | 8 +++++-- fs/ocfs2/file.c | 16 ++++++------- fs/ocfs2/refcounttree.c | 2 +- fs/ocfs2/refcounttree.h | 2 +- fs/overlayfs/copy_up.c | 6 ++--- fs/overlayfs/file.c | 12 +++++----- fs/read_write.c | 49 +++++++++++++++++++++------------------ fs/xfs/xfs_file.c | 9 ++++--- fs/xfs/xfs_reflink.c | 4 ++-- fs/xfs/xfs_reflink.h | 2 +- include/linux/fs.h | 27 +++++++++++---------- mm/filemap.c | 2 +- 18 files changed, 108 insertions(+), 82 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 6f5babfee27b..1bd2919deaca 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -883,9 +883,9 @@ struct file_operations { unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); }; @@ -966,8 +966,8 @@ otherwise noted. implementation should remap len bytes at pos_in of the source file into the dest file at pos_out. Implementations must handle callers passing in len == 0; this means "remap to the end of the source file". The - return value should be zero if all bytes were remapped, or the usual - negative error code if the remapping did not succeed completely. + return value should the number of bytes remapped, or the usual + negative error code if errors occurred before any bytes were remapped. The remap_flags parameter accepts REMAP_FILE_* flags. If REMAP_FILE_DEDUP is set then the implementation must only remap if the requested file ranges have identical contents. diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 124a05662fc2..771a961d77ad 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3247,9 +3247,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); -int btrfs_remap_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, - unsigned int remap_flags); +loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bfd99c66723e..b0c513e10977 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4328,10 +4328,12 @@ out_unlock: return ret; } -int btrfs_remap_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len, +loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; @@ -4349,10 +4351,11 @@ int btrfs_remap_file_range(struct file *src_file, loff_t off, return -EINVAL; } - return btrfs_extent_same(src, off, len, dst, destoff); + ret = btrfs_extent_same(src, off, len, dst, destoff); + } else { + ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); } - - return btrfs_clone_files(dst_file, src_file, off, len, destoff); + return ret < 0 ? ret : len; } static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e8144d0dcde2..5ca71c6c8be2 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -975,8 +975,8 @@ const struct inode_operations cifs_symlink_inode_ops = { .listxattr = cifs_listxattr, }; -static int cifs_remap_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len, +static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); @@ -1029,7 +1029,7 @@ static int cifs_remap_file_range(struct file *src_file, loff_t off, unlock_two_nondirectories(src_inode, target_inode); out: free_xid(xid); - return rc; + return rc < 0 ? rc : len; } ssize_t cifs_file_copychunk_range(unsigned int xid, diff --git a/fs/ioctl.c b/fs/ioctl.c index 2005529af560..72537b68c272 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -223,6 +223,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); + loff_t cloned; int ret; if (!src_file.file) @@ -230,7 +231,14 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; - ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); + cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, + olen); + if (cloned < 0) + ret = cloned; + else if (olen && cloned != olen) + ret = -EINVAL; + else + ret = 0; fdput: fdput(src_file); return ret; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index ae5780ce41dc..46d691ba04bc 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -180,8 +180,8 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_allocate(filep, offset, len); } -static int nfs42_remap_file_range(struct file *src_file, loff_t src_off, - struct file *dst_file, loff_t dst_off, u64 count, +static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, loff_t count, unsigned int remap_flags) { struct inode *dst_inode = file_inode(dst_file); @@ -244,7 +244,7 @@ out_unlock: inode_unlock(src_inode); } out: - return ret; + return ret < 0 ? ret : count; } #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b53e76391e52..ac6cb6101cbe 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -541,8 +541,12 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { - return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, - count)); + loff_t cloned; + + cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count); + if (count && cloned != count) + cloned = -EINVAL; + return nfserrno(cloned < 0 ? cloned : 0); } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9809b0e5746f..fbaeafe44b5f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2527,18 +2527,18 @@ out: return offset; } -static int ocfs2_remap_file_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - unsigned int remap_flags) +static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; - return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, remap_flags); + ret = ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, + len, remap_flags); + return ret < 0 ? ret : len; } const struct inode_operations ocfs2_file_iops = { diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index df9781567ec0..6a42c04ac0ab 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4824,7 +4824,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index d2c5f526edff..eb65c1d0843c 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -119,7 +119,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags); #endif /* OCFS2_REFCOUNTTREE_H */ diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 1cc797a08a5b..8750b7235516 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -125,6 +125,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) struct file *new_file; loff_t old_pos = 0; loff_t new_pos = 0; + loff_t cloned; int error = 0; if (len == 0) @@ -141,11 +142,10 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) } /* Try to use clone_file_range to clone up within the same fs */ - error = do_clone_file_range(old_file, 0, new_file, 0, len); - if (!error) + cloned = do_clone_file_range(old_file, 0, new_file, 0, len); + if (cloned == len) goto out; /* Couldn't clone, so now we try to copy the data */ - error = 0; /* FIXME: copy up sparse files efficiently */ while (len) { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index fffb36fd5920..6c3fec6168e9 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -434,14 +434,14 @@ enum ovl_copyop { OVL_DEDUPE, }; -static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in, +static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, unsigned int flags, enum ovl_copyop op) + loff_t len, unsigned int flags, enum ovl_copyop op) { struct inode *inode_out = file_inode(file_out); struct fd real_in, real_out; const struct cred *old_cred; - ssize_t ret; + loff_t ret; ret = ovl_real_fdget(file_out, &real_out); if (ret) @@ -489,9 +489,9 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in, OVL_COPY); } -static int ovl_remap_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags) +static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { enum ovl_copyop op; diff --git a/fs/read_write.c b/fs/read_write.c index b61bd3fc7154..356641afa487 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1589,10 +1589,13 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * more efficient if both clone and copy are supported (e.g. NFS). */ if (file_in->f_op->remap_file_range) { - ret = file_in->f_op->remap_file_range(file_in, pos_in, - file_out, pos_out, len, 0); - if (ret == 0) { - ret = len; + loff_t cloned; + + cloned = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, + min_t(loff_t, MAX_RW_COUNT, len), 0); + if (cloned > 0) { + ret = cloned; goto done; } } @@ -1686,11 +1689,12 @@ out2: return ret; } -static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write) +static int remap_verify_area(struct file *file, loff_t pos, loff_t len, + bool write) { struct inode *inode = file_inode(file); - if (unlikely(pos < 0)) + if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely((loff_t) (pos + len) < 0)) @@ -1721,7 +1725,7 @@ static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write) static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, - u64 *len, + loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; @@ -1747,7 +1751,7 @@ static int generic_remap_check_len(struct inode *inode_in, */ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, unsigned int remap_flags) + loff_t *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -1843,12 +1847,12 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(generic_remap_file_range_prep); -int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t len) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); - int ret; + loff_t ret; if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; @@ -1881,19 +1885,19 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, 0); - if (!ret) { - fsnotify_access(file_in); - fsnotify_modify(file_out); - } + if (ret < 0) + return ret; + fsnotify_access(file_in); + fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(do_clone_file_range); -int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t len) { - int ret; + loff_t ret; file_start_write(file_out); ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len); @@ -1999,10 +2003,11 @@ out_error: } EXPORT_SYMBOL(vfs_dedupe_file_range_compare); -int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, u64 len) +loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len) { - s64 ret; + loff_t ret; ret = mnt_want_write_file(dst_file); if (ret) @@ -2051,7 +2056,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) int i; int ret; u16 count = same->dest_count; - int deduped; + loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 20314eb4677a..38fde4e11714 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -919,20 +919,23 @@ out_unlock: return error; } -STATIC int +STATIC loff_t xfs_file_remap_range( struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; - return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, + ret = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, remap_flags); + return ret < 0 ? ret : len; } STATIC int diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 2d7dd8b28d7c..3dbe5fb7e9c0 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1296,7 +1296,7 @@ xfs_reflink_remap_prep( loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, + loff_t *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); @@ -1387,7 +1387,7 @@ xfs_reflink_remap_range( loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 6f82d628bf17..c3c46c276fe1 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -28,7 +28,7 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, + struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *has_shared); diff --git a/include/linux/fs.h b/include/linux/fs.h index c5435ca81132..c72d8c3c065a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,9 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, unsigned int remap_flags); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len); struct super_operations { @@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, unsigned int remap_flags); + loff_t *count, unsigned int remap_flags); 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 *); diff --git a/mm/filemap.c b/mm/filemap.c index 410dc58f7b16..e9091d731f84 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks); */ int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *req_count, unsigned int remap_flags) + loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; -- cgit v1.2.3-71-gd317 From 452ce65951a2f0719e4e119ecca134c06cfe22ee Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:56 +1100 Subject: vfs: plumb remap flags through the vfs clone functions Plumb a remap_flags argument through the {do,vfs}_clone_file_range functions so that clone can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- fs/ioctl.c | 2 +- fs/nfsd/vfs.c | 2 +- fs/overlayfs/copy_up.c | 2 +- fs/overlayfs/file.c | 6 +++--- fs/read_write.c | 13 +++++++++---- include/linux/fs.h | 4 ++-- 6 files changed, 17 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/ioctl.c b/fs/ioctl.c index 72537b68c272..505275ec5596 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -232,7 +232,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, - olen); + olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ac6cb6101cbe..726fc5b2b27a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -543,7 +543,7 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, { loff_t cloned; - cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count); + cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); if (count && cloned != count) cloned = -EINVAL; return nfserrno(cloned < 0 ? cloned : 0); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 8750b7235516..5f82fece64a0 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -142,7 +142,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) } /* Try to use clone_file_range to clone up within the same fs */ - cloned = do_clone_file_range(old_file, 0, new_file, 0, len); + cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); if (cloned == len) goto out; /* Couldn't clone, so now we try to copy the data */ diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 6c3fec6168e9..0393815c8971 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -462,7 +462,7 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, case OVL_CLONE: ret = vfs_clone_file_range(real_in.file, pos_in, - real_out.file, pos_out, len); + real_out.file, pos_out, len, flags); break; case OVL_DEDUPE: @@ -512,8 +512,8 @@ static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, !ovl_inode_upper(file_inode(file_out)))) return -EPERM; - return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0, - op); + return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, + remap_flags, op); } const struct file_operations ovl_file_operations = { diff --git a/fs/read_write.c b/fs/read_write.c index 356641afa487..0d1ac1b9bc22 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1848,12 +1848,15 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, EXPORT_SYMBOL(generic_remap_file_range_prep); loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, loff_t len) + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); loff_t ret; + WARN_ON_ONCE(remap_flags); + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) @@ -1884,7 +1887,7 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, return ret; ret = file_in->f_op->remap_file_range(file_in, pos_in, - file_out, pos_out, len, 0); + file_out, pos_out, len, remap_flags); if (ret < 0) return ret; @@ -1895,12 +1898,14 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, EXPORT_SYMBOL(do_clone_file_range); loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, loff_t len) + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { loff_t ret; file_start_write(file_out); - ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len); + ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len, + remap_flags); file_end_write(file_out); return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index c72d8c3c065a..1c5e55d2a67d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1848,10 +1848,10 @@ extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - loff_t len); + loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); -- cgit v1.2.3-71-gd317 From df3658361951e17364f1e1c3fa92862a990ad8bd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:03 +1100 Subject: vfs: plumb remap flags through the vfs dedupe functions Plumb a remap_flags argument through the vfs_dedupe_file_range_one functions so that dedupe can take advantage of it. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- fs/overlayfs/file.c | 3 ++- fs/read_write.c | 9 ++++++--- include/linux/fs.h | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 0393815c8971..84dd957efa24 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -467,7 +467,8 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, case OVL_DEDUPE: ret = vfs_dedupe_file_range_one(real_in.file, pos_in, - real_out.file, pos_out, len); + real_out.file, pos_out, len, + flags); break; } revert_creds(old_cred); diff --git a/fs/read_write.c b/fs/read_write.c index 0d1ac1b9bc22..ea30666013b0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -2010,10 +2010,12 @@ EXPORT_SYMBOL(vfs_dedupe_file_range_compare); loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, - loff_t len) + loff_t len, unsigned int remap_flags) { loff_t ret; + WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP)); + ret = mnt_want_write_file(dst_file); if (ret) return ret; @@ -2044,7 +2046,7 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, } ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, - dst_pos, len, REMAP_FILE_DEDUP); + dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); @@ -2112,7 +2114,8 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) } deduped = vfs_dedupe_file_range_one(file, off, dst_file, - info->dest_offset, len); + info->dest_offset, len, + 0); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) diff --git a/include/linux/fs.h b/include/linux/fs.h index 1c5e55d2a67d..544ab5083b48 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1859,7 +1859,7 @@ extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, - loff_t len); + loff_t len, unsigned int remap_flags); struct super_operations { -- cgit v1.2.3-71-gd317 From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:10 +1100 Subject: vfs: enable remap callers that can handle short operations Plumb in a remap flag that enables the filesystem remap handler to shorten remapping requests for callers that can handle it. Now copy_file_range can report partial success (in case we run up against alignment problems, resource limits, etc.). We also enable CAN_SHORTEN for fideduperange to maintain existing userspace-visible behavior where xfs/btrfs shorten the dedupe range to avoid stale post-eof data exposure. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- Documentation/filesystems/vfs.txt | 4 +++- fs/read_write.c | 28 ++++++++++++++++++++-------- include/linux/fs.h | 5 +++-- mm/filemap.c | 11 +++++++---- 4 files changed, 33 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 1bd2919deaca..5f71a252e2e0 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -970,7 +970,9 @@ otherwise noted. negative error code if errors occurred before any bytes were remapped. The remap_flags parameter accepts REMAP_FILE_* flags. If REMAP_FILE_DEDUP is set then the implementation must only remap if the - requested file ranges have identical contents. + requested file ranges have identical contents. If REMAP_CAN_SHORTEN is + set, the caller is ok with the implementation shortening the request + length to satisfy alignment or EOF requirements (or any other reason). fadvise: possibly called by the fadvise64() system call. diff --git a/fs/read_write.c b/fs/read_write.c index ea30666013b0..c0bcc1a20650 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1593,7 +1593,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, cloned = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, - min_t(loff_t, MAX_RW_COUNT, len), 0); + min_t(loff_t, MAX_RW_COUNT, len), + REMAP_FILE_CAN_SHORTEN); if (cloned > 0) { ret = cloned; goto done; @@ -1721,6 +1722,8 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len, * can't meaningfully compare post-EOF contents. * * For clone we only link a partial EOF block above the destination file's EOF. + * + * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, @@ -1729,16 +1732,24 @@ static int generic_remap_check_len(struct inode *inode_in, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; + loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; - if (remap_flags & REMAP_FILE_DEDUP) - *len &= ~blkmask; - else if (pos_out + *len < i_size_read(inode_out)) - return -EINVAL; + if ((remap_flags & REMAP_FILE_DEDUP) || + pos_out + *len < i_size_read(inode_out)) + new_len &= ~blkmask; - return 0; + if (new_len == *len) + return 0; + + if (remap_flags & REMAP_FILE_CAN_SHORTEN) { + *len = new_len; + return 0; + } + + return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* @@ -2014,7 +2025,8 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, { loff_t ret; - WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP)); + WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | + REMAP_FILE_CAN_SHORTEN)); ret = mnt_want_write_file(dst_file); if (ret) @@ -2115,7 +2127,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) deduped = vfs_dedupe_file_range_one(file, off, dst_file, info->dest_offset, len, - 0); + REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) diff --git a/include/linux/fs.h b/include/linux/fs.h index 544ab5083b48..34c22d695011 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,8 +1727,10 @@ struct block_device_operations; * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of @@ -1736,9 +1738,8 @@ struct block_device_operations; * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. - * There are no flags yet, but subsequent commits will add some. */ -#define REMAP_FILE_ADVISORY (0) +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; diff --git a/mm/filemap.c b/mm/filemap.c index e9091d731f84..1775d4ad3317 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3045,8 +3045,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) - return -EINVAL; - + count = ALIGN_DOWN(count, bs); bcount = count; } @@ -3056,10 +3055,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, pos_out < pos_in + bcount) return -EINVAL; - /* For now we don't support changing the length. */ - if (*req_count != count) + /* + * We shortened the request but the caller can't deal with that, so + * bounce the request back to userspace. + */ + if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; + *req_count = count; return 0; } -- cgit v1.2.3-71-gd317 From c32e5f39953fa6bbff35c655bdcb7b3128f1e79f Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:17 +1100 Subject: vfs: hide file range comparison function There are no callers of vfs_dedupe_file_range_compare, so we might as well make it a static helper and remove the export. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/read_write.c | 187 ++++++++++++++++++++++++++--------------------------- include/linux/fs.h | 3 - 2 files changed, 91 insertions(+), 99 deletions(-) (limited to 'include/linux') diff --git a/fs/read_write.c b/fs/read_write.c index c0bcc1a20650..e4d295d0d236 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1752,6 +1752,97 @@ static int generic_remap_check_len(struct inode *inode_in, return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } +/* + * Read a page's worth of file data into the page cache. Return the page + * locked. + */ +static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) +{ + struct page *page; + + page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL); + if (IS_ERR(page)) + return page; + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-EIO); + } + lock_page(page); + return page; +} + +/* + * Compare extents of two files to see if they are the same. + * Caller must have locked both inodes to prevent write races. + */ +static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same) +{ + loff_t src_poff; + loff_t dest_poff; + void *src_addr; + void *dest_addr; + struct page *src_page; + struct page *dest_page; + loff_t cmp_len; + bool same; + int error; + + error = -EINVAL; + same = true; + while (len) { + src_poff = srcoff & (PAGE_SIZE - 1); + dest_poff = destoff & (PAGE_SIZE - 1); + cmp_len = min(PAGE_SIZE - src_poff, + PAGE_SIZE - dest_poff); + cmp_len = min(cmp_len, len); + if (cmp_len <= 0) + goto out_error; + + src_page = vfs_dedupe_get_page(src, srcoff); + if (IS_ERR(src_page)) { + error = PTR_ERR(src_page); + goto out_error; + } + dest_page = vfs_dedupe_get_page(dest, destoff); + if (IS_ERR(dest_page)) { + error = PTR_ERR(dest_page); + unlock_page(src_page); + put_page(src_page); + goto out_error; + } + src_addr = kmap_atomic(src_page); + dest_addr = kmap_atomic(dest_page); + + flush_dcache_page(src_page); + flush_dcache_page(dest_page); + + if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) + same = false; + + kunmap_atomic(dest_addr); + kunmap_atomic(src_addr); + unlock_page(dest_page); + unlock_page(src_page); + put_page(dest_page); + put_page(src_page); + + if (!same) + break; + + srcoff += cmp_len; + destoff += cmp_len; + len -= cmp_len; + } + + *is_same = same; + return 0; + +out_error: + return error; +} + /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the @@ -1923,102 +2014,6 @@ loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(vfs_clone_file_range); -/* - * Read a page's worth of file data into the page cache. Return the page - * locked. - */ -static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) -{ - struct address_space *mapping; - struct page *page; - pgoff_t n; - - n = offset >> PAGE_SHIFT; - mapping = inode->i_mapping; - page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return page; - if (!PageUptodate(page)) { - put_page(page); - return ERR_PTR(-EIO); - } - lock_page(page); - return page; -} - -/* - * Compare extents of two files to see if they are the same. - * Caller must have locked both inodes to prevent write races. - */ -int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same) -{ - loff_t src_poff; - loff_t dest_poff; - void *src_addr; - void *dest_addr; - struct page *src_page; - struct page *dest_page; - loff_t cmp_len; - bool same; - int error; - - error = -EINVAL; - same = true; - while (len) { - src_poff = srcoff & (PAGE_SIZE - 1); - dest_poff = destoff & (PAGE_SIZE - 1); - cmp_len = min(PAGE_SIZE - src_poff, - PAGE_SIZE - dest_poff); - cmp_len = min(cmp_len, len); - if (cmp_len <= 0) - goto out_error; - - src_page = vfs_dedupe_get_page(src, srcoff); - if (IS_ERR(src_page)) { - error = PTR_ERR(src_page); - goto out_error; - } - dest_page = vfs_dedupe_get_page(dest, destoff); - if (IS_ERR(dest_page)) { - error = PTR_ERR(dest_page); - unlock_page(src_page); - put_page(src_page); - goto out_error; - } - src_addr = kmap_atomic(src_page); - dest_addr = kmap_atomic(dest_page); - - flush_dcache_page(src_page); - flush_dcache_page(dest_page); - - if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) - same = false; - - kunmap_atomic(dest_addr); - kunmap_atomic(src_addr); - unlock_page(dest_page); - unlock_page(src_page); - put_page(dest_page); - put_page(src_page); - - if (!same) - break; - - srcoff += cmp_len; - destoff += cmp_len; - len -= cmp_len; - } - - *is_same = same; - return 0; - -out_error: - return error; -} -EXPORT_SYMBOL(vfs_dedupe_file_range_compare); - loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags) diff --git a/include/linux/fs.h b/include/linux/fs.h index 34c22d695011..346036a84f18 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1853,9 +1853,6 @@ extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); -extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, -- cgit v1.2.3-71-gd317 From 966c37f2d77eb44d47af8e919267b1ba675b2eca Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 26 Oct 2018 11:30:35 +0800 Subject: ipv4/igmp: fix v1/v2 switchback timeout based on rfc3376, 8.12 Similiar with ipv6 mcast commit 89225d1ce6af3 ("net: ipv6: mld: fix v1/v2 switchback timeout to rfc3810, 9.12.") i) RFC3376 8.12. Older Version Querier Present Timeout says: The Older Version Querier Interval is the time-out for transitioning a host back to IGMPv3 mode once an older version query is heard. When an older version query is received, hosts set their Older Version Querier Present Timer to Older Version Querier Interval. This value MUST be ((the Robustness Variable) times (the Query Interval in the last Query received)) plus (one Query Response Interval). Currently we only use a hardcode value IGMP_V1/v2_ROUTER_PRESENT_TIMEOUT. Fix it by adding two new items mr_qi(Query Interval) and mr_qri(Query Response Interval) in struct in_device. Now we can calculate the switchback time via (mr_qrv * mr_qi) + mr_qri. We need update these values when receive IGMPv3 queries. Reported-by: Ying Xu Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 4 +++- net/ipv4/igmp.c | 53 +++++++++++++++++++++++++++++++--------------- 2 files changed, 39 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index c759d1cbcedd..a64f21a97369 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -37,7 +37,9 @@ struct in_device { unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; - unsigned char mr_qrv; + unsigned long mr_qi; /* Query Interval */ + unsigned long mr_qri; /* Query Response Interval */ + unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; unsigned char mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 4da39446da2d..765b2b32c4a4 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -111,13 +111,10 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V1_ROUTER_PRESENT_TIMEOUT (400*HZ) -#define IGMP_V2_ROUTER_PRESENT_TIMEOUT (400*HZ) #define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) #define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) +#define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) -#define IGMP_QUERY_ROBUSTNESS_VARIABLE 2 - #define IGMP_INITIAL_REPORT_DELAY (1) @@ -935,13 +932,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + - IGMP_V1_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + - IGMP_V2_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; } /* cancel the interface change timer */ in_dev->mr_ifc_count = 0; @@ -981,8 +980,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; - if (ih3->qrv) - in_dev->mr_qrv = ih3->qrv; + + /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently + * received value was zero, use the default or statically + * configured value. + */ + in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; + + /* RFC3376, 8.3. Query Response Interval: + * The number of seconds represented by the [Query Response + * Interval] must be less than the [Query Interval]. + */ + if (in_dev->mr_qri >= in_dev->mr_qi) + in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; + if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ @@ -1723,18 +1735,30 @@ void ip_mc_down(struct in_device *in_dev) ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } -void ip_mc_init_dev(struct in_device *in_dev) -{ #ifdef CONFIG_IP_MULTICAST +static void ip_mc_reset(struct in_device *in_dev) +{ struct net *net = dev_net(in_dev->dev); + + in_dev->mr_qi = IGMP_QUERY_INTERVAL; + in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; +} +#else +static void ip_mc_reset(struct in_device *in_dev) +{ +} #endif + +void ip_mc_init_dev(struct in_device *in_dev) +{ ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif + ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1744,15 +1768,10 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); -#ifdef CONFIG_IP_MULTICAST - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; -#endif + ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { -- cgit v1.2.3-71-gd317 From ffb6ce7086ee2d68d8d6d987882f1c5e923fee7e Mon Sep 17 00:00:00 2001 From: Daniel Drake Date: Tue, 9 Oct 2018 14:40:55 +0800 Subject: platform/x86: asus-wmi: export function for evaluating WMI methods Export asus_wmi_evaluate_method() and related headers for use by other drivers. hid-asus is going to use this to avoid advertising that it has a keyboard backlight when the keyboard backlight is controlled via WMI. Signed-off-by: Daniel Drake Signed-off-by: Andy Shevchenko --- drivers/platform/x86/asus-wmi.c | 88 +------------------------ include/linux/platform_data/x86/asus-wmi.h | 101 +++++++++++++++++++++++++++++ 2 files changed, 104 insertions(+), 85 deletions(-) create mode 100644 include/linux/platform_data/x86/asus-wmi.h (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index a805227b31e1..b52b192a4f16 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -69,89 +70,6 @@ MODULE_LICENSE("GPL"); #define NOTIFY_KBD_BRTDWN 0xc5 #define NOTIFY_KBD_BRTTOGGLE 0xc7 -/* WMI Methods */ -#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ -#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ -#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ -#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ -#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ -#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ -#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ -#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ -#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ -#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ -#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ -#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ -#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ -#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ -#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ -#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ -#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ -#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ -#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ -#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ - -#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE - -/* Wireless */ -#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 -#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 -#define ASUS_WMI_DEVID_CWAP 0x00010003 -#define ASUS_WMI_DEVID_WLAN 0x00010011 -#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 -#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 -#define ASUS_WMI_DEVID_GPS 0x00010015 -#define ASUS_WMI_DEVID_WIMAX 0x00010017 -#define ASUS_WMI_DEVID_WWAN3G 0x00010019 -#define ASUS_WMI_DEVID_UWB 0x00010021 - -/* Leds */ -/* 0x000200XX and 0x000400XX */ -#define ASUS_WMI_DEVID_LED1 0x00020011 -#define ASUS_WMI_DEVID_LED2 0x00020012 -#define ASUS_WMI_DEVID_LED3 0x00020013 -#define ASUS_WMI_DEVID_LED4 0x00020014 -#define ASUS_WMI_DEVID_LED5 0x00020015 -#define ASUS_WMI_DEVID_LED6 0x00020016 - -/* Backlight and Brightness */ -#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ -#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 -#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 -#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 -#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ -#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 - -/* Misc */ -#define ASUS_WMI_DEVID_CAMERA 0x00060013 - -/* Storage */ -#define ASUS_WMI_DEVID_CARDREADER 0x00080013 - -/* Input */ -#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 -#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 - -/* Fan, Thermal */ -#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 -#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 - -/* Power */ -#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 - -/* Deep S3 / Resume on LID open */ -#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 - -/* DSTS masks */ -#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 -#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 -#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 -#define ASUS_WMI_DSTS_USER_BIT 0x00020000 -#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 -#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF -#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 -#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F - #define ASUS_FAN_DESC "cpu_fan" #define ASUS_FAN_MFUN 0x13 #define ASUS_FAN_SFUN_READ 0x06 @@ -301,8 +219,7 @@ static void asus_wmi_input_exit(struct asus_wmi *asus) asus->inputdev = NULL; } -static int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, - u32 *retval) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval) { struct bios_args args = { .arg0 = arg0, @@ -338,6 +255,7 @@ exit: return 0; } +EXPORT_SYMBOL_GPL(asus_wmi_evaluate_method); static int asus_wmi_evaluate_method_agfn(const struct acpi_buffer args) { diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h new file mode 100644 index 000000000000..53dfc2541960 --- /dev/null +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_X86_ASUS_WMI_H +#define __PLATFORM_DATA_X86_ASUS_WMI_H + +#include +#include + +/* WMI Methods */ +#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ +#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ +#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ +#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ +#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ +#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ +#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ +#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ +#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ +#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ +#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ +#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ +#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ +#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ +#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ +#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ +#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ +#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ +#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ +#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ + +#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE + +/* Wireless */ +#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 +#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 +#define ASUS_WMI_DEVID_CWAP 0x00010003 +#define ASUS_WMI_DEVID_WLAN 0x00010011 +#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 +#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 +#define ASUS_WMI_DEVID_GPS 0x00010015 +#define ASUS_WMI_DEVID_WIMAX 0x00010017 +#define ASUS_WMI_DEVID_WWAN3G 0x00010019 +#define ASUS_WMI_DEVID_UWB 0x00010021 + +/* Leds */ +/* 0x000200XX and 0x000400XX */ +#define ASUS_WMI_DEVID_LED1 0x00020011 +#define ASUS_WMI_DEVID_LED2 0x00020012 +#define ASUS_WMI_DEVID_LED3 0x00020013 +#define ASUS_WMI_DEVID_LED4 0x00020014 +#define ASUS_WMI_DEVID_LED5 0x00020015 +#define ASUS_WMI_DEVID_LED6 0x00020016 + +/* Backlight and Brightness */ +#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ +#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 +#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 +#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 +#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ +#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 + +/* Misc */ +#define ASUS_WMI_DEVID_CAMERA 0x00060013 + +/* Storage */ +#define ASUS_WMI_DEVID_CARDREADER 0x00080013 + +/* Input */ +#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 +#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 + +/* Fan, Thermal */ +#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 +#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 + +/* Power */ +#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 + +/* Deep S3 / Resume on LID open */ +#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 + +/* DSTS masks */ +#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 +#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 +#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 +#define ASUS_WMI_DSTS_USER_BIT 0x00020000 +#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 +#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF +#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 +#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F + +#if IS_REACHABLE(CONFIG_ASUS_WMI) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval); +#else +static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, + u32 *retval) +{ + return -ENODEV; +} +#endif + +#endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ -- cgit v1.2.3-71-gd317 From f813f21971b96f61a789dd48151f92220fdd2e0a Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:06 -0700 Subject: mm/hmm: fix utf8 ... MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "HMM updates, improvements and fixes", v2 Few fixes that only affect HMM users. Improve the synchronization call back so that we match was other mmu_notifier listener do and add proper support to the new blockable flags in the process. For curious folks here are branches to leverage HMM in various existing device drivers: https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-nouveau-v01 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-radeon-v00 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-intel-v00 More to come (amd gpu, Mellanox, ...) I expect more of the preparatory work for nouveau will be merge in 4.20 (like we have been doing since 4.16) and i will wait until this patchset is upstream before pushing the patches that actualy make use of HMM (to avoid complex tree inter-dependency). This patch (of 6): Somehow utf=8 must have been broken. Link: http://lkml.kernel.org/r/20181019160442.18723-2-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 2 +- mm/hmm.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index dde947083d4e..42b1ae915915 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Heterogeneous Memory Management (HMM) diff --git a/mm/hmm.c b/mm/hmm.c index 774d684fa2b4..de9840f60100 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Refer to include/linux/hmm.h for information about heterogeneous memory -- cgit v1.2.3-71-gd317 From 44532d4c591c10d6907ac5030373bc306617d92b Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:24 -0700 Subject: mm/hmm: use a structure for update callback parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use a structure to gather all the parameters for the update callback. This make it easier when adding new parameters by avoiding having to update all callback function signature. The hmm_update structure is always associated with a mmu_notifier callbacks so we are not planing on grouping multiple updates together. Nor do we care about page size for the range as range will over fully cover the page being invalidated (this is a mmu_notifier property). Link: http://lkml.kernel.org/r/20181019160442.18723-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 31 ++++++++++++++++++++++--------- mm/hmm.c | 33 ++++++++++++++++++++++----------- 2 files changed, 44 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 42b1ae915915..c6fb869a81c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -274,13 +274,28 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, struct hmm_mirror; /* - * enum hmm_update_type - type of update + * enum hmm_update_event - type of update * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) */ -enum hmm_update_type { +enum hmm_update_event { HMM_UPDATE_INVALIDATE, }; +/* + * struct hmm_update - HMM update informations for callback + * + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * @event: event triggering the update (what is happening) + * @blockable: can the callback block/sleep ? + */ +struct hmm_update { + unsigned long start; + unsigned long end; + enum hmm_update_event event; + bool blockable; +}; + /* * struct hmm_mirror_ops - HMM mirror device operations callback * @@ -300,9 +315,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update_type: type of update that occurred to the CPU page table - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update + * @update: update informations (see struct hmm_update) + * Returns: -EAGAIN if update.blockable false and callback need to + * block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -313,10 +328,8 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - enum hmm_update_type update_type, - unsigned long start, - unsigned long end); + int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + const struct hmm_update *update); }; /* diff --git a/mm/hmm.c b/mm/hmm.c index a3d532ff7c3d..b4e9afdc2181 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -126,10 +126,8 @@ void hmm_mm_destroy(struct mm_struct *mm) kfree(mm->hmm); } -static void hmm_invalidate_range(struct hmm *hmm, - enum hmm_update_type action, - unsigned long start, - unsigned long end) +static int hmm_invalidate_range(struct hmm *hmm, + const struct hmm_update *update) { struct hmm_mirror *mirror; struct hmm_range *range; @@ -138,22 +136,30 @@ static void hmm_invalidate_range(struct hmm *hmm, list_for_each_entry(range, &hmm->ranges, list) { unsigned long addr, idx, npages; - if (end < range->start || start >= range->end) + if (update->end < range->start || update->start >= range->end) continue; range->valid = false; - addr = max(start, range->start); + addr = max(update->start, range->start); idx = (addr - range->start) >> PAGE_SHIFT; - npages = (min(range->end, end) - addr) >> PAGE_SHIFT; + npages = (min(range->end, update->end) - addr) >> PAGE_SHIFT; memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages); } spin_unlock(&hmm->lock); down_read(&hmm->mirrors_sem); - list_for_each_entry(mirror, &hmm->mirrors, list) - mirror->ops->sync_cpu_device_pagetables(mirror, action, - start, end); + list_for_each_entry(mirror, &hmm->mirrors, list) { + int ret; + + ret = mirror->ops->sync_cpu_device_pagetables(mirror, update); + if (!update->blockable && ret == -EAGAIN) { + up_read(&hmm->mirrors_sem); + return -EAGAIN; + } + } up_read(&hmm->mirrors_sem); + + return 0; } static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) @@ -202,11 +208,16 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn, unsigned long start, unsigned long end) { + struct hmm_update update; struct hmm *hmm = mm->hmm; VM_BUG_ON(!hmm); - hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end); + update.start = start; + update.end = end; + update.event = HMM_UPDATE_INVALIDATE; + update.blockable = true; + hmm_invalidate_range(hmm, &update); } static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { -- cgit v1.2.3-71-gd317 From 7275b097851a5e2e0dd4da039c7e96b59ac5314e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:04:59 -0700 Subject: linux/bitmap.h: handle constant zero-size bitmaps correctly The static inlines in bitmap.h do not handle a compile-time constant nbits==0 correctly (they dereference the passed src or dst pointers, despite only 0 words being valid to access). I had the 0-day buildbot chew on a patch [1] that would cause build failures for such cases without complaining, suggesting that we don't have any such users currently, at least for the 70 .config/arch combinations that was built. Should any turn up, make sure they use the out-of-line versions, which do handle nbits==0 correctly. This is of course not the most efficient, but it's much less churn than teaching all the static inlines an "if (zero_const_nbits())", and since we don't have any current instances, this doesn't affect existing code at all. [1] lkml.kernel.org/r/20180815085539.27485-1-linux@rasmusvillemoes.dk Link: http://lkml.kernel.org/r/20180818131623.8755-3-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index acf5e8df3504..a9805bacbd7c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -204,8 +204,13 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +/* + * The static inlines below do not handle constant nbits==0 correctly, + * so make such users (should any ever turn up) call the out-of-line + * versions. + */ #define small_const_nbits(nbits) \ - (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG) + (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { -- cgit v1.2.3-71-gd317 From c8cebc553368209426f7279736db4f88f1853396 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:02 -0700 Subject: linux/bitmap.h: remove redundant uses of small_const_nbits() In the _zero, _fill and _copy functions, the small_const_nbits branch is redundant. If nbits is small and const, gcc knows full well that BITS_TO_LONGS(nbits) is 1, so len is also a compile-time constant (sizeof(long)), and calling memset or memcpy with a length argument of sizeof(long) makes gcc generate the expected code anyway: #include void a(unsigned long *x) { memset(x, 0, 8); } void b(unsigned long *x) { memset(x, 0xff, 8); } void c(unsigned long *x, const unsigned long *y) { memcpy(x, y, 8); } turns into 0000000000000000 : 0: 48 c7 07 00 00 00 00 movq $0x0,(%rdi) 7: c3 retq 8: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) f: 00 0000000000000010 : 10: 48 c7 07 ff ff ff ff movq $0xffffffffffffffff,(%rdi) 17: c3 retq 18: 0f 1f 84 00 00 00 00 nopl 0x0(%rax,%rax,1) 1f: 00 0000000000000020 : 20: 48 8b 06 mov (%rsi),%rax 23: 48 89 07 mov %rax,(%rdi) 26: c3 retq Link: http://lkml.kernel.org/r/20180818131623.8755-4-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 24 ++++++------------------ 1 file changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a9805bacbd7c..004cd42a3c4d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -214,33 +214,21 @@ extern int bitmap_print_to_pagebuf(bool list, char *buf, static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = 0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = ~0UL; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0xff, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - if (small_const_nbits(nbits)) - *dst = *src; - else { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memcpy(dst, src, len); - } + unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memcpy(dst, src, len); } /* -- cgit v1.2.3-71-gd317 From d9873969fa8725dc6a5a21ab788c057fd8719751 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:07 -0700 Subject: linux/bitmap.h: fix type of nbits in bitmap_shift_right() Most other bitmap API, including the OOL version __bitmap_shift_right, take unsigned nbits. This was accidentally left out from 2fbad29917c98. Link: http://lkml.kernel.org/r/20180818131623.8755-5-linux@rasmusvillemoes.dk Fixes: 2fbad29917c98 ("lib: bitmap: change bitmap_shift_right to take unsigned parameters") Signed-off-by: Rasmus Villemoes Reported-by: Yury Norov Reviewed-by: Andy Shevchenko Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 004cd42a3c4d..4032680e629d 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -391,7 +391,7 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, - unsigned int shift, int nbits) + unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; -- cgit v1.2.3-71-gd317 From 41e7b1661ffbf562d3aa2b7ce4ad283db50b711a Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Tue, 30 Oct 2018 15:05:10 -0700 Subject: linux/bitmap.h: relax comment on compile-time constant nbits It's not clear what's so horrible about emitting a function call to handle a run-time sized bitmap. Moreover, gcc also emits a function call for a compile-time-constant-but-huge nbits, so the comment isn't even accurate. Link: http://lkml.kernel.org/r/20180818131623.8755-6-linux@rasmusvillemoes.dk Signed-off-by: Rasmus Villemoes Reviewed-by: Andy Shevchenko Cc: Yury Norov Cc: Rasmus Villemoes Cc: Sudeep Holla Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 4032680e629d..f58e97446abc 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -28,8 +28,8 @@ * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * - * Note that nbits should be always a compile time evaluable constant. - * Otherwise many inlines will generate horrible code. + * The generated code is more efficient when nbits is known at + * compile-time and at most BITS_PER_LONG. * * :: * -- cgit v1.2.3-71-gd317 From 7e5ca363a5a1ec42c54dc1e0644b361a2daf984c Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 30 Oct 2018 15:05:42 -0700 Subject: lib/rbtree.c: fix typo in comment of rb_insert_augmented() The function name in the comment is not correct. Link: http://lkml.kernel.org/r/20181010021344.60433-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree_augmented.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index af8a61be2d8d..9510c677ac70 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -51,8 +51,8 @@ extern void __rb_insert_augmented(struct rb_node *node, * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and - * rb_augment_inserted() instead of the usual rb_insert_color() call. - * If rb_augment_inserted() rebalances the rbtree, it will callback into + * rb_insert_augmented() instead of the usual rb_insert_color() call. + * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ -- cgit v1.2.3-71-gd317 From 89976005536c47a788bdd6cef5a4e9fef3c0de32 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:05:49 -0700 Subject: include/linux/compat.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013115048.GA3262@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..06e77473f175 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -488,8 +488,11 @@ put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; + /* fall through */ case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; + /* fall through */ case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; + /* fall through */ case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; -- cgit v1.2.3-71-gd317 From 3819ddec1f8c8a5daf215bec4067f8fd1dc40d6d Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 30 Oct 2018 15:07:10 -0700 Subject: include/linux/signal.h: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. Link: http://lkml.kernel.org/r/20181013114847.GA3160@embeddedor.com Signed-off-by: Gustavo A. R. Silva Acked-by: Kees Cook Reviewed-by: Michael Ellerman Cc: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 200ed96a05af..f428e86f4800 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -129,9 +129,11 @@ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ + /* fall through */ \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ + /* fall through */ \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ @@ -161,7 +163,9 @@ static inline void name(sigset_t *set) \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ + /* fall through */ \ case 2: set->sig[1] = op(set->sig[1]); \ + /* fall through */ \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ @@ -182,6 +186,7 @@ static inline void sigemptyset(sigset_t *set) memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; + /* fall through */ case 1: set->sig[0] = 0; break; } @@ -194,6 +199,7 @@ static inline void sigfillset(sigset_t *set) memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; + /* fall through */ case 1: set->sig[0] = -1; break; } -- cgit v1.2.3-71-gd317 From 69a60bc75fe73511af89328ded1b33bc4a625a5c Mon Sep 17 00:00:00 2001 From: Alexander Pateenok Date: Tue, 30 Oct 2018 15:07:36 -0700 Subject: percpu: remove PER_CPU_DEF_ATTRIBUTES macro The macro is not used: $ grep -r PER_CPU_DEF_ATTRIBUTES include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ include/linux/percpu-defs.h: __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ include/asm-generic/percpu.h:#ifndef PER_CPU_DEF_ATTRIBUTES include/asm-generic/percpu.h:#define PER_CPU_DEF_ATTRIBUTES It was added with b01e8dc34379 ("alpha: fix percpu build breakage") and removed in 2009 with b01e8dc34379..6088464cf1ae. Link: http://lkml.kernel.org/r/20180821164904.qqhcduimjznods66@K55DR.localdomain Signed-off-by: Alexander Pateenok Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/percpu.h | 4 ---- include/linux/percpu-defs.h | 6 ++---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 1817a8415a5e..c2de013b2cf4 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -62,10 +62,6 @@ extern void setup_per_cpu_areas(void); #define PER_CPU_ATTRIBUTES #endif -#ifndef PER_CPU_DEF_ATTRIBUTES -#define PER_CPU_DEF_ATTRIBUTES -#endif - #define raw_cpu_generic_read(pcp) \ ({ \ *raw_cpu_ptr(&(pcp)); \ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 2d2096ba1cfe..1ce8e264a269 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -91,8 +91,7 @@ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ extern __PCPU_ATTRS(sec) __typeof__(type) name; \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ - __typeof__(type) name + __PCPU_ATTRS(sec) __weak __typeof__(type) name #else /* * Normal declaration and definition macros. @@ -101,8 +100,7 @@ extern __PCPU_ATTRS(sec) __typeof__(type) name #define DEFINE_PER_CPU_SECTION(type, name, sec) \ - __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES \ - __typeof__(type) name + __PCPU_ATTRS(sec) __typeof__(type) name #endif /* -- cgit v1.2.3-71-gd317 From b4a991ec584b3ce333342c431c3cc4fef8a690d7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:40 -0700 Subject: mm: remove CONFIG_NO_BOOTMEM All achitectures select NO_BOOTMEM which essentially becomes 'Y' for any kernel configuration and therefore it can be removed. [alexander.h.duyck@linux.intel.com: remove now defunct NO_BOOTMEM from depends list for deferred init] Link: http://lkml.kernel.org/r/20180925201814.3576.15105.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/1536927045-23536-3-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Alexander Duyck Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/um/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 3 --- arch/xtensa/Kconfig | 1 - include/linux/bootmem.h | 36 ++---------------------------------- include/linux/mmzone.h | 5 +---- mm/Kconfig | 4 ---- mm/Makefile | 7 +------ mm/memblock.c | 2 -- 29 files changed, 4 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 620b0a711ee4..04de6be101bc 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -32,7 +32,6 @@ config ALPHA select OLD_SIGSUSPEND select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67 select HAVE_MEMBLOCK - select NO_BOOTMEM help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index e98c6b8e6186..56995f356f69 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -44,7 +44,6 @@ config ARC select HANDLE_DOMAIN_IRQ select IRQ_DOMAIN select MODULES_USE_ELF_RELA - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b8c6062ca0c1..37d4c40f405a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -100,7 +100,6 @@ config ARM select IRQ_FORCED_THREADING select MODULES_USE_ELF_REL select NEED_DMA_MAP_STATE - select NO_BOOTMEM select OF_EARLY_FLATTREE if OF select OF_RESERVED_MEM if OF select OLD_SIGACTION diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 964f682a2b7b..a8f36c7041ff 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -161,7 +161,6 @@ config ARM64 select MULTI_IRQ_HANDLER select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 0a0558567eaa..46966f576249 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -39,7 +39,6 @@ config CSKY select HAVE_MEMBLOCK select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 0b334b671e90..5e89d40be8cd 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -16,7 +16,6 @@ config H8300 select OF_IRQ select OF_EARLY_FLATTREE select HAVE_MEMBLOCK - select NO_BOOTMEM select TIMER_OF select H8300_TMR8 select HAVE_KERNEL_GZIP diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 7b25d7c8fa49..7823f15e17b2 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -23,7 +23,6 @@ config HEXAGON select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM select NEED_SG_DMA_LENGTH select NO_IOPORT_MAP select GENERIC_IOMAP diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8b4a0c1748c0..2bf4ef792f2c 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -28,7 +28,6 @@ config IA64 select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select NO_BOOTMEM select HAVE_VIRT_CPU_ACCOUNTING select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_SG_CHAIN diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index c7b2a8d60a41..26edf2542295 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -29,7 +29,6 @@ config M68K select DMA_DIRECT_OPS if HAS_DMA select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM config CPU_BIG_ENDIAN def_bool y diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 164a4857737a..5c2777bb5555 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -28,7 +28,6 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select NO_BOOTMEM select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 80778b40f8fa..366934157632 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -78,7 +78,6 @@ config MIPS select RTC_LIB select SYSCTL_EXCEPTION_TRACE select VIRT_TO_BUS - select NO_BOOTMEM menu "Machine selection" diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 56992330026a..93c0b587ee23 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -36,7 +36,6 @@ config NDS32 select MODULES_USE_ELF_RELA select OF select OF_EARLY_FLATTREE - select NO_BOOTMEM select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 2df0c57f2833..b01febeb5ce3 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -25,7 +25,6 @@ config NIOS2 select CPU_NO_EFFICIENT_FFS select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM config GENERIC_CSUM def_bool y diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index a655ae280637..cbfaf15f9d70 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -32,7 +32,6 @@ config OPENRISC select HAVE_DEBUG_STACKOVERFLOW select OR1K_PIC select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1 - select NO_BOOTMEM select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_QUEUED_RWLOCKS select OMPIC if SMP diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index f1cd12afd943..7418ebeeb4a4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -16,7 +16,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select HAVE_MEMBLOCK - select NO_BOOTMEM select BUG select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e84943d24e5c..5798ffb1379b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -231,7 +231,6 @@ config PPC select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_SG_DMA_LENGTH - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index fe451348ae57..f7c6b7cf124a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -35,7 +35,6 @@ config RISCV select HAVE_GENERIC_DMA_COHERENT select HAVE_PERF_EVENTS select IRQ_DOMAIN - select NO_BOOTMEM select RISCV_ISA_A if SMP select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8b25e1f45b27..c7af83a15b2d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -175,7 +175,6 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select MODULES_USE_ELF_RELA - select NO_BOOTMEM select OLD_SIGACTION select OLD_SIGSUSPEND3 select SPARSE_IRQ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 475d786a65b0..7aaea9690e18 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -11,7 +11,6 @@ config SUPERH select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select NO_BOOTMEM select ARCH_DISCARD_MEMBLOCK select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 7e2aa59fcc29..98c0996f3c2c 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -46,7 +46,6 @@ config SPARC select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH select HAVE_MEMBLOCK - select NO_BOOTMEM config SPARC32 def_bool !64BIT diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 10c15b8853ae..ce3d56299b28 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -13,7 +13,6 @@ config UML select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK select HAVE_MEMBLOCK - select NO_BOOTMEM select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 0c5111b206bd..3a3b40f79558 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -6,7 +6,6 @@ config UNICORE32 select ARCH_MIGHT_HAVE_PC_SERIO select DMA_DIRECT_OPS select HAVE_MEMBLOCK - select NO_BOOTMEM select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ffebfc3f43c1..0354f52ef30e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -834,9 +834,6 @@ config JAILHOUSE_GUEST endif #HYPERVISOR_GUEST -config NO_BOOTMEM - def_bool y - source "arch/x86/Kconfig.cpu" config HPET_TIMER diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index ea5d8d03e53b..df43d2e76842 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -34,7 +34,6 @@ config XTENSA select HAVE_STACKPROTECTOR select IRQ_DOMAIN select MODULES_USE_ELF_RELA - select NO_BOOTMEM select PERF_USE_VMALLOC select VIRT_TO_BUS help diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 42515195d7d8..1f005b5c1555 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,34 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#ifndef CONFIG_NO_BOOTMEM -/** - * struct bootmem_data - per-node information used by the bootmem allocator - * @node_min_pfn: the starting physical address of the node's memory - * @node_low_pfn: the end physical address of the directly addressable memory - * @node_bootmem_map: is a bitmap pointer - the bits represent all physical - * memory pages (including holes) on the node. - * @last_end_off: the offset within the page of the end of the last allocation; - * if 0, the page used is full - * @hint_idx: the PFN of the page used with the last allocation; - * together with using this with the @last_end_offset field, - * a test can be made to see if allocations can be merged - * with the page used for the last allocation rather than - * using up a full new page. - * @list: list entry in the linked list ordered by the memory addresses - */ -typedef struct bootmem_data { - unsigned long node_min_pfn; - unsigned long node_low_pfn; - void *node_bootmem_map; - unsigned long last_end_off; - unsigned long hint_idx; - struct list_head list; -} bootmem_data_t; - -extern bootmem_data_t bootmem_node_data[]; -#endif - extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem_node(pg_data_t *pgdat, @@ -125,12 +97,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long align, unsigned long goal) __malloc; -#ifdef CONFIG_NO_BOOTMEM /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -#else -#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) -#endif #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL @@ -165,7 +133,7 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#if defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) +#if defined(CONFIG_HAVE_MEMBLOCK) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 @@ -373,7 +341,7 @@ static inline void __init memblock_free_late( { free_bootmem_late(base, size); } -#endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */ +#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f0caccd5833..847705a6d0ec 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -633,9 +633,6 @@ typedef struct pglist_data { struct page_ext *node_page_ext; #endif #endif -#ifndef CONFIG_NO_BOOTMEM - struct bootmem_data *bdata; -#endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, node_present_pages @@ -869,7 +866,7 @@ static inline int is_highmem_idx(enum zone_type idx) } /** - * is_highmem - helper function to quickly check if a struct zone is a + * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable diff --git a/mm/Kconfig b/mm/Kconfig index 02301a89089e..f7cb608f9ab2 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -142,9 +142,6 @@ config HAVE_GENERIC_GUP config ARCH_DISCARD_MEMBLOCK bool -config NO_BOOTMEM - bool - config MEMORY_ISOLATION bool @@ -634,7 +631,6 @@ config MAX_STACK_SIZE_MB config DEFERRED_STRUCT_PAGE_INIT bool "Defer initialisation of struct pages to kthreads" default n - depends on NO_BOOTMEM depends on SPARSEMEM depends on !NEED_PER_CPU_KM depends on 64BIT diff --git a/mm/Makefile b/mm/Makefile index 6485d5745dd7..ea5333886593 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -42,12 +42,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ debug.o $(mmu-y) obj-y += init-mm.o - -ifdef CONFIG_NO_BOOTMEM - obj-y += nobootmem.o -else - obj-y += bootmem.o -endif +obj-y += nobootmem.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o diff --git a/mm/memblock.c b/mm/memblock.c index a85315083b5a..d6897fbe021f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1318,7 +1318,6 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -#if defined(CONFIG_NO_BOOTMEM) /** * memblock_virt_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes @@ -1524,7 +1523,6 @@ void * __init memblock_virt_alloc_try_nid( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr); return NULL; } -#endif /** * __memblock_free_early - free boot memory block -- cgit v1.2.3-71-gd317 From aca52c39838910605b1063a2243f553aa2a02d5c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:44 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK All architecures use memblock for early memory management. There is no need for the CONFIG_HAVE_MEMBLOCK configuration option. [rppt@linux.vnet.ibm.com: of/fdt: fixup #ifdefs] Link: http://lkml.kernel.org/r/20180919103457.GA20545@rapoport-lnx [rppt@linux.vnet.ibm.com: csky: fixups after bootmem removal] Link: http://lkml.kernel.org/r/20180926112744.GC4628@rapoport-lnx [rppt@linux.vnet.ibm.com: remove stale #else and the code it protects] Link: http://lkml.kernel.org/r/1538067825-24835-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1536927045-23536-4-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Tested-by: Jonathan Cameron Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/c6x/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/csky/kernel/setup.c | 1 - arch/csky/mm/highmem.c | 4 +- arch/csky/mm/init.c | 3 +- arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/um/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - drivers/of/fdt.c | 21 ------- drivers/of/of_reserved_mem.c | 13 +---- drivers/staging/android/ion/Kconfig | 2 +- fs/pstore/Kconfig | 1 - include/linux/bootmem.h | 112 ------------------------------------ include/linux/memblock.h | 7 --- include/linux/mm.h | 2 +- lib/Kconfig.debug | 3 +- mm/Kconfig | 5 +- mm/Makefile | 2 +- mm/nobootmem.c | 4 -- mm/page_alloc.c | 5 +- 40 files changed, 11 insertions(+), 199 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 04de6be101bc..5b4f88363453 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -31,7 +31,6 @@ config ALPHA select ODD_RT_SIGACTION select OLD_SIGSUSPEND select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67 - select HAVE_MEMBLOCK help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 56995f356f69..c9e2a1323536 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -37,7 +37,6 @@ config ARC select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_MEMBLOCK select HAVE_MOD_ARCH_SPECIFIC select HAVE_OPROFILE select HAVE_PERF_EVENTS diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 37d4c40f405a..91be74d8df65 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -82,7 +82,6 @@ config ARM select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M select HAVE_KRETPROBES if (HAVE_KPROBES) - select HAVE_MEMBLOCK select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPROFILE if (HAVE_PERF_EVENTS) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a8f36c7041ff..787d7850e064 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -139,7 +139,6 @@ config ARM64 select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP if NUMA select HAVE_NMI select HAVE_PATA_PLATFORM diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index f65a084607fd..84420109113d 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -13,7 +13,6 @@ config C6X select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select SPARSE_IRQ select IRQ_DOMAIN select OF diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 46966f576249..cb64f8dacd08 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -36,7 +36,6 @@ config CSKY select HAVE_C_RECORDMCOUNT select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS - select HAVE_MEMBLOCK select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES select OF diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index a5e3ab1d5360..dff8b89444ec 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -3,7 +3,6 @@ #include #include -#include #include #include #include diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index e168ac087ccb..53b1bfa4c462 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include @@ -140,7 +140,7 @@ static void __init fixrange_init(unsigned long start, unsigned long end, pmd = (pmd_t *)pud; for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { if (pmd_none(*pmd)) { - pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(pte))); BUG_ON(pte != pte_offset_kernel(pmd, 0)); } diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index ce2711e050ad..dc07c078f9b8 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -47,7 +46,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 5e89d40be8cd..d19c6b16cd5d 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -15,7 +15,6 @@ config H8300 select OF select OF_IRQ select OF_EARLY_FLATTREE - select HAVE_MEMBLOCK select TIMER_OF select H8300_TMR8 select HAVE_KERNEL_GZIP diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 7823f15e17b2..2b688af379e6 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -21,7 +21,6 @@ config HEXAGON select GENERIC_IRQ_SHOW select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK select NEED_SG_DMA_LENGTH select NO_IOPORT_MAP diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 2bf4ef792f2c..36773def6920 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -26,7 +26,6 @@ config IA64 select HAVE_FUNCTION_TRACER select TTY select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING select ARCH_HAS_DMA_MARK_CLEAN diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 26edf2542295..1bc9f1ba759a 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -27,7 +27,6 @@ config M68K select OLD_SIGSUSPEND3 select OLD_SIGACTION select DMA_DIRECT_OPS if HAS_DMA - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK config CPU_BIG_ENDIAN diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 5c2777bb5555..effed2efd306 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -28,7 +28,6 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE select IRQ_DOMAIN diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 366934157632..8272ea4c7264 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -60,7 +60,6 @@ config MIPS select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 93c0b587ee23..7a04adacb2f0 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -29,7 +29,6 @@ config NDS32 select HANDLE_DOMAIN_IRQ select HAVE_ARCH_TRACEHOOK select HAVE_DEBUG_KMEMLEAK - select HAVE_MEMBLOCK select HAVE_REGS_AND_STACK_ACCESS_API select IRQ_DOMAIN select LOCKDEP_SUPPORT diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index b01febeb5ce3..7e95506e957a 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -23,7 +23,6 @@ config NIOS2 select SPARSE_IRQ select USB_ARCH_HAS_HCD if USB_SUPPORT select CPU_NO_EFFICIENT_FFS - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK config GENERIC_CSUM diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index cbfaf15f9d70..285f7d05c8ed 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -12,7 +12,6 @@ config OPENRISC select OF_EARLY_FLATTREE select IRQ_DOMAIN select HANDLE_DOMAIN_IRQ - select HAVE_MEMBLOCK select GPIOLIB select HAVE_ARCH_TRACEHOOK select SPARSE_IRQ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7418ebeeb4a4..92a339ee28b3 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -15,7 +15,6 @@ config PARISC select RTC_CLASS select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE - select HAVE_MEMBLOCK select BUG select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5798ffb1379b..2d51b2bd4aa1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -206,7 +206,6 @@ config PPC select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f7c6b7cf124a..d86842c21710 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -28,7 +28,6 @@ config RISCV select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_CONTIGUOUS select HAVE_FUTEX_CMPXCHG if FUTEX diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c7af83a15b2d..5173366af8f3 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -163,7 +163,6 @@ config S390 select HAVE_LIVEPATCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 7aaea9690e18..f82a4da7adf3 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -9,7 +9,6 @@ config SUPERH select CLKDEV_LOOKUP select DMA_DIRECT_OPS select HAVE_IDE if HAS_IOPORT_MAP - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select ARCH_DISCARD_MEMBLOCK select HAVE_OPROFILE diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 98c0996f3c2c..490b2c95c212 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -45,7 +45,6 @@ config SPARC select LOCKDEP_SMALL if LOCKDEP select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH - select HAVE_MEMBLOCK config SPARC32 def_bool !64BIT diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ce3d56299b28..6b9938919f0b 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -12,7 +12,6 @@ config UML select HAVE_UID16 select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK - select HAVE_MEMBLOCK select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 3a3b40f79558..a4c05159dca5 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -5,7 +5,6 @@ config UNICORE32 select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select DMA_DIRECT_OPS - select HAVE_MEMBLOCK select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0354f52ef30e..c51c989c19c0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -169,7 +169,6 @@ config X86 select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index df43d2e76842..60c141af222b 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -28,7 +28,6 @@ config XTENSA select HAVE_FUTEX_CMPXCHG if !MMU select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_MEMBLOCK select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_STACKPROTECTOR diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 76c83c1ffeda..4f915cea6f75 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1115,7 +1115,6 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, return 1; } -#ifdef CONFIG_HAVE_MEMBLOCK #ifndef MIN_MEMBLOCK_ADDR #define MIN_MEMBLOCK_ADDR __pa(PAGE_OFFSET) #endif @@ -1178,26 +1177,6 @@ int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, return memblock_reserve(base, size); } -#else -void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) -{ - WARN_ON(1); -} - -int __init __weak early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size) -{ - return -ENOSYS; -} - -int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, - phys_addr_t size, bool nomap) -{ - pr_err("Reserved memory not supported, ignoring range %pa - %pa%s\n", - &base, &size, nomap ? " (nomap)" : ""); - return -ENOSYS; -} -#endif - static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { return memblock_virt_alloc(size, align); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 895c83e0c7b6..d6255c276a41 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -20,13 +20,12 @@ #include #include #include +#include #define MAX_RESERVED_REGIONS 32 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS]; static int reserved_mem_count; -#if defined(CONFIG_HAVE_MEMBLOCK) -#include int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap, phys_addr_t *res_base) @@ -54,16 +53,6 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, return memblock_remove(base, size); return 0; } -#else -int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, - phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap, - phys_addr_t *res_base) -{ - pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n", - size, nomap ? " (nomap)" : ""); - return -ENOSYS; -} -#endif /** * res_mem_save_node() - save fdt node for second pass initialization diff --git a/drivers/staging/android/ion/Kconfig b/drivers/staging/android/ion/Kconfig index c16dd16afe6a..0fdda6f62953 100644 --- a/drivers/staging/android/ion/Kconfig +++ b/drivers/staging/android/ion/Kconfig @@ -1,6 +1,6 @@ menuconfig ION bool "Ion Memory Manager" - depends on HAVE_MEMBLOCK && HAS_DMA && MMU + depends on HAS_DMA && MMU select GENERIC_ALLOCATOR select DMA_SHARED_BUFFER help diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 503086f7f7c1..0d19d191ae70 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -141,7 +141,6 @@ config PSTORE_RAM tristate "Log panic/oops to a RAM buffer" depends on PSTORE depends on HAS_IOMEM - depends on HAVE_MEMBLOCK select REED_SOLOMON select REED_SOLOMON_ENC8 select REED_SOLOMON_DEC8 diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 1f005b5c1555..ee61ac355104 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -132,9 +132,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) - -#if defined(CONFIG_HAVE_MEMBLOCK) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) @@ -234,115 +231,6 @@ static inline void __init memblock_free_late( __memblock_free_late(base, size); } -#else - -#define BOOTMEM_ALLOC_ACCESSIBLE 0 - - -/* Fall back to all the existing bootmem APIs */ -static inline void * __init memblock_virt_alloc( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low_nopanic(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return __alloc_bootmem_nopanic(size, align, min_addr); -} - -static inline void * __init memblock_virt_alloc_node( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node(NODE_DATA(nid), size, SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return __alloc_bootmem_node_high(NODE_DATA(nid), size, align, - min_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_raw( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_nopanic( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - free_bootmem_node(NODE_DATA(nid), base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem_late(base, size); -} -#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2acdd046df2d..224d27363cca 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,7 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. * @@ -440,12 +439,6 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } #endif -#else -static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) -{ - return 0; -} -#endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1e52b8fd1685..fcf9cc9d535f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2163,7 +2163,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e0ba05e6f6bd..1af29b8224fd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1292,7 +1292,7 @@ config DEBUG_KOBJECT depends on DEBUG_KERNEL help If you say Y here, some extra kobject debugging messages will be sent - to the syslog. + to the syslog. config DEBUG_KOBJECT_RELEASE bool "kobject release debugging" @@ -1980,7 +1980,6 @@ endif # RUNTIME_TESTING_MENU config MEMTEST bool "Memtest" - depends on HAVE_MEMBLOCK ---help--- This option adds a kernel parameter 'memtest', which allows memtest to be set. diff --git a/mm/Kconfig b/mm/Kconfig index f7cb608f9ab2..d85e39da47ae 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -127,9 +127,6 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. -config HAVE_MEMBLOCK - bool - config HAVE_MEMBLOCK_NODE_MAP bool @@ -478,7 +475,7 @@ config FRONTSWAP config CMA bool "Contiguous Memory Allocator" - depends on HAVE_MEMBLOCK && MMU + depends on MMU select MIGRATION select MEMORY_ISOLATION help diff --git a/mm/Makefile b/mm/Makefile index ea5333886593..ca3c844d7a56 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -43,11 +43,11 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ obj-y += init-mm.o obj-y += nobootmem.o +obj-y += memblock.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif -obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o swap_slots.o obj-$(CONFIG_FRONTSWAP) += frontswap.o diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 439af3b765a7..d4d0cd474087 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -23,10 +23,6 @@ #include "internal.h" -#ifndef CONFIG_HAVE_MEMBLOCK -#error CONFIG_HAVE_MEMBLOCK not defined -#endif - #ifndef CONFIG_NEED_MULTIPLE_NODES struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 863d46da6586..59d171f84445 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6508,8 +6508,7 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) - +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* * Zero all valid struct pages in range [spfn, epfn), return number of struct * pages zeroed @@ -6569,7 +6568,7 @@ void __init zero_resv_unavail(void) if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); } -#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ +#endif /* !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -- cgit v1.2.3-71-gd317 From 355c45affca7114ab510e296a5b7012943aeea17 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:50 -0700 Subject: mm: remove bootmem allocator implementation. All architectures have been converted to use MEMBLOCK + NO_BOOTMEM. The bootmem allocator implementation can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-5-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 16 - mm/bootmem.c | 811 ------------------------------------------------ 2 files changed, 827 deletions(-) delete mode 100644 mm/bootmem.c (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ee61ac355104..fce6278a1724 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,14 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long bootmem_bootmap_pages(unsigned long); - -extern unsigned long init_bootmem_node(pg_data_t *pgdat, - unsigned long freepfn, - unsigned long startpfn, - unsigned long endpfn); -extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); - extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); @@ -55,14 +47,6 @@ extern void free_bootmem_late(unsigned long physaddr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -extern int reserve_bootmem(unsigned long addr, - unsigned long size, - int flags); -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); diff --git a/mm/bootmem.c b/mm/bootmem.c deleted file mode 100644 index 97db0e8e362b..000000000000 --- a/mm/bootmem.c +++ /dev/null @@ -1,811 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bootmem - A boot-time physical memory allocator and configurator - * - * Copyright (C) 1999 Ingo Molnar - * 1999 Kanoj Sarcar, SGI - * 2008 Johannes Weiner - * - * Access to this subsystem has to be serialized externally (which is true - * for the boot process anyway). - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -/** - * DOC: bootmem overview - * - * Bootmem is a boot-time physical memory allocator and configurator. - * - * It is used early in the boot process before the page allocator is - * set up. - * - * Bootmem is based on the most basic of allocators, a First Fit - * allocator which uses a bitmap to represent memory. If a bit is 1, - * the page is allocated and 0 if unallocated. To satisfy allocations - * of sizes smaller than a page, the allocator records the Page Frame - * Number (PFN) of the last allocation and the offset the allocation - * ended at. Subsequent small allocations are merged together and - * stored on the same page. - * - * The information used by the bootmem allocator is represented by - * :c:type:`struct bootmem_data`. An array to hold up to %MAX_NUMNODES - * such structures is statically allocated and then it is discarded - * when the system initialization completes. Each entry in this array - * corresponds to a node with memory. For UMA systems only entry 0 is - * used. - * - * The bootmem allocator is initialized during early architecture - * specific setup. Each architecture is required to supply a - * :c:func:`setup_arch` function which, among other tasks, is - * responsible for acquiring the necessary parameters to initialise - * the boot memory allocator. These parameters define limits of usable - * physical memory: - * - * * @min_low_pfn - the lowest PFN that is available in the system - * * @max_low_pfn - the highest PFN that may be addressed by low - * memory (%ZONE_NORMAL) - * * @max_pfn - the last PFN available to the system. - * - * After those limits are determined, the :c:func:`init_bootmem` or - * :c:func:`init_bootmem_node` function should be called to initialize - * the bootmem allocator. The UMA case should use the `init_bootmem` - * function. It will initialize ``contig_page_data`` structure that - * represents the only memory node in the system. In the NUMA case the - * `init_bootmem_node` function should be called to initialize the - * bootmem allocator for each node. - * - * Once the allocator is set up, it is possible to use either single - * node or NUMA variant of the allocation APIs. - */ - -#ifndef CONFIG_NEED_MULTIPLE_NODES -struct pglist_data __refdata contig_page_data = { - .bdata = &bootmem_node_data[0] -}; -EXPORT_SYMBOL(contig_page_data); -#endif - -unsigned long max_low_pfn; -unsigned long min_low_pfn; -unsigned long max_pfn; -unsigned long long max_possible_pfn; - -bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata; - -static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list); - -static int bootmem_debug; - -static int __init bootmem_debug_setup(char *buf) -{ - bootmem_debug = 1; - return 0; -} -early_param("bootmem_debug", bootmem_debug_setup); - -#define bdebug(fmt, args...) ({ \ - if (unlikely(bootmem_debug)) \ - pr_info("bootmem::%s " fmt, \ - __func__, ## args); \ -}) - -static unsigned long __init bootmap_bytes(unsigned long pages) -{ - unsigned long bytes = DIV_ROUND_UP(pages, BITS_PER_BYTE); - - return ALIGN(bytes, sizeof(long)); -} - -/** - * bootmem_bootmap_pages - calculate bitmap size in pages - * @pages: number of pages the bitmap has to represent - * - * Return: the number of pages needed to hold the bitmap. - */ -unsigned long __init bootmem_bootmap_pages(unsigned long pages) -{ - unsigned long bytes = bootmap_bytes(pages); - - return PAGE_ALIGN(bytes) >> PAGE_SHIFT; -} - -/* - * link bdata in order - */ -static void __init link_bootmem(bootmem_data_t *bdata) -{ - bootmem_data_t *ent; - - list_for_each_entry(ent, &bdata_list, list) { - if (bdata->node_min_pfn < ent->node_min_pfn) { - list_add_tail(&bdata->list, &ent->list); - return; - } - } - - list_add_tail(&bdata->list, &bdata_list); -} - -/* - * Called once to set up the allocator itself. - */ -static unsigned long __init init_bootmem_core(bootmem_data_t *bdata, - unsigned long mapstart, unsigned long start, unsigned long end) -{ - unsigned long mapsize; - - mminit_validate_memmodel_limits(&start, &end); - bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart)); - bdata->node_min_pfn = start; - bdata->node_low_pfn = end; - link_bootmem(bdata); - - /* - * Initially all pages are reserved - setup_arch() has to - * register free RAM areas explicitly. - */ - mapsize = bootmap_bytes(end - start); - memset(bdata->node_bootmem_map, 0xff, mapsize); - - bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n", - bdata - bootmem_node_data, start, mapstart, end, mapsize); - - return mapsize; -} - -/** - * init_bootmem_node - register a node as boot memory - * @pgdat: node to register - * @freepfn: pfn where the bitmap for this node is to be placed - * @startpfn: first pfn on the node - * @endpfn: first pfn after the node - * - * Return: the number of bytes needed to hold the bitmap for this node. - */ -unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn, - unsigned long startpfn, unsigned long endpfn) -{ - return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn); -} - -/** - * init_bootmem - register boot memory - * @start: pfn where the bitmap is to be placed - * @pages: number of available physical pages - * - * Return: the number of bytes needed to hold the bitmap. - */ -unsigned long __init init_bootmem(unsigned long start, unsigned long pages) -{ - max_low_pfn = pages; - min_low_pfn = start; - return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages); -} - -void __init free_bootmem_late(unsigned long physaddr, unsigned long size) -{ - unsigned long cursor, end; - - kmemleak_free_part_phys(physaddr, size); - - cursor = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); - totalram_pages++; - } -} - -static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) -{ - struct page *page; - unsigned long *map, start, end, pages, cur, count = 0; - - if (!bdata->node_bootmem_map) - return 0; - - map = bdata->node_bootmem_map; - start = bdata->node_min_pfn; - end = bdata->node_low_pfn; - - bdebug("nid=%td start=%lx end=%lx\n", - bdata - bootmem_node_data, start, end); - - while (start < end) { - unsigned long idx, vec; - unsigned shift; - - idx = start - bdata->node_min_pfn; - shift = idx & (BITS_PER_LONG - 1); - /* - * vec holds at most BITS_PER_LONG map bits, - * bit 0 corresponds to start. - */ - vec = ~map[idx / BITS_PER_LONG]; - - if (shift) { - vec >>= shift; - if (end - start >= BITS_PER_LONG) - vec |= ~map[idx / BITS_PER_LONG + 1] << - (BITS_PER_LONG - shift); - } - /* - * If we have a properly aligned and fully unreserved - * BITS_PER_LONG block of pages in front of us, free - * it in one go. - */ - if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) { - int order = ilog2(BITS_PER_LONG); - - __free_pages_bootmem(pfn_to_page(start), start, order); - count += BITS_PER_LONG; - start += BITS_PER_LONG; - } else { - cur = start; - - start = ALIGN(start + 1, BITS_PER_LONG); - while (vec && cur != start) { - if (vec & 1) { - page = pfn_to_page(cur); - __free_pages_bootmem(page, cur, 0); - count++; - } - vec >>= 1; - ++cur; - } - } - } - - cur = bdata->node_min_pfn; - page = virt_to_page(bdata->node_bootmem_map); - pages = bdata->node_low_pfn - bdata->node_min_pfn; - pages = bootmem_bootmap_pages(pages); - count += pages; - while (pages--) - __free_pages_bootmem(page++, cur++, 0); - bdata->node_bootmem_map = NULL; - - bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count); - - return count; -} - -static int reset_managed_pages_done __initdata; - -void reset_node_managed_pages(pg_data_t *pgdat) -{ - struct zone *z; - - for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) - z->managed_pages = 0; -} - -void __init reset_all_zones_managed_pages(void) -{ - struct pglist_data *pgdat; - - if (reset_managed_pages_done) - return; - - for_each_online_pgdat(pgdat) - reset_node_managed_pages(pgdat); - - reset_managed_pages_done = 1; -} - -unsigned long __init free_all_bootmem(void) -{ - unsigned long total_pages = 0; - bootmem_data_t *bdata; - - reset_all_zones_managed_pages(); - - list_for_each_entry(bdata, &bdata_list, list) - total_pages += free_all_bootmem_core(bdata); - - totalram_pages += total_pages; - - return total_pages; -} - -static void __init __free(bootmem_data_t *bdata, - unsigned long sidx, unsigned long eidx) -{ - unsigned long idx; - - bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data, - sidx + bdata->node_min_pfn, - eidx + bdata->node_min_pfn); - - if (WARN_ON(bdata->node_bootmem_map == NULL)) - return; - - if (bdata->hint_idx > sidx) - bdata->hint_idx = sidx; - - for (idx = sidx; idx < eidx; idx++) - if (!test_and_clear_bit(idx, bdata->node_bootmem_map)) - BUG(); -} - -static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx, - unsigned long eidx, int flags) -{ - unsigned long idx; - int exclusive = flags & BOOTMEM_EXCLUSIVE; - - bdebug("nid=%td start=%lx end=%lx flags=%x\n", - bdata - bootmem_node_data, - sidx + bdata->node_min_pfn, - eidx + bdata->node_min_pfn, - flags); - - if (WARN_ON(bdata->node_bootmem_map == NULL)) - return 0; - - for (idx = sidx; idx < eidx; idx++) - if (test_and_set_bit(idx, bdata->node_bootmem_map)) { - if (exclusive) { - __free(bdata, sidx, idx); - return -EBUSY; - } - bdebug("silent double reserve of PFN %lx\n", - idx + bdata->node_min_pfn); - } - return 0; -} - -static int __init mark_bootmem_node(bootmem_data_t *bdata, - unsigned long start, unsigned long end, - int reserve, int flags) -{ - unsigned long sidx, eidx; - - bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n", - bdata - bootmem_node_data, start, end, reserve, flags); - - BUG_ON(start < bdata->node_min_pfn); - BUG_ON(end > bdata->node_low_pfn); - - sidx = start - bdata->node_min_pfn; - eidx = end - bdata->node_min_pfn; - - if (reserve) - return __reserve(bdata, sidx, eidx, flags); - else - __free(bdata, sidx, eidx); - return 0; -} - -static int __init mark_bootmem(unsigned long start, unsigned long end, - int reserve, int flags) -{ - unsigned long pos; - bootmem_data_t *bdata; - - pos = start; - list_for_each_entry(bdata, &bdata_list, list) { - int err; - unsigned long max; - - if (pos < bdata->node_min_pfn || - pos >= bdata->node_low_pfn) { - BUG_ON(pos != start); - continue; - } - - max = min(bdata->node_low_pfn, end); - - err = mark_bootmem_node(bdata, pos, max, reserve, flags); - if (reserve && err) { - mark_bootmem(start, pos, 0, 0); - return err; - } - - if (max == end) - return 0; - pos = bdata->node_low_pfn; - } - BUG(); -} - -void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size) -{ - unsigned long start, end; - - kmemleak_free_part_phys(physaddr, size); - - start = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - mark_bootmem_node(pgdat->bdata, start, end, 0, 0); -} - -void __init free_bootmem(unsigned long physaddr, unsigned long size) -{ - unsigned long start, end; - - kmemleak_free_part_phys(physaddr, size); - - start = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - mark_bootmem(start, end, 0, 0); -} - -/** - * reserve_bootmem_node - mark a page range as reserved - * @pgdat: node the range resides on - * @physaddr: starting address of the range - * @size: size of the range in bytes - * @flags: reservation flags (see linux/bootmem.h) - * - * Partial pages will be reserved. - * - * The range must reside completely on the specified node. - * - * Return: 0 on success, -errno on failure. - */ -int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size, int flags) -{ - unsigned long start, end; - - start = PFN_DOWN(physaddr); - end = PFN_UP(physaddr + size); - - return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); -} - -/** - * reserve_bootmem - mark a page range as reserved - * @addr: starting address of the range - * @size: size of the range in bytes - * @flags: reservation flags (see linux/bootmem.h) - * - * Partial pages will be reserved. - * - * The range must be contiguous but may span node boundaries. - * - * Return: 0 on success, -errno on failure. - */ -int __init reserve_bootmem(unsigned long addr, unsigned long size, - int flags) -{ - unsigned long start, end; - - start = PFN_DOWN(addr); - end = PFN_UP(addr + size); - - return mark_bootmem(start, end, 1, flags); -} - -static unsigned long __init align_idx(struct bootmem_data *bdata, - unsigned long idx, unsigned long step) -{ - unsigned long base = bdata->node_min_pfn; - - /* - * Align the index with respect to the node start so that the - * combination of both satisfies the requested alignment. - */ - - return ALIGN(base + idx, step) - base; -} - -static unsigned long __init align_off(struct bootmem_data *bdata, - unsigned long off, unsigned long align) -{ - unsigned long base = PFN_PHYS(bdata->node_min_pfn); - - /* Same as align_idx for byte offsets */ - - return ALIGN(base + off, align) - base; -} - -static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - unsigned long fallback = 0; - unsigned long min, max, start, sidx, midx, step; - - bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n", - bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT, - align, goal, limit); - - BUG_ON(!size); - BUG_ON(align & (align - 1)); - BUG_ON(limit && goal + size > limit); - - if (!bdata->node_bootmem_map) - return NULL; - - min = bdata->node_min_pfn; - max = bdata->node_low_pfn; - - goal >>= PAGE_SHIFT; - limit >>= PAGE_SHIFT; - - if (limit && max > limit) - max = limit; - if (max <= min) - return NULL; - - step = max(align >> PAGE_SHIFT, 1UL); - - if (goal && min < goal && goal < max) - start = ALIGN(goal, step); - else - start = ALIGN(min, step); - - sidx = start - bdata->node_min_pfn; - midx = max - bdata->node_min_pfn; - - if (bdata->hint_idx > sidx) { - /* - * Handle the valid case of sidx being zero and still - * catch the fallback below. - */ - fallback = sidx + 1; - sidx = align_idx(bdata, bdata->hint_idx, step); - } - - while (1) { - int merge; - void *region; - unsigned long eidx, i, start_off, end_off; -find_block: - sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx); - sidx = align_idx(bdata, sidx, step); - eidx = sidx + PFN_UP(size); - - if (sidx >= midx || eidx > midx) - break; - - for (i = sidx; i < eidx; i++) - if (test_bit(i, bdata->node_bootmem_map)) { - sidx = align_idx(bdata, i, step); - if (sidx == i) - sidx += step; - goto find_block; - } - - if (bdata->last_end_off & (PAGE_SIZE - 1) && - PFN_DOWN(bdata->last_end_off) + 1 == sidx) - start_off = align_off(bdata, bdata->last_end_off, align); - else - start_off = PFN_PHYS(sidx); - - merge = PFN_DOWN(start_off) < sidx; - end_off = start_off + size; - - bdata->last_end_off = end_off; - bdata->hint_idx = PFN_UP(end_off); - - /* - * Reserve the area now: - */ - if (__reserve(bdata, PFN_DOWN(start_off) + merge, - PFN_UP(end_off), BOOTMEM_EXCLUSIVE)) - BUG(); - - region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) + - start_off); - memset(region, 0, size); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(region, size, 0, 0); - return region; - } - - if (fallback) { - sidx = align_idx(bdata, fallback - 1, step); - fallback = 0; - goto find_block; - } - - return NULL; -} - -static void * __init alloc_bootmem_core(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - bootmem_data_t *bdata; - void *region; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); - - list_for_each_entry(bdata, &bdata_list, list) { - if (goal && bdata->node_low_pfn <= PFN_DOWN(goal)) - continue; - if (limit && bdata->node_min_pfn >= PFN_DOWN(limit)) - break; - - region = alloc_bootmem_bdata(bdata, size, align, goal, limit); - if (region) - return region; - } - - return NULL; -} - -static void * __init ___alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - -restart: - ptr = alloc_bootmem_core(size, align, goal, limit); - if (ptr) - return ptr; - if (goal) { - goal = 0; - goto restart; - } - - return NULL; -} - -void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = 0; - - return ___alloc_bootmem_nopanic(size, align, goal, limit); -} - -static void * __init ___alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit); - - if (mem) - return mem; - /* - * Whoops, we cannot satisfy the allocation request. - */ - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -void * __init __alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = 0; - - return ___alloc_bootmem(size, align, goal, limit); -} - -void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *ptr; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); -again: - - /* do not panic in alloc_bootmem_bdata() */ - if (limit && goal + size > limit) - limit = 0; - - ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); - if (ptr) - return ptr; - - ptr = alloc_bootmem_core(size, align, goal, limit); - if (ptr) - return ptr; - - if (goal) { - goal = 0; - goto again; - } - - return NULL; -} - -void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); -} - -void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal, - unsigned long limit) -{ - void *ptr; - - ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); - if (ptr) - return ptr; - - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, 0); -} - -void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ -#ifdef MAX_DMA32_PFN - unsigned long end_pfn; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - /* update goal according ...MAX_DMA32_PFN */ - end_pfn = pgdat_end_pfn(pgdat); - - if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) && - (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) { - void *ptr; - unsigned long new_goal; - - new_goal = MAX_DMA32_PFN << PAGE_SHIFT; - ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, - new_goal, 0); - if (ptr) - return ptr; - } -#endif - - return __alloc_bootmem_node(pgdat, size, align, goal); - -} - -void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); -} - -void * __init __alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem_nopanic(size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} - -void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, - goal, ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3-71-gd317 From b146ada221c178a384fee2a8e2e5b2e8a04476b1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:54 -0700 Subject: mm: nobootmem: remove dead code Several bootmem functions and macros are not used. Remove them. Link: http://lkml.kernel.org/r/1536927045-23536-6-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 26 -------------------------- mm/nobootmem.c | 35 ----------------------------------- 2 files changed, 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index fce6278a1724..b74bafd110b9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,17 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -/* - * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, - * the architecture-specific code should honor this). - * - * If flags is BOOTMEM_DEFAULT, then the return value is always 0 (success). - * If flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the memory - * already was reserved. - */ -#define BOOTMEM_DEFAULT 0 -#define BOOTMEM_EXCLUSIVE (1<<0) - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); @@ -73,13 +62,6 @@ void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal) __malloc; -void *__alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -92,8 +74,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_nopanic(x) \ @@ -104,17 +84,11 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages_nopanic(x) \ - __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) -#define alloc_bootmem_low_pages_node(pgdat, x) \ - __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 diff --git a/mm/nobootmem.c b/mm/nobootmem.c index d4d0cd474087..44ce7de1be8f 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -404,38 +404,3 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, { return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } - -void * __init __alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem_nopanic(size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} - -/** - * __alloc_bootmem_low_node - allocate low boot memory from a specific node - * @pgdat: node to allocate from - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may fall back to any node in the system if the specified node - * can not hold the requested memory. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3-71-gd317 From 9a8dd708d547268c899f1cb443c49bd4d8c84eb3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:59 -0700 Subject: memblock: rename memblock_alloc{_nid,_try_nid} to memblock_phys_alloc* Make it explicit that the caller gets a physical address rather than a virtual one. This will also allow using meblock_alloc prefix for memblock allocations returning virtual address, which is done in the following patches. The conversion is done using the following semantic patch: @@ expression e1, e2, e3; @@ ( - memblock_alloc(e1, e2) + memblock_phys_alloc(e1, e2) | - memblock_alloc_nid(e1, e2, e3) + memblock_phys_alloc_nid(e1, e2, e3) | - memblock_alloc_try_nid(e1, e2, e3) + memblock_phys_alloc_try_nid(e1, e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-7-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/mmu.c | 2 +- arch/arm64/mm/mmu.c | 2 +- arch/arm64/mm/numa.c | 2 +- arch/c6x/mm/dma-coherent.c | 4 ++-- arch/nds32/mm/init.c | 8 ++++---- arch/openrisc/mm/init.c | 2 +- arch/openrisc/mm/ioremap.c | 2 +- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 +--- arch/powerpc/kernel/paca.c | 2 +- arch/powerpc/kernel/prom.c | 2 +- arch/powerpc/kernel/setup-common.c | 3 +-- arch/powerpc/kernel/setup_32.c | 10 +++++----- arch/powerpc/mm/numa.c | 2 +- arch/powerpc/mm/pgtable_32.c | 2 +- arch/powerpc/mm/ppc_mmu_32.c | 2 +- arch/powerpc/platforms/pasemi/iommu.c | 2 +- arch/powerpc/platforms/powernv/opal.c | 2 +- arch/powerpc/sysdev/dart_iommu.c | 2 +- arch/s390/kernel/crash_dump.c | 2 +- arch/s390/kernel/setup.c | 3 ++- arch/s390/mm/vmem.c | 4 ++-- arch/s390/numa/numa.c | 2 +- arch/sparc/kernel/mdesc.c | 2 +- arch/sparc/kernel/prom_64.c | 2 +- arch/sparc/mm/init_64.c | 11 ++++++----- arch/unicore32/mm/mmu.c | 2 +- arch/x86/mm/numa.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- include/linux/memblock.h | 6 +++--- mm/memblock.c | 8 ++++---- 30 files changed, 50 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e46a6a446cdd..f5cc1ccfea3d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -721,7 +721,7 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc_aligned(unsigned long sz, unsigned long align) { - void *ptr = __va(memblock_alloc(sz, align)); + void *ptr = __va(memblock_phys_alloc(sz, align)); memset(ptr, 0, sz); return ptr; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9498c15b847b..394b8d554def 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -101,7 +101,7 @@ static phys_addr_t __init early_pgtable_alloc(void) phys_addr_t phys; void *ptr; - phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); /* * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index d7b66fc5e1c5..c7fb34efd23e 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -237,7 +237,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) if (start_pfn >= end_pfn) pr_info("Initmem setup node %d []\n", nid); - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); /* report and initialize */ diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c index d0a8e0c4b27e..01305c787201 100644 --- a/arch/c6x/mm/dma-coherent.c +++ b/arch/c6x/mm/dma-coherent.c @@ -135,8 +135,8 @@ void __init coherent_mem_init(phys_addr_t start, u32 size) if (dma_size & (PAGE_SIZE - 1)) ++dma_pages; - bitmap_phys = memblock_alloc(BITS_TO_LONGS(dma_pages) * sizeof(long), - sizeof(long)); + bitmap_phys = memblock_phys_alloc(BITS_TO_LONGS(dma_pages) * sizeof(long), + sizeof(long)); dma_bitmap = phys_to_virt(bitmap_phys); memset(dma_bitmap, 0, dma_pages * PAGE_SIZE); diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index c713d2ad55dc..5af81b866aa5 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -81,7 +81,7 @@ static void __init map_ram(void) } /* Alloc one page for holding PTE's... */ - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(pte, 0, PAGE_SIZE); set_pmd(pme, __pmd(__pa(pte) + _PAGE_KERNEL_TABLE)); @@ -114,7 +114,7 @@ static void __init fixedrange_init(void) pgd = swapper_pg_dir + pgd_index(vaddr); pud = pud_offset(pgd, vaddr); pmd = pmd_offset(pud, vaddr); - fixmap_pmd_p = (pmd_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + fixmap_pmd_p = (pmd_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(fixmap_pmd_p, 0, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(fixmap_pmd_p) + _PAGE_KERNEL_TABLE)); @@ -127,7 +127,7 @@ static void __init fixedrange_init(void) pgd = swapper_pg_dir + pgd_index(vaddr); pud = pud_offset(pgd, vaddr); pmd = pmd_offset(pud, vaddr); - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(pte, 0, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(pte) + _PAGE_KERNEL_TABLE)); pkmap_page_table = pte; @@ -153,7 +153,7 @@ void __init paging_init(void) fixedrange_init(); /* allocate space for empty_zero_page */ - zero_page = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + zero_page = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(zero_page, 0, PAGE_SIZE); zone_sizes_init(); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 6972d5d6f23f..b7670de26c11 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -106,7 +106,7 @@ static void __init map_ram(void) } /* Alloc one page for holding PTE's... */ - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); set_pmd(pme, __pmd(_KERNPG_TABLE + __pa(pte))); /* Fill the newly allocated page with PTE'S */ diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 2175e4bfd9fc..c9697529b3f0 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -126,7 +126,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm, if (likely(mem_init_done)) { pte = (pte_t *) __get_free_page(GFP_KERNEL); } else { - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); } if (pte) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index f432054234a4..8be3721d9302 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1008,9 +1008,7 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char /* Count and allocate space for cpu features */ of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes, &nr_dt_cpu_features); - dt_cpu_features = __va( - memblock_alloc(sizeof(struct dt_cpu_feature)* - nr_dt_cpu_features, PAGE_SIZE)); + dt_cpu_features = __va(memblock_phys_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE)); cpufeatures_setup_start(isa); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0ee3e6d50f28..f331a0054b3a 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -198,7 +198,7 @@ void __init allocate_paca_ptrs(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; - paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0)); + paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, 0)); memset(paca_ptrs, 0x88, paca_ptrs_size); } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index c4d7078e5295..fe758cedb93f 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -126,7 +126,7 @@ static void __init move_device_tree(void) if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { - p = __va(memblock_alloc(size, PAGE_SIZE)); + p = __va(memblock_phys_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = p; DBG("Moved device tree to 0x%p\n", p); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9ca9db707bcb..2b56d1f30387 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -460,8 +460,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32), - __alignof__(u32))); + cpu_to_phys_id = __va(memblock_phys_alloc(nr_cpu_ids * sizeof(u32), __alignof__(u32))); memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32)); for_each_node_by_type(dn, "cpu") { diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 8c507be12c3c..81909600013a 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -206,9 +206,9 @@ void __init irqstack_early_init(void) * as the memblock is limited to lowmem by default */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); hardirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); } } @@ -227,12 +227,12 @@ void __init exc_lvl_early_init(void) #endif critirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE dbgirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); mcheckirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); #endif } } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 693ae1c1acba..f04f15f9d232 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -788,7 +788,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) void *nd; int tnid; - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); /* report and initialize */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 5877f5aa8f5d..bda3c6f1bd32 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -50,7 +50,7 @@ __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) if (slab_is_available()) { pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); } else { - pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) clear_page(pte); } diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 38a793bfca37..f6f575bae3bc 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -224,7 +224,7 @@ void __init MMU_init_hw(void) * Find some memory for the hash table. */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); - Hash = __va(memblock_alloc(Hash_size, Hash_size)); + Hash = __va(memblock_phys_alloc(Hash_size, Hash_size)); memset(Hash, 0, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index f06c83f321e6..f2971522fb4a 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -213,7 +213,7 @@ static int __init iob_init(struct device_node *dn) pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base); /* Allocate a spare page to map all invalid IOTLB pages. */ - tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); + tmp = memblock_phys_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); if (!tmp) panic("IOBMAP: Cannot allocate spare page!"); /* Empty l1 is marked invalid */ diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index a4641515956f..beed86f4224b 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -171,7 +171,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, /* * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64))); + mc_recoverable_range =__va(memblock_phys_alloc(size, __alignof__(u64))); memset(mc_recoverable_range, 0, size); for (i = 0; i < mc_recoverable_range_len; i++) { diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 5ca3e22d0512..a5b40d1460f1 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -261,7 +261,7 @@ static void allocate_dart(void) * that to work around what looks like a problem with the HT bridge * prefetching into invalid pages and corrupting data */ - tmp = memblock_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); + tmp = memblock_phys_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) & DARTMAP_RPNMASK); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 376f6b6dfb3c..d17566a8c76f 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -61,7 +61,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) { struct save_area *sa; - sa = (void *) memblock_alloc(sizeof(*sa), 8); + sa = (void *) memblock_phys_alloc(sizeof(*sa), 8); if (is_boot_cpu) list_add(&sa->list, &dump_save_areas); else diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a2e952b66248..204ccfa54bf3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -967,7 +967,8 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); + vmms = (struct sysinfo_3_2_2 *) memblock_phys_alloc(PAGE_SIZE, + PAGE_SIZE); if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); memblock_free((unsigned long) vmms, PAGE_SIZE); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index db55561c5981..04638b0b9ef1 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -36,7 +36,7 @@ static void __ref *vmem_alloc_pages(unsigned int order) if (slab_is_available()) return (void *)__get_free_pages(GFP_KERNEL, order); - return (void *) memblock_alloc(size, size); + return (void *) memblock_phys_alloc(size, size); } void *vmem_crst_alloc(unsigned long val) @@ -57,7 +57,7 @@ pte_t __ref *vmem_pte_alloc(void) if (slab_is_available()) pte = (pte_t *) page_table_alloc(&init_mm); else - pte = (pte_t *) memblock_alloc(size, size); + pte = (pte_t *) memblock_phys_alloc(size, size); if (!pte) return NULL; memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 5bd374491f94..297f5d8b0890 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -64,7 +64,7 @@ static __init pg_data_t *alloc_node_data(void) { pg_data_t *res; - res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8); + res = (pg_data_t *) memblock_phys_alloc(sizeof(pg_data_t), 8); memset(res, 0, sizeof(pg_data_t)); return res; } diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 39a2503fa3e1..59131e72ee78 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -170,7 +170,7 @@ static struct mdesc_handle * __init mdesc_memblock_alloc(unsigned int mdesc_size mdesc_size); alloc_size = PAGE_ALIGN(handle_size); - paddr = memblock_alloc(alloc_size, PAGE_SIZE); + paddr = memblock_phys_alloc(alloc_size, PAGE_SIZE); hp = NULL; if (paddr) { diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index baeaeed64993..c37955d127fe 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -34,7 +34,7 @@ void * __init prom_early_alloc(unsigned long size) { - unsigned long paddr = memblock_alloc(size, SMP_CACHE_BYTES); + unsigned long paddr = memblock_phys_alloc(size, SMP_CACHE_BYTES); void *ret; if (!paddr) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 39822f611c01..b338f0440f6b 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1092,7 +1092,8 @@ static void __init allocate_node_data(int nid) #ifdef CONFIG_NEED_MULTIPLE_NODES unsigned long paddr; - paddr = memblock_alloc_try_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid); + paddr = memblock_phys_alloc_try_nid(sizeof(struct pglist_data), + SMP_CACHE_BYTES, nid); if (!paddr) { prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); prom_halt(); @@ -1266,8 +1267,8 @@ static int __init grab_mlgroups(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = memblock_alloc(count * sizeof(struct mdesc_mlgroup), - SMP_CACHE_BYTES); + paddr = memblock_phys_alloc(count * sizeof(struct mdesc_mlgroup), + SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; @@ -1307,8 +1308,8 @@ static int __init grab_mblocks(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = memblock_alloc(count * sizeof(struct mdesc_mblock), - SMP_CACHE_BYTES); + paddr = memblock_phys_alloc(count * sizeof(struct mdesc_mblock), + SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c index 0c94b7b4514d..18b355a20f0b 100644 --- a/arch/unicore32/mm/mmu.c +++ b/arch/unicore32/mm/mmu.c @@ -144,7 +144,7 @@ static void __init build_mem_type_table(void) static void __init *early_alloc(unsigned long sz) { - void *ptr = __va(memblock_alloc(sz, sz)); + void *ptr = __va(memblock_phys_alloc(sz, sz)); memset(ptr, 0, sz); return ptr; } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fa150855647c..16e37d712ffd 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -196,7 +196,7 @@ static void __init alloc_node_data(int nid) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, MEMBLOCK_ALLOC_ACCESSIBLE); diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 5fc70520e04c..ef618bceb79a 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,7 +15,7 @@ static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) { - return memblock_alloc(size, 0); + return memblock_phys_alloc(size, 0); } static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 224d27363cca..9d46a7204975 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -300,10 +300,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); +phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); /* * Set the allocation direction to bottom-up or top-down. diff --git a/mm/memblock.c b/mm/memblock.c index d6897fbe021f..20358374e8a8 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1269,7 +1269,7 @@ phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags); } -phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t ret; @@ -1304,14 +1304,14 @@ phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys return alloc; } -phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) +phys_addr_t __init memblock_phys_alloc(phys_addr_t size, phys_addr_t align) { return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { - phys_addr_t res = memblock_alloc_nid(size, align, nid); + phys_addr_t res = memblock_phys_alloc_nid(size, align, nid); if (res) return res; -- cgit v1.2.3-71-gd317 From eb31d559f1e8390195372cd51cfb198da8bc84b9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:04 -0700 Subject: memblock: remove _virt from APIs returning virtual address The conversion is done using sed -i 's@memblock_virt_alloc@memblock_alloc@g' \ $(git grep -l memblock_virt_alloc) Link: http://lkml.kernel.org/r/1536927045-23536-8-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/setup.c | 4 ++-- arch/arm/mach-omap2/omap_hwmod.c | 6 ++--- arch/arm64/mm/kasan_init.c | 2 +- arch/arm64/mm/numa.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/pci_32.c | 2 +- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/mmu_context_nohash.c | 6 ++--- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 6 ++--- arch/powerpc/platforms/ps3/setup.c | 2 +- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/s390/kernel/setup.c | 8 +++---- arch/s390/kernel/smp.c | 2 +- arch/s390/kernel/topology.c | 4 ++-- arch/s390/numa/mode_emu.c | 2 +- arch/s390/numa/toptree.c | 2 +- arch/x86/mm/kasan_init_64.c | 4 ++-- arch/xtensa/mm/kasan_init.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/of/fdt.c | 2 +- drivers/of/unittest.c | 2 +- include/linux/bootmem.h | 38 +++++++++++++++---------------- init/main.c | 6 ++--- kernel/dma/swiotlb.c | 6 ++--- kernel/power/snapshot.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/cpumask.c | 2 +- mm/hugetlb.c | 2 +- mm/kasan/kasan_init.c | 2 +- mm/memblock.c | 26 ++++++++++----------- mm/page_alloc.c | 8 +++---- mm/page_ext.c | 2 +- mm/percpu.c | 28 +++++++++++------------ mm/sparse-vmemmap.c | 2 +- mm/sparse.c | 12 +++++----- 37 files changed, 105 insertions(+), 105 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 4c249cb261f3..39e6090d23ac 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -857,7 +857,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) */ boot_alias_start = phys_to_idmap(start); if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { - res = memblock_virt_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), 0); res->name = "System RAM (boot alias)"; res->start = boot_alias_start; res->end = phys_to_idmap(end); @@ -865,7 +865,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&iomem_resource, res); } - res = memblock_virt_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), 0); res->name = "System RAM"; res->start = start; res->end = end; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 56a1fe90d394..1f9b34a7eccd 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -726,7 +726,7 @@ static int __init _setup_clkctrl_provider(struct device_node *np) u64 size; int i; - provider = memblock_virt_alloc(sizeof(*provider), 0); + provider = memblock_alloc(sizeof(*provider), 0); if (!provider) return -ENOMEM; @@ -736,12 +736,12 @@ static int __init _setup_clkctrl_provider(struct device_node *np) of_property_count_elems_of_size(np, "reg", sizeof(u32)) / 2; provider->addr = - memblock_virt_alloc(sizeof(void *) * provider->num_addrs, 0); + memblock_alloc(sizeof(void *) * provider->num_addrs, 0); if (!provider->addr) return -ENOMEM; provider->size = - memblock_virt_alloc(sizeof(u32) * provider->num_addrs, 0); + memblock_alloc(sizeof(u32) * provider->num_addrs, 0); if (!provider->size) return -ENOMEM; diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index fccb1a6f8c6f..6a65a2912d36 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -38,7 +38,7 @@ static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); static phys_addr_t __init kasan_alloc_zeroed_page(int node) { - void *p = memblock_virt_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, + void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, node); return __pa(p); diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index c7fb34efd23e..0bff116c07a8 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -168,7 +168,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, { int nid = early_cpu_to_node(cpu); - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 01a5ff4c41ff..0c997645e8f0 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -859,7 +859,7 @@ static void __init arch_mem_init(char **cmdline_p) * Prevent memblock from allocating high memory. * This cannot be done before max_low_pfn is detected, so up * to this point is possible to only reserve physical memory - * with memblock_reserve; memblock_virt_alloc* can be used + * with memblock_reserve; memblock_alloc* can be used * only after this point */ memblock_set_current_limit(PFN_PHYS(max_low_pfn)); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 4da8ed576229..d39ec3a4550a 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -203,7 +203,7 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0); + of_prop = memblock_alloc(sizeof(struct property) + 256, 0); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index 06796dec01ea..bf87d6e13369 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -14,7 +14,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (slab_is_available()) p = kzalloc(size, mask); else { - p = memblock_virt_alloc(size, 0); + p = memblock_alloc(size, 0); } return p; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 4d80239ef83c..954f1986af4d 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -461,10 +461,10 @@ void __init mmu_context_init(void) /* * Allocate the maps used by context management */ - context_map = memblock_virt_alloc(CTX_MAP_SIZE, 0); - context_mm = memblock_virt_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); + context_map = memblock_alloc(CTX_MAP_SIZE, 0); + context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); #ifdef CONFIG_SMP - stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0); + stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, 0); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index 60b03a1703d1..f45b369177a4 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -513,7 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) printk(KERN_ERR "nvram: no address\n"); return -EINVAL; } - nvram_image = memblock_virt_alloc(NVRAM_SIZE, 0); + nvram_image = memblock_alloc(NVRAM_SIZE, 0); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cde710297a4e..23a67b545b70 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3770,7 +3770,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb_id = be64_to_cpup(prop64); pr_debug(" PHB-ID : 0x%016llx\n", phb_id); - phb = memblock_virt_alloc(sizeof(*phb), 0); + phb = memblock_alloc(sizeof(*phb), 0); /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); @@ -3816,7 +3816,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, else phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE; - phb->diag_data = memblock_virt_alloc(phb->diag_data_size, 0); + phb->diag_data = memblock_alloc(phb->diag_data_size, 0); /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(hose, np, !hose->global_number); @@ -3875,7 +3875,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, } pemap_off = size; size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe); - aux = memblock_virt_alloc(size, 0); + aux = memblock_alloc(size, 0); phb->ioda.pe_alloc = aux; phb->ioda.m64_segmap = aux + m64map_off; phb->ioda.m32_segmap = aux + m32map_off; diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 77a37520068d..12519857a33c 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -126,7 +126,7 @@ static void __init prealloc(struct ps3_prealloc *p) if (!p->size) return; - p->address = memblock_virt_alloc(p->size, p->align); + p->address = memblock_alloc(p->size, p->align); printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size, p->address); diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index e64a411d1a00..349a9ff6ca5b 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -128,7 +128,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, if (bmp->bitmap_from_slab) bmp->bitmap = kzalloc(size, GFP_KERNEL); else { - bmp->bitmap = memblock_virt_alloc(size, 0); + bmp->bitmap = memblock_alloc(size, 0); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 204ccfa54bf3..781c1053a773 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -378,7 +378,7 @@ static void __init setup_lowcore(void) * Setup lowcore for boot cpu */ BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * PAGE_SIZE); - lc = memblock_virt_alloc_low(sizeof(*lc), sizeof(*lc)); + lc = memblock_alloc_low(sizeof(*lc), sizeof(*lc)); lc->restart_psw.mask = PSW_KERNEL_BITS; lc->restart_psw.addr = (unsigned long) restart_int_handler; lc->external_new_psw.mask = PSW_KERNEL_BITS | @@ -422,7 +422,7 @@ static void __init setup_lowcore(void) * Allocate the global restart stack which is the same for * all CPUs in cast *one* of them does a PSW restart. */ - restart_stack = memblock_virt_alloc(THREAD_SIZE, THREAD_SIZE); + restart_stack = memblock_alloc(THREAD_SIZE, THREAD_SIZE); restart_stack += STACK_INIT_OFFSET; /* @@ -488,7 +488,7 @@ static void __init setup_resources(void) bss_resource.end = (unsigned long) __bss_stop - 1; for_each_memblock(memory, reg) { - res = memblock_virt_alloc(sizeof(*res), 8); + res = memblock_alloc(sizeof(*res), 8); res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; res->name = "System RAM"; @@ -502,7 +502,7 @@ static void __init setup_resources(void) std_res->start > res->end) continue; if (std_res->end > res->end) { - sub_res = memblock_virt_alloc(sizeof(*sub_res), 8); + sub_res = memblock_alloc(sizeof(*sub_res), 8); *sub_res = *std_res; sub_res->end = res->end; std_res->start = res->end + 1; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1b3188f57b58..44f9a7d6450b 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -761,7 +761,7 @@ void __init smp_detect_cpus(void) u16 address; /* Get CPU information */ - info = memblock_virt_alloc(sizeof(*info), 8); + info = memblock_alloc(sizeof(*info), 8); smp_get_core_info(info, 1); /* Find boot CPU type */ if (sclp.has_core_type) { diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index e8184a15578a..799a91882a76 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -519,7 +519,7 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i]; nr_masks = max(nr_masks, 1); for (i = 0; i < nr_masks; i++) { - mask->next = memblock_virt_alloc(sizeof(*mask->next), 8); + mask->next = memblock_alloc(sizeof(*mask->next), 8); mask = mask->next; } } @@ -537,7 +537,7 @@ void __init topology_init_early(void) } if (!MACHINE_HAS_TOPOLOGY) goto out; - tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE); + tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE); info = tl_info; store_topology(info); pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n", diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 83b222c57609..5a381fc8e958 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -313,7 +313,7 @@ static void __ref create_core_to_node_map(void) { int i; - emu_cores = memblock_virt_alloc(sizeof(*emu_cores), 8); + emu_cores = memblock_alloc(sizeof(*emu_cores), 8); for (i = 0; i < ARRAY_SIZE(emu_cores->to_node_id); i++) emu_cores->to_node_id[i] = NODE_ID_FREE; } diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c index 21d1e8a1546d..7f61cc3fd4d1 100644 --- a/arch/s390/numa/toptree.c +++ b/arch/s390/numa/toptree.c @@ -34,7 +34,7 @@ struct toptree __ref *toptree_alloc(int level, int id) if (slab_is_available()) res = kzalloc(sizeof(*res), GFP_KERNEL); else - res = memblock_virt_alloc(sizeof(*res), 8); + res = memblock_alloc(sizeof(*res), 8); if (!res) return res; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index e3e77527f8df..77b857cb036f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -28,10 +28,10 @@ static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); static __init void *early_alloc(size_t size, int nid, bool panic) { if (panic) - return memblock_virt_alloc_try_nid(size, size, + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); else - return memblock_virt_alloc_try_nid_nopanic(size, size, + return memblock_alloc_try_nid_nopanic(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index 6b532b6bd785..1a30a258ccd0 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -43,7 +43,7 @@ static void __init populate(void *start, void *end) unsigned long vaddr = (unsigned long)start; pgd_t *pgd = pgd_offset_k(vaddr); pmd_t *pmd = pmd_offset(pgd, vaddr); - pte_t *pte = memblock_virt_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); + pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); pr_debug("%s: %p - %p\n", __func__, start, end); diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 7d22e1af2247..5c54d3734daf 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -342,7 +342,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem) { struct clk_iomap *io; - io = memblock_virt_alloc(sizeof(*io), 0); + io = memblock_alloc(sizeof(*io), 0); io->mem = mem; diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 5de3ed29282c..03cead6d5f97 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -333,7 +333,7 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; - entry = memblock_virt_alloc(sizeof(struct firmware_map_entry), 0); + entry = memblock_alloc(sizeof(struct firmware_map_entry), 0); if (WARN_ON(!entry)) return -ENOMEM; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 4f915cea6f75..ffe62a7ae19b 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1179,7 +1179,7 @@ int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - return memblock_virt_alloc(size, align); + return memblock_alloc(size, align); } bool __init early_init_dt_verify(void *params) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index a3a6866765f2..01e23b85e798 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -2192,7 +2192,7 @@ static struct device_node *overlay_base_root; static void * __init dt_alloc_memory(u64 size, u64 align) { - return memblock_virt_alloc(size, align); + return memblock_alloc(size, align); } /* diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b74bafd110b9..7d91f0f5ee44 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -95,78 +95,78 @@ extern void *__alloc_bootmem_low(unsigned long size, #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) /* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_virt_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size, +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); void __memblock_free_early(phys_addr_t base, phys_addr_t size); void __memblock_free_late(phys_addr_t base, phys_addr_t size); -static inline void * __init memblock_virt_alloc( +static inline void * __init memblock_alloc( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_raw( +static inline void * __init memblock_alloc_raw( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_nopanic( +static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low( +static inline void * __init memblock_alloc_low( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low_nopanic( +static inline void * __init memblock_alloc_low_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_from_nopanic( +static inline void * __init memblock_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { - return memblock_virt_alloc_try_nid_nopanic(size, align, min_addr, + return memblock_alloc_try_nid_nopanic(size, align, min_addr, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_node( +static inline void * __init memblock_alloc_node( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -static inline void * __init memblock_virt_alloc_node_nopanic( +static inline void * __init memblock_alloc_node_nopanic( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/init/main.c b/init/main.c index 1c3f90264280..86b59cf3bec7 100644 --- a/init/main.c +++ b/init/main.c @@ -375,10 +375,10 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } static void __init setup_command_line(char *command_line) { saved_command_line = - memblock_virt_alloc(strlen(boot_command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, 0); initcall_command_line = - memblock_virt_alloc(strlen(boot_command_line) + 1, 0); - static_command_line = memblock_virt_alloc(strlen(command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, 0); + static_command_line = memblock_alloc(strlen(command_line) + 1, 0); strcpy(saved_command_line, boot_command_line); strcpy(static_command_line, command_line); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ebecaf255ea2..801da67e957b 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -204,10 +204,10 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. */ - io_tlb_list = memblock_virt_alloc( + io_tlb_list = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), PAGE_SIZE); - io_tlb_orig_addr = memblock_virt_alloc( + io_tlb_orig_addr = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { @@ -242,7 +242,7 @@ swiotlb_init(int verbose) bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ - vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + vstart = memblock_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3d37c279c090..34116a6097be 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -963,7 +963,7 @@ void __init __register_nosave_region(unsigned long start_pfn, BUG_ON(!region); } else { /* This allocation cannot fail */ - region = memblock_virt_alloc(sizeof(struct nosave_region), 0); + region = memblock_alloc(sizeof(struct nosave_region), 0); } region->start_pfn = start_pfn; region->end_pfn = end_pfn; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b77150ad1965..429e4a3833ca 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1111,9 +1111,9 @@ void __init setup_log_buf(int early) if (early) { new_log_buf = - memblock_virt_alloc(new_log_buf_len, LOG_ALIGN); + memblock_alloc(new_log_buf_len, LOG_ALIGN); } else { - new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, + new_log_buf = memblock_alloc_nopanic(new_log_buf_len, LOG_ALIGN); } diff --git a/lib/cpumask.c b/lib/cpumask.c index beca6244671a..1405cb22e6bc 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -163,7 +163,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_virt_alloc(cpumask_size(), 0); + *mask = memblock_alloc(cpumask_size(), 0); } /** diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7b5c0ad9a6bd..51e9f17dbd5c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2100,7 +2100,7 @@ int __alloc_bootmem_huge_page(struct hstate *h) for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = memblock_virt_alloc_try_nid_raw( + addr = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, BOOTMEM_ALLOC_ACCESSIBLE, node); if (addr) { diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 7a2a2f13f86f..24d734bdff6b 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -83,7 +83,7 @@ static inline bool kasan_zero_page_entry(pte_t pte) static __init void *early_alloc(size_t size, int node) { - return memblock_virt_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, node); } diff --git a/mm/memblock.c b/mm/memblock.c index 20358374e8a8..58340de3ebc6 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1319,7 +1319,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali } /** - * memblock_virt_alloc_internal - allocate boot memory block + * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) @@ -1345,7 +1345,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -static void * __init memblock_virt_alloc_internal( +static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1412,7 +1412,7 @@ done: } /** - * memblock_virt_alloc_try_nid_raw - allocate boot memory block without zeroing + * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size @@ -1430,7 +1430,7 @@ done: * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_raw( +void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1441,7 +1441,7 @@ void * __init memblock_virt_alloc_try_nid_raw( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr && size > 0) page_init_poison(ptr, size); @@ -1450,7 +1450,7 @@ void * __init memblock_virt_alloc_try_nid_raw( } /** - * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block + * memblock_alloc_try_nid_nopanic - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation @@ -1466,7 +1466,7 @@ void * __init memblock_virt_alloc_try_nid_raw( * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_nopanic( +void * __init memblock_alloc_try_nid_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1477,7 +1477,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) memset(ptr, 0, size); @@ -1485,7 +1485,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( } /** - * memblock_virt_alloc_try_nid - allocate boot memory block with panicking + * memblock_alloc_try_nid - allocate boot memory block with panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation @@ -1495,14 +1495,14 @@ void * __init memblock_virt_alloc_try_nid_nopanic( * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * - * Public panicking version of memblock_virt_alloc_try_nid_nopanic() + * Public panicking version of memblock_alloc_try_nid_nopanic() * which provides debug information (including caller info), if enabled, * and panics if the request can not be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid( +void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1512,7 +1512,7 @@ void * __init memblock_virt_alloc_try_nid( memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) { memset(ptr, 0, size); @@ -1529,7 +1529,7 @@ void * __init memblock_virt_alloc_try_nid( * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * - * Free boot memory block previously allocated by memblock_virt_alloc_xx() API. + * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 59d171f84445..8ca6954fdcdc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6209,7 +6209,7 @@ static void __ref setup_usemap(struct pglist_data *pgdat, zone->pageblock_flags = NULL; if (usemapsize) zone->pageblock_flags = - memblock_virt_alloc_node_nopanic(usemapsize, + memblock_alloc_node_nopanic(usemapsize, pgdat->node_id); } #else @@ -6439,7 +6439,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); - map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id); + map = memblock_alloc_node_nopanic(size, pgdat->node_id); pgdat->node_mem_map = map + offset; } pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", @@ -7711,9 +7711,9 @@ void *__init alloc_large_system_hash(const char *tablename, size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) - table = memblock_virt_alloc_nopanic(size, 0); + table = memblock_alloc_nopanic(size, 0); else - table = memblock_virt_alloc_raw(size, 0); + table = memblock_alloc_raw(size, 0); } else if (hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); } else { diff --git a/mm/page_ext.c b/mm/page_ext.c index a9826da84ccb..e77c0f031dd0 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -161,7 +161,7 @@ static int __init alloc_node_page_ext(int nid) table_size = get_entry_size() * nr_pages; - base = memblock_virt_alloc_try_nid_nopanic( + base = memblock_alloc_try_nid_nopanic( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); if (!base) diff --git a/mm/percpu.c b/mm/percpu.c index 4b90682623e9..3050c1d37d37 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1101,7 +1101,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ - chunk = memblock_virt_alloc(sizeof(struct pcpu_chunk) + + chunk = memblock_alloc(sizeof(struct pcpu_chunk) + BITS_TO_LONGS(region_size >> PAGE_SHIFT), 0); @@ -1114,11 +1114,11 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); - chunk->alloc_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits) * + chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), 0); - chunk->bound_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits + 1) * + chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), 0); - chunk->md_blocks = memblock_virt_alloc(pcpu_chunk_nr_blocks(chunk) * + chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), 0); pcpu_init_md_blocks(chunk); @@ -1888,7 +1888,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); - ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), PAGE_SIZE); + ptr = memblock_alloc_nopanic(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; @@ -2075,12 +2075,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = memblock_virt_alloc(ai->nr_groups * + group_offsets = memblock_alloc(ai->nr_groups * sizeof(group_offsets[0]), 0); - group_sizes = memblock_virt_alloc(ai->nr_groups * + group_sizes = memblock_alloc(ai->nr_groups * sizeof(group_sizes[0]), 0); - unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); - unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); + unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); + unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -2144,7 +2144,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = memblock_virt_alloc( + pcpu_slot = memblock_alloc( pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -2458,7 +2458,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = memblock_virt_alloc_nopanic(areas_size, 0); + areas = memblock_alloc_nopanic(areas_size, 0); if (!areas) { rc = -ENOMEM; goto out_free; @@ -2599,7 +2599,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = memblock_virt_alloc(pages_size, 0); + pages = memblock_alloc(pages_size, 0); /* allocate pages */ j = 0; @@ -2688,7 +2688,7 @@ EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return memblock_virt_alloc_from_nopanic( + return memblock_alloc_from_nopanic( size, align, __pa(MAX_DMA_ADDRESS)); } @@ -2737,7 +2737,7 @@ void __init setup_per_cpu_areas(void) void *fc; ai = pcpu_alloc_alloc_info(1, 1); - fc = memblock_virt_alloc_from_nopanic(unit_size, + fc = memblock_alloc_from_nopanic(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 8301293331a2..91c2c3d25827 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -42,7 +42,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return memblock_virt_alloc_try_nid_raw(size, align, goal, + return memblock_alloc_try_nid_raw(size, align, goal, BOOTMEM_ALLOC_ACCESSIBLE, node); } diff --git a/mm/sparse.c b/mm/sparse.c index 67ad061f7fb8..cb900dda7fd2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_virt_alloc_node(array_size, nid); + section = memblock_alloc_node(array_size, nid); return section; } @@ -216,7 +216,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end) size = sizeof(struct mem_section*) * NR_SECTION_ROOTS; align = 1 << (INTERNODE_CACHE_SHIFT); - mem_section = memblock_virt_alloc(size, align); + mem_section = memblock_alloc(size, align); } #endif @@ -306,7 +306,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: - p = memblock_virt_alloc_try_nid_nopanic(size, + p = memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, goal, limit, nid); if (!p && limit) { @@ -362,7 +362,7 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - return memblock_virt_alloc_node_nopanic(size, pgdat->node_id); + return memblock_alloc_node_nopanic(size, pgdat->node_id); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -391,7 +391,7 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid, if (map) return map; - map = memblock_virt_alloc_try_nid(size, + map = memblock_alloc_try_nid(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); return map; @@ -405,7 +405,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) { WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */ sparsemap_buf = - memblock_virt_alloc_try_nid_raw(size, PAGE_SIZE, + memblock_alloc_try_nid_raw(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); sparsemap_buf_end = sparsemap_buf + size; -- cgit v1.2.3-71-gd317 From 3913c8f9f96bb75a062ad16ea10a1cdad48bb716 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:36 -0700 Subject: memblock: add align parameter to memblock_alloc_node() With the align parameter memblock_alloc_node() can be used as drop in replacement for alloc_bootmem_pages_node() and __alloc_bootmem_node(), which is done in the following patches. Link: http://lkml.kernel.org/r/1536927045-23536-15-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++-- mm/sparse.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7d91f0f5ee44..3896af205303 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -157,9 +157,9 @@ static inline void * __init memblock_alloc_from_nopanic( } static inline void * __init memblock_alloc_node( - phys_addr_t size, int nid) + phys_addr_t size, phys_addr_t align, int nid) { - return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/mm/sparse.c b/mm/sparse.c index cb900dda7fd2..d1296610562b 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_alloc_node(array_size, nid); + section = memblock_alloc_node(array_size, 0, nid); return section; } -- cgit v1.2.3-71-gd317 From 4fc4a09e4cc1126c4e8a86c293425cffa2a2eb3c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:03 -0700 Subject: memblock: replace __alloc_bootmem with memblock_alloc_from The functions are equivalent, just the later does not require nobootmem translation layer. The conversion is done using the following semantic patch: @@ expression size, align, goal; @@ - __alloc_bootmem(size, align, goal) + memblock_alloc_from(size, align, goal) Link: http://lkml.kernel.org/r/1536927045-23536-21-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_cia.c | 2 +- arch/alpha/kernel/pci_iommu.c | 4 ++-- arch/alpha/kernel/setup.c | 2 +- arch/ia64/kernel/mca.c | 4 ++-- arch/ia64/mm/contig.c | 5 +++-- arch/mips/kernel/traps.c | 2 +- arch/sparc/kernel/prom_32.c | 2 +- arch/sparc/kernel/smp_64.c | 10 +++++----- arch/sparc/mm/init_32.c | 2 +- arch/sparc/mm/init_64.c | 9 ++++++--- arch/sparc/mm/srmmu.c | 10 +++++----- include/linux/bootmem.h | 8 ++++++++ 12 files changed, 36 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c index 4b38386f6e62..026ee955fd10 100644 --- a/arch/alpha/kernel/core_cia.c +++ b/arch/alpha/kernel/core_cia.c @@ -331,7 +331,7 @@ cia_prepare_tbia_workaround(int window) long i; /* Use minimal 1K map. */ - ppte = __alloc_bootmem(CIA_BROKEN_TBIA_SIZE, 32768, 0); + ppte = memblock_alloc_from(CIA_BROKEN_TBIA_SIZE, 32768, 0); pte = (virt_to_phys(ppte) >> (PAGE_SHIFT - 1)) | 1; for (i = 0; i < CIA_BROKEN_TBIA_SIZE / sizeof(unsigned long); ++i) diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index b52d76fd534e..0c05493e6495 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -87,13 +87,13 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, printk("%s: couldn't allocate arena ptes from node %d\n" " falling back to system-wide allocation\n", __func__, nid); - arena->ptes = __alloc_bootmem(mem_size, align, 0); + arena->ptes = memblock_alloc_from(mem_size, align, 0); } #else /* CONFIG_DISCONTIGMEM */ arena = alloc_bootmem(sizeof(*arena)); - arena->ptes = __alloc_bootmem(mem_size, align, 0); + arena->ptes = memblock_alloc_from(mem_size, align, 0); #endif /* CONFIG_DISCONTIGMEM */ diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 4f0d94471bc9..64c06a0adf3d 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -294,7 +294,7 @@ move_initrd(unsigned long mem_limit) unsigned long size; size = initrd_end - initrd_start; - start = __alloc_bootmem(PAGE_ALIGN(size), PAGE_SIZE, 0); + start = memblock_alloc_from(PAGE_ALIGN(size), PAGE_SIZE, 0); if (!start || __pa(start) + size > mem_limit) { initrd_start = initrd_end = 0; return NULL; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 6115464d5f03..5586926dd85d 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1835,8 +1835,8 @@ format_mca_init_stack(void *mca_data, unsigned long offset, /* Caller prevents this from being called after init */ static void * __ref mca_bootmem(void) { - return __alloc_bootmem(sizeof(struct ia64_mca_cpu), - KERNEL_STACK_SIZE, 0); + return memblock_alloc_from(sizeof(struct ia64_mca_cpu), + KERNEL_STACK_SIZE, 0); } /* Do per-CPU MCA-related initialization. */ diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index e2e40bbd391c..9e5c23a6b8b4 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -85,8 +85,9 @@ skip: static inline void alloc_per_cpu_data(void) { - cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * num_possible_cpus(), - PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); + cpu_data = memblock_alloc_from(PERCPU_PAGE_SIZE * num_possible_cpus(), + PERCPU_PAGE_SIZE, + __pa(MAX_DMA_ADDRESS)); } /** diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 5feef28deac8..623dc18f7f2f 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -2263,7 +2263,7 @@ void __init trap_init(void) memblock_set_bottom_up(true); ebase = (unsigned long) - __alloc_bootmem(size, 1 << fls(size), 0); + memblock_alloc_from(size, 1 << fls(size), 0); memblock_set_bottom_up(false); /* diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index b51cbb9e87dc..4389944735c6 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -32,7 +32,7 @@ void * __init prom_early_alloc(unsigned long size) { void *ret; - ret = __alloc_bootmem(size, SMP_CACHE_BYTES, 0UL); + ret = memblock_alloc_from(size, SMP_CACHE_BYTES, 0UL); if (ret != NULL) memset(ret, 0, size); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 83ff88df6bdf..337febdf94b8 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1588,7 +1588,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, void *ptr; if (!node_online(node) || !NODE_DATA(node)) { - ptr = __alloc_bootmem(size, align, goal); + ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", @@ -1601,7 +1601,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, } return ptr; #else - return __alloc_bootmem(size, align, goal); + return memblock_alloc_from(size, align, goal); #endif } @@ -1627,7 +1627,7 @@ static void __init pcpu_populate_pte(unsigned long addr) if (pgd_none(*pgd)) { pud_t *new; - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); pgd_populate(&init_mm, pgd, new); } @@ -1635,7 +1635,7 @@ static void __init pcpu_populate_pte(unsigned long addr) if (pud_none(*pud)) { pmd_t *new; - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, new); } @@ -1643,7 +1643,7 @@ static void __init pcpu_populate_pte(unsigned long addr) if (!pmd_present(*pmd)) { pte_t *new; - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); pmd_populate_kernel(&init_mm, pmd, new); } } diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 92634d4e440c..885dd3881874 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -265,7 +265,7 @@ void __init mem_init(void) i = last_valid_pfn >> ((20 - PAGE_SHIFT) + 5); i += 1; sparc_valid_addr_bitmap = (unsigned long *) - __alloc_bootmem(i << 2, SMP_CACHE_BYTES, 0UL); + memblock_alloc_from(i << 2, SMP_CACHE_BYTES, 0UL); if (sparc_valid_addr_bitmap == NULL) { prom_printf("mem_init: Cannot alloc valid_addr_bitmap.\n"); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index b338f0440f6b..6f965e6d01cc 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1811,7 +1811,8 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, if (pgd_none(*pgd)) { pud_t *new; - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, + PAGE_SIZE); alloc_bytes += PAGE_SIZE; pgd_populate(&init_mm, pgd, new); } @@ -1823,7 +1824,8 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, vstart = kernel_map_hugepud(vstart, vend, pud); continue; } - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, + PAGE_SIZE); alloc_bytes += PAGE_SIZE; pud_populate(&init_mm, pud, new); } @@ -1836,7 +1838,8 @@ static unsigned long __ref kernel_map_range(unsigned long pstart, vstart = kernel_map_hugepmd(vstart, vend, pmd); continue; } - new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, + PAGE_SIZE); alloc_bytes += PAGE_SIZE; pmd_populate_kernel(&init_mm, pmd, new); } diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index be9cb0065179..b48fea5ad9ef 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -303,13 +303,13 @@ static void __init srmmu_nocache_init(void) bitmap_bits = srmmu_nocache_size >> SRMMU_NOCACHE_BITMAP_SHIFT; - srmmu_nocache_pool = __alloc_bootmem(srmmu_nocache_size, - SRMMU_NOCACHE_ALIGN_MAX, 0UL); + srmmu_nocache_pool = memblock_alloc_from(srmmu_nocache_size, + SRMMU_NOCACHE_ALIGN_MAX, 0UL); memset(srmmu_nocache_pool, 0, srmmu_nocache_size); srmmu_nocache_bitmap = - __alloc_bootmem(BITS_TO_LONGS(bitmap_bits) * sizeof(long), - SMP_CACHE_BYTES, 0UL); + memblock_alloc_from(BITS_TO_LONGS(bitmap_bits) * sizeof(long), + SMP_CACHE_BYTES, 0UL); bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits); srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE); @@ -467,7 +467,7 @@ static void __init sparc_context_init(int numctx) unsigned long size; size = numctx * sizeof(struct ctx_list); - ctx_list_pool = __alloc_bootmem(size, SMP_CACHE_BYTES, 0UL); + ctx_list_pool = memblock_alloc_from(size, SMP_CACHE_BYTES, 0UL); for (ctx = 0; ctx < numctx; ctx++) { struct ctx_list *clist; diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 3896af205303..c97c105cfc67 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -122,6 +122,14 @@ static inline void * __init memblock_alloc_raw( NUMA_NO_NODE); } +static inline void * __init memblock_alloc_from( + phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + BOOTMEM_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { -- cgit v1.2.3-71-gd317 From 6c7835f8d0d1839ca93bd3cf6faa15706f03d604 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:15 -0700 Subject: mm: nobootmem: remove bootmem allocation APIs The bootmem compatibility APIs are not used and can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-23-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 47 ---------- mm/nobootmem.c | 224 ------------------------------------------------ 2 files changed, 271 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index c97c105cfc67..73f1272fce20 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,33 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -extern void *__alloc_bootmem(unsigned long size, - unsigned long align, - unsigned long goal); -extern void *__alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *__alloc_bootmem_node_high(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) __malloc; -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -70,26 +43,6 @@ extern void *__alloc_bootmem_low(unsigned long size, #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif -#define alloc_bootmem(x) \ - __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_align(x, align) \ - __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) - -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 44ce7de1be8f..bc38e5673d31 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -33,41 +33,6 @@ unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; -static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - void *ptr; - u64 addr; - enum memblock_flags flags = choose_memblock_flags(); - - if (limit > memblock.current_limit) - limit = memblock.current_limit; - -again: - addr = memblock_find_in_range_node(size, align, goal, limit, nid, - flags); - if (!addr && (flags & MEMBLOCK_MIRROR)) { - flags &= ~MEMBLOCK_MIRROR; - pr_warn("Could not allocate %pap bytes of mirrored memory\n", - &size); - goto again; - } - if (!addr) - return NULL; - - if (memblock_reserve(addr, size)) - return NULL; - - ptr = phys_to_virt(addr); - memset(ptr, 0, size); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(ptr, size, 0, 0); - return ptr; -} - /** * free_bootmem_late - free bootmem pages directly to page allocator * @addr: starting address of the range @@ -215,192 +180,3 @@ void __init free_bootmem(unsigned long addr, unsigned long size) { memblock_free(addr, size); } - -static void * __init ___alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); - -restart: - - ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); - - if (ptr) - return ptr; - - if (goal != 0) { - goal = 0; - goto restart; - } - - return NULL; -} - -/** - * __alloc_bootmem_nopanic - allocate boot memory without panicking - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * Return: address of the allocated region or %NULL on failure. - */ -void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = -1UL; - - return ___alloc_bootmem_nopanic(size, align, goal, limit); -} - -static void * __init ___alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit); - - if (mem) - return mem; - /* - * Whoops, we cannot satisfy the allocation request. - */ - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -/** - * __alloc_bootmem - allocate boot memory - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = -1UL; - - return ___alloc_bootmem(size, align, goal, limit); -} - -void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - -again: - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, - goal, limit); - if (ptr) - return ptr; - - ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, - goal, limit); - if (ptr) - return ptr; - - if (goal) { - goal = 0; - goto again; - } - - return NULL; -} - -void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); -} - -static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal, - unsigned long limit) -{ - void *ptr; - - ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit); - if (ptr) - return ptr; - - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -/** - * __alloc_bootmem_node - allocate boot memory from a specific node - * @pgdat: node to allocate from - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may fall back to any node in the system if the specified node - * can not hold the requested memory. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, 0); -} - -void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - return __alloc_bootmem_node(pgdat, size, align, goal); -} - - -/** - * __alloc_bootmem_low - allocate low boot memory - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3-71-gd317 From 2013288f723887837d2f1cebef5fcf663b2319de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:21 -0700 Subject: memblock: replace free_bootmem{_node} with memblock_free The free_bootmem and free_bootmem_node are merely wrappers for memblock_free. Replace their usage with a call to memblock_free using the following semantic patch: @@ expression e1, e2, e3; @@ ( - free_bootmem(e1, e2) + memblock_free(e1, e2) | - free_bootmem_node(e1, e2, e3) + memblock_free(e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-24-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 +-- arch/arm64/mm/init.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 3 ++- arch/unicore32/mm/init.c | 2 +- arch/x86/kernel/setup_percpu.c | 3 ++- arch/x86/kernel/tce_64.c | 3 ++- arch/x86/xen/p2m.c | 3 ++- drivers/macintosh/smu.c | 2 +- drivers/usb/early/xhci-dbc.c | 11 ++++++----- drivers/xen/swiotlb-xen.c | 4 +++- include/linux/bootmem.h | 4 ---- mm/nobootmem.c | 30 ------------------------------ 15 files changed, 24 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index f70986683fc6..35572be9deb5 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -234,8 +234,7 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - free_bootmem_node(NODE_DATA(0), __pa(initrd_start), - PAGE_ALIGN(size)); + memblock_free(__pa(initrd_start), PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 3cf87341859f..2ddb1c5e988d 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -536,7 +536,7 @@ static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn) * memmap array. */ if (pg < pgend) - free_bootmem(pg, pgend - pg); + memblock_free(pg, pgend - pg); } /* diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index c1f95359d298..31522d3bc8bf 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -561,7 +561,7 @@ static void __init bootmem_init(void) extern void show_kernel_relocation(const char *level); offset = __pa_symbol(_text) - __pa_symbol(VMLINUX_LOAD_ADDRESS); - free_bootmem(__pa_symbol(VMLINUX_LOAD_ADDRESS), offset); + memblock_free(__pa_symbol(VMLINUX_LOAD_ADDRESS), offset); #if defined(CONFIG_DEBUG_KERNEL) && defined(CONFIG_DEBUG_INFO) /* diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 26d7c49a157b..f90ab3ea9af3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -771,7 +771,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 337febdf94b8..a087a6a25f06 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1607,7 +1607,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 185f6bb79269..3555c139389c 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -46,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - free_bootmem(__pa(brk_end), uml_reserved - brk_end); + memblock_free(__pa(brk_end), uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 8f8699e62bd5..4ba51991c7de 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -238,7 +238,7 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn) * free the section of the memmap array. */ if (pg < pgend) - free_bootmem(pg, pgend - pg); + memblock_free(pg, pgend - pg); } /* diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 041663abc028..a006f1ba4c39 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -135,7 +136,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 54c9b5a696b1..75730ce01f8d 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -186,5 +187,5 @@ void __init free_tce_table(void *tbl) size = table_size_to_number_of_entries(specified_table_size); size *= TCE_ENTRY_SIZE; - free_bootmem(__pa(tbl), size); + memblock_free(__pa(tbl), size); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 5de761b4cec8..b3e11afed25b 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -68,6 +68,7 @@ #include #include #include +#include #include #include @@ -190,7 +191,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - free_bootmem((unsigned long)p, PAGE_SIZE); + memblock_free((unsigned long)p, PAGE_SIZE); return; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 332fcca30944..0069f9084f9f 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -569,7 +569,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - free_bootmem(__pa(smu), sizeof(struct smu_device)); + memblock_free(__pa(smu), sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index 21494c8973b6..ddc5fa88f268 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -191,7 +192,7 @@ static void __init xdbc_free_ring(struct xdbc_ring *ring) if (!seg) return; - free_bootmem(seg->dma, PAGE_SIZE); + memblock_free(seg->dma, PAGE_SIZE); ring->segment = NULL; } @@ -675,10 +676,10 @@ int __init early_xdbc_setup_hardware(void) xdbc_free_ring(&xdbc.in_ring); if (xdbc.table_dma) - free_bootmem(xdbc.table_dma, PAGE_SIZE); + memblock_free(xdbc.table_dma, PAGE_SIZE); if (xdbc.out_dma) - free_bootmem(xdbc.out_dma, PAGE_SIZE); + memblock_free(xdbc.out_dma, PAGE_SIZE); xdbc.table_base = NULL; xdbc.out_buf = NULL; @@ -997,8 +998,8 @@ free_and_quit: xdbc_free_ring(&xdbc.evt_ring); xdbc_free_ring(&xdbc.out_ring); xdbc_free_ring(&xdbc.in_ring); - free_bootmem(xdbc.table_dma, PAGE_SIZE); - free_bootmem(xdbc.out_dma, PAGE_SIZE); + memblock_free(xdbc.table_dma, PAGE_SIZE); + memblock_free(xdbc.out_dma, PAGE_SIZE); writel(0, &xdbc.xdbc_reg->control); early_iounmap(xdbc.xhci_base, xdbc.xhci_length); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 91a6208ec1a5..c5f26a87d238 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -36,6 +36,7 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -248,7 +249,8 @@ retry: xen_io_tlb_nslabs); if (rc) { if (early) - free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes)); + memblock_free(__pa(xen_io_tlb_start), + PAGE_ALIGN(bytes)); else { free_pages((unsigned long)xen_io_tlb_start, order); xen_io_tlb_start = NULL; diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 73f1272fce20..706cf8ef6678 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,10 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_node(pg_data_t *pgdat, - unsigned long addr, - unsigned long size); -extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); /* We are using top down, so it is safe to use 0 here */ diff --git a/mm/nobootmem.c b/mm/nobootmem.c index bc38e5673d31..85e1822ce918 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -150,33 +150,3 @@ unsigned long __init free_all_bootmem(void) return pages; } - -/** - * free_bootmem_node - mark a page range as usable - * @pgdat: node the range resides on - * @physaddr: starting physical address of the range - * @size: size of the range in bytes - * - * Partial pages will be considered reserved and left as they are. - * - * The range must reside completely on the specified node. - */ -void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size) -{ - memblock_free(physaddr, size); -} - -/** - * free_bootmem - mark a page range as usable - * @addr: starting physical address of the range - * @size: size of the range in bytes - * - * Partial pages will be considered reserved and left as they are. - * - * The range must be contiguous but may span node boundaries. - */ -void __init free_bootmem(unsigned long addr, unsigned long size) -{ - memblock_free(addr, size); -} -- cgit v1.2.3-71-gd317 From 53ab85ebfd27cdf16c8ddc72781c072a63bef3cb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:25 -0700 Subject: memblock: replace free_bootmem_late with memblock_free_late The free_bootmem_late and memblock_free_late do exactly the same thing: they iterate over a range and give pages to the page allocator. Replace calls to free_bootmem_late with calls to memblock_free_late and remove the bootmem variant. Link: http://lkml.kernel.org/r/1536927045-23536-25-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/mdesc.c | 3 ++- arch/x86/platform/efi/quirks.c | 6 +++--- drivers/firmware/efi/apple-properties.c | 2 +- include/linux/bootmem.h | 2 -- mm/nobootmem.c | 24 ------------------------ 5 files changed, 6 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 59131e72ee78..a41526bd91e2 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -190,7 +191,7 @@ static void __init mdesc_memblock_free(struct mdesc_handle *hp) alloc_size = PAGE_ALIGN(hp->handle_size); start = __pa(hp); - free_bootmem_late(start, alloc_size); + memblock_free_late(start, alloc_size); } static struct mdesc_mem_ops memblock_mdesc_ops = { diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 669babcaf245..4b70d0f5a803 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -333,7 +333,7 @@ void __init efi_reserve_boot_services(void) /* * Because the following memblock_reserve() is paired - * with free_bootmem_late() for this region in + * with memblock_free_late() for this region in * efi_free_boot_services(), we must be extremely * careful not to reserve, and subsequently free, * critical regions of memory (like the kernel image) or @@ -364,7 +364,7 @@ void __init efi_reserve_boot_services(void) * doesn't make sense as far as the firmware is * concerned, but it does provide us with a way to tag * those regions that must not be paired with - * free_bootmem_late(). + * memblock_free_late(). */ md->attribute |= EFI_MEMORY_RUNTIME; } @@ -414,7 +414,7 @@ void __init efi_free_boot_services(void) size -= rm_size; } - free_bootmem_late(start, size); + memblock_free_late(start, size); } if (!num_entries) diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 60a95719ecb8..2b675f788b61 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -235,7 +235,7 @@ static int __init map_properties(void) */ data->len = 0; memunmap(data); - free_bootmem_late(pa_data + sizeof(*data), data_len); + memblock_free_late(pa_data + sizeof(*data), data_len); return ret; } diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 706cf8ef6678..bcc7e2fcb6a6 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,8 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_late(unsigned long physaddr, unsigned long size); - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 85e1822ce918..ee0f7fc37fd1 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -33,30 +33,6 @@ unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; -/** - * free_bootmem_late - free bootmem pages directly to page allocator - * @addr: starting address of the range - * @size: size of the range in bytes - * - * This is only useful when the bootmem allocator has already been torn - * down, but we are still initializing the system. Pages are given directly - * to the page allocator, no bootmem metadata is updated because it is gone. - */ -void __init free_bootmem_late(unsigned long addr, unsigned long size) -{ - unsigned long cursor, end; - - kmemleak_free_part_phys(addr, size); - - cursor = PFN_UP(addr); - end = PFN_DOWN(addr + size); - - for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); - totalram_pages++; - } -} - static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; -- cgit v1.2.3-71-gd317 From c6ffc5ca8fb311a89cb6de5c31b6511308ddac8d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:30 -0700 Subject: memblock: rename free_all_bootmem to memblock_free_all The conversion is done using sed -i 's@free_all_bootmem@memblock_free_all@' \ $(git grep -l free_all_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-26-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/mm/init.c | 2 +- arch/arc/mm/init.c | 2 +- arch/arm/mm/init.c | 2 +- arch/arm64/mm/init.c | 2 +- arch/c6x/mm/init.c | 2 +- arch/h8300/mm/init.c | 2 +- arch/hexagon/mm/init.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/init.c | 2 +- arch/microblaze/mm/init.c | 2 +- arch/mips/loongson64/loongson-3/numa.c | 2 +- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 2 +- arch/nds32/mm/init.c | 2 +- arch/nios2/mm/init.c | 2 +- arch/openrisc/mm/init.c | 2 +- arch/parisc/mm/init.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/riscv/mm/init.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 2 +- arch/sparc/mm/init_32.c | 2 +- arch/sparc/mm/init_64.c | 4 ++-- arch/um/kernel/mem.c | 2 +- arch/unicore32/mm/init.c | 2 +- arch/x86/mm/highmem_32.c | 2 +- arch/x86/mm/init_32.c | 4 ++-- arch/x86/mm/init_64.c | 4 ++-- arch/x86/xen/mmu_pv.c | 2 +- arch/xtensa/mm/init.c | 2 +- include/linux/bootmem.h | 2 +- mm/memblock.c | 2 +- mm/nobootmem.c | 4 ++-- mm/page_alloc.c | 2 +- mm/page_poison.c | 2 +- 35 files changed, 39 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 9d74520298ab..853d15344934 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -282,7 +282,7 @@ mem_init(void) { set_max_mapnr(max_low_pfn); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index ba145065c579..0f29c6548779 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -218,7 +218,7 @@ void __init mem_init(void) free_highmem_page(pfn_to_page(tmp)); #endif - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 0cc8e04295a4..d421a10c93a8 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -508,7 +508,7 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ free_unused_memmap(); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 2ddb1c5e988d..d8d73073835f 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -599,7 +599,7 @@ void __init mem_init(void) free_unused_memmap(); #endif /* this will put all unused low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); kexec_reserve_crashkres_pages(); diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index dc369ad8b0ba..3383df8b3508 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -62,7 +62,7 @@ void __init mem_init(void) high_memory = (void *)(memory_end & PAGE_MASK); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index 5d31ac9d7a8d..f2bf4487aabd 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -96,7 +96,7 @@ void __init mem_init(void) max_mapnr = MAP_NR(high_memory); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index d789b9cc0189..88643faf3981 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -68,7 +68,7 @@ unsigned long long kmap_generation; void __init mem_init(void) { /* No idea where this is actually declared. Seems to evade LXR. */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); /* diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 2169ca52bdf4..43ea4a47163d 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -627,7 +627,7 @@ mem_init (void) set_max_mapnr(max_low_pfn); high_memory = __va(max_low_pfn * PAGE_SIZE); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); /* diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 977363eda125..ae49ae4d3049 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -140,7 +140,7 @@ static inline void init_pointer_tables(void) void __init mem_init(void) { /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); init_pointer_tables(); mem_init_print_info(NULL); } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 8c7f074ec20f..9989740d397a 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -204,7 +204,7 @@ void __init mem_init(void) high_memory = (void *)__va(memory_start + lowmem_size - 1); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM highmem_setup(); #endif diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index c1e6ec52c614..703ad4536fe0 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -272,7 +272,7 @@ void __init paging_init(void) void __init mem_init(void) { high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ mem_init_print_info(NULL); } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 842a49ef9909..0893b6136498 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -463,7 +463,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); maar_init(); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ mem_init_free_highmem(); mem_init_print_info(NULL); diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 6f7bef052b7f..cb1f1a6a166d 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -475,7 +475,7 @@ void __init paging_init(void) void __init mem_init(void) { high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ mem_init_print_info(NULL); } diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index 5af81b866aa5..66d3e9cf498d 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -192,7 +192,7 @@ void __init mem_init(void) free_highmem(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); pr_info("virtual kernel memory layout:\n" diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index c92fe4234009..12923501d94f 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -73,7 +73,7 @@ void __init mem_init(void) high_memory = __va(end_mem); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index b7670de26c11..91a6a9ab7598 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -213,7 +213,7 @@ void __init mem_init(void) memset((void *)empty_zero_page, 0, PAGE_SIZE); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index f88a52b8531c..7e7a3126c5e9 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -621,7 +621,7 @@ void __init mem_init(void) high_memory = __va((max_pfn << PAGE_SHIFT)); set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_PA11 if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index dd949d6649a2..b3fe79064a69 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -349,7 +349,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); set_max_mapnr(max_pfn); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 58a522f9bcc3..d58c111099b3 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -55,7 +55,7 @@ void __init mem_init(void) #endif /* CONFIG_FLATMEM */ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 92d7a153e72a..873f6ee1c46d 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -139,7 +139,7 @@ void __init mem_init(void) cmma_init(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ cmma_init_nodat(); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index c884b760e52f..21447f866415 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -350,7 +350,7 @@ void __init mem_init(void) high_memory = max_t(void *, high_memory, __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT)); - free_all_bootmem(); + memblock_free_all(); /* Set this up early, so we can take care of the zero page */ cpu_cache_init(); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 885dd3881874..880714565c40 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -277,7 +277,7 @@ void __init mem_init(void) max_mapnr = last_valid_pfn - pfn_base; high_memory = __va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); for (i = 0; sp_banks[i].num_bytes != 0; i++) { unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 6f965e6d01cc..a8c3453195e6 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2545,12 +2545,12 @@ void __init mem_init(void) { high_memory = __va(last_valid_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been - * initialized, and free_all_bootmem() initializes all the reserved + * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 3555c139389c..2c672a8f4571 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -51,7 +51,7 @@ void __init mem_init(void) uml_reserved = brk_end; /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); max_low_pfn = totalram_pages; max_pfn = totalram_pages; mem_init_print_info(NULL); diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 4ba51991c7de..44fd0e8fbe87 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -286,7 +286,7 @@ void __init mem_init(void) free_unused_memmap(&meminfo); /* this will put all unused low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); printk(KERN_NOTICE "Virtual kernel memory layout:\n" diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 6d18b70ed5a9..62915a5e0fa2 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -111,7 +111,7 @@ void __init set_highmem_pages_init(void) /* * Explicitly reset zone->managed_pages because set_highmem_pages_init() - * is invoked before free_all_bootmem() + * is invoked before memblock_free_all() */ reset_all_zones_managed_pages(); for_each_zone(zone) { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 142c7d9f89cc..3bbe5f58a67d 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -771,7 +771,7 @@ void __init mem_init(void) #endif /* * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to - * be done before free_all_bootmem(). Memblock use free low memory for + * be done before memblock_free_all(). Memblock use free low memory for * temporary data (see find_range_array()) and for this purpose can use * pages that was already passed to the buddy allocator, hence marked as * not accessible in the page tables when compiled with @@ -781,7 +781,7 @@ void __init mem_init(void) set_highmem_pages_init(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f39b51244fe2..bfb0bedc21d3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1188,14 +1188,14 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been - * initialized, and free_all_bootmem() initializes all the reserved + * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 70ea598a37d2..0d7b3ae4960b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -864,7 +864,7 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, * The init_mm pagetable is really pinned as soon as its created, but * that's before we have page structures to store the bits. So do all * the book-keeping now once struct pages for allocated pages are - * initialized. This happens only after free_all_bootmem() is called. + * initialized. This happens only after memblock_free_all() is called. */ static void __init xen_after_bootmem(void) { diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 34aead7dcb48..f7fbe6334939 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -152,7 +152,7 @@ void __init mem_init(void) max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); pr_info("virtual kernel memory layout:\n" diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index bcc7e2fcb6a6..b58873a567b2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,7 +26,7 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long free_all_bootmem(void); +extern unsigned long memblock_free_all(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); diff --git a/mm/memblock.c b/mm/memblock.c index 58340de3ebc6..e2f397174734 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1360,7 +1360,7 @@ static void * __init memblock_alloc_internal( /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its - * internal data may be destroyed (after execution of free_all_bootmem) + * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); diff --git a/mm/nobootmem.c b/mm/nobootmem.c index ee0f7fc37fd1..bb64b09ca4d2 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -111,11 +111,11 @@ void __init reset_all_zones_managed_pages(void) } /** - * free_all_bootmem - release free pages to the buddy allocator + * memblock_free_all - release free pages to the buddy allocator * * Return: the number of pages actually released. */ -unsigned long __init free_all_bootmem(void) +unsigned long __init memblock_free_all(void) { unsigned long pages; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8ca6954fdcdc..6e9b8387a706 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5476,7 +5476,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) /* * Initially all pages are reserved - free ones are freed - * up by free_all_bootmem() once the early boot process is + * up by memblock_free_all() once the early boot process is * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, diff --git a/mm/page_poison.c b/mm/page_poison.c index aa2b3d34e8ea..f7e2a676365a 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -21,7 +21,7 @@ bool page_poisoning_enabled(void) { /* * Assumes that debug_pagealloc_enabled is set before - * free_all_bootmem. + * memblock_free_all. * Page poisoning is debug page alloc for some arches. If * either of those options are enabled, enable poisoning. */ -- cgit v1.2.3-71-gd317 From 57c8a661d95dff48dd9c2f2496139082bbaf241a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:49 -0700 Subject: mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include @@ @@ - #include + #include [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_cia.c | 2 +- arch/alpha/kernel/core_irongate.c | 1 - arch/alpha/kernel/core_marvel.c | 2 +- arch/alpha/kernel/core_titan.c | 2 +- arch/alpha/kernel/core_tsunami.c | 2 +- arch/alpha/kernel/pci-noop.c | 2 +- arch/alpha/kernel/pci.c | 2 +- arch/alpha/kernel/pci_iommu.c | 2 +- arch/alpha/kernel/setup.c | 1 - arch/alpha/kernel/sys_nautilus.c | 2 +- arch/alpha/mm/init.c | 2 +- arch/alpha/mm/numa.c | 1 - arch/arc/kernel/unwind.c | 2 +- arch/arc/mm/highmem.c | 2 +- arch/arc/mm/init.c | 1 - arch/arm/kernel/devtree.c | 1 - arch/arm/kernel/setup.c | 1 - arch/arm/mach-omap2/omap_hwmod.c | 2 +- arch/arm/mm/dma-mapping.c | 1 - arch/arm/mm/init.c | 1 - arch/arm/xen/mm.c | 1 - arch/arm/xen/p2m.c | 2 +- arch/arm64/kernel/acpi.c | 1 - arch/arm64/kernel/acpi_numa.c | 1 - arch/arm64/kernel/setup.c | 1 - arch/arm64/mm/dma-mapping.c | 2 +- arch/arm64/mm/init.c | 1 - arch/arm64/mm/kasan_init.c | 1 - arch/arm64/mm/numa.c | 1 - arch/c6x/kernel/setup.c | 1 - arch/c6x/mm/init.c | 2 +- arch/h8300/kernel/setup.c | 1 - arch/h8300/mm/init.c | 2 +- arch/hexagon/kernel/dma.c | 2 +- arch/hexagon/kernel/setup.c | 2 +- arch/hexagon/mm/init.c | 1 - arch/ia64/kernel/crash.c | 2 +- arch/ia64/kernel/efi.c | 2 +- arch/ia64/kernel/ia64_ksyms.c | 2 +- arch/ia64/kernel/iosapic.c | 2 +- arch/ia64/kernel/mca.c | 2 +- arch/ia64/kernel/mca_drv.c | 2 +- arch/ia64/kernel/setup.c | 1 - arch/ia64/kernel/smpboot.c | 2 +- arch/ia64/kernel/topology.c | 2 +- arch/ia64/kernel/unwind.c | 2 +- arch/ia64/mm/contig.c | 1 - arch/ia64/mm/discontig.c | 1 - arch/ia64/mm/init.c | 1 - arch/ia64/mm/numa.c | 2 +- arch/ia64/mm/tlb.c | 2 +- arch/ia64/pci/pci.c | 2 +- arch/ia64/sn/kernel/bte.c | 2 +- arch/ia64/sn/kernel/io_common.c | 2 +- arch/ia64/sn/kernel/setup.c | 2 +- arch/m68k/atari/stram.c | 2 +- arch/m68k/coldfire/m54xx.c | 2 +- arch/m68k/kernel/setup_mm.c | 1 - arch/m68k/kernel/setup_no.c | 1 - arch/m68k/kernel/uboot.c | 2 +- arch/m68k/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c | 1 - arch/m68k/mm/motorola.c | 1 - arch/m68k/mm/sun3mmu.c | 2 +- arch/m68k/sun3/config.c | 2 +- arch/m68k/sun3/dvma.c | 2 +- arch/m68k/sun3/mmu_emu.c | 2 +- arch/m68k/sun3/sun3dvma.c | 2 +- arch/m68k/sun3x/dvma.c | 2 +- arch/microblaze/mm/consistent.c | 2 +- arch/microblaze/mm/init.c | 3 +- arch/microblaze/pci/pci-common.c | 2 +- arch/mips/ar7/memory.c | 2 +- arch/mips/ath79/setup.c | 2 +- arch/mips/bcm63xx/prom.c | 2 +- arch/mips/bcm63xx/setup.c | 2 +- arch/mips/bmips/setup.c | 2 +- arch/mips/cavium-octeon/dma-octeon.c | 2 +- arch/mips/dec/prom/memory.c | 2 +- arch/mips/emma/common/prom.c | 2 +- arch/mips/fw/arc/memory.c | 2 +- arch/mips/jazz/jazzdma.c | 2 +- arch/mips/kernel/crash.c | 2 +- arch/mips/kernel/crash_dump.c | 2 +- arch/mips/kernel/prom.c | 2 +- arch/mips/kernel/setup.c | 1 - arch/mips/kernel/traps.c | 1 - arch/mips/kernel/vpe.c | 2 +- arch/mips/kvm/commpage.c | 2 +- arch/mips/kvm/dyntrans.c | 2 +- arch/mips/kvm/emulate.c | 2 +- arch/mips/kvm/interrupt.c | 2 +- arch/mips/kvm/mips.c | 2 +- arch/mips/lantiq/prom.c | 2 +- arch/mips/lasat/prom.c | 2 +- arch/mips/loongson64/common/init.c | 2 +- arch/mips/loongson64/loongson-3/numa.c | 1 - arch/mips/mm/init.c | 2 +- arch/mips/mm/pgtable-32.c | 2 +- arch/mips/mti-malta/malta-memory.c | 2 +- arch/mips/netlogic/xlp/dt.c | 2 +- arch/mips/pci/pci-legacy.c | 2 +- arch/mips/pci/pci.c | 2 +- arch/mips/ralink/of.c | 2 +- arch/mips/rb532/prom.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 1 - arch/mips/sibyte/common/cfe.c | 2 +- arch/mips/sibyte/swarm/setup.c | 2 +- arch/mips/txx9/rbtx4938/prom.c | 2 +- arch/nds32/kernel/setup.c | 3 +- arch/nds32/mm/highmem.c | 2 +- arch/nds32/mm/init.c | 3 +- arch/nios2/kernel/prom.c | 2 +- arch/nios2/kernel/setup.c | 1 - arch/nios2/mm/init.c | 2 +- arch/openrisc/kernel/setup.c | 3 +- arch/openrisc/mm/init.c | 3 +- arch/parisc/mm/init.c | 1 - arch/powerpc/kernel/pci_32.c | 2 +- arch/powerpc/kernel/setup-common.c | 1 - arch/powerpc/kernel/setup_64.c | 3 +- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 1 - arch/powerpc/mm/mem.c | 3 +- arch/powerpc/mm/mmu_context_nohash.c | 2 +- arch/powerpc/mm/numa.c | 3 +- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 3 +- arch/powerpc/platforms/ps3/setup.c | 2 +- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/riscv/mm/init.c | 3 +- arch/s390/kernel/crash_dump.c | 3 +- arch/s390/kernel/setup.c | 1 - arch/s390/kernel/smp.c | 3 +- arch/s390/kernel/topology.c | 2 +- arch/s390/kernel/vdso.c | 2 +- arch/s390/mm/extmem.c | 2 +- arch/s390/mm/init.c | 3 +- arch/s390/mm/vmem.c | 3 +- arch/s390/numa/mode_emu.c | 1 - arch/s390/numa/numa.c | 1 - arch/s390/numa/toptree.c | 2 +- arch/sh/mm/init.c | 3 +- arch/sh/mm/ioremap_fixed.c | 2 +- arch/sparc/kernel/mdesc.c | 2 - arch/sparc/kernel/prom_32.c | 2 +- arch/sparc/kernel/setup_64.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/sparc/mm/init_32.c | 1 - arch/sparc/mm/init_64.c | 3 +- arch/sparc/mm/srmmu.c | 2 +- arch/um/drivers/net_kern.c | 2 +- arch/um/drivers/vector_kern.c | 2 +- arch/um/kernel/initrd.c | 2 +- arch/um/kernel/mem.c | 1 - arch/um/kernel/physmem.c | 1 - arch/unicore32/kernel/hibernate.c | 2 +- arch/unicore32/kernel/setup.c | 3 +- arch/unicore32/mm/init.c | 3 +- arch/unicore32/mm/mmu.c | 1 - arch/x86/kernel/acpi/boot.c | 2 +- arch/x86/kernel/acpi/sleep.c | 1 - arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/e820.c | 3 +- arch/x86/kernel/mpparse.c | 1 - arch/x86/kernel/pci-dma.c | 2 +- arch/x86/kernel/pci-swiotlb.c | 2 +- arch/x86/kernel/pvclock.c | 2 +- arch/x86/kernel/setup.c | 1 - arch/x86/kernel/setup_percpu.c | 1 - arch/x86/kernel/smpboot.c | 2 +- arch/x86/kernel/tce_64.c | 1 - arch/x86/mm/amdtopology.c | 1 - arch/x86/mm/fault.c | 2 +- arch/x86/mm/highmem_32.c | 2 +- arch/x86/mm/init.c | 1 - arch/x86/mm/init_32.c | 1 - arch/x86/mm/init_64.c | 1 - arch/x86/mm/ioremap.c | 2 +- arch/x86/mm/kasan_init_64.c | 3 +- arch/x86/mm/kaslr.c | 1 + arch/x86/mm/numa.c | 1 - arch/x86/mm/numa_32.c | 1 - arch/x86/mm/numa_64.c | 2 +- arch/x86/mm/numa_emulation.c | 1 - arch/x86/mm/pageattr-test.c | 2 +- arch/x86/mm/pageattr.c | 2 +- arch/x86/mm/pat.c | 2 +- arch/x86/mm/physaddr.c | 2 +- arch/x86/pci/i386.c | 2 +- arch/x86/platform/efi/efi.c | 3 +- arch/x86/platform/efi/efi_64.c | 2 +- arch/x86/platform/efi/quirks.c | 1 - arch/x86/platform/olpc/olpc_dt.c | 2 +- arch/x86/power/hibernate_32.c | 2 +- arch/x86/xen/enlighten.c | 2 +- arch/x86/xen/enlighten_pv.c | 3 +- arch/x86/xen/p2m.c | 1 - arch/xtensa/kernel/pci.c | 2 +- arch/xtensa/mm/cache.c | 2 +- arch/xtensa/mm/init.c | 2 +- arch/xtensa/mm/kasan_init.c | 3 +- arch/xtensa/mm/mmu.c | 2 +- arch/xtensa/platforms/iss/network.c | 2 +- arch/xtensa/platforms/iss/setup.c | 2 +- block/blk-settings.c | 2 +- block/bounce.c | 2 +- drivers/acpi/numa.c | 1 - drivers/acpi/tables.c | 3 +- drivers/base/platform.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/dmi_scan.c | 2 +- drivers/firmware/efi/apple-properties.c | 2 +- drivers/firmware/iscsi_ibft_find.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/mtk_iommu_v1.c | 2 +- drivers/macintosh/smu.c | 3 +- drivers/mtd/ar7part.c | 2 +- drivers/net/arcnet/arc-rimi.c | 2 +- drivers/net/arcnet/com20020-isa.c | 2 +- drivers/net/arcnet/com90io.c | 2 +- drivers/of/fdt.c | 1 - drivers/of/unittest.c | 2 +- drivers/s390/char/fs3270.c | 2 +- drivers/s390/char/tty3270.c | 2 +- drivers/s390/cio/cmf.c | 2 +- drivers/s390/virtio/virtio_ccw.c | 2 +- drivers/sfi/sfi_core.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_core.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c | 2 +- drivers/usb/early/xhci-dbc.c | 1 - drivers/xen/balloon.c | 2 +- drivers/xen/events/events_base.c | 2 +- drivers/xen/grant-table.c | 2 +- drivers/xen/swiotlb-xen.c | 1 - drivers/xen/xen-selfballoon.c | 2 +- fs/dcache.c | 2 +- fs/inode.c | 2 +- fs/namespace.c | 2 +- fs/proc/kcore.c | 2 +- fs/proc/page.c | 2 +- fs/proc/vmcore.c | 2 +- include/linux/bootmem.h | 173 ---------------------------- include/linux/memblock.h | 151 +++++++++++++++++++++++- init/main.c | 2 +- kernel/dma/direct.c | 2 +- kernel/dma/swiotlb.c | 2 +- kernel/futex.c | 2 +- kernel/locking/qspinlock_paravirt.h | 2 +- kernel/pid.c | 2 +- kernel/power/snapshot.c | 2 +- kernel/printk/printk.c | 1 - kernel/profile.c | 2 +- lib/cpumask.c | 2 +- mm/hugetlb.c | 1 - mm/kasan/kasan_init.c | 3 +- mm/kmemleak.c | 2 +- mm/memblock.c | 1 - mm/memory_hotplug.c | 1 - mm/page_alloc.c | 1 - mm/page_ext.c | 2 +- mm/page_idle.c | 2 +- mm/page_owner.c | 2 +- mm/percpu.c | 2 +- mm/sparse-vmemmap.c | 1 - mm/sparse.c | 1 - net/ipv4/inet_hashtables.c | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/udp.c | 2 +- net/sctp/protocol.c | 2 +- net/xfrm/xfrm_hash.c | 2 +- 275 files changed, 353 insertions(+), 476 deletions(-) delete mode 100644 include/linux/bootmem.h (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c index 026ee955fd10..867e8730b0c5 100644 --- a/arch/alpha/kernel/core_cia.c +++ b/arch/alpha/kernel/core_cia.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index 35572be9deb5..a9fd133a7fb2 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 1f00c9433b10..8a568c4d8e81 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 132b06bdf903..97551597581b 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c index e7c956ea46b6..f334b8928d72 100644 --- a/arch/alpha/kernel/core_tsunami.c +++ b/arch/alpha/kernel/core_tsunami.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index 59cbfc2bf2c5..a9378ee0c2f1 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 4cc3eb92f55b..13937e72d875 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 5d178c7ba5b2..82cf950bda2a 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 64c06a0adf3d..a37fd990bd55 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index ff4f54b86c7f..cd9a112d67ff 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 853d15344934..a42fc5c4db89 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -19,7 +19,7 @@ #include #include #include -#include /* max_low_pfn */ +#include /* max_low_pfn */ #include #include diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 26cd925d19b1..74846553e3f1 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 2a01dd1005f4..d34f69eb1a95 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -15,7 +15,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index f582dc8944c9..48e700151810 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -7,7 +7,7 @@ * */ -#include +#include #include #include #include diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 0f29c6548779..f8fe5668b30f 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -8,7 +8,6 @@ #include #include -#include #include #ifdef CONFIG_BLK_DEV_INITRD #include diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 13bcd3b867cb..e3057c1b55b9 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 39e6090d23ac..840a4adc69fc 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 1f9b34a7eccd..cd5732ab0cdf 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -141,7 +141,7 @@ #include #include #include -#include +#include #include diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 66566472c153..661fe48ab78d 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -9,7 +9,6 @@ * * DMA uncached mapping support. */ -#include #include #include #include diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d421a10c93a8..32e4845af2b6 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 785d2a562a23..cb44aa290e73 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -1,6 +1,5 @@ #include #include -#include #include #include #include diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 0641ba54ab62..e70a49fc8dcd 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -1,4 +1,4 @@ -#include +#include #include #include #include diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index ed46dc188b22..44e3c351e1ea 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -16,7 +16,6 @@ #define pr_fmt(fmt) "ACPI: " fmt #include -#include #include #include #include diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index 4f4f1815e047..eac1d0cc595c 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -18,7 +18,6 @@ #include #include -#include #include #include #include diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 3428427f6c93..7ce7306f1d75 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index d190612b8f33..3a703e5d4e32 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -19,7 +19,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d8d73073835f..9d9582cac6c4 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6a65a2912d36..63527e585aac 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -11,7 +11,6 @@ */ #define pr_fmt(fmt) "kasan: " fmt -#include #include #include #include diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 0bff116c07a8..27a31efd9e8e 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -20,7 +20,6 @@ #define pr_fmt(fmt) "NUMA: " fmt #include -#include #include #include #include diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index 05d96a9541b5..2e1c0ea22eb0 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 3383df8b3508..af5ada0520be 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #ifdef CONFIG_BLK_DEV_RAM #include #endif diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index 34e2df5c0d6d..b32bfa1fe99e 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index f2bf4487aabd..6519252ac4db 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 706699374444..38eaa7b703e7 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -19,7 +19,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/hexagon/kernel/setup.c b/arch/hexagon/kernel/setup.c index dc8c7e75b5d1..b3c3e04d4e57 100644 --- a/arch/hexagon/kernel/setup.c +++ b/arch/hexagon/kernel/setup.c @@ -20,7 +20,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 88643faf3981..1719ede9e9bd 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -20,7 +20,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 39f4433a6f0e..bec762a9b418 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index f77d80edddfe..8f106638913c 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -23,7 +23,7 @@ * Skip non-WB memory and ignore empty memory ranges. */ #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 6b51c88e3578..b49fe6f618ed 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -6,7 +6,7 @@ #ifdef CONFIG_VIRTUAL_MEM_MAP #include #include -#include +#include EXPORT_SYMBOL(min_low_pfn); /* defined by bootmem.c, but not exported by generic code */ EXPORT_SYMBOL(max_low_pfn); /* defined by bootmem.c, but not exported by generic code */ #endif diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 550243a94b5d..fe6e4946672e 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -90,7 +90,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 71209766c47f..9a6603f8e409 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -77,7 +77,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index dfe40cbdf3b3..45f956ad715a 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 0e6c2d9fb498..583a3746d70b 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -27,7 +27,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 74fe317477e6..51ec944b036c 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -24,7 +24,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 9b820f7a6a98..e311ee13e61d 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index e04efa088902..7601fe0622d2 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -28,7 +28,7 @@ * acquired, then the read-write lock must be acquired first. */ #include -#include +#include #include #include #include diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 9e5c23a6b8b4..6e447234205c 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -14,7 +14,6 @@ * Routines used by ia64 machines with contiguous (or virtually contiguous) * memory. */ -#include #include #include #include diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 70609f823960..8a965784340c 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 43ea4a47163d..d5e12ff1d73c 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -8,7 +8,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index aa19b7ac8222..3861d6e32d5f 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 5554863b4c9b..ab545daff7c3 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 5d71800df431..196a0dd7ff97 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/sn/kernel/bte.c b/arch/ia64/sn/kernel/bte.c index 9146192b86f5..9900e6d4add6 100644 --- a/arch/ia64/sn/kernel/bte.c +++ b/arch/ia64/sn/kernel/bte.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c index 8b05d5581615..98f55220c67d 100644 --- a/arch/ia64/sn/kernel/io_common.c +++ b/arch/ia64/sn/kernel/io_common.c @@ -6,7 +6,7 @@ * Copyright (C) 2006 Silicon Graphics, Inc. All rights reserved. */ -#include +#include #include #include #include diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index ab2564f95199..71ad6b0ccab4 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/atari/stram.c b/arch/m68k/atari/stram.c index 1089d67df315..6ffc204eb07d 100644 --- a/arch/m68k/atari/stram.c +++ b/arch/m68k/atari/stram.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c index adad03ca6e11..360c723c0ae6 100644 --- a/arch/m68k/coldfire/m54xx.c +++ b/arch/m68k/coldfire/m54xx.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 5d3596c180f9..a1a3eaeaf58c 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index cfd5475bfc31..3c5def10d486 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c index 107082877064..1b4c562753da 100644 --- a/arch/m68k/kernel/uboot.c +++ b/arch/m68k/kernel/uboot.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index ae49ae4d3049..933c33e76a48 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 38a1d92dd555..0de4999a3810 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 2113eec8dbf9..7497cf30bf1c 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c index 19c05ab9824d..f736db48a2e1 100644 --- a/arch/m68k/mm/sun3mmu.c +++ b/arch/m68k/mm/sun3mmu.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 79a2bb857906..542c4404861c 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/sun3/dvma.c b/arch/m68k/sun3/dvma.c index 5f92c72b05c3..a2c1c9304895 100644 --- a/arch/m68k/sun3/dvma.c +++ b/arch/m68k/sun3/dvma.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c index d30da12a1702..582a1284059a 100644 --- a/arch/m68k/sun3/mmu_emu.c +++ b/arch/m68k/sun3/mmu_emu.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index 72d94585b52e..8be8b750c629 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -7,7 +7,7 @@ * Contains common routines for sun3/sun3x DVMA management. */ -#include +#include #include #include #include diff --git a/arch/m68k/sun3x/dvma.c b/arch/m68k/sun3x/dvma.c index b2acbc862f60..89e630e66555 100644 --- a/arch/m68k/sun3x/dvma.c +++ b/arch/m68k/sun3x/dvma.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c index d801cc5f5b95..45e0a1aa9357 100644 --- a/arch/microblaze/mm/consistent.c +++ b/arch/microblaze/mm/consistent.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 9989740d397a..8c14988f52f2 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -7,10 +7,9 @@ * for more details. */ -#include +#include #include #include -#include #include /* mem_init */ #include #include diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 2ffd171af8b6..6b89a66ec1a5 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/ar7/memory.c b/arch/mips/ar7/memory.c index 0332f0514d05..80390a9ec264 100644 --- a/arch/mips/ar7/memory.c +++ b/arch/mips/ar7/memory.c @@ -16,7 +16,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -#include +#include #include #include #include diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 4c7a93f4039a..9728abcb18fa 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -14,7 +14,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index 7019e2967009..77a836e661c9 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index 2be9caaa2085..e28ee9a7cc7e 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 6329c5f780d6..1738a06396f9 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index c44c1a654471..e8eb60ed99f2 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -11,7 +11,7 @@ * Copyright (C) 2010 Cavium Networks, Inc. */ #include -#include +#include #include #include #include diff --git a/arch/mips/dec/prom/memory.c b/arch/mips/dec/prom/memory.c index a2acc6454cf3..5073d2ed78bb 100644 --- a/arch/mips/dec/prom/memory.c +++ b/arch/mips/dec/prom/memory.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/emma/common/prom.c b/arch/mips/emma/common/prom.c index cae42259d6da..675337b8a4a0 100644 --- a/arch/mips/emma/common/prom.c +++ b/arch/mips/emma/common/prom.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index dd9496f26e6a..429b7f8d2aeb 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index 0a0aaf39fd16..4c41ed0a637e 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index 2c7288041a99..81845ba04835 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c index a8657d29c62e..01b2bd95ba1f 100644 --- a/arch/mips/kernel/crash_dump.c +++ b/arch/mips/kernel/crash_dump.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index 89950b7bf536..93b8e0b4332f 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 31522d3bc8bf..41c1683761bb 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 623dc18f7f2f..0f852e1b5891 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 0bef238d2c0c..6176b9acba95 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/commpage.c b/arch/mips/kvm/commpage.c index f43629979a0e..5812e6145801 100644 --- a/arch/mips/kvm/commpage.c +++ b/arch/mips/kvm/commpage.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/dyntrans.c b/arch/mips/kvm/dyntrans.c index f8e772564d74..d77b61b3d6ee 100644 --- a/arch/mips/kvm/dyntrans.c +++ b/arch/mips/kvm/dyntrans.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include "commpage.h" diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 4144bfaef137..ec9ed23bca7f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/interrupt.c b/arch/mips/kvm/interrupt.c index aa0a1a00faf6..7257e8b6f5a9 100644 --- a/arch/mips/kvm/interrupt.c +++ b/arch/mips/kvm/interrupt.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index f7ea8e21656b..1fcc4d149054 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index d984bd5c2ec5..14d4c5e2b42f 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c index 37b8fc5b9ac9..5ce1407de2d5 100644 --- a/arch/mips/lasat/prom.c +++ b/arch/mips/lasat/prom.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson64/common/init.c index 6ef17120722f..c073fbcb9805 100644 --- a/arch/mips/loongson64/common/init.c +++ b/arch/mips/loongson64/common/init.c @@ -8,7 +8,7 @@ * option) any later version. */ -#include +#include #include #include #include diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 703ad4536fe0..622761878cd1 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 0893b6136498..b521d8e2d359 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index b19a3c506b1e..e2a33adc0f29 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -7,7 +7,7 @@ */ #include #include -#include +#include #include #include #include diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c index a47556723b85..868921adef1d 100644 --- a/arch/mips/mti-malta/malta-memory.c +++ b/arch/mips/mti-malta/malta-memory.c @@ -12,7 +12,7 @@ * Steven J. Hill */ #include -#include +#include #include #include diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c index b5ba83f4c646..c856f2a3ea42 100644 --- a/arch/mips/netlogic/xlp/dt.c +++ b/arch/mips/netlogic/xlp/dt.c @@ -33,7 +33,7 @@ */ #include -#include +#include #include #include diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 3c3b1e6abb53..687513880fbf 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index c2e94cf5ecda..e68b44b27c0d 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 1ada8492733b..d544e7b07f7a 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/rb532/prom.c b/arch/mips/rb532/prom.c index 6484e4a4597b..361a690facbf 100644 --- a/arch/mips/rb532/prom.c +++ b/arch/mips/rb532/prom.c @@ -29,7 +29,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index cb1f1a6a166d..d8b8444d6795 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 092fb2a6ec4a..12a780f251e1 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 152ca71cc2d7..3b034b7178d6 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -23,7 +23,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/txx9/rbtx4938/prom.c b/arch/mips/txx9/rbtx4938/prom.c index bcb469247e8c..2b36a2ee744c 100644 --- a/arch/mips/txx9/rbtx4938/prom.c +++ b/arch/mips/txx9/rbtx4938/prom.c @@ -11,7 +11,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c index 63a1a5ef5219..eacc79024879 100644 --- a/arch/nds32/kernel/setup.c +++ b/arch/nds32/kernel/setup.c @@ -2,9 +2,8 @@ // Copyright (C) 2005-2017 Andes Technology Corporation #include -#include -#include #include +#include #include #include #include diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c index e17cb8a69315..022779af6148 100644 --- a/arch/nds32/mm/highmem.c +++ b/arch/nds32/mm/highmem.c @@ -6,7 +6,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index 66d3e9cf498d..131104bd2538 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -7,12 +7,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c index a6d4f7530247..232a36b511aa 100644 --- a/arch/nios2/kernel/prom.c +++ b/arch/nios2/kernel/prom.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index 2d0011ddd4d5..6bbd4ae2beb0 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 12923501d94f..16cea5776b87 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index e17fcd83120f..c605bdad1746 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -30,13 +30,12 @@ #include #include #include -#include +#include #include #include #include #include #include -#include #include #include diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 91a6a9ab7598..d157310eb377 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -26,12 +26,11 @@ #include #include #include -#include +#include #include #include #include /* for initrd_* */ #include -#include #include #include diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 7e7a3126c5e9..2d7cffcaa476 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -14,7 +14,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index d39ec3a4550a..274bd1442dd9 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 2b56d1f30387..93ee3703b42f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 9216c3a7fcfc..2a51e4cc8246 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -29,10 +29,9 @@ #include #include #include -#include +#include #include #include -#include #include #include diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index bf87d6e13369..5b61704447c1 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -2,7 +2,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index a7226ed9cae6..8cf035e68378 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index b3fe79064a69..0a64fffabee1 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -27,12 +27,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 954f1986af4d..67b9d7b669a1 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -44,7 +44,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f04f15f9d232..3a048e98a132 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -11,7 +11,7 @@ #define pr_fmt(fmt) "numa: " fmt #include -#include +#include #include #include #include @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index f45b369177a4..f3391be7c762 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 23a67b545b70..aba81cbf0b36 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -17,11 +17,10 @@ #include #include #include -#include +#include #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 12519857a33c..658bfab3350b 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 349a9ff6ca5b..2444feda831f 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index d58c111099b3..1d9bfaff60bc 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -13,9 +13,8 @@ #include #include -#include -#include #include +#include #include #include diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index d17566a8c76f..97eae3871868 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -13,10 +13,9 @@ #include #include #include -#include +#include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 781c1053a773..72dd23ef771b 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44f9a7d6450b..f82b3d3c36e2 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -20,7 +20,7 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include -#include +#include #include #include #include @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 799a91882a76..8992b04c0ade 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -8,7 +8,7 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include -#include +#include #include #include #include diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index ec31b48a42a5..ebe748a9f472 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 84111a43ea29..eba2def3414d 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 873f6ee1c46d..76d0708438e9 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include #include @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 04638b0b9ef1..0472e27febdf 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -4,14 +4,13 @@ * Author(s): Heiko Carstens */ -#include +#include #include #include #include #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 5a381fc8e958..bfba273c32c0 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 297f5d8b0890..ae0d9e889534 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c index 7f61cc3fd4d1..71a608cd4f61 100644 --- a/arch/s390/numa/toptree.c +++ b/arch/s390/numa/toptree.c @@ -8,7 +8,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 21447f866415..c8c13c777162 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -11,12 +11,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include #include diff --git a/arch/sh/mm/ioremap_fixed.c b/arch/sh/mm/ioremap_fixed.c index 927a1294c465..07e744d75fa0 100644 --- a/arch/sh/mm/ioremap_fixed.c +++ b/arch/sh/mm/ioremap_fixed.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index a41526bd91e2..9a26b442f820 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -5,13 +5,11 @@ */ #include #include -#include #include #include #include #include #include -#include #include #include #include diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index 4389944735c6..d41e2a749c5d 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index de7c87b153fe..cd2825cb8420 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 6cc80d0f4b9f..4792e08ad36b 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 880714565c40..d900952bfc5f 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index a8c3453195e6..3c8aac21f426 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include @@ -25,7 +25,6 @@ #include #include #include -#include #include #include diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index b48fea5ad9ef..a6142c5abf61 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index ef19a391214f..673816880cce 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -6,7 +6,7 @@ * Licensed under the GPL. */ -#include +#include #include #include #include diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 20442d20bd09..2b4dded11a7a 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -9,7 +9,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 844056cf313e..3678f5b05e42 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -4,7 +4,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 2c672a8f4571..1067469ba2ea 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -5,7 +5,6 @@ #include #include -#include #include #include #include diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 296a91a04598..5bf56af4d5b9 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -4,7 +4,6 @@ */ #include -#include #include #include #include diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c index 9969ec374abb..29b71c68eb7c 100644 --- a/arch/unicore32/kernel/hibernate.c +++ b/arch/unicore32/kernel/hibernate.c @@ -13,7 +13,7 @@ #include #include -#include +#include #include #include diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index 9f163f976315..b2c38b32ea57 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include #include @@ -27,7 +27,6 @@ #include #include #include -#include #include #include diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 44fd0e8fbe87..cf4eb9481fd6 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -11,13 +11,12 @@ #include #include #include -#include +#include #include #include #include #include #include -#include #include #include #include diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c index 18b355a20f0b..040a8c279761 100644 --- a/arch/unicore32/mm/mmu.c +++ b/arch/unicore32/mm/mmu.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index f5ea6415b778..7f5d212551d4 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index f1915b744052..ca13851f0570 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -7,7 +7,6 @@ */ #include -#include #include #include #include diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ab731ab09f06..32b2b7a41ef5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8c7450900e0e..5fbc57e4b0b9 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -47,7 +47,7 @@ #include #include /* time_after() */ #include -#include +#include #include #include diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 660d0b22e962..cbbd57ae06ee 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,7 +1,7 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 -#include +#include #include #include #include diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a0ec4c37265a..68ff62bffbab 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -9,11 +9,10 @@ * allocation code routines via a platform independent interface (memblock, etc.). */ #include -#include +#include #include #include #include -#include #include #include diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index f1c5eb99d445..3482460d984d 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 7ba73fe0d917..f4562fcec681 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 71c0b01d93b1..bd08b9e1c9e2 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 637982efecd8..9b158b4716d2 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 7005f89bf3b2..b74e7bfed6ab 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 483412fb8a24..e8796fcd7e5a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5369d7fac797..a9134d1910b9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -49,7 +49,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 75730ce01f8d..285aaa62d153 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 048c761d97b0..058b2f36b3a6 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b24eb4eb9984..71d4b9d4d43f 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -8,7 +8,7 @@ #include /* task_stack_*(), ... */ #include /* oops_begin/end, ... */ #include /* search_exception_tables */ -#include /* max_low_pfn */ +#include /* max_low_pfn */ #include /* NOKPROBE_SYMBOL, ... */ #include /* kmmio_handler, ... */ #include /* perf_sw_event */ diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 62915a5e0fa2..0d4bdcb84da5 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -1,7 +1,7 @@ #include #include #include /* for totalram_pages */ -#include +#include void *kmap(struct page *page) { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index faca978ebf9d..ef99f3892e1f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -3,7 +3,6 @@ #include #include #include -#include /* for max_low_pfn */ #include #include diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 3bbe5f58a67d..49ecf5ecf6d3 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bfb0bedc21d3..5fab264948c2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24e0920a9b25..5378d10f1d31 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -6,7 +6,7 @@ * (C) Copyright 1995 1996 Linus Torvalds */ -#include +#include #include #include #include diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 8f87499124b8..04a9cf6b034f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -5,10 +5,9 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 -#include +#include #include #include -#include #include #include #include diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 61db77b0eda9..3f452ffed7e9 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 16e37d712ffd..1308f5408bf7 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index e8a4a09e20f1..f2bd3d61e16b 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -22,7 +22,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include #include #include diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 066f3511d5f1..59d80160fa5a 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -3,7 +3,7 @@ * Generic VM initialization for x86-64 NUMA setups. * Copyright 2002,2003 Andi Kleen, SuSE Labs. */ -#include +#include #include "numa_internal.h" diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index b54d52a2d00a..a80fdd7fb40f 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -6,7 +6,6 @@ #include #include #include -#include #include #include "numa_internal.h" diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index a25588ad75ef..08f8f76a4852 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -5,7 +5,7 @@ * Clears the a test pte bit on random pages in the direct mapping, * then reverts and compares page tables forwards and afterwards. */ -#include +#include #include #include #include diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 62bb30b4bd2a..f799076e3d57 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -3,7 +3,7 @@ * Thanks to Ben LaHaise for precious feedback. */ #include -#include +#include #include #include #include diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 3d0c83ef6aab..08013524fba1 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -8,7 +8,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index 7f9acb68324c..bdc98150d4db 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include #include #include diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index ed4ac215305d..8cd66152cdb0 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 9061babfbc83..7ae939e353cd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -36,9 +36,8 @@ #include #include #include -#include -#include #include +#include #include #include #include diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e8da7f492970..cf0347f61b21 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4b70d0f5a803..95e77a667ba5 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 140cd76ee897..115c8e4173bb 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -17,7 +17,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 15695e30f982..be15bdcb20df 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 67b2f31a1265..e996e8e744cb 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG -#include +#include #endif #include #include diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index ec7a4209f310..2f6787fc7106 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -31,7 +31,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b3e11afed25b..b06731705529 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -67,7 +67,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c index 21f13e9aabe1..5ca440a74316 100644 --- a/arch/xtensa/kernel/pci.c +++ b/arch/xtensa/kernel/pci.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 9220dcde7520..b27359e2a464 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index f7fbe6334939..9750a48f491b 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -18,7 +18,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index 1a30a258ccd0..6b95ca43aec0 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -8,11 +8,10 @@ * Copyright (C) 2017 Cadence Design Systems Inc. */ -#include +#include #include #include #include -#include #include #include #include diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index f33a1ff2662a..a4dcfd39bc5c 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -4,7 +4,7 @@ * * Extracted from init.c */ -#include +#include #include #include #include diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 206b9d4591e8..190846dddc67 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index 58709e89a8ed..c14cc673976c 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -16,7 +16,7 @@ * option) any later version. * */ -#include +#include #include #include #include diff --git a/block/blk-settings.c b/block/blk-settings.c index ffd459969689..696c04c1ab6c 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -6,7 +6,7 @@ #include #include #include -#include /* for max_pfn/max_low_pfn */ +#include /* for max_pfn/max_low_pfn */ #include #include #include diff --git a/block/bounce.c b/block/bounce.c index ec0d99995f5f..cf49fe02f65c 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 85167603b9c9..274699463b4f 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index a3d012b08fc5..61203eebf3a1 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -31,9 +31,8 @@ #include #include #include -#include -#include #include +#include #include #include "internal.h" diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 23cf4427f425..41b91af95afb 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 5c54d3734daf..5b2867a33b98 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include "clock.h" diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index f2483548cde9..099d83e4e910 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 2b675f788b61..ac1654f74dc7 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -20,7 +20,7 @@ #define pr_fmt(fmt) "apple-properties: " fmt -#include +#include #include #include #include diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c index 2224f1dc074b..72d9ea18270b 100644 --- a/drivers/firmware/iscsi_ibft_find.c +++ b/drivers/firmware/iscsi_ibft_find.c @@ -18,7 +18,7 @@ * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 03cead6d5f97..2a23453f005a 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f9f69f7111a9..44bd5b9166bb 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 676c029494e4..0e780848f59b 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -13,7 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 0069f9084f9f..880a81c82b7a 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -38,7 +38,6 @@ #include #include #include -#include #include #include diff --git a/drivers/mtd/ar7part.c b/drivers/mtd/ar7part.c index fc15ec58230a..0d33cf0842ad 100644 --- a/drivers/mtd/ar7part.c +++ b/drivers/mtd/ar7part.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index a07e24970be4..11c5bad95226 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 38fa60ddaf2e..28510e33924f 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include "arcdevice.h" diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 4e56aaf2b984..2c546013a980 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index ffe62a7ae19b..bb532aae0d92 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 01e23b85e798..49ae2aa744d6 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -5,7 +5,7 @@ #define pr_fmt(fmt) "### dt-test ### " fmt -#include +#include #include #include #include diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 16a4e8528bbc..8f3a2eeb28dc 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -8,7 +8,7 @@ * Copyright IBM Corp. 2003, 2009 */ -#include +#include #include #include #include diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 5b8af2782282..2b0c36c2c568 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -19,7 +19,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c index 8af4948dae80..72dd2471ec1e 100644 --- a/drivers/s390/cio/cmf.c +++ b/drivers/s390/cio/cmf.c @@ -13,7 +13,7 @@ #define KMSG_COMPONENT "cio" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt -#include +#include #include #include #include diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 8f5c1d7f751a..97b6f197f007 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/sfi/sfi_core.c b/drivers/sfi/sfi_core.c index 153b3f3cc795..a5136901dd8a 100644 --- a/drivers/sfi/sfi_core.c +++ b/drivers/sfi/sfi_core.c @@ -59,7 +59,7 @@ #define KMSG_COMPONENT "SFI" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt -#include +#include #include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 79ad30d34949..b929c7ae3a27 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c b/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c index 4eba17f3d293..56fc527015cb 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c b/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c index e3bff068dc3c..6a1cd03bfe39 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index ddc5fa88f268..d2652dccc699 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index e12bb256036f..a3f5cbfcd4a1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -44,7 +44,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index e6c1934734b7..93194f3e7540 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 84575baceebc..f15f89df1f36 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -33,7 +33,7 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt -#include +#include #include #include #include diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index c5f26a87d238..2a7f545bd0b5 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -35,7 +35,6 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt -#include #include #include #include diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 55988b8418ee..5165aa82bf7d 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -68,7 +68,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include +#include #include #include #include diff --git a/fs/dcache.c b/fs/dcache.c index c2e443fb76ae..2593153471cf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/inode.c b/fs/inode.c index 9b808986d440..9e198f00b64c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/namespace.c b/fs/namespace.c index d86830c86ce8..98d27da43304 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d297fe4472a9..bbcc185062bb 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/proc/page.c b/fs/proc/page.c index 792c78a49174..6c517b11acf8 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include #include #include diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 0377a104495b..3fe90443c1bb 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h deleted file mode 100644 index b58873a567b2..000000000000 --- a/include/linux/bootmem.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 - */ -#ifndef _LINUX_BOOTMEM_H -#define _LINUX_BOOTMEM_H - -#include -#include -#include -#include - -/* - * simple boot-time physical memory area allocator. - */ - -extern unsigned long max_low_pfn; -extern unsigned long min_low_pfn; - -/* - * highest page - */ -extern unsigned long max_pfn; -/* - * highest possible page - */ -extern unsigned long long max_possible_pfn; - -extern unsigned long memblock_free_all(void); -extern void reset_node_managed_pages(pg_data_t *pgdat); -extern void reset_all_zones_managed_pages(void); - -/* We are using top down, so it is safe to use 0 here */ -#define BOOTMEM_LOW_LIMIT 0 - -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - -/* FIXME: use MEMBLOCK_ALLOC_* variants here */ -#define BOOTMEM_ALLOC_ACCESSIBLE 0 -#define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) - -/* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid_nopanic(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void __memblock_free_early(phys_addr_t base, phys_addr_t size); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); - -static inline void * __init memblock_alloc( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} -static inline void * __init memblock_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid_nopanic(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_node( - phys_addr_t size, phys_addr_t align, int nid) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, nid); -} - -static inline void * __init memblock_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - nid); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - -extern void *alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit); - -#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min - * shift passed via *_hash_shift */ -#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ - -/* Only NUMA needs hash distribution. 64bit NUMA architectures have - * sufficient vmalloc space. - */ -#ifdef CONFIG_NUMA -#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) -extern int hashdist; /* Distribute hashes across NUMA nodes? */ -#else -#define hashdist (0) -#endif - - -#endif /* _LINUX_BOOTMEM_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9d46a7204975..1b4d85879cbe 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -15,6 +15,19 @@ #include #include +#include + +extern unsigned long max_low_pfn; +extern unsigned long min_low_pfn; + +/* + * highest page + */ +extern unsigned long max_pfn; +/* + * highest possible page + */ +extern unsigned long long max_possible_pfn; #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 @@ -119,6 +132,10 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); enum memblock_flags choose_memblock_flags(void); +unsigned long memblock_free_all(void); +void reset_node_managed_pages(pg_data_t *pgdat); +void reset_all_zones_managed_pages(void); + /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, @@ -300,11 +317,116 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +/* Flags for memblock allocation APIs */ +#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) +#define MEMBLOCK_ALLOC_ACCESSIBLE 0 + +/* We are using top down, so it is safe to use 0 here */ +#define MEMBLOCK_LOW_LIMIT 0 + +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); + +static inline void * __init memblock_alloc(phys_addr_t size, phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_raw(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_low(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); +} +static inline void * __init memblock_alloc_low_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from_nopanic(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid_nopanic(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_node(phys_addr_t size, + phys_addr_t align, int nid) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, + int nid) +{ + return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void __init memblock_free_early(phys_addr_t base, + phys_addr_t size) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_early_nid(phys_addr_t base, + phys_addr_t size, int nid) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + __memblock_free_late(base, size); +} + /* * Set the allocation direction to bottom-up or top-down. */ @@ -323,10 +445,6 @@ static inline bool memblock_bottom_up(void) return memblock.bottom_up; } -/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ -#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) -#define MEMBLOCK_ALLOC_ACCESSIBLE 0 - phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, enum memblock_flags flags); @@ -432,6 +550,31 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) +extern void *alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit); + +#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ +#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min + * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ + +/* Only NUMA needs hash distribution. 64bit NUMA architectures have + * sufficient vmalloc space. + */ +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ +#else +#define hashdist (0) +#endif + #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else diff --git a/init/main.c b/init/main.c index 8cef69c61389..51b8e7b8ae5b 100644 --- a/init/main.c +++ b/init/main.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index f14c376937e5..22a12ab5a5e9 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -4,7 +4,7 @@ * * DMA operations that map physical memory directly without using an IOMMU. */ -#include /* for max_pfn */ +#include /* for max_pfn */ #include #include #include diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 801da67e957b..5731daa09a32 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -40,7 +40,7 @@ #include #include -#include +#include #include #define CREATE_TRACE_POINTS diff --git a/kernel/futex.c b/kernel/futex.c index 3e2de8fc1891..f423f9b6577e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -65,7 +65,7 @@ #include #include #include -#include +#include #include #include diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 0130e488ebfe..8f36c27c1794 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -4,7 +4,7 @@ #endif #include -#include +#include #include /* diff --git a/kernel/pid.c b/kernel/pid.c index cdf63e53a014..b2f6c506035d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 34116a6097be..3c9e365438ad 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 429e4a3833ca..1b2a029360b7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/profile.c b/kernel/profile.c index 9aa2a4445b0d..9c08a2c7cb1d 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include #include #include diff --git a/lib/cpumask.c b/lib/cpumask.c index 1405cb22e6bc..75b5e7672c4c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include /** * cpumask_next - get the next cpu in a cpumask diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e35d99844612..c007fb5fb8d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 785a9707786b..c7550eb65922 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -10,11 +10,10 @@ * */ -#include +#include #include #include #include -#include #include #include #include diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 4f7e4b5a2f08..877de4fa0720 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -92,7 +92,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/mm/memblock.c b/mm/memblock.c index 2ed73245b5da..c655342569f8 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 7e6509a53d79..41e326472ef9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5f3291601945..ef289fadec0e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/page_ext.c b/mm/page_ext.c index 5323c2ade686..ae44f7adbe07 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include -#include +#include #include #include #include diff --git a/mm/page_idle.c b/mm/page_idle.c index 6302bc62c27d..b9e4b42b33ab 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include +#include #include #include #include diff --git a/mm/page_owner.c b/mm/page_owner.c index d80adfe702d3..87bc0dfdb52b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/mm/percpu.c b/mm/percpu.c index 3050c1d37d37..61cdbb3b3736 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -65,7 +65,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include +#include #include #include #include diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 7408cabed61a..7fec05796796 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -20,7 +20,6 @@ */ #include #include -#include #include #include #include diff --git a/mm/sparse.c b/mm/sparse.c index b139fbc61d10..ab2ac45e0440 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f5c9ef2586de..411dd7a90046 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1834818ed07b..9e6bc4d6daa7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -262,7 +262,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca3ed931f2a9..1976fddb9e00 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -81,7 +81,7 @@ #include #include -#include +#include #include #include #include diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e948db29ab53..9b277bd36d1a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -46,7 +46,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c index 2ad33ce1ea17..eca8d84d99bf 100644 --- a/net/xfrm/xfrm_hash.c +++ b/net/xfrm/xfrm_hash.c @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include #include -- cgit v1.2.3-71-gd317 From 7e1c4e27928e5f87b9b1eaf06dc31773b2f1e7f1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:57 -0700 Subject: memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Suggested-by: Michal Hocko Acked-by: Paul Burton [MIPS] Acked-by: Michael Ellerman [powerpc] Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Ingo Molnar Cc: Matt Turner Cc: Michal Simek Cc: Richard Weinberger Cc: Russell King Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_apecs.c | 3 ++- arch/alpha/kernel/core_lca.c | 3 ++- arch/alpha/kernel/core_marvel.c | 4 ++-- arch/alpha/kernel/core_mcpcia.c | 6 +++-- arch/alpha/kernel/core_t2.c | 2 +- arch/alpha/kernel/core_titan.c | 6 +++-- arch/alpha/kernel/core_tsunami.c | 6 +++-- arch/alpha/kernel/core_wildfire.c | 6 +++-- arch/alpha/kernel/pci-noop.c | 4 ++-- arch/alpha/kernel/pci.c | 4 ++-- arch/alpha/kernel/pci_iommu.c | 4 ++-- arch/arm/kernel/setup.c | 4 ++-- arch/arm/mach-omap2/omap_hwmod.c | 8 ++++--- arch/arm64/kernel/setup.c | 2 +- arch/ia64/kernel/mca.c | 4 ++-- arch/ia64/mm/tlb.c | 6 +++-- arch/ia64/sn/kernel/io_common.c | 4 +++- arch/ia64/sn/kernel/setup.c | 5 ++-- arch/m68k/sun3/sun3dvma.c | 2 +- arch/microblaze/mm/init.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/paca.c | 2 +- arch/powerpc/kernel/pci_32.c | 3 ++- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/mmu_context_nohash.c | 7 +++--- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 6 ++--- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/um/drivers/net_kern.c | 2 +- arch/um/drivers/vector_kern.c | 2 +- arch/um/kernel/initrd.c | 2 +- arch/unicore32/kernel/setup.c | 2 +- arch/x86/kernel/acpi/boot.c | 2 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/e820.c | 3 ++- arch/x86/platform/olpc/olpc_dt.c | 2 +- arch/xtensa/platforms/iss/network.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- drivers/firmware/memmap.c | 3 ++- drivers/macintosh/smu.c | 2 +- drivers/of/of_reserved_mem.c | 1 + include/linux/memblock.h | 3 ++- init/main.c | 13 +++++++---- kernel/power/snapshot.c | 3 ++- lib/cpumask.c | 2 +- mm/memblock.c | 8 ------- mm/page_alloc.c | 6 +++-- mm/percpu.c | 38 ++++++++++++++++--------------- mm/sparse.c | 3 ++- 50 files changed, 120 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_apecs.c b/arch/alpha/kernel/core_apecs.c index 1bf3eef34c22..6df765ff2b10 100644 --- a/arch/alpha/kernel/core_apecs.c +++ b/arch/alpha/kernel/core_apecs.c @@ -346,7 +346,8 @@ apecs_init_arch(void) * Window 1 is direct access 1GB at 1GB * Window 2 is scatter-gather 8MB at 8MB (for isa) */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = NULL; __direct_map_base = 0x40000000; __direct_map_size = 0x40000000; diff --git a/arch/alpha/kernel/core_lca.c b/arch/alpha/kernel/core_lca.c index 81c0c43635b0..57e0750419f2 100644 --- a/arch/alpha/kernel/core_lca.c +++ b/arch/alpha/kernel/core_lca.c @@ -275,7 +275,8 @@ lca_init_arch(void) * Note that we do not try to save any of the DMA window CSRs * before setting them, since we cannot read those CSRs on LCA. */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = NULL; __direct_map_base = 0x40000000; __direct_map_size = 0x40000000; diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 8a568c4d8e81..c1d0c18c71ca 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -82,7 +82,7 @@ mk_resource_name(int pe, int port, char *str) char *name; sprintf(tmp, "PCI %s PE %d PORT %d", str, pe, port); - name = memblock_alloc(strlen(tmp) + 1, 0); + name = memblock_alloc(strlen(tmp) + 1, SMP_CACHE_BYTES); strcpy(name, tmp); return name; @@ -117,7 +117,7 @@ alloc_io7(unsigned int pe) return NULL; } - io7 = memblock_alloc(sizeof(*io7), 0); + io7 = memblock_alloc(sizeof(*io7), SMP_CACHE_BYTES); io7->pe = pe; raw_spin_lock_init(&io7->irq_lock); diff --git a/arch/alpha/kernel/core_mcpcia.c b/arch/alpha/kernel/core_mcpcia.c index b1549db54260..74b1d018124c 100644 --- a/arch/alpha/kernel/core_mcpcia.c +++ b/arch/alpha/kernel/core_mcpcia.c @@ -364,9 +364,11 @@ mcpcia_startup_hose(struct pci_controller *hose) * Window 1 is scatter-gather (up to) 1GB at 1GB (for pci) * Window 2 is direct access 2GB at 2GB */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = iommu_arena_new(hose, 0x40000000, - size_for_memory(0x40000000), 0); + size_for_memory(0x40000000), + SMP_CACHE_BYTES); __direct_map_base = 0x80000000; __direct_map_size = 0x80000000; diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c index 2c00b61ca379..98d5b6ff8a76 100644 --- a/arch/alpha/kernel/core_t2.c +++ b/arch/alpha/kernel/core_t2.c @@ -351,7 +351,7 @@ t2_sg_map_window2(struct pci_controller *hose, /* Note we can only do 1 SG window, as the other is for direct, so do an ISA SG area, especially for the floppy. */ - hose->sg_isa = iommu_arena_new(hose, base, length, 0); + hose->sg_isa = iommu_arena_new(hose, base, length, SMP_CACHE_BYTES); hose->sg_pci = NULL; temp = (base & 0xfff00000UL) | ((base + length - 1) >> 20); diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 97551597581b..2a2820fb1be6 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -316,10 +316,12 @@ titan_init_one_pachip_port(titan_pachip_port *port, int index) * Window 1 is direct access 1GB at 2GB * Window 2 is scatter-gather 1GB at 3GB */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_isa->align_entry = 8; /* 64KB for ISA */ - hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000, 0); + hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000, + SMP_CACHE_BYTES); hose->sg_pci->align_entry = 4; /* Titan caches 4 PTEs at a time */ port->wsba[0].csr = hose->sg_isa->dma_base | 3; diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c index f334b8928d72..fc1ab73f23de 100644 --- a/arch/alpha/kernel/core_tsunami.c +++ b/arch/alpha/kernel/core_tsunami.c @@ -319,12 +319,14 @@ tsunami_init_one_pchip(tsunami_pchip *pchip, int index) * NOTE: we need the align_entry settings for Acer devices on ES40, * specifically floppy and IDE when memory is larger than 2GB. */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); /* Initially set for 4 PTEs, but will be overridden to 64K for ISA. */ hose->sg_isa->align_entry = 4; hose->sg_pci = iommu_arena_new(hose, 0x40000000, - size_for_memory(0x40000000), 0); + size_for_memory(0x40000000), + SMP_CACHE_BYTES); hose->sg_pci->align_entry = 4; /* Tsunami caches 4 PTEs at a time */ __direct_map_base = 0x80000000; diff --git a/arch/alpha/kernel/core_wildfire.c b/arch/alpha/kernel/core_wildfire.c index cad36fc6ed7d..353c03d15442 100644 --- a/arch/alpha/kernel/core_wildfire.c +++ b/arch/alpha/kernel/core_wildfire.c @@ -111,8 +111,10 @@ wildfire_init_hose(int qbbno, int hoseno) * ??? We ought to scale window 3 memory. * */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); - hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); + hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000, + SMP_CACHE_BYTES); pci = WILDFIRE_pci(qbbno, hoseno); diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index a9378ee0c2f1..091cff3c68fd 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -33,7 +33,7 @@ alloc_pci_controller(void) { struct pci_controller *hose; - hose = memblock_alloc(sizeof(*hose), 0); + hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES); *hose_tail = hose; hose_tail = &hose->next; @@ -44,7 +44,7 @@ alloc_pci_controller(void) struct resource * __init alloc_resource(void) { - return memblock_alloc(sizeof(struct resource), 0); + return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); } SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, bus, diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 13937e72d875..97098127df83 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -392,7 +392,7 @@ alloc_pci_controller(void) { struct pci_controller *hose; - hose = memblock_alloc(sizeof(*hose), 0); + hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES); *hose_tail = hose; hose_tail = &hose->next; @@ -403,7 +403,7 @@ alloc_pci_controller(void) struct resource * __init alloc_resource(void) { - return memblock_alloc(sizeof(struct resource), 0); + return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); } diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 82cf950bda2a..46e08e0d9181 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -79,7 +79,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, printk("%s: couldn't allocate arena from node %d\n" " falling back to system-wide allocation\n", __func__, nid); - arena = memblock_alloc(sizeof(*arena), 0); + arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); } arena->ptes = memblock_alloc_node(sizeof(*arena), align, nid); @@ -92,7 +92,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, #else /* CONFIG_DISCONTIGMEM */ - arena = memblock_alloc(sizeof(*arena), 0); + arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); arena->ptes = memblock_alloc_from(mem_size, align, 0); #endif /* CONFIG_DISCONTIGMEM */ diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 840a4adc69fc..ac7e08886863 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -856,7 +856,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) */ boot_alias_start = phys_to_idmap(start); if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { - res = memblock_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM (boot alias)"; res->start = boot_alias_start; res->end = phys_to_idmap(end); @@ -864,7 +864,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&iomem_resource, res); } - res = memblock_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM"; res->start = start; res->end = end; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index cd5732ab0cdf..083dcd9942ce 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -726,7 +726,7 @@ static int __init _setup_clkctrl_provider(struct device_node *np) u64 size; int i; - provider = memblock_alloc(sizeof(*provider), 0); + provider = memblock_alloc(sizeof(*provider), SMP_CACHE_BYTES); if (!provider) return -ENOMEM; @@ -736,12 +736,14 @@ static int __init _setup_clkctrl_provider(struct device_node *np) of_property_count_elems_of_size(np, "reg", sizeof(u32)) / 2; provider->addr = - memblock_alloc(sizeof(void *) * provider->num_addrs, 0); + memblock_alloc(sizeof(void *) * provider->num_addrs, + SMP_CACHE_BYTES); if (!provider->addr) return -ENOMEM; provider->size = - memblock_alloc(sizeof(u32) * provider->num_addrs, 0); + memblock_alloc(sizeof(u32) * provider->num_addrs, + SMP_CACHE_BYTES); if (!provider->size) return -ENOMEM; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7ce7306f1d75..953e316521fc 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -218,7 +218,7 @@ static void __init request_standard_resources(void) num_standard_resources = memblock.memory.cnt; standard_resources = memblock_alloc_low(num_standard_resources * sizeof(*standard_resources), - 0); + SMP_CACHE_BYTES); for_each_memblock(memory, region) { res = &standard_resources[i++]; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 9a6603f8e409..91bd1e129379 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -361,9 +361,9 @@ static ia64_state_log_t ia64_state_log[IA64_MAX_LOG_TYPES]; #define IA64_LOG_ALLOCATE(it, size) \ {ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)] = \ - (ia64_err_rec_t *)memblock_alloc(size, 0); \ + (ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES); \ ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)] = \ - (ia64_err_rec_t *)memblock_alloc(size, 0);} + (ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES);} #define IA64_LOG_LOCK_INIT(it) spin_lock_init(&ia64_state_log[it].isl_lock) #define IA64_LOG_LOCK(it) spin_lock_irqsave(&ia64_state_log[it].isl_lock, s) #define IA64_LOG_UNLOCK(it) spin_unlock_irqrestore(&ia64_state_log[it].isl_lock,s) diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index ab545daff7c3..9340bcb4f29c 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -59,8 +59,10 @@ struct ia64_tr_entry *ia64_idtrs[NR_CPUS]; void __init mmu_context_init (void) { - ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0); - ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0); + ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, + SMP_CACHE_BYTES); + ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, + SMP_CACHE_BYTES); } /* diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c index 98f55220c67d..8df13d0d96fa 100644 --- a/arch/ia64/sn/kernel/io_common.c +++ b/arch/ia64/sn/kernel/io_common.c @@ -391,7 +391,9 @@ void __init hubdev_init_node(nodepda_t * npda, cnodeid_t node) if (node >= num_online_nodes()) /* Headless/memless IO nodes */ node = 0; - hubdev_info = (struct hubdev_info *)memblock_alloc_node(size, 0, node); + hubdev_info = (struct hubdev_info *)memblock_alloc_node(size, + SMP_CACHE_BYTES, + node); npda->pdinfo = (void *)hubdev_info; } diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index 71ad6b0ccab4..a6d40a2c5bff 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -511,7 +511,8 @@ static void __init sn_init_pdas(char **cmdline_p) */ for_each_online_node(cnode) { nodepdaindr[cnode] = - memblock_alloc_node(sizeof(nodepda_t), 0, cnode); + memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES, + cnode); memset(nodepdaindr[cnode]->phys_cpuid, -1, sizeof(nodepdaindr[cnode]->phys_cpuid)); spin_lock_init(&nodepdaindr[cnode]->ptc_lock); @@ -522,7 +523,7 @@ static void __init sn_init_pdas(char **cmdline_p) */ for (cnode = num_online_nodes(); cnode < num_cnodes; cnode++) nodepdaindr[cnode] = - memblock_alloc_node(sizeof(nodepda_t), 0, 0); + memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES, 0); /* * Now copy the array of nodepda pointers to each nodepda. diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index 8be8b750c629..4d64711d3d47 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -268,7 +268,7 @@ void __init dvma_init(void) list_add(&(hole->list), &hole_list); iommu_use = memblock_alloc(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long), - 0); + SMP_CACHE_BYTES); dvma_unmap_iommu(DVMA_START, DVMA_SIZE); diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 8c14988f52f2..b17fd8aafd64 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -376,7 +376,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (mem_init_done) p = kzalloc(size, mask); else { - p = memblock_alloc(size, 0); + p = memblock_alloc(size, SMP_CACHE_BYTES); if (p) memset(p, 0, size); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 41c1683761bb..ea09ed6a80a9 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -916,7 +916,7 @@ static void __init resource_init(void) if (end >= HIGHMEM_START) end = HIGHMEM_START - 1; - res = memblock_alloc(sizeof(struct resource), 0); + res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); res->start = start; res->end = end; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index f331a0054b3a..913bfca09c4f 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -198,7 +198,7 @@ void __init allocate_paca_ptrs(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; - paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, 0)); + paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, SMP_CACHE_BYTES)); memset(paca_ptrs, 0x88, paca_ptrs_size); } diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 274bd1442dd9..d3f04f2d8249 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -203,7 +203,8 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = memblock_alloc(sizeof(struct property) + 256, 0); + of_prop = memblock_alloc(sizeof(struct property) + 256, + SMP_CACHE_BYTES); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index 5b61704447c1..dedf88a76f58 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -14,7 +14,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (slab_is_available()) p = kzalloc(size, mask); else { - p = memblock_alloc(size, 0); + p = memblock_alloc(size, SMP_CACHE_BYTES); } return p; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 67b9d7b669a1..2faca46ad720 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -461,10 +461,11 @@ void __init mmu_context_init(void) /* * Allocate the maps used by context management */ - context_map = memblock_alloc(CTX_MAP_SIZE, 0); - context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); + context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); + context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), + SMP_CACHE_BYTES); #ifdef CONFIG_SMP - stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, 0); + stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index f3391be7c762..ae54d7fe68f3 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -513,7 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) printk(KERN_ERR "nvram: no address\n"); return -EINVAL; } - nvram_image = memblock_alloc(NVRAM_SIZE, 0); + nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index aba81cbf0b36..dd807446801e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3769,7 +3769,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb_id = be64_to_cpup(prop64); pr_debug(" PHB-ID : 0x%016llx\n", phb_id); - phb = memblock_alloc(sizeof(*phb), 0); + phb = memblock_alloc(sizeof(*phb), SMP_CACHE_BYTES); /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); @@ -3815,7 +3815,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, else phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE; - phb->diag_data = memblock_alloc(phb->diag_data_size, 0); + phb->diag_data = memblock_alloc(phb->diag_data_size, SMP_CACHE_BYTES); /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(hose, np, !hose->global_number); @@ -3874,7 +3874,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, } pemap_off = size; size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe); - aux = memblock_alloc(size, 0); + aux = memblock_alloc(size, SMP_CACHE_BYTES); phb->ioda.pe_alloc = aux; phb->ioda.m64_segmap = aux + m64map_off; phb->ioda.m32_segmap = aux + m32map_off; diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 2444feda831f..d45450f6666a 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -128,7 +128,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, if (bmp->bitmap_from_slab) bmp->bitmap = kzalloc(size, GFP_KERNEL); else { - bmp->bitmap = memblock_alloc(size, 0); + bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 673816880cce..624cb47cc9cd 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -650,7 +650,7 @@ static int __init eth_setup(char *str) return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->index = n; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 2b4dded11a7a..10d8d20eb9ec 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1580,7 +1580,7 @@ static int __init vector_setup(char *str) str, error); return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->unit = n; new->arguments = str; diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 3678f5b05e42..ce169ea87e61 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -36,7 +36,7 @@ int __init read_initrd(void) return 0; } - area = memblock_alloc(size, 0); + area = memblock_alloc(size, SMP_CACHE_BYTES); if (load_initrd(initrd, area, size) == -1) return 0; diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index b2c38b32ea57..4b0cb68c355a 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -206,7 +206,7 @@ request_standard_resources(struct meminfo *mi) if (mi->bank[i].size == 0) continue; - res = memblock_alloc_low(sizeof(*res), 0); + res = memblock_alloc_low(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM"; res->start = mi->bank[i].start; res->end = mi->bank[i].start + mi->bank[i].size - 1; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7f5d212551d4..92c76bf97ad8 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -934,7 +934,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) */ #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, - 0); + SMP_CACHE_BYTES); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5fbc57e4b0b9..2953bbf05c08 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2578,7 +2578,7 @@ static struct resource * __init ioapic_setup_resources(void) n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource); n *= nr_ioapics; - mem = memblock_alloc(n, 0); + mem = memblock_alloc(n, SMP_CACHE_BYTES); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 68ff62bffbab..50895c2f937d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1093,7 +1093,8 @@ void __init e820__reserve_resources(void) struct resource *res; u64 end; - res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, 0); + res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, + SMP_CACHE_BYTES); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 115c8e4173bb..24d2175a9480 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -141,7 +141,7 @@ void * __init prom_early_alloc(unsigned long size) * fast enough on the platforms we care about while minimizing * wasted bootmem) and hand off chunks of it to callers. */ - res = memblock_alloc(chunk_size, 0); + res = memblock_alloc(chunk_size, SMP_CACHE_BYTES); BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 190846dddc67..d052712373b6 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -646,7 +646,7 @@ static int __init iss_net_setup(char *str) return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); if (new == NULL) { pr_err("Alloc_bootmem failed\n"); return 1; diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 5b2867a33b98..e205af814582 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -342,7 +342,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem) { struct clk_iomap *io; - io = memblock_alloc(sizeof(*io), 0); + io = memblock_alloc(sizeof(*io), SMP_CACHE_BYTES); io->mem = mem; diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index ef618bceb79a..fa2904fb841f 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,7 +15,7 @@ static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) { - return memblock_phys_alloc(size, 0); + return memblock_phys_alloc(size, SMP_CACHE_BYTES); } static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 2a23453f005a..d168c87c7d30 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -333,7 +333,8 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; - entry = memblock_alloc(sizeof(struct firmware_map_entry), 0); + entry = memblock_alloc(sizeof(struct firmware_map_entry), + SMP_CACHE_BYTES); if (WARN_ON(!entry)) return -ENOMEM; diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 880a81c82b7a..0a0b8e1f4236 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -492,7 +492,7 @@ int __init smu_init (void) goto fail_np; } - smu = memblock_alloc(sizeof(struct smu_device), 0); + smu = memblock_alloc(sizeof(struct smu_device), SMP_CACHE_BYTES); spin_lock_init(&smu->lock); INIT_LIST_HEAD(&smu->cmd_list); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index d6255c276a41..1977ee0adcb1 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -36,6 +36,7 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, * panic()s on allocation failure. */ end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end; + align = !align ? SMP_CACHE_BYTES : align; base = __memblock_alloc_base(size, align, end); if (!base) return -ENOMEM; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1b4d85879cbe..aee299a6aa76 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -406,7 +406,8 @@ static inline void * __init memblock_alloc_node(phys_addr_t size, static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, int nid) { - return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, + MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } diff --git a/init/main.c b/init/main.c index 51b8e7b8ae5b..ee147103ba1b 100644 --- a/init/main.c +++ b/init/main.c @@ -375,10 +375,11 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } static void __init setup_command_line(char *command_line) { saved_command_line = - memblock_alloc(strlen(boot_command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, SMP_CACHE_BYTES); initcall_command_line = - memblock_alloc(strlen(boot_command_line) + 1, 0); - static_command_line = memblock_alloc(strlen(command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, SMP_CACHE_BYTES); + static_command_line = memblock_alloc(strlen(command_line) + 1, + SMP_CACHE_BYTES); strcpy(saved_command_line, boot_command_line); strcpy(static_command_line, command_line); } @@ -773,8 +774,10 @@ static int __init initcall_blacklist(char *str) str_entry = strsep(&str, ","); if (str_entry) { pr_debug("blacklisting initcall %s\n", str_entry); - entry = memblock_alloc(sizeof(*entry), 0); - entry->buf = memblock_alloc(strlen(str_entry) + 1, 0); + entry = memblock_alloc(sizeof(*entry), + SMP_CACHE_BYTES); + entry->buf = memblock_alloc(strlen(str_entry) + 1, + SMP_CACHE_BYTES); strcpy(entry->buf, str_entry); list_add(&entry->next, &blacklisted_initcalls); } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3c9e365438ad..b0308a2c6000 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -963,7 +963,8 @@ void __init __register_nosave_region(unsigned long start_pfn, BUG_ON(!region); } else { /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), 0); + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); } region->start_pfn = start_pfn; region->end_pfn = end_pfn; diff --git a/lib/cpumask.c b/lib/cpumask.c index 75b5e7672c4c..8d666ab84b5c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -163,7 +163,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_alloc(cpumask_size(), 0); + *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); } /** diff --git a/mm/memblock.c b/mm/memblock.c index c655342569f8..839531133816 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1247,9 +1247,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, { phys_addr_t found; - if (!align) - align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) { @@ -1343,8 +1340,6 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * The allocation is performed from memory region limited by * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE. * - * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0. - * * The phys address of allocated boot memory block is converted to virtual and * allocated memory is reset to 0. * @@ -1374,9 +1369,6 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); - if (!align) - align = SMP_CACHE_BYTES; - if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; again: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ef289fadec0e..a919ba5cb3c8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7710,9 +7710,11 @@ void *__init alloc_large_system_hash(const char *tablename, size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) - table = memblock_alloc_nopanic(size, 0); + table = memblock_alloc_nopanic(size, + SMP_CACHE_BYTES); else - table = memblock_alloc_raw(size, 0); + table = memblock_alloc_raw(size, + SMP_CACHE_BYTES); } else if (hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); } else { diff --git a/mm/percpu.c b/mm/percpu.c index 61cdbb3b3736..a6b74c6fe0be 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1102,8 +1102,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, /* allocate chunk */ chunk = memblock_alloc(sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT), - 0); + BITS_TO_LONGS(region_size >> PAGE_SHIFT), + SMP_CACHE_BYTES); INIT_LIST_HEAD(&chunk->list); @@ -1114,12 +1114,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); - chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * - sizeof(chunk->alloc_map[0]), 0); - chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * - sizeof(chunk->bound_map[0]), 0); - chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * - sizeof(chunk->md_blocks[0]), 0); + chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), + SMP_CACHE_BYTES); + chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), + SMP_CACHE_BYTES); + chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), + SMP_CACHE_BYTES); pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ @@ -2075,12 +2075,14 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = memblock_alloc(ai->nr_groups * - sizeof(group_offsets[0]), 0); - group_sizes = memblock_alloc(ai->nr_groups * - sizeof(group_sizes[0]), 0); - unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); - unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); + group_offsets = memblock_alloc(ai->nr_groups * sizeof(group_offsets[0]), + SMP_CACHE_BYTES); + group_sizes = memblock_alloc(ai->nr_groups * sizeof(group_sizes[0]), + SMP_CACHE_BYTES); + unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), + SMP_CACHE_BYTES); + unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), + SMP_CACHE_BYTES); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -2144,8 +2146,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = memblock_alloc( - pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); + pcpu_slot = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_slot[0]), + SMP_CACHE_BYTES); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -2458,7 +2460,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = memblock_alloc_nopanic(areas_size, 0); + areas = memblock_alloc_nopanic(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; @@ -2599,7 +2601,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = memblock_alloc(pages_size, 0); + pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); /* allocate pages */ j = 0; diff --git a/mm/sparse.c b/mm/sparse.c index ab2ac45e0440..33307fc05c4d 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,8 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_alloc_node(array_size, 0, nid); + section = memblock_alloc_node(array_size, SMP_CACHE_BYTES, + nid); return section; } -- cgit v1.2.3-71-gd317 From d15e59260f62bd5e0f625cf5f5240f6ffac78ab6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:18 -0700 Subject: mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: Boris Ostrovsky Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/powernv/memtrace.c | 2 +- arch/powerpc/platforms/pseries/hotplug-memory.c | 6 +++--- drivers/acpi/acpi_memhotplug.c | 2 +- include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 9 ++++++++- 5 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index a29fdf8a2e56..773623f6bfb1 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -121,7 +121,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) lock_device_hotplug(); end_pfn = base_pfn + nr_pages; for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) { - remove_memory(nid, pfn << PAGE_SHIFT, bytes); + __remove_memory(nid, pfn << PAGE_SHIFT, bytes); } unlock_device_hotplug(); return base_pfn << PAGE_SHIFT; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2b796da822c2..d79b31e7a6cf 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -300,7 +300,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz nid = memory_add_physaddr_to_nid(base); for (i = 0; i < sections_per_block; i++) { - remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); base += MIN_MEMORY_BLOCK_SIZE; } @@ -389,7 +389,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) block_sz = pseries_memory_block_size(); nid = memory_add_physaddr_to_nid(lmb->base_addr); - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); @@ -676,7 +676,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 6b0d3ef7309c..811148415993 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -282,7 +282,7 @@ static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device) nid = memory_add_physaddr_to_nid(info->start_addr); acpi_unbind_memory_blocks(info); - remove_memory(nid, info->start_addr, info->length); + __remove_memory(nid, info->start_addr, info->length); list_del(&info->list); kfree(info); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 34a28227068d..1f096852f479 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -301,6 +301,7 @@ 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 void 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, @@ -317,6 +318,7 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) } static inline void remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void __ref free_area_init_core_hotplug(int nid); @@ -330,7 +332,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 41e326472ef9..8f38e689da25 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1806,7 +1806,7 @@ EXPORT_SYMBOL(try_offline_node); * and online/offline operations before this call, as required by * try_offline_node(). */ -void __ref remove_memory(int nid, u64 start, u64 size) +void __ref __remove_memory(int nid, u64 start, u64 size) { int ret; @@ -1835,5 +1835,12 @@ void __ref remove_memory(int nid, u64 start, u64 size) mem_hotplug_done(); } + +void remove_memory(int nid, u64 start, u64 size) +{ + lock_device_hotplug(); + __remove_memory(nid, start, size); + unlock_device_hotplug(); +} EXPORT_SYMBOL_GPL(remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ -- cgit v1.2.3-71-gd317 From 8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:24 -0700 Subject: mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Mathieu Malaterre Cc: Pavel Tatashin Cc: YASUAKI ISHIMATSU Cc: Balbir Singh Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 2 +- drivers/acpi/acpi_memhotplug.c | 2 +- drivers/base/memory.c | 9 +++++++-- drivers/xen/balloon.c | 3 +++ include/linux/memory_hotplug.h | 1 + mm/memory_hotplug.c | 22 +++++++++++++++++++--- 6 files changed, 32 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index d79b31e7a6cf..2a983b5a52e1 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -668,7 +668,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) nid = memory_add_physaddr_to_nid(lmb->base_addr); /* Add the memory */ - rc = add_memory(nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 811148415993..8fe0960ea572 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -228,7 +228,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) if (node < 0) node = memory_add_physaddr_to_nid(info->start_addr); - result = add_memory(node, info->start_addr, info->length); + result = __add_memory(node, info->start_addr, info->length); /* * If the memory block has been used by the kernel, add_memory() diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 817320c7c4c1..40cac122ec73 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -519,15 +519,20 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1)) return -EINVAL; + ret = lock_device_hotplug_sysfs(); + if (ret) + goto out; + nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, - MIN_MEMORY_BLOCK_SIZE * sections_per_block); + ret = __add_memory(nid, phys_addr, + MIN_MEMORY_BLOCK_SIZE * sections_per_block); if (ret) goto out; ret = count; out: + unlock_device_hotplug(); return ret; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index a3f5cbfcd4a1..fdfc64f5acea 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -395,7 +395,10 @@ static enum bp_state reserve_additional_memory(void) * callers drop the mutex before trying again. */ mutex_unlock(&balloon_mutex); + /* add_memory_resource() requires the device_hotplug lock */ + lock_device_hotplug(); rc = add_memory_resource(nid, resource, memhp_auto_online); + unlock_device_hotplug(); mutex_lock(&balloon_mutex); if (rc) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1f096852f479..ffd9cd10fcf3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,6 +324,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); +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, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8f38e689da25..39cc887bbdcc 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1068,7 +1068,12 @@ static int online_memory_block(struct memory_block *mem, void *arg) return device_online(&mem->dev); } -/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +/* + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations (triggered e.g. by sysfs). + * + * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG + */ int __ref add_memory_resource(int nid, struct resource *res, bool online) { u64 start, size; @@ -1137,9 +1142,9 @@ out: mem_hotplug_done(); return ret; } -EXPORT_SYMBOL_GPL(add_memory_resource); -int __ref add_memory(int nid, u64 start, u64 size) +/* requires device_hotplug_lock, see add_memory_resource() */ +int __ref __add_memory(int nid, u64 start, u64 size) { struct resource *res; int ret; @@ -1153,6 +1158,17 @@ int __ref add_memory(int nid, u64 start, u64 size) release_memory_resource(res); return ret; } + +int add_memory(int nid, u64 start, u64 size) +{ + int rc; + + lock_device_hotplug(); + rc = __add_memory(nid, start, size); + unlock_device_hotplug(); + + return rc; +} EXPORT_SYMBOL_GPL(add_memory); #ifdef CONFIG_MEMORY_HOTREMOVE -- cgit v1.2.3-71-gd317 From bb58fd7eeffc9bd5d6e2a16cbf0e9e259f8d09f2 Mon Sep 17 00:00:00 2001 From: Mitch Williams Date: Fri, 19 Oct 2018 14:11:03 -0700 Subject: i40e: Update status codes Add a few new status code which will be used by the ice driver, and rename a few to make them more consistent. Error code are mapped to similar values as in i40e_status.h, so as to be compatible with older VF drivers not using this status enum. Signed-off-by: Mitch Williams Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- include/linux/avf/virtchnl.h | 12 +++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 81b0e1f8d14b..ac5698ed0b11 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3674,7 +3674,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n", local_vf_id, v_opcode, msglen); switch (ret) { - case VIRTCHNL_ERR_PARAM: + case VIRTCHNL_STATUS_ERR_PARAM: return -EPERM; default: return -EINVAL; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2c9756bd9c4c..b2488055fd1d 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -62,13 +62,19 @@ /* Error Codes */ enum virtchnl_status_code { VIRTCHNL_STATUS_SUCCESS = 0, - VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_NO_MEMORY = -18, VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, - VIRTCHNL_STATUS_NOT_SUPPORTED = -64, + VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR = -53, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED = -64, }; +/* Backward compatibility */ +#define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM +#define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED + #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 @@ -831,7 +837,7 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: default: - return VIRTCHNL_ERR_PARAM; + return VIRTCHNL_STATUS_ERR_PARAM; } /* few more checks */ if (err_msg_format || valid_len != msglen) -- cgit v1.2.3-71-gd317 From a324e9396ca3d00e1101476ba067b412e0aba232 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 31 Oct 2018 19:20:20 +0100 Subject: EDAC, skx: Fix randconfig builds The driver depends on the ADXL component glue and selects it. However, ADXL itself implicitly depends on ACPI and in nonsensical randconfig builds like this: # CONFIG_ACPI is not set CONFIG_ACPI_ADXL=y where ACPI is not enabled, the build fails with: drivers/edac/skx_edac.o: In function `skx_mce_check_error': skx_edac.c:(.text+0xab): undefined reference to `adxl_decode' drivers/edac/skx_edac.o: In function `skx_init': skx_edac.c:(.init.text+0x8bf): undefined reference to `adxl_get_component_names' make: *** [vmlinux] Error 1 Add stubs for that case so that the build succeeds. CONFIG_ACPI=n doesn't make any sense for real configurations but this fix will at least silence randconfig builds. Signed-off-by: Borislav Petkov Acked-by: Tony Luck Cc: "Rafael J. Wysocki" --- drivers/edac/Kconfig | 2 +- include/linux/adxl.h | 5 +++++ 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index ffd349c12479..68e479b4d9c9 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -234,7 +234,7 @@ config EDAC_SKX depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG depends on ACPI_NFIT || !ACPI_NFIT # if ACPI_NFIT=m, EDAC_SKX can't be y select DMI - select ACPI_ADXL + select ACPI_ADXL if ACPI help Support for error detection and correction the Intel Skylake server Integrated Memory Controllers. If your diff --git a/include/linux/adxl.h b/include/linux/adxl.h index 2a629acb4c3f..2d29f55923e3 100644 --- a/include/linux/adxl.h +++ b/include/linux/adxl.h @@ -7,7 +7,12 @@ #ifndef _LINUX_ADXL_H #define _LINUX_ADXL_H +#ifdef CONFIG_ACPI_ADXL const char * const *adxl_get_component_names(void); int adxl_decode(u64 addr, u64 component_values[]); +#else +static inline const char * const *adxl_get_component_names(void) { return NULL; } +static inline int adxl_decode(u64 addr, u64 component_values[]) { return -EOPNOTSUPP; } +#endif #endif /* _LINUX_ADXL_H */ -- cgit v1.2.3-71-gd317 From 439cd39ea136d2c026805264d58a91f36b6b64ca Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Sat, 14 Jul 2018 21:59:43 +0200 Subject: netfilter: ipset: list:set: Decrease refcount synchronously on deletion and replace Commit 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") postponed decreasing set reference counters to the RCU callback. An 'ipset del' command can terminate before the RCU grace period is elapsed, and if sets are listed before then, the reference counter shown in userspace will be wrong: # ipset create h hash:ip; ipset create l list:set; ipset add l # ipset del l h; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 1 Number of entries: 0 Members: # sleep 1; ipset list h Name: h Type: hash:ip Revision: 4 Header: family inet hashsize 1024 maxelem 65536 Size in memory: 88 References: 0 Number of entries: 0 Members: Fix this by making the reference count update synchronous again. As a result, when sets are listed, ip_set_name_byindex() might now fetch a set whose reference count is already zero. Instead of relying on the reference count to protect against concurrent set renaming, grab ip_set_ref_lock as reader and copy the name, while holding the same lock in ip_set_rename() as writer instead. Reported-by: Li Shuang Fixes: 45040978c899 ("netfilter: ipset: Fix set:list type crash when flush/dump set in parallel") Signed-off-by: Stefano Brivio Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 2 +- net/netfilter/ipset/ip_set_core.c | 23 +++++++++++------------ net/netfilter/ipset/ip_set_list_set.c | 17 +++++++++++------ 3 files changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..fa15a831aeee 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -693,21 +693,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -1153,7 +1152,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1169,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..4eef55da0878 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; -- cgit v1.2.3-71-gd317 From 0962590e553331db2cc0aef2dc35c57f6300dbbe Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 1 Nov 2018 00:05:52 +0100 Subject: bpf: fix partial copy of map_ptr when dst is scalar ALU operations on pointers such as scalar_reg += map_value_ptr are handled in adjust_ptr_min_max_vals(). Problem is however that map_ptr and range in the register state share a union, so transferring state through dst_reg->range = ptr_reg->range is just buggy as any new map_ptr in the dst_reg is then truncated (or null) for subsequent checks. Fix this by adding a raw member and use it for copying state over to dst_reg. Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Signed-off-by: Daniel Borkmann Cc: Edward Cree Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 +++ kernel/bpf/verifier.c | 10 ++++++---- 2 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9e8056ec20fa..d93e89761a8b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -51,6 +51,9 @@ struct bpf_reg_state { * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; + + /* Max size from any of the above. */ + unsigned long raw; }; /* Fixed part of pointer offset, pointer types only */ s32 off; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 171a2c88e77d..774fa40a32ae 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3046,7 +3046,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off @@ -3076,10 +3076,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_SUB: @@ -3108,7 +3109,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known @@ -3134,11 +3135,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_AND: -- cgit v1.2.3-71-gd317 From a846446b1914d1e3d996d657754f43fde89bab51 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Fri, 12 Oct 2018 14:42:52 +0100 Subject: x86/compat: Adjust in_compat_syscall() to generic code under !COMPAT The result of in_compat_syscall() can be pictured as: x86 platform: --------------------------------------------------- | Arch\syscall | 64-bit | ia32 | x32 | |-------------------------------------------------| | x86_64 | false | true | true | |-------------------------------------------------| | i686 | | | | --------------------------------------------------- Other platforms: ------------------------------------------- | Arch\syscall | 64-bit | compat | |-----------------------------------------| | 64-bit | false | true | |-----------------------------------------| | 32-bit(?) | | | ------------------------------------------- As seen, the result of in_compat_syscall() on generic 32-bit platform differs from i686. There is no reason for in_compat_syscall() == true on native i686. It also easy to misread code if the result on native 32-bit platform differs between arches. Because of that non arch-specific code has many places with: if (IS_ENABLED(CONFIG_COMPAT) && in_compat_syscall()) in different variations. It looks-like the only non-x86 code which uses in_compat_syscall() not under CONFIG_COMPAT guard is in amd/amdkfd. But according to the commit a18069c132cb ("amdkfd: Disable support for 32-bit user processes"), it actually should be disabled on native i686. Rename in_compat_syscall() to in_32bit_syscall() for x86-specific code and make in_compat_syscall() false under !CONFIG_COMPAT. A follow on patch will clean up generic users which were forced to check IS_ENABLED(CONFIG_COMPAT) with in_compat_syscall(). Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Ard Biesheuvel Cc: "David S. Miller" Cc: Herbert Xu Cc: "H. Peter Anvin" Cc: John Stultz Cc: "Kirill A. Shutemov" Cc: Oleg Nesterov Cc: Steffen Klassert Cc: Stephen Boyd Cc: Steven Rostedt Cc: linux-efi@vger.kernel.org Cc: netdev@vger.kernel.org Link: https://lkml.kernel.org/r/20181012134253.23266-2-dima@arista.com --- arch/x86/include/asm/compat.h | 9 ++++++++- arch/x86/include/asm/ftrace.h | 4 +--- arch/x86/kernel/process_64.c | 4 ++-- arch/x86/kernel/sys_x86_64.c | 11 ++++++----- arch/x86/mm/hugetlbpage.c | 4 ++-- arch/x86/mm/mmap.c | 2 +- include/linux/compat.h | 4 ++-- 7 files changed, 22 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fab4df16a3c4..22c4dfe65992 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -217,11 +217,18 @@ static inline bool in_x32_syscall(void) return false; } -static inline bool in_compat_syscall(void) +static inline bool in_32bit_syscall(void) { return in_ia32_syscall() || in_x32_syscall(); } + +#ifdef CONFIG_COMPAT +static inline bool in_compat_syscall(void) +{ + return in_32bit_syscall(); +} #define in_compat_syscall in_compat_syscall /* override the generic impl */ +#endif struct compat_siginfo; int __copy_siginfo_to_user32(struct compat_siginfo __user *to, diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index c18ed65287d5..cf350639e76d 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -76,9 +76,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name #define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1 static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) { - if (in_compat_syscall()) - return true; - return false; + return in_32bit_syscall(); } #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */ #endif /* !COMPILE_OFFSETS */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 31b4755369f0..0e0b4288a4b2 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -701,10 +701,10 @@ static void __set_personality_x32(void) current->mm->context.ia32_compat = TIF_X32; current->personality &= ~READ_IMPLIES_EXEC; /* - * in_compat_syscall() uses the presence of the x32 syscall bit + * in_32bit_syscall() uses the presence of the x32 syscall bit * flag to determine compat status. The x86 mmap() code relies on * the syscall bitness so set x32 syscall bit right here to make - * in_compat_syscall() work during exec(). + * in_32bit_syscall() work during exec(). * * Pretend to come from a x32 execve. */ diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 6a78d4b36a79..f7476ce23b6e 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -105,7 +105,7 @@ out: static void find_start_end(unsigned long addr, unsigned long flags, unsigned long *begin, unsigned long *end) { - if (!in_compat_syscall() && (flags & MAP_32BIT)) { + if (!in_32bit_syscall() && (flags & MAP_32BIT)) { /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit it to that. This means we need to move the @@ -122,7 +122,7 @@ static void find_start_end(unsigned long addr, unsigned long flags, } *begin = get_mmap_base(1); - if (in_compat_syscall()) + if (in_32bit_syscall()) *end = task_size_32bit(); else *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); @@ -193,7 +193,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, return addr; /* for MAP_32BIT mappings we force the legacy mmap base */ - if (!in_compat_syscall() && (flags & MAP_32BIT)) + if (!in_32bit_syscall() && (flags & MAP_32BIT)) goto bottomup; /* requesting a specific address */ @@ -217,9 +217,10 @@ get_unmapped_area: * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area * in the full address space. * - * !in_compat_syscall() check to avoid high addresses for x32. + * !in_32bit_syscall() check to avoid high addresses for x32 + * (and make it no op on native i386). */ - if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; info.align_mask = 0; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 00b296617ca4..92e4c4b85bba 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -92,7 +92,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area * in the full address space. */ - info.high_limit = in_compat_syscall() ? + info.high_limit = in_32bit_syscall() ? task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW); info.align_mask = PAGE_MASK & ~huge_page_mask(h); @@ -116,7 +116,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area * in the full address space. */ - if (addr > DEFAULT_MAP_WINDOW && !in_compat_syscall()) + if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall()) info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW; info.align_mask = PAGE_MASK & ~huge_page_mask(h); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 1e95d57760cf..db3165714521 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -166,7 +166,7 @@ unsigned long get_mmap_base(int is_legacy) struct mm_struct *mm = current->mm; #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - if (in_compat_syscall()) { + if (in_32bit_syscall()) { return is_legacy ? mm->mmap_compat_legacy_base : mm->mmap_compat_base; } diff --git a/include/linux/compat.h b/include/linux/compat.h index d30e4dbd4be2..f1ef24c68fcc 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -1029,9 +1029,9 @@ int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) -#ifndef in_compat_syscall +/* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ +#define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } -#endif #endif /* CONFIG_COMPAT */ -- cgit v1.2.3-71-gd317 From c3be6577d82a9f0163eb1e2c37a477414d12a209 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Thu, 1 Nov 2018 17:51:34 +0000 Subject: SUNRPC: Use atomic(64)_t for seq_send(64) The seq_send & seq_send64 fields in struct krb5_ctx are used as atomically incrementing counters. This is implemented using cmpxchg() & cmpxchg64() to implement what amount to custom versions of atomic_fetch_inc() & atomic64_fetch_inc(). Besides the duplication, using cmpxchg64() has another major drawback in that some 32 bit architectures don't provide it. As such commit 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") resulted in build failures for some architectures. Change seq_send to be an atomic_t and seq_send64 to be an atomic64_t, then use atomic(64)_* functions to manipulate the values. The atomic64_t type & associated functions are provided even on architectures which lack real 64 bit atomic memory access via CONFIG_GENERIC_ATOMIC64 which uses spinlocks to serialize access. This fixes the build failures for architectures lacking cmpxchg64(). A potential alternative that was raised would be to provide cmpxchg64() on the 32 bit architectures that currently lack it, using spinlocks. However this would provide a version of cmpxchg64() with semantics a little different to the implementations on architectures with real 64 bit atomics - the spinlock-based implementation would only work if all access to the memory used with cmpxchg64() is *always* performed using cmpxchg64(). That is not currently a requirement for users of cmpxchg64(), and making it one seems questionable. As such avoiding cmpxchg64() outside of architecture-specific code seems best, particularly in cases where atomic64_t seems like a better fit anyway. The CONFIG_GENERIC_ATOMIC64 implementation of atomic64_* functions will use spinlocks & so faces the same issue, but with the key difference that the memory backing an atomic64_t ought to always be accessed via the atomic64_* functions anyway making the issue moot. Signed-off-by: Paul Burton Fixes: 571ed1fd2390 ("SUNRPC: Replace krb5_seq_lock with a lockless scheme") Cc: Trond Myklebust Cc: Anna Schumaker Cc: J. Bruce Fields Cc: Jeff Layton Cc: David S. Miller Cc: linux-nfs@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Trond Myklebust --- include/linux/sunrpc/gss_krb5.h | 7 ++----- net/sunrpc/auth_gss/gss_krb5_mech.c | 16 ++++++++++------ net/sunrpc/auth_gss/gss_krb5_seal.c | 28 ++-------------------------- net/sunrpc/auth_gss/gss_krb5_wrap.c | 4 ++-- 4 files changed, 16 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 69f749afa617..4162de72e95c 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -107,8 +107,8 @@ struct krb5_ctx { u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; - u32 seq_send; - u64 seq_send64; + atomic_t seq_send; + atomic64_t seq_send64; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; @@ -118,9 +118,6 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); -extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); - /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 7bb2514aadd9..71cb29dc86c2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -275,6 +275,7 @@ out_err: static int gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) { + u32 seq_send; int tmp; p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate)); @@ -316,9 +317,10 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); if (IS_ERR(p)) goto out_err; - p = simple_get_bytes(p, end, &ctx->seq_send, sizeof(ctx->seq_send)); + p = simple_get_bytes(p, end, &seq_send, sizeof(seq_send)); if (IS_ERR(p)) goto out_err; + atomic_set(&ctx->seq_send, seq_send); p = simple_get_netobj(p, end, &ctx->mech_used); if (IS_ERR(p)) goto out_err; @@ -610,6 +612,7 @@ static int gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, gfp_t gfp_mask) { + u64 seq_send64; int keylen; p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags)); @@ -620,14 +623,15 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); if (IS_ERR(p)) goto out_err; - p = simple_get_bytes(p, end, &ctx->seq_send64, sizeof(ctx->seq_send64)); + p = simple_get_bytes(p, end, &seq_send64, sizeof(seq_send64)); if (IS_ERR(p)) goto out_err; + atomic64_set(&ctx->seq_send64, seq_send64); /* set seq_send for use by "older" enctypes */ - ctx->seq_send = ctx->seq_send64; - if (ctx->seq_send64 != ctx->seq_send) { - dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__, - (unsigned long)ctx->seq_send64, ctx->seq_send); + atomic_set(&ctx->seq_send, seq_send64); + if (seq_send64 != atomic_read(&ctx->seq_send)) { + dprintk("%s: seq_send64 %llx, seq_send %x overflow?\n", __func__, + seq_send64, atomic_read(&ctx->seq_send)); p = ERR_PTR(-EINVAL); goto out_err; } diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index b4adeb06660b..48fe4a591b54 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -123,30 +123,6 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token) return krb5_hdr; } -u32 -gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx) -{ - u32 old, seq_send = READ_ONCE(ctx->seq_send); - - do { - old = seq_send; - seq_send = cmpxchg(&ctx->seq_send, old, old + 1); - } while (old != seq_send); - return seq_send; -} - -u64 -gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx) -{ - u64 old, seq_send = READ_ONCE(ctx->seq_send); - - do { - old = seq_send; - seq_send = cmpxchg64(&ctx->seq_send64, old, old + 1); - } while (old != seq_send); - return seq_send; -} - static u32 gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj *token) @@ -177,7 +153,7 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - seq_send = gss_seq_send_fetch_and_inc(ctx); + seq_send = atomic_fetch_inc(&ctx->seq_send); if (krb5_make_seq_num(ctx, ctx->seq, ctx->initiate ? 0 : 0xff, seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)) @@ -205,7 +181,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, /* Set up the sequence number. Now 64-bits in clear * text and w/o direction indicator */ - seq_send_be64 = cpu_to_be64(gss_seq_send64_fetch_and_inc(ctx)); + seq_send_be64 = cpu_to_be64(atomic64_fetch_inc(&ctx->seq_send64)); memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8); if (ctx->initiate) { diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 41cb294cd071..6af6f119d9c1 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -228,7 +228,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - seq_send = gss_seq_send_fetch_and_inc(kctx); + seq_send = atomic_fetch_inc(&kctx->seq_send); /* XXX would probably be more efficient to compute checksum * and encrypt at the same time: */ @@ -475,7 +475,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, *be16ptr++ = 0; be64ptr = (__be64 *)be16ptr; - *be64ptr = cpu_to_be64(gss_seq_send64_fetch_and_inc(kctx)); + *be64ptr = cpu_to_be64(atomic64_fetch_inc(&kctx->seq_send64)); err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages); if (err) -- cgit v1.2.3-71-gd317 From b5f2954d30c77649bce9c27e7a0a94299d9cfdf8 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Thu, 1 Nov 2018 17:24:10 -0400 Subject: blkcg: revert blkcg cleanups series This reverts a series committed earlier due to null pointer exception bug report in [1]. It seems there are edge case interactions that I did not consider and will need some time to understand what causes the adverse interactions. The original series can be found in [2] with a follow up series in [3]. [1] https://www.spinics.net/lists/cgroups/msg20719.html [2] https://lore.kernel.org/lkml/20180911184137.35897-1-dennisszhou@gmail.com/ [3] https://lore.kernel.org/lkml/20181020185612.51587-1-dennis@kernel.org/ This reverts the following commits: d459d853c2ed, b2c3fa546705, 101246ec02b5, b3b9f24f5fcc, e2b0989954ae, f0fcb3ec89f3, c839e7a03f92, bdc2491708c4, 74b7c02a9bc1, 5bf9a1f3b4ef, a7b39b4e961c, 07b05bcc3213, 49f4c2dc2b50, 27e6fa996c53 Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- Documentation/admin-guide/cgroup-v2.rst | 8 +- block/bfq-cgroup.c | 4 +- block/bfq-iosched.c | 2 +- block/bio.c | 174 +++++++++----------------------- block/blk-cgroup.c | 123 +++++++--------------- block/blk-core.c | 1 - block/blk-iolatency.c | 26 ++++- block/blk-throttle.c | 13 ++- block/bounce.c | 4 +- block/cfq-iosched.c | 4 +- drivers/block/loop.c | 5 +- drivers/md/raid0.c | 2 +- fs/buffer.c | 10 +- fs/ext4/page-io.c | 2 +- include/linux/bio.h | 26 ++--- include/linux/blk-cgroup.h | 145 +++++++++----------------- include/linux/blk_types.h | 1 + include/linux/cgroup.h | 2 - include/linux/writeback.h | 5 +- kernel/cgroup/cgroup.c | 48 ++------- kernel/trace/blktrace.c | 4 +- mm/page_io.c | 2 +- 22 files changed, 208 insertions(+), 403 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index caf36105a1c7..184193bcb262 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1857,10 +1857,8 @@ following two functions. wbc_init_bio(@wbc, @bio) Should be called for each bio carrying writeback data and - associates the bio with the inode's owner cgroup and the - corresponding request queue. This must be called after - a queue (device) has been associated with the bio and - before submission. + associates the bio with the inode's owner cgroup. Can be + called anytime between bio allocation and submission. wbc_account_io(@wbc, @page, @bytes) Should be called for each data segment being written out. @@ -1879,7 +1877,7 @@ the configuration, the bio may be executed at a lower priority and if the writeback session is holding shared resources, e.g. a journal entry, may lead to priority inversion. There is no one easy solution for the problem. Filesystems can try to work around specific problem -cases by skipping wbc_init_bio() or using bio_associate_create_blkg() +cases by skipping wbc_init_bio() or using bio_associate_blkcg() directly. diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d9a7916ff0ab..9fe5952d117d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -642,7 +642,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger @@ -651,7 +651,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) goto out; - bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio)); + bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio)); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 6075100f03a5..3a27d31fcda6 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4384,7 +4384,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, rcu_read_lock(); - bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio)); + bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); if (!bfqg) { bfqq = &bfqd->oom_bfqq; goto out; diff --git a/block/bio.c b/block/bio.c index bbfeb4ee2892..4a5a036268fb 100644 --- a/block/bio.c +++ b/block/bio.c @@ -609,9 +609,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); } EXPORT_SYMBOL(__bio_clone_fast); @@ -1956,151 +1954,69 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP -/** - * bio_associate_blkg - associate a bio with the a blkg - * @bio: target bio - * @blkg: the blkg to associate - * - * This tries to associate @bio with the specified blkg. Association failure - * is handled by walking up the blkg tree. Therefore, the blkg associated can - * be anything between @blkg and the root_blkg. This situation only happens - * when a cgroup is dying and then the remaining bios will spill to the closest - * alive blkg. - * - * A reference will be taken on the @blkg and will be released when @bio is - * freed. - */ -int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - bio->bi_blkg = blkg_tryget_closest(blkg); - return 0; -} - -/** - * __bio_associate_blkg_from_css - internal blkg association function - * - * This in the core association function that all association paths rely on. - * A blkg reference is taken which is released upon freeing of the bio. - */ -static int __bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - struct request_queue *q = bio->bi_disk->queue; - struct blkcg_gq *blkg; - int ret; - - rcu_read_lock(); - - if (!css || !css->parent) - blkg = q->root_blkg; - else - blkg = blkg_lookup_create(css_to_blkcg(css), q); - - ret = bio_associate_blkg(bio, blkg); - - rcu_read_unlock(); - return ret; -} - -/** - * bio_associate_blkg_from_css - associate a bio with a specified css - * @bio: target bio - * @css: target css - * - * Associate @bio with the blkg found by combining the css's blkg and the - * request_queue of the @bio. This falls back to the queue's root_blkg if - * the association fails with the css. - */ -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - return __bio_associate_blkg_from_css(bio, css); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); - #ifdef CONFIG_MEMCG /** - * bio_associate_blkg_from_page - associate a bio with the page's blkg + * bio_associate_blkcg_from_page - associate a bio with the page's blkcg * @bio: target bio * @page: the page to lookup the blkcg from * - * Associate @bio with the blkg from @page's owning memcg and the respective - * request_queue. If cgroup_e_css returns NULL, fall back to the queue's - * root_blkg. - * - * Note: this must be called after bio has an associated device. + * Associate @bio with the blkcg from @page's owning memcg. This works like + * every other associate function wrt references. */ -int bio_associate_blkg_from_page(struct bio *bio, struct page *page) +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) { - struct cgroup_subsys_state *css; - int ret; + struct cgroup_subsys_state *blkcg_css; - if (unlikely(bio->bi_blkg)) + if (unlikely(bio->bi_css)) return -EBUSY; if (!page->mem_cgroup) return 0; - - rcu_read_lock(); - - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, + &io_cgrp_subsys); + bio->bi_css = blkcg_css; + return 0; } #endif /* CONFIG_MEMCG */ /** - * bio_associate_create_blkg - associate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio + * @blkcg_css: css of the blkcg to associate + * + * Associate @bio with the blkcg specified by @blkcg_css. Block layer will + * treat @bio as if it were issued by a task which belongs to the blkcg. * - * Associate @bio with the blkg found from the bio's css and the request_queue. - * If one is not found, bio_lookup_blkg creates the blkg. This falls back to - * the queue's root_blkg if association fails. + * This function takes an extra reference of @blkcg_css which will be put + * when @bio is released. The caller must own @bio and is responsible for + * synchronizing calls to this function. */ -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { - struct cgroup_subsys_state *css; - int ret = 0; - - /* someone has already associated this bio with a blkg */ - if (bio->bi_blkg) - return ret; - - rcu_read_lock(); - - css = blkcg_css(); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + if (unlikely(bio->bi_css)) + return -EBUSY; + css_get(blkcg_css); + bio->bi_css = blkcg_css; + return 0; } +EXPORT_SYMBOL_GPL(bio_associate_blkcg); /** - * bio_reassociate_blkg - reassociate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkg - associate a bio with the specified blkg * @bio: target bio + * @blkg: the blkg to associate * - * When submitting a bio, multiple recursive calls to make_request() may occur. - * This causes the initial associate done in blkcg_bio_issue_check() to be - * incorrect and reference the prior request_queue. This performs reassociation - * when this situation happens. + * Associate @bio with the blkg specified by @blkg. This is the queue specific + * blkcg information associated with the @bio, a reference will be taken on the + * @blkg and will be freed when the bio is freed. */ -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { - if (bio->bi_blkg) { - blkg_put(bio->bi_blkg); - bio->bi_blkg = NULL; - } - - return bio_associate_create_blkg(q, bio); + if (unlikely(bio->bi_blkg)) + return -EBUSY; + if (!blkg_try_get(blkg)) + return -ENODEV; + bio->bi_blkg = blkg; + return 0; } /** @@ -2113,6 +2029,10 @@ void bio_disassociate_task(struct bio *bio) put_io_context(bio->bi_ioc); bio->bi_ioc = NULL; } + if (bio->bi_css) { + css_put(bio->bi_css); + bio->bi_css = NULL; + } if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; @@ -2120,16 +2040,16 @@ void bio_disassociate_task(struct bio *bio) } /** - * bio_clone_blkg_association - clone blkg association from src to dst bio + * bio_clone_blkcg_association - clone blkcg association from src to dst bio * @dst: destination bio * @src: source bio */ -void bio_clone_blkg_association(struct bio *dst, struct bio *src) +void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { - if (src->bi_blkg) - bio_associate_blkg(dst, src->bi_blkg); + if (src->bi_css) + WARN_ON(bio_associate_blkcg(dst, src->bi_css)); } -EXPORT_SYMBOL_GPL(bio_clone_blkg_association); +EXPORT_SYMBOL_GPL(bio_clone_blkcg_association); #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 992da5592c6e..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -84,37 +84,6 @@ static void blkg_free(struct blkcg_gq *blkg) kfree(blkg); } -static void __blkg_release(struct rcu_head *rcu) -{ - struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); - - percpu_ref_exit(&blkg->refcnt); - - /* release the blkcg and parent blkg refs this blkg has been holding */ - css_put(&blkg->blkcg->css); - if (blkg->parent) - blkg_put(blkg->parent); - - wb_congested_put(blkg->wb_congested); - - blkg_free(blkg); -} - -/* - * A group is RCU protected, but having an rcu lock does not mean that one - * can access all the fields of blkg and assume these are valid. For - * example, don't try to follow throtl_data and request queue links. - * - * Having a reference to blkg under an rcu allows accesses to only values - * local to groups like group stats and group rate limits. - */ -static void blkg_release(struct percpu_ref *ref) -{ - struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); - - call_rcu(&blkg->rcu_head, __blkg_release); -} - /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with @@ -141,6 +110,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + atomic_set(&blkg->refcnt, 1); /* root blkg uses @q->root_rl, init rl only for !root blkgs */ if (blkcg != &blkcg_root) { @@ -247,11 +217,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_get(blkg->parent); } - ret = percpu_ref_init(&blkg->refcnt, blkg_release, 0, - GFP_NOWAIT | __GFP_NOWARN); - if (ret) - goto err_cancel_ref; - /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -284,8 +249,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_put(blkg); return ERR_PTR(ret); -err_cancel_ref: - percpu_ref_exit(&blkg->refcnt); err_put_congested: wb_congested_put(wb_congested); err_put_css: @@ -296,7 +259,7 @@ err_free_blkg: } /** - * __blkg_lookup_create - lookup blkg, try to create one if not there + * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * @@ -305,11 +268,12 @@ err_free_blkg: * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and @q->queue_lock. * - * Returns the blkg or the closest blkg if blkg_create fails as it walks - * down from root. + * Returns pointer to the looked up or created blkg on success, ERR_PTR() + * value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not + * dead and bypassing, returns ERR_PTR(-EBUSY). */ -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) +struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q) { struct blkcg_gq *blkg; @@ -321,7 +285,7 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, * we shouldn't allow anything to go through for a bypassing queue. */ if (unlikely(blk_queue_bypass(q))) - return q->root_blkg; + return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); blkg = __blkg_lookup(blkcg, q, true); if (blkg) @@ -329,58 +293,23 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, /* * Create blkgs walking down from blkcg_root to @blkcg, so that all - * non-root blkgs have access to their parents. Returns the closest - * blkg to the intended blkg should blkg_create() fail. + * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); - struct blkcg_gq *ret_blkg = q->root_blkg; - - while (parent) { - blkg = __blkg_lookup(parent, q, false); - if (blkg) { - /* remember closest blkg */ - ret_blkg = blkg; - break; - } + + while (parent && !__blkg_lookup(parent, q, false)) { pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, q, NULL); - if (IS_ERR(blkg)) - return ret_blkg; - if (pos == blkcg) + if (pos == blkcg || IS_ERR(blkg)) return blkg; } } -/** - * blkg_lookup_create - find or create a blkg - * @blkcg: target block cgroup - * @q: target request_queue - * - * This looks up or creates the blkg representing the unique pair - * of the blkcg and the request_queue. - */ -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) -{ - struct blkcg_gq *blkg = blkg_lookup(blkcg, q); - unsigned long flags; - - if (unlikely(!blkg)) { - spin_lock_irqsave(q->queue_lock, flags); - - blkg = __blkg_lookup_create(blkcg, q); - - spin_unlock_irqrestore(q->queue_lock, flags); - } - - return blkg; -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; @@ -424,7 +353,7 @@ static void blkg_destroy(struct blkcg_gq *blkg) * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ - percpu_ref_kill(&blkg->refcnt); + blkg_put(blkg); } /** @@ -451,6 +380,29 @@ static void blkg_destroy_all(struct request_queue *q) q->root_rl.blkg = NULL; } +/* + * A group is RCU protected, but having an rcu lock does not mean that one + * can access all the fields of blkg and assume these are valid. For + * example, don't try to follow throtl_data and request queue links. + * + * Having a reference to blkg under an rcu allows accesses to only values + * local to groups like group stats and group rate limits. + */ +void __blkg_release_rcu(struct rcu_head *rcu_head) +{ + struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head); + + /* release the blkcg and parent blkg refs this blkg has been holding */ + css_put(&blkg->blkcg->css); + if (blkg->parent) + blkg_put(blkg->parent); + + wb_congested_put(blkg->wb_congested); + + blkg_free(blkg); +} +EXPORT_SYMBOL_GPL(__blkg_release_rcu); + /* * The next function used by blk_queue_for_each_rl(). It's a bit tricky * because the root blkg uses @q->root_rl instead of its own rl. @@ -1796,7 +1748,8 @@ void blkcg_maybe_throttle_current(void) blkg = blkg_lookup(blkcg, q); if (!blkg) goto out; - if (!blkg_tryget(blkg)) + blkg = blkg_try_get(blkg); + if (!blkg) goto out; rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 26a5dac80ed9..ce12515f9b9b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2435,7 +2435,6 @@ blk_qc_t generic_make_request(struct bio *bio) if (q) blk_queue_exit(q); q = bio->bi_disk->queue; - bio_reassociate_blkg(q, bio); flags = 0; if (bio->bi_opf & REQ_NOWAIT) flags = BLK_MQ_REQ_NOWAIT; diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 35c48d7b8f78..bb240a0c1309 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -480,12 +480,34 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock) { struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); - struct blkcg_gq *blkg = bio->bi_blkg; + struct blkcg *blkcg; + struct blkcg_gq *blkg; + struct request_queue *q = rqos->q; bool issue_as_root = bio_issue_as_root_blkg(bio); if (!blk_iolatency_enabled(blkiolat)) return; + rcu_read_lock(); + blkcg = bio_blkcg(bio); + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + if (!lock) + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + if (!lock) + spin_unlock_irq(q->queue_lock); + } + if (!blkg) + goto out; + + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); + bio_associate_blkg(bio, blkg); +out: + rcu_read_unlock(); while (blkg && blkg->parent) { struct iolatency_grp *iolat = blkg_to_lat(blkg); if (!iolat) { @@ -706,7 +728,7 @@ static void blkiolatency_timer_fn(struct timer_list *t) * We could be exiting, don't access the pd unless we have a * ref on the blkg. */ - if (!blkg_tryget(blkg)) + if (!blkg_try_get(blkg)) continue; iolat = blkg_to_lat(blkg); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 4bda70e8db48..db1a3a2ae006 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2115,11 +2115,21 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) } #endif +static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) +{ +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); +#endif +} + bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio) { struct throtl_qnode *qn = NULL; - struct throtl_grp *tg = blkg_to_tg(blkg); + struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; @@ -2138,6 +2148,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, if (unlikely(blk_queue_bypass(q))) goto out_unlock; + blk_throtl_assoc_bio(tg, bio); blk_throtl_update_idletime(tg); sq = &tg->service_queue; diff --git a/block/bounce.c b/block/bounce.c index ec0d99995f5f..418677dcec60 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -276,9 +276,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, } } - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); return bio; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 6a3d87dd3c1a..ed41aa978c4a 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3759,7 +3759,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; rcu_read_unlock(); /* @@ -3824,7 +3824,7 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, struct cfq_group *cfqg; rcu_read_lock(); - cfqg = cfq_lookup_cfqg(cfqd, __bio_blkcg(bio)); + cfqg = cfq_lookup_cfqg(cfqd, bio_blkcg(bio)); if (!cfqg) { cfqq = &cfqd->oom_cfqq; goto out; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index abad6d15f956..ea9debf59b22 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -77,7 +77,6 @@ #include #include #include -#include #include "loop.h" @@ -1761,8 +1760,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP - if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { - cmd->css = &bio_blkcg(rq->bio)->css; + if (cmd->use_aio && rq->bio && rq->bio->bi_css) { + cmd->css = rq->bio->bi_css; css_get(cmd->css); } else #endif diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f3fb5bb8c82a..ac1cffd2a09b 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -542,7 +542,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) !discard_bio) continue; bio_chain(discard_bio, bio); - bio_clone_blkg_association(discard_bio, bio); + bio_clone_blkcg_association(discard_bio, bio); if (mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rdev->bdev), discard_bio, disk_devt(mddev->gendisk), diff --git a/fs/buffer.c b/fs/buffer.c index 109f55196866..6f1ae3ac9789 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3060,6 +3060,11 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, */ bio = bio_alloc(GFP_NOIO, 1); + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_io(wbc, bh->b_page, bh->b_size); + } + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; @@ -3079,11 +3084,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); - if (wbc) { - wbc_init_bio(wbc, bio); - wbc_account_io(wbc, bh->b_page, bh->b_size); - } - submit_bio(bio); return 0; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 2aa62d58d8dd..db7590178dfc 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -374,13 +374,13 @@ static int io_submit_init_bio(struct ext4_io_submit *io, bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); if (!bio) return -ENOMEM; + wbc_init_bio(io->io_wbc, bio); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); io->io_bio = bio; io->io_next_block = bh->b_blocknr; - wbc_init_bio(io->io_wbc, bio); return 0; } diff --git a/include/linux/bio.h b/include/linux/bio.h index b47c7f716731..056fb627edb3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -503,31 +503,23 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css); -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ return 0; } -static inline int bio_associate_create_blkg(struct request_queue *q, - struct bio *bio) { return 0; } -static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) -{ return 0; } +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1e76ceebeb5d..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - struct percpu_ref refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -184,8 +184,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -232,59 +230,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal version of bio_blkcg for bfq and cfq - * - * DO NOT USE. - * There is a flaw using this version of the function. In particular, this was - * used in a broken paradigm where association was called on the given css. It - * is possible though that the returned css from task_css() is in the process - * of dying due to migration of the current task. So it is improper to assume - * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will - * take additional work to handle more gracefully. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, NULL if not associated. - * Callers are expected to either handle NULL or know association has been - * done prior to calling this. - */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; + struct cgroup_subsys_state *css; + + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } static inline bool blk_cgroup_congested(void) @@ -490,35 +451,26 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - percpu_ref_get(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } /** - * blkg_tryget - try and get a blkg reference + * blkg_try_get - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - while (!percpu_ref_tryget(&blkg->refcnt)) - blkg = blkg->parent; - return blkg; -} +void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference @@ -526,7 +478,9 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) */ static inline void blkg_put(struct blkcg_gq *blkg) { - percpu_ref_put(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); } /** @@ -579,36 +533,25 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - if (bio && bio->bi_blkg) { - blkcg = bio->bi_blkg->blkcg; - if (blkcg == &blkcg_root) - goto rl_use_root; - - blkg_get(bio->bi_blkg); - rcu_read_unlock(); - return &bio->bi_blkg->rl; - } + blkcg = bio_blkcg(bio); - blkcg = css_to_blkcg(blkcg_css()); + /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) - goto rl_use_root; + goto root_rl; + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - blkg = __blkg_lookup_create(blkcg, q); - - if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) - goto rl_use_root; + goto root_rl; + blkg_get(blkg); rcu_read_unlock(); return &blkg->rl; - - /* - * Each blkg has its own request_list, however, the root blkcg - * uses the request_queue's root_rl. This is to avoid most - * overhead for the root blkcg. - */ -rl_use_root: +root_rl: rcu_read_unlock(); return &q->root_rl; } @@ -854,26 +797,32 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { + struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); + blkcg = bio_blkcg(bio); + + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); - bio_associate_create_blkg(q, bio); - blkg = bio->bi_blkg; + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -885,8 +834,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } @@ -983,7 +930,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, @@ -999,7 +945,6 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 093a818c5b68..1dcf652ba0aa 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,6 +178,7 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; + struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b8bcbdeb2eac..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,8 +93,6 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..fdfd04e348f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,8 +246,7 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. Must be called after the bio has been associated with - * a device. + * writeback context. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -258,7 +257,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); + bio_associate_blkcg(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4c1cf0969a80..4a3dae2a8283 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -492,7 +492,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, } /** - * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * @@ -501,8 +501,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ -static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, - struct cgroup_subsys *ss) +static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); @@ -522,35 +522,6 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, return cgroup_css(cgrp, ss); } -/** - * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem - * @cgrp: the cgroup of interest - * @ss: the subsystem of interest - * - * Find and get the effective css of @cgrp for @ss. The effective css is - * defined as the matching css of the nearest ancestor including self which - * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, - * the root css is returned, so this function always returns a valid css. - * - * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. - */ -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, - struct cgroup_subsys *ss) -{ - struct cgroup_subsys_state *css; - - do { - css = cgroup_css(cgrp, ss); - - if (css) - return css; - cgrp = cgroup_parent(cgrp); - } while (cgrp); - - return init_css_set.subsys[ss->id]; -} - /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest @@ -633,11 +604,10 @@ EXPORT_SYMBOL_GPL(of_css); * * Should be called under cgroup_[tree_]mutex. */ -#define for_each_e_css(css, ssid, cgrp) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((css) = cgroup_e_css_by_mask(cgrp, \ - cgroup_subsys[(ssid)]))) \ - ; \ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ + ; \ else /** @@ -1036,7 +1006,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ - template[i] = cgroup_e_css_by_mask(cgrp, ss); + template[i] = cgroup_e_css(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want @@ -3053,7 +3023,7 @@ static int cgroup_apply_control(struct cgroup *cgrp) return ret; /* - * At this point, cgroup_e_css_by_mask() results reflect the new csses + * At this point, cgroup_e_css() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fac0ddf8a8e2..2868d85f1fb1 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_blkg) + if (!bio->bi_css) return NULL; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_get_kernfs_id(bio->bi_css->cgroup); } #else static union kernfs_node_id * diff --git a/mm/page_io.c b/mm/page_io.c index 573d3663d846..aafd19ec1db4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); - bio_associate_blkg_from_page(bio, page); + bio_associate_blkcg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3-71-gd317 From 6d212db11947ae5464e4717536ed9faf61c01e86 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 15 Oct 2018 10:30:23 +0200 Subject: mm: add mm_pxd_folded checks to pgtable_bytes accounting functions The common mm code calls mm_dec_nr_pmds() and mm_dec_nr_puds() in free_pgtables() if the address range spans a full pud or pmd. If mm_dec_nr_puds/mm_dec_nr_pmds are non-empty due to configuration settings they blindly subtract the size of the pmd or pud table from pgtable_bytes even if the pud or pmd page table layer is folded. Add explicit mm_[pmd|pud]_folded checks to the four pgtable_bytes accounting functions mm_inc_nr_puds, mm_inc_nr_pmds, mm_dec_nr_puds and mm_dec_nr_pmds. As the check for folded page tables can be overwritten by the architecture, this allows to keep a correct pgtable_bytes value for platforms that use a dynamic number of page table levels. Acked-by: Kirill A. Shutemov Signed-off-by: Martin Schwidefsky --- include/linux/mm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..a3701e91bb57 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1742,11 +1742,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1766,11 +1770,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif -- cgit v1.2.3-71-gd317 From a7ad38b0dd3c1ba8d6e5a55241e875e9db8331ab Mon Sep 17 00:00:00 2001 From: Guo Ren Date: Sat, 3 Nov 2018 00:51:28 +0800 Subject: clocksource/drivers/c-sky: Add C-SKY SMP timer The driver is for C-SKY SMP timer. It only supports oneshot event and 32bit overflow for clocksource. Per cpu core has one timer and all timers share one clock-counter-input from the same clocksource. This use mfcr&mtcr instructions to access the regs. Signed-off-by: Guo Ren Cc: Daniel Lezcano Cc: Thomas Gleixner Signed-off-by: Daniel Lezcano --- drivers/clocksource/Kconfig | 10 +++ drivers/clocksource/Makefile | 1 + drivers/clocksource/timer-mp-csky.c | 173 ++++++++++++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 4 files changed, 185 insertions(+) create mode 100644 drivers/clocksource/timer-mp-csky.c (limited to 'include/linux') diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index a11f4ba98b05..591c9a8649a5 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -620,4 +620,14 @@ config RISCV_TIMER is accessed via both the SBI and the rdcycle instruction. This is required for all RISC-V systems. +config CSKY_MP_TIMER + bool "SMP Timer for the C-SKY platform" if COMPILE_TEST + depends on CSKY + select TIMER_OF + help + Say yes here to enable C-SKY SMP timer driver used for C-SKY SMP + system. + csky,mptimer is not only used in SMP system, it also could be used + single core system. It's not a mmio reg and it use mtcr/mfcr instruction. + endmenu diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index db51b2427e8a..5ce82d39cda7 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -79,3 +79,4 @@ obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += riscv_timer.o +obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o diff --git a/drivers/clocksource/timer-mp-csky.c b/drivers/clocksource/timer-mp-csky.c new file mode 100644 index 000000000000..a8acc431a774 --- /dev/null +++ b/drivers/clocksource/timer-mp-csky.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. + +#include +#include +#include +#include +#include +#include + +#include "timer-of.h" + +#define PTIM_CCVR "cr<3, 14>" +#define PTIM_CTLR "cr<0, 14>" +#define PTIM_LVR "cr<6, 14>" +#define PTIM_TSR "cr<1, 14>" + +static int csky_mptimer_irq; + +static int csky_mptimer_set_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + mtcr(PTIM_LVR, delta); + + return 0; +} + +static int csky_mptimer_shutdown(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 0); + + return 0; +} + +static int csky_mptimer_oneshot(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 1); + + return 0; +} + +static int csky_mptimer_oneshot_stopped(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 0); + + return 0; +} + +static DEFINE_PER_CPU(struct timer_of, csky_to) = { + .flags = TIMER_OF_CLOCK, + .clkevt = { + .rating = 300, + .features = CLOCK_EVT_FEAT_PERCPU | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_shutdown = csky_mptimer_shutdown, + .set_state_oneshot = csky_mptimer_oneshot, + .set_state_oneshot_stopped = csky_mptimer_oneshot_stopped, + .set_next_event = csky_mptimer_set_next_event, + }, +}; + +static irqreturn_t csky_timer_interrupt(int irq, void *dev) +{ + struct timer_of *to = this_cpu_ptr(&csky_to); + + mtcr(PTIM_TSR, 0); + + to->clkevt.event_handler(&to->clkevt); + + return IRQ_HANDLED; +} + +/* + * clock event for percpu + */ +static int csky_mptimer_starting_cpu(unsigned int cpu) +{ + struct timer_of *to = per_cpu_ptr(&csky_to, cpu); + + to->clkevt.cpumask = cpumask_of(cpu); + + clockevents_config_and_register(&to->clkevt, timer_of_rate(to), + 2, ULONG_MAX); + + enable_percpu_irq(csky_mptimer_irq, 0); + + return 0; +} + +static int csky_mptimer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(csky_mptimer_irq); + + return 0; +} + +/* + * clock source + */ +static u64 sched_clock_read(void) +{ + return (u64)mfcr(PTIM_CCVR); +} + +static u64 clksrc_read(struct clocksource *c) +{ + return (u64)mfcr(PTIM_CCVR); +} + +struct clocksource csky_clocksource = { + .name = "csky", + .rating = 400, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clksrc_read, +}; + +static int __init csky_mptimer_init(struct device_node *np) +{ + int ret, cpu, cpu_rollback; + struct timer_of *to = NULL; + + /* + * Csky_mptimer is designed for C-SKY SMP multi-processors and + * every core has it's own private irq and regs for clkevt and + * clksrc. + * + * The regs is accessed by cpu instruction: mfcr/mtcr instead of + * mmio map style. So we needn't mmio-address in dts, but we still + * need to give clk and irq number. + * + * We use private irq for the mptimer and irq number is the same + * for every core. So we use request_percpu_irq() in timer_of_init. + */ + csky_mptimer_irq = irq_of_parse_and_map(np, 0); + if (csky_mptimer_irq <= 0) + return -EINVAL; + + ret = request_percpu_irq(csky_mptimer_irq, csky_timer_interrupt, + "csky_mp_timer", &csky_to); + if (ret) + return -EINVAL; + + for_each_possible_cpu(cpu) { + to = per_cpu_ptr(&csky_to, cpu); + ret = timer_of_init(np, to); + if (ret) + goto rollback; + } + + clocksource_register_hz(&csky_clocksource, timer_of_rate(to)); + sched_clock_register(sched_clock_read, 32, timer_of_rate(to)); + + ret = cpuhp_setup_state(CPUHP_AP_CSKY_TIMER_STARTING, + "clockevents/csky/timer:starting", + csky_mptimer_starting_cpu, + csky_mptimer_dying_cpu); + if (ret) + return -EINVAL; + + return 0; + +rollback: + for_each_possible_cpu(cpu_rollback) { + if (cpu_rollback == cpu) + break; + + to = per_cpu_ptr(&csky_to, cpu_rollback); + timer_of_cleanup(to); + } + return -EINVAL; +} +TIMER_OF_DECLARE(csky_mptimer, "csky,mptimer", csky_mptimer_init); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index caf40ad0bbc6..e0cd2baa8380 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -126,6 +126,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, -- cgit v1.2.3-71-gd317 From 17b8b74c0f8dbf9b9e3301f9ca5b65dd1c079951 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Fri, 19 Oct 2018 19:35:19 +0200 Subject: netfilter: ipset: Correct rcu_dereference() call in ip_set_put_comment() The function is called when rcu_read_lock() is held and not when rcu_read_lock_bh() is held. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_comment.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; -- cgit v1.2.3-71-gd317 From 94e297c50b529f5d01cfd1dbc808d61e95180ab7 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Fri, 2 Nov 2018 15:47:53 -0700 Subject: include/linux/notifier.h: SRCU: fix ctags ctags indexing ("make tags" command) throws this warning: ctags: Warning: include/linux/notifier.h:125: null expansion of name pattern "\1" This is the result of DEFINE_PER_CPU() macro expansion. Fix that by getting rid of line break. Similar fix was already done in commit 25528213fe9f ("tags: Fix DEFINE_PER_CPU expansions"), but this one probably wasn't noticed. Link: http://lkml.kernel.org/r/20181030202808.28027-1-semen.protsenko@linaro.org Fixes: 9c80172b902d ("kernel/SRCU: provide a static initializer") Signed-off-by: Sam Protsenko Cc: Sebastian Andrzej Siewior Cc: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/notifier.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f35c7bf76143..0096a05395e3 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -122,8 +122,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ - static DEFINE_PER_CPU(struct srcu_data, \ - name##_head_srcu_data); \ + static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) -- cgit v1.2.3-71-gd317 From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:31 -0700 Subject: mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask THP allocation mode is quite complex and it depends on the defrag mode. This complexity is hidden in alloc_hugepage_direct_gfpmask from a large part currently. The NUMA special casing (namely __GFP_THISNODE) is however independent and placed in alloc_pages_vma currently. This both adds an unnecessary branch to all vma based page allocation requests and it makes the code more complex unnecessarily as well. Not to mention that e.g. shmem THP used to do the node reclaiming unconditionally regardless of the defrag mode until recently. This was not only unexpected behavior but it was also hardly a good default behavior and I strongly suspect it was just a side effect of the code sharing more than a deliberate decision which suggests that such a layering is wrong. Get rid of the thp special casing from alloc_pages_vma and move the logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the resulting gfp mask only when the direct reclaim is not requested and when there is no explicit numa binding to preserve the current logic. Please note that there's also a slight difference wrt MPOL_BIND now. The previous code would avoid using __GFP_THISNODE if the local node was outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided for all MPOL_BIND policies. So there's a difference that if local node is actually allowed by the bind policy's nodemask, previously __GFP_THISNODE would be added, but now it won't be. From the behavior POV this is still correct because the policy nodemask is used. Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Stefan Priebe - Profihost AG Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 +++------ include/linux/mempolicy.h | 2 ++ mm/huge_memory.c | 38 +++++++++++++++++++++------- mm/mempolicy.c | 63 +++-------------------------------------------- mm/shmem.c | 2 +- 5 files changed, 40 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 24bcc5eec6b4..76f8db0b0e71 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4e4ef8fa479d..55478ab3c83b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -629,21 +629,40 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + gfp_t this_node = 0; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - 0); - return GFP_TRANSHUGE_LIGHT; + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ @@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 58fb833fce0c..5837a067124d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2040,60 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && - !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - /* - * We cannot invoke reclaim if __GFP_THISNODE - * is set. Invoking reclaim with - * __GFP_THISNODE set, would cause THP - * allocations to trigger heavy swapping - * despite there may be tons of free memory - * (including potentially plenty of THP - * already available in the buddy) on all the - * other NUMA nodes. - * - * At most we could invoke compaction when - * __GFP_THISNODE is set (but we would need to - * refrain from invoking reclaim even if - * compaction returned COMPACT_SKIPPED because - * there wasn't not enough memory to succeed - * compaction). For now just avoid - * __GFP_THISNODE instead of limiting the - * allocation path to a strict and single - * compaction invocation. - * - * Supposedly if direct reclaim was enabled by - * the caller, the app prefers THP regardless - * of the node it comes from so this would be - * more desiderable behavior than only - * providing THP originated from the local - * node in such case. - */ - if (!(gfp & __GFP_DIRECT_RECLAIM)) - gfp |= __GFP_THISNODE; - page = __alloc_pages_node(hpage_node, gfp, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/shmem.c b/mm/shmem.c index 56bf122e0bb4..ea26d7a0342d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3-71-gd317 From 3e59020abf0f88182730527ee5b862e786eb485a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Oct 2018 08:39:12 -0700 Subject: net: bql: add __netdev_tx_sent_queue() When qdisc_run() tries to use BQL budget to bulk-dequeue a batch of packets, GSO can later transform this list in another list of skbs, and each skb is sent to device ndo_start_xmit(), one at a time, with skb->xmit_more being set to one but for last skb. Problem is that very often, BQL limit is hit in the middle of the packet train, forcing dev_hard_start_xmit() to stop the bulk send and requeue the end of the list. BQL role is to avoid head of line blocking, making sure a qdisc can deliver high priority packets before low priority ones. But there is no way requeued packets can be bypassed by fresh packets in the qdisc. Aborting the bulk send increases TX softirqs, and hot cache lines (after skb_segment()) are wasted. Note that for TSO packets, we never split a packet in the middle because of BQL limit being hit. Drivers should be able to update BQL counters without flipping/caring about BQL status, if the current skb has xmit_more set. Upper layers are ultimately responsible to stop sending another packet train when BQL limit is hit. Code template in a driver might look like the following : send_doorbell = __netdev_tx_sent_queue(tx_queue, nr_bytes, skb->xmit_more); Note that __netdev_tx_sent_queue() use is not mandatory, since following patch will change dev_hard_start_xmit() to not care about BQL status. But it is highly recommended so that xmit_more full benefits can be reached (less doorbells sent, and less atomic operations as well) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device -- cgit v1.2.3-71-gd317 From 35b69a420bfb56b7b74cb635ea903db05e357bec Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Sun, 4 Nov 2018 03:48:54 +0000 Subject: clockevents/drivers/i8253: Add support for PIT shutdown quirk Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown. Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override. Signed-off-by: Michael Kelley Signed-off-by: Thomas Gleixner Cc: "gregkh@linuxfoundation.org" Cc: "devel@linuxdriverproject.org" Cc: "daniel.lezcano@linaro.org" Cc: "virtualization@lists.linux-foundation.org" Cc: "jgross@suse.com" Cc: "akataria@vmware.com" Cc: "olaf@aepfle.de" Cc: "apw@canonical.com" Cc: vkuznets Cc: "jasowang@redhat.com" Cc: "marcelo.cerri@canonical.com" Cc: KY Srinivasan Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1541303219-11142-2-git-send-email-mikelley@microsoft.com --- drivers/clocksource/i8253.c | 14 ++++++++++++-- include/linux/i8253.h | 1 + 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 9c38895542f4..d4350bb10b83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,6 +20,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); -- cgit v1.2.3-71-gd317 From d098093ba06eb032057d1aca1c2e45889e099d00 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Sun, 28 Oct 2018 12:29:55 +0100 Subject: mtd: nand: Fix nanddev_neraseblocks() nanddev_neraseblocks() currently returns the number pages per LUN instead of the total number of eraseblocks. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Cc: Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..78b86dea2f29 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** -- cgit v1.2.3-71-gd317 From 163c8d54a997153ee1a1e07fcac087492ad85b37 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Mon, 5 Nov 2018 07:36:28 +0100 Subject: compiler: remove __no_sanitize_address_or_inline again The __no_sanitize_address_or_inline and __no_kasan_or_inline defines are almost identical. The only difference is that __no_kasan_or_inline does not have the 'notrace' attribute. To be able to replace __no_sanitize_address_or_inline with the older definition, add 'notrace' to __no_kasan_or_inline and change to two users of __no_sanitize_address_or_inline in the s390 code. The 'notrace' option is necessary for e.g. the __load_psw_mask function in arch/s390/include/asm/processor.h. Without the option it is possible to trace __load_psw_mask which leads to kernel stack overflow. Signed-off-by: Martin Schwidefsky Pointed-out-by: Andrey Ryabinin Acked-by: Steven Rostedt (VMware) Signed-off-by: Linus Torvalds --- arch/s390/include/asm/processor.h | 4 ++-- include/linux/compiler-gcc.h | 12 ------------ include/linux/compiler.h | 2 +- 3 files changed, 3 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 302795c47c06..81038ab357ce 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -236,7 +236,7 @@ static inline unsigned long current_stack_pointer(void) return sp; } -static __no_sanitize_address_or_inline unsigned short stap(void) +static __no_kasan_or_inline unsigned short stap(void) { unsigned short cpu_address; @@ -330,7 +330,7 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ -static __no_sanitize_address_or_inline void __load_psw_mask(unsigned long mask) +static __no_kasan_or_inline void __load_psw_mask(unsigned long mask) { unsigned long addr; psw_t psw; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#endif - #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * 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 __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif -- cgit v1.2.3-71-gd317 From 4c0608f4a0e76dfb82d3accd20081f4bf47ed143 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 30 Oct 2018 09:45:55 -0400 Subject: XArray: Regularise xa_reserve The xa_reserve() function was a little unusual in that it attempted to be callable for all kinds of locking scenarios. Make it look like the other APIs with __xa_reserve, xa_reserve_bh and xa_reserve_irq variants. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 13 +++++++ include/linux/xarray.h | 80 ++++++++++++++++++++++++++++++++++++++- lib/test_xarray.c | 6 +++ lib/xarray.c | 18 ++++----- 4 files changed, 105 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index a4e705108f42..65c77a81b689 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -105,6 +105,15 @@ may result in the entry being marked at some, but not all of the other indices. Storing into one index may result in the entry retrieved by some, but not all of the other indices changing. +Sometimes you need to ensure that a subsequent call to :c:func:`xa_store` +will not need to allocate memory. The :c:func:`xa_reserve` function +will store a reserved entry at the indicated index. Users of the normal +API will see this entry as containing ``NULL``. If you do not need to +use the reserved entry, you can call :c:func:`xa_release` to remove the +unused entry. If another user has stored to the entry in the meantime, +:c:func:`xa_release` will do nothing; if instead you want the entry to +become ``NULL``, you should use :c:func:`xa_erase`. + Finally, you can remove all entries from an XArray by calling :c:func:`xa_destroy`. If the XArray entries are pointers, you may wish to free the entries first. You can do this by iterating over all present @@ -167,6 +176,9 @@ Takes xa_lock internally: * :c:func:`xa_alloc` * :c:func:`xa_alloc_bh` * :c:func:`xa_alloc_irq` + * :c:func:`xa_reserve` + * :c:func:`xa_reserve_bh` + * :c:func:`xa_reserve_irq` * :c:func:`xa_destroy` * :c:func:`xa_set_mark` * :c:func:`xa_clear_mark` @@ -177,6 +189,7 @@ Assumes xa_lock held on entry: * :c:func:`__xa_erase` * :c:func:`__xa_cmpxchg` * :c:func:`__xa_alloc` + * :c:func:`__xa_reserve` * :c:func:`__xa_set_mark` * :c:func:`__xa_clear_mark` diff --git a/include/linux/xarray.h b/include/linux/xarray.h index d9514928ddac..c2cb0426c60c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -291,7 +291,6 @@ void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); -int xa_reserve(struct xarray *, unsigned long index, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -455,6 +454,7 @@ void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); +int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -621,6 +621,84 @@ static inline int xa_alloc_irq(struct xarray *xa, u32 *id, u32 max, void *entry, return err; } +/** + * xa_reserve() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * Ensures there is somewhere to store an entry at @index in the array. + * If there is already something stored at @index, this function does + * nothing. If there was nothing there, the entry is marked as reserved. + * Loading from a reserved entry returns a %NULL pointer. + * + * If you do not use the entry that you have reserved, call xa_release() + * or xa_erase() to free any unnecessary memory. + * + * Context: Any context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock(xa); + + return ret; +} + +/** + * xa_reserve_bh() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * A softirq-disabling version of xa_reserve(). + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_bh(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_bh(xa); + + return ret; +} + +/** + * xa_reserve_irq() - Reserve this index in the XArray. + * @xa: XArray. + * @index: Index into array. + * @gfp: Memory allocation flags. + * + * An interrupt-disabling version of xa_reserve(). + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: 0 if the reservation succeeded or -ENOMEM if it failed. + */ +static inline +int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) +{ + int ret; + + xa_lock_irq(xa); + ret = __xa_reserve(xa, index, gfp); + xa_unlock_irq(xa); + + return ret; +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 126127658b49..e5294b20b52f 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -373,6 +373,12 @@ static noinline void check_reserve(struct xarray *xa) xa_erase_index(xa, 12345678); XA_BUG_ON(xa, !xa_empty(xa)); + /* And so does xa_insert */ + xa_reserve(xa, 12345678, GFP_KERNEL); + XA_BUG_ON(xa, xa_insert(xa, 12345678, xa_mk_value(12345678), 0) != 0); + xa_erase_index(xa, 12345678); + XA_BUG_ON(xa, !xa_empty(xa)); + /* Can iterate through a reserved entry */ xa_store_index(xa, 5, GFP_KERNEL); xa_reserve(xa, 6, GFP_KERNEL); diff --git a/lib/xarray.c b/lib/xarray.c index e7be4e47c6a9..9cab8cfef8a8 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1488,7 +1488,7 @@ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, EXPORT_SYMBOL(__xa_cmpxchg); /** - * xa_reserve() - Reserve this index in the XArray. + * __xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. @@ -1496,33 +1496,29 @@ EXPORT_SYMBOL(__xa_cmpxchg); * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. - * Loads from @index will continue to see a %NULL pointer until a - * subsequent store to @index. + * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * - * Context: Process context. Takes and releases the xa_lock, IRQ or BH safe - * if specified in XArray flags. May sleep if the @gfp flags permit. + * Context: Any context. Expects the xa_lock to be held on entry. May + * release the lock, sleep and reacquire the lock if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ -int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) +int __xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { XA_STATE(xas, xa, index); - unsigned int lock_type = xa_lock_type(xa); void *curr; do { - xas_lock_type(&xas, lock_type); curr = xas_load(&xas); if (!curr) xas_store(&xas, XA_ZERO_ENTRY); - xas_unlock_type(&xas, lock_type); - } while (xas_nomem(&xas, gfp)); + } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } -EXPORT_SYMBOL(xa_reserve); +EXPORT_SYMBOL(__xa_reserve); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, -- cgit v1.2.3-71-gd317 From c5beb07e7a06b24f4f27304f6282b5dbd929543b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 31 Oct 2018 14:39:28 -0400 Subject: XArray: Unify xa_cmpxchg and __xa_cmpxchg xa_cmpxchg() was one of the largest functions in the xarray implementation. By turning it into a wrapper and having the callers take the lock (like several other functions), we save 160 bytes on a tinyconfig build and reduce the duplication in xarray.c. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 113 ++++++++++++++++++++++++++++++------------------- lib/xarray.c | 41 ------------------ 2 files changed, 69 insertions(+), 85 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index c2cb0426c60c..8e59d4fbd55e 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,8 +289,6 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); -void *xa_cmpxchg(struct xarray *, unsigned long index, - void *old, void *entry, gfp_t); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -359,48 +357,6 @@ static inline void *xa_erase(struct xarray *xa, unsigned long index) return xa_store(xa, index, NULL, 0); } -/** - * xa_insert() - Store this entry in the XArray unless another entry is - * already present. - * @xa: XArray. - * @index: Index into array. - * @entry: New entry. - * @gfp: Memory allocation flags. - * - * If you would rather see the existing entry in the array, use xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. - * - * Context: Process context. Takes and releases the xa_lock. - * May sleep if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. - * -ENOMEM if memory could not be allocated. - */ -static inline int xa_insert(struct xarray *xa, unsigned long index, - void *entry, gfp_t gfp) -{ - void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; -} - -/** - * xa_release() - Release a reserved entry. - * @xa: XArray. - * @index: Index of entry. - * - * After calling xa_reserve(), you can call this function to release the - * reservation. If the entry at @index has been stored to, this function - * will do nothing. - */ -static inline void xa_release(struct xarray *xa, unsigned long index) -{ - xa_cmpxchg(xa, index, NULL, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. @@ -534,6 +490,61 @@ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) return entry; } +/** + * xa_cmpxchg() - Conditionally replace an entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @old: Old value to test against. + * @entry: New value to place in array. + * @gfp: Memory allocation flags. + * + * If the entry at @index is the same as @old, replace it with @entry. + * If the return value is equal to @old, then the exchange was successful. + * + * Context: Any context. Takes and releases the xa_lock. May sleep + * if the @gfp flags permit. + * Return: The old value at this index or xa_err() if an error happened. + */ +static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, + void *old, void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock(xa); + curr = __xa_cmpxchg(xa, index, old, entry, gfp); + xa_unlock(xa); + + return curr; +} + +/** + * xa_insert() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * If you would rather see the existing entry in the array, use xa_cmpxchg(). + * This function is for users who don't care what the entry is, only that + * one is present. + * + * Context: Process context. Takes and releases the xa_lock. + * May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); + if (!curr) + return 0; + if (xa_is_err(curr)) + return xa_err(curr); + return -EEXIST; +} + /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. @@ -699,6 +710,20 @@ int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) return ret; } +/** + * xa_release() - Release a reserved entry. + * @xa: XArray. + * @index: Index of entry. + * + * After calling xa_reserve(), you can call this function to release the + * reservation. If the entry at @index has been stored to, this function + * will do nothing. + */ +static inline void xa_release(struct xarray *xa, unsigned long index) +{ + xa_cmpxchg(xa, index, NULL, NULL, 0); +} + /* Everything below here is the Advanced API. Proceed with caution. */ /* diff --git a/lib/xarray.c b/lib/xarray.c index 9cab8cfef8a8..77671d4a7910 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1406,47 +1406,6 @@ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) } EXPORT_SYMBOL(__xa_store); -/** - * xa_cmpxchg() - Conditionally replace an entry in the XArray. - * @xa: XArray. - * @index: Index into array. - * @old: Old value to test against. - * @entry: New value to place in array. - * @gfp: Memory allocation flags. - * - * If the entry at @index is the same as @old, replace it with @entry. - * If the return value is equal to @old, then the exchange was successful. - * - * Context: Process context. Takes and releases the xa_lock. May sleep - * if the @gfp flags permit. - * Return: The old value at this index or xa_err() if an error happened. - */ -void *xa_cmpxchg(struct xarray *xa, unsigned long index, - void *old, void *entry, gfp_t gfp) -{ - XA_STATE(xas, xa, index); - void *curr; - - if (WARN_ON_ONCE(xa_is_internal(entry))) - return XA_ERROR(-EINVAL); - - do { - xas_lock(&xas); - curr = xas_load(&xas); - if (curr == XA_ZERO_ENTRY) - curr = NULL; - if (curr == old) { - xas_store(&xas, entry); - if (xa_track_free(xa) && entry) - xas_clear_mark(&xas, XA_FREE_MARK); - } - xas_unlock(&xas); - } while (xas_nomem(&xas, gfp)); - - return xas_result(&xas, curr); -} -EXPORT_SYMBOL(xa_cmpxchg); - /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. -- cgit v1.2.3-71-gd317 From 9c16bb88905456a9b1299338041f05fa7699971b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 15:48:49 -0500 Subject: XArray: Turn xa_erase into an exported function Make xa_erase() take the spinlock and then call __xa_erase(), but make it out of line since it's such a common function. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +----------------- lib/xarray.c | 24 ++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 8e59d4fbd55e..4c839c17a99b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -289,6 +289,7 @@ struct xarray { void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); +void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); @@ -340,23 +341,6 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) return xa->xa_flags & XA_FLAGS_MARK(mark); } -/** - * xa_erase() - Erase this entry from the XArray. - * @xa: XArray. - * @index: Index of entry. - * - * This function is the equivalent of calling xa_store() with %NULL as - * the third argument. The XArray does not need to allocate memory, so - * the user does not need to provide GFP flags. - * - * Context: Process context. Takes and releases the xa_lock. - * Return: The entry which used to be at this index. - */ -static inline void *xa_erase(struct xarray *xa, unsigned long index) -{ - return xa_store(xa, index, NULL, 0); -} - /** * xa_for_each() - Iterate over a portion of an XArray. * @xa: XArray. diff --git a/lib/xarray.c b/lib/xarray.c index 77671d4a7910..b55aa8c1c20f 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1336,6 +1336,30 @@ void *__xa_erase(struct xarray *xa, unsigned long index) } EXPORT_SYMBOL(__xa_erase); +/** + * xa_erase() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index of entry. + * + * This function is the equivalent of calling xa_store() with %NULL as + * the third argument. The XArray does not need to allocate memory, so + * the user does not need to provide GFP flags. + * + * Context: Any context. Takes and releases the xa_lock. + * Return: The entry which used to be at this index. + */ +void *xa_erase(struct xarray *xa, unsigned long index) +{ + void *entry; + + xa_lock(xa); + entry = __xa_erase(xa, index); + xa_unlock(xa); + + return entry; +} +EXPORT_SYMBOL(xa_erase); + /** * xa_store() - Store this entry in the XArray. * @xa: XArray. -- cgit v1.2.3-71-gd317 From 84e5acb76dacb8ebd648a86a53907ce0dd616534 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 14:41:29 -0400 Subject: XArray: Add xa_store_bh() and xa_store_irq() These convenience wrappers disable interrupts while taking the spinlock. A number of drivers would otherwise have to open-code these functions. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 5 +++- include/linux/xarray.h | 52 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 65c77a81b689..8a6e2087de77 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -167,6 +167,8 @@ Takes RCU read lock: Takes xa_lock internally: * :c:func:`xa_store` + * :c:func:`xa_store_bh` + * :c:func:`xa_store_irq` * :c:func:`xa_insert` * :c:func:`xa_erase` * :c:func:`xa_erase_bh` @@ -247,7 +249,8 @@ Sharing the XArray with interrupt context is also possible, either using :c:func:`xa_lock_irqsave` in both the interrupt handler and process context, or :c:func:`xa_lock_irq` in process context and :c:func:`xa_lock` in the interrupt handler. Some of the more common patterns have helper -functions such as :c:func:`xa_erase_bh` and :c:func:`xa_erase_irq`. +functions such as :c:func:`xa_store_bh`, :c:func:`xa_store_irq`, +:c:func:`xa_erase_bh` and :c:func:`xa_erase_irq`. Sometimes you need to protect access to the XArray with a mutex because that lock sits above another mutex in the locking hierarchy. That does diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4c839c17a99b..52d9732e4ec4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -426,6 +426,58 @@ static inline int __xa_insert(struct xarray *xa, unsigned long index, return -EEXIST; } +/** + * xa_store_bh() - Store this entry in the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables softirqs + * while holding the array lock. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_bh(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return curr; +} + +/** + * xa_store_irq() - Erase this entry from the XArray. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * This function is like calling xa_store() except it disables interrupts + * while holding the array lock. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. + * Return: The entry which used to be at this index. + */ +static inline void *xa_store_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + void *curr; + + xa_lock_irq(xa); + curr = __xa_store(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return curr; +} + /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. -- cgit v1.2.3-71-gd317 From 804dfaf01bcc9daa4298c608ba9018abf616ec48 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 5 Nov 2018 16:37:15 -0500 Subject: XArray: Fix Documentation Minor fixes. Signed-off-by: Matthew Wilcox --- Documentation/core-api/xarray.rst | 6 +++++- include/linux/xarray.h | 4 ++-- lib/xarray.c | 10 +++++----- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index 616ac406bf86..dbe96cb5558e 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -74,7 +74,8 @@ using :c:func:`xa_load`. xa_store will overwrite any entry with the new entry and return the previous entry stored at that index. You can use :c:func:`xa_erase` instead of calling :c:func:`xa_store` with a ``NULL`` entry. There is no difference between an entry that has never -been stored to and one that has most recently had ``NULL`` stored to it. +been stored to, one that has been erased and one that has most recently +had ``NULL`` stored to it. You can conditionally replace an entry at an index by using :c:func:`xa_cmpxchg`. Like :c:func:`cmpxchg`, it will only succeed if @@ -114,6 +115,9 @@ unused entry. If another user has stored to the entry in the meantime, :c:func:`xa_release` will do nothing; if instead you want the entry to become ``NULL``, you should use :c:func:`xa_erase`. +If all entries in the array are ``NULL``, the :c:func:`xa_empty` function +will return ``true``. + Finally, you can remove all entries from an XArray by calling :c:func:`xa_destroy`. If the XArray entries are pointers, you may wish to free the entries first. You can do this by iterating over all present diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 52d9732e4ec4..564892e19f8c 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -487,7 +487,7 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, * the third argument. The XArray does not need to allocate memory, so * the user does not need to provide GFP flags. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ @@ -622,7 +622,7 @@ static inline int xa_alloc(struct xarray *xa, u32 *id, u32 max, void *entry, * Updates the @id pointer with the index, then stores the entry at that * index. A concurrent lookup will not see an uninitialised @id. * - * Context: Process context. Takes and releases the xa_lock while + * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory allocation fails or -ENOSPC if * there is no more space in the XArray. diff --git a/lib/xarray.c b/lib/xarray.c index c3e2084aa313..7946380cd6c9 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -610,8 +610,8 @@ static int xas_expand(struct xa_state *xas, void *head) * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. - * If the slot was newly created, returns NULL. If it failed to create the - * slot, returns NULL and indicates the error in @xas. + * If the slot was newly created, returns %NULL. If it failed to create the + * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas) { @@ -1640,7 +1640,7 @@ EXPORT_SYMBOL(__xa_alloc); * @index: Index of entry. * @mark: Mark number. * - * Attempting to set a mark on a NULL entry does not succeed. + * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ @@ -1710,7 +1710,7 @@ EXPORT_SYMBOL(xa_get_mark); * @index: Index of entry. * @mark: Mark number. * - * Attempting to set a mark on a NULL entry does not succeed. + * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ @@ -1879,7 +1879,7 @@ static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in - * which case all entries which are not NULL will be copied. + * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then -- cgit v1.2.3-71-gd317 From aa9b760cec2385ad408bb2e346c7f6dc1be69a79 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Sun, 4 Nov 2018 11:32:47 +0100 Subject: HID: fix up .raw_event() documentation The documentation for the .raw_event() callback says that if the driver return 1, there will be no further processing of the event, but this is not true, the actual code in hid-core.c looks like this: if (hdrv && hdrv->raw_event && hid_match_report(hid, report)) { ret = hdrv->raw_event(hid, report, data, size); if (ret < 0) goto unlock; } ret = hid_report_raw_event(hid, type, data, size, interrupt); The only return value that has any effect on the processing is a negative error. Correct this as it seems to confuse people: I found bogus code in the Razer out-of-tree driver attempting to return 1 here. Signed-off-by: Linus Walleij Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this -- cgit v1.2.3-71-gd317 From 8bd66d147c88bd441178c7b4c774ae5a185f19b8 Mon Sep 17 00:00:00 2001 From: "ndesaulniers@google.com" Date: Wed, 31 Oct 2018 12:39:01 -0700 Subject: include/linux/compiler*.h: define asm_volatile_goto asm_volatile_goto should also be defined for other compilers that support asm goto. Fixes commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive"). Signed-off-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) -- cgit v1.2.3-71-gd317 From 98ee3fc7ef8395f8b7a379e6608aee91efc66d48 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 6 Nov 2018 17:25:37 +0100 Subject: mtd: nand: Fix nanddev_pos_next_page() kernel-doc header Function name is wrong in the kernel-doc header. Fixes: 9c3736a3de21 ("mtd: nand: Add core infrastructure to deal with NAND devices") Signed-off-by: Boris Brezillon Reviewed-by: Miquel Raynal --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 78b86dea2f29..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -568,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * -- cgit v1.2.3-71-gd317 From 81bd415c91eb966118d773dddf254aebf3022411 Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Wed, 6 Jun 2018 21:42:32 +0200 Subject: watchdog/core: Add missing prototypes for weak functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The split out of the hard lockup detector exposed two new weak functions, but no prototypes for them, which triggers the build warning: kernel/watchdog.c:109:12: warning: no previous prototype for ‘watchdog_nmi_enable’ [-Wmissing-prototypes] kernel/watchdog.c:115:13: warning: no previous prototype for ‘watchdog_nmi_disable’ [-Wmissing-prototypes] Add the prototypes. Fixes: 73ce0511c436 ("kernel/watchdog.c: move hardlockup detector to separate file") Signed-off-by: Mathieu Malaterre Signed-off-by: Thomas Gleixner Cc: Babu Moger Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180606194232.17653-1-malat@debian.org --- include/linux/nmi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. -- cgit v1.2.3-71-gd317 From 99b77fef3c6c69bb7664f1ac97a69d5b17968dae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 31 Oct 2018 12:20:28 +0200 Subject: net/mlx5: Fix XRC SRQ umem valid bits Adapt XRC SRQ to the latest HW specification with fixed definition around umem valid bits. The previous definition relied on a bit which was taken for other purposes in legacy FW. Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; -- cgit v1.2.3-71-gd317 From 781f0766cc41a9dd2e5d118ef4b1d5d89430257b Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Fri, 19 Oct 2018 16:14:50 +0800 Subject: USB: Wait for extra delay time after USB_PORT_FEAT_RESET for quirky hub Devices connected under Terminus Technology Inc. Hub (1a40:0101) may fail to work after the system resumes from suspend: [ 206.063325] usb 3-2.4: reset full-speed USB device number 4 using xhci_hcd [ 206.143691] usb 3-2.4: device descriptor read/64, error -32 [ 206.351671] usb 3-2.4: device descriptor read/64, error -32 Info for this hub: T: Bus=03 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 2 Spd=480 MxCh= 4 D: Ver= 2.00 Cls=09(hub ) Sub=00 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=1a40 ProdID=0101 Rev=01.11 S: Product=USB 2.0 Hub C: #Ifs= 1 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 1 Cls=09(hub ) Sub=00 Prot=00 Driver=hub Some expirements indicate that the USB devices connected to the hub are innocent, it's the hub itself is to blame. The hub needs extra delay time after it resets its port. Hence wait for extra delay, if the device is connected to this quirky hub. Signed-off-by: Kai-Heng Feng Cc: stable Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/kernel-parameters.txt | 2 ++ drivers/usb/core/hub.c | 14 +++++++++++--- drivers/usb/core/quirks.c | 6 ++++++ include/linux/usb/quirks.h | 3 +++ 4 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 81d1d5a74728..19f4423e70d9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4713,6 +4713,8 @@ prevent spurious wakeup); n = USB_QUIRK_DELAY_CTRL_MSG (Device needs a pause after every control message); + o = USB_QUIRK_HUB_SLOW_RESET (Hub needs extra + delay after resetting its port); Example: quirks=0781:5580:bk,0a5c:5834:gij usbhid.mousepoll= diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index c6077d582d29..d9bd7576786a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2794,6 +2794,7 @@ static int hub_port_reset(struct usb_hub *hub, int port1, int i, status; u16 portchange, portstatus; struct usb_port *port_dev = hub->ports[port1 - 1]; + int reset_recovery_time; if (!hub_is_superspeed(hub->hdev)) { if (warm) { @@ -2885,11 +2886,18 @@ static int hub_port_reset(struct usb_hub *hub, int port1, done: if (status == 0) { - /* TRSTRCY = 10 ms; plus some extra */ if (port_dev->quirks & USB_PORT_QUIRK_FAST_ENUM) usleep_range(10000, 12000); - else - msleep(10 + 40); + else { + /* TRSTRCY = 10 ms; plus some extra */ + reset_recovery_time = 10 + 40; + + /* Hub needs extra delay after resetting its port. */ + if (hub->hdev->quirks & USB_QUIRK_HUB_SLOW_RESET) + reset_recovery_time += 100; + + msleep(reset_recovery_time); + } if (udev) { struct usb_hcd *hcd = bus_to_hcd(udev->bus); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 178d6c6063c0..4d7d948eae63 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -128,6 +128,9 @@ static int quirks_param_set(const char *val, const struct kernel_param *kp) case 'n': flags |= USB_QUIRK_DELAY_CTRL_MSG; break; + case 'o': + flags |= USB_QUIRK_HUB_SLOW_RESET; + break; /* Ignore unrecognized flag characters */ } } @@ -380,6 +383,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Terminus Technology Inc. Hub */ + { USB_DEVICE(0x1a40, 0x0101), .driver_info = USB_QUIRK_HUB_SLOW_RESET }, + /* Corsair K70 RGB */ { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index b7a99ce56bc9..a1be64c9940f 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -66,4 +66,7 @@ /* Device needs a pause after every control message. */ #define USB_QUIRK_DELAY_CTRL_MSG BIT(13) +/* Hub needs extra delay after resetting its port. */ +#define USB_QUIRK_HUB_SLOW_RESET BIT(14) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3-71-gd317 From 24efee412c75843755da0ddd7bbc2db2ce9129f5 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Tue, 6 Nov 2018 22:52:11 +0100 Subject: Compiler Attributes: improve explanation of header Explain better what "optional" attributes are, and avoid calling them so to avoid confusion. Simply retain "Optional" as a word to look for in the comments. Moreover, add a couple sentences to explain a bit more the intention and the documentation links. Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have -- cgit v1.2.3-71-gd317 From 23c625ce3065e40c933a4239efb9b11f1194a343 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 8 Nov 2018 14:55:21 +0100 Subject: libceph: assume argonaut on the server side No one is running pre-argonaut. In addition one of the argonaut features (NOSRCADDR) has been required since day one (and a half, 2.6.34 vs 2.6.35) of the kernel client. Allow for the possibility of reusing these feature bits later. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- fs/ceph/mds_client.c | 12 +++--------- include/linux/ceph/ceph_features.h | 8 +------- 2 files changed, 4 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 67a9aeb2f4ec..bd13a3267ae0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end, info->symlink = *p; *p += info->symlink_len; - if (features & CEPH_FEATURE_DIRLAYOUTHASH) - ceph_decode_copy_safe(p, end, &info->dir_layout, - sizeof(info->dir_layout), bad); - else - memset(&info->dir_layout, 0, sizeof(info->dir_layout)); - + ceph_decode_copy_safe(p, end, &info->dir_layout, + sizeof(info->dir_layout), bad); ceph_decode_32_safe(p, end, info->xattr_len, bad); ceph_decode_need(p, end, info->xattr_len, bad); info->xattr_data = *p; @@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.pagelist = pagelist; if (session->s_con.peer_features & CEPH_FEATURE_MDSENC) recon_state.msg_version = 3; - else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK) - recon_state.msg_version = 2; else - recon_state.msg_version = 1; + recon_state.msg_version = 2; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif -- cgit v1.2.3-71-gd317 From a4310fa2f24687888ce80fdb0e88583561a23700 Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Wed, 31 Oct 2018 10:37:46 +0100 Subject: can: dev: can_get_echo_skb(): factor out non sending code to __can_get_echo_skb() This patch factors out all non sending parts of can_get_echo_skb() into a seperate function __can_get_echo_skb(), so that it can be re-used in an upcoming patch. Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev.c | 36 +++++++++++++++++++++++++----------- include/linux/can/dev.h | 1 + 2 files changed, 26 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 49163570a63a..80530ab37b1e 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -477,14 +477,7 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, } EXPORT_SYMBOL_GPL(can_put_echo_skb); -/* - * Get the skb from the stack and loop it back locally - * - * The function is typically called when the TX done interrupt - * is handled in the device driver. The driver must protect - * access to priv->echo_skb, if necessary. - */ -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr) { struct can_priv *priv = netdev_priv(dev); @@ -495,13 +488,34 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) struct can_frame *cf = (struct can_frame *)skb->data; u8 dlc = cf->can_dlc; - netif_rx(priv->echo_skb[idx]); + *len_ptr = dlc; priv->echo_skb[idx] = NULL; - return dlc; + return skb; } - return 0; + return NULL; +} + +/* + * Get the skb from the stack and loop it back locally + * + * The function is typically called when the TX done interrupt + * is handled in the device driver. The driver must protect + * access to priv->echo_skb, if necessary. + */ +unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx) +{ + struct sk_buff *skb; + u8 len; + + skb = __can_get_echo_skb(dev, idx, &len); + if (!skb) + return 0; + + netif_rx(skb); + + return len; } EXPORT_SYMBOL_GPL(can_get_echo_skb); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index a83e1f632eb7..f01623aef2f7 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -169,6 +169,7 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx); +struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr); unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); -- cgit v1.2.3-71-gd317 From 55059f2b7f868cd43b3ad30e28e18347e1b46ace Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:38 +0200 Subject: can: rx-offload: introduce can_rx_offload_get_echo_skb() and can_rx_offload_queue_sorted() functions Current CAN framework can't guarantee proper/chronological order of RX and TX-ECHO messages. To make this possible, drivers should use this functions instead of can_get_echo_skb(). Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/rx-offload.c | 46 ++++++++++++++++++++++++++++++++++++++++++ include/linux/can/rx-offload.h | 4 ++++ 2 files changed, 50 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index c7d05027a7a0..c368686e2164 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -211,6 +211,52 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload) } EXPORT_SYMBOL_GPL(can_rx_offload_irq_offload_fifo); +int can_rx_offload_queue_sorted(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp) +{ + struct can_rx_offload_cb *cb; + unsigned long flags; + + if (skb_queue_len(&offload->skb_queue) > + offload->skb_queue_len_max) + return -ENOMEM; + + cb = can_rx_offload_get_cb(skb); + cb->timestamp = timestamp; + + spin_lock_irqsave(&offload->skb_queue.lock, flags); + __skb_queue_add_sort(&offload->skb_queue, skb, can_rx_offload_compare); + spin_unlock_irqrestore(&offload->skb_queue.lock, flags); + + can_rx_offload_schedule(offload); + + return 0; +} +EXPORT_SYMBOL_GPL(can_rx_offload_queue_sorted); + +unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp) +{ + struct net_device *dev = offload->dev; + struct net_device_stats *stats = &dev->stats; + struct sk_buff *skb; + u8 len; + int err; + + skb = __can_get_echo_skb(dev, idx, &len); + if (!skb) + return 0; + + err = can_rx_offload_queue_sorted(offload, skb, timestamp); + if (err) { + stats->rx_errors++; + stats->tx_fifo_errors++; + } + + return len; +} +EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb); + int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb) { if (skb_queue_len(&offload->skb_queue) > diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index cb31683bbe15..01a7c9e5d8d8 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -41,6 +41,10 @@ int can_rx_offload_add_timestamp(struct net_device *dev, struct can_rx_offload * int can_rx_offload_add_fifo(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight); int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 reg); int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload); +int can_rx_offload_queue_sorted(struct can_rx_offload *offload, + struct sk_buff *skb, u32 timestamp); +unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, + unsigned int idx, u32 timestamp); int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); -- cgit v1.2.3-71-gd317 From 4530ec36bb1e0d24f41c33229694adacda3d5d89 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 18 Sep 2018 11:40:40 +0200 Subject: can: rx-offload: rename can_rx_offload_irq_queue_err_skb() to can_rx_offload_queue_tail() This function has nothing todo with error. Signed-off-by: Oleksij Rempel Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/flexcan.c | 4 ++-- drivers/net/can/rx-offload.c | 5 +++-- include/linux/can/rx-offload.h | 3 ++- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 41a175f80c4b..5923bd0ec118 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -610,7 +610,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr) if (tx_errors) dev->stats.tx_errors++; - can_rx_offload_irq_queue_err_skb(&priv->offload, skb); + can_rx_offload_queue_tail(&priv->offload, skb); } static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) @@ -650,7 +650,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr) if (unlikely(new_state == CAN_STATE_BUS_OFF)) can_bus_off(dev); - can_rx_offload_irq_queue_err_skb(&priv->offload, skb); + can_rx_offload_queue_tail(&priv->offload, skb); } static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *offload) diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index c368686e2164..2ce4fa8698c7 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -257,7 +257,8 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, } EXPORT_SYMBOL_GPL(can_rx_offload_get_echo_skb); -int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb) +int can_rx_offload_queue_tail(struct can_rx_offload *offload, + struct sk_buff *skb) { if (skb_queue_len(&offload->skb_queue) > offload->skb_queue_len_max) @@ -268,7 +269,7 @@ int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_b return 0; } -EXPORT_SYMBOL_GPL(can_rx_offload_irq_queue_err_skb); +EXPORT_SYMBOL_GPL(can_rx_offload_queue_tail); static int can_rx_offload_init_queue(struct net_device *dev, struct can_rx_offload *offload, unsigned int weight) { diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01a7c9e5d8d8..8268811a697e 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -45,7 +45,8 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload, struct sk_buff *skb, u32 timestamp); unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); -int can_rx_offload_irq_queue_err_skb(struct can_rx_offload *offload, struct sk_buff *skb); +int can_rx_offload_queue_tail(struct can_rx_offload *offload, + struct sk_buff *skb); void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); -- cgit v1.2.3-71-gd317 From d19f9130b814d33c03118493c17454f7d90075d1 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 10 Nov 2018 04:22:09 +0100 Subject: x86/ptrace: Fix documentation for tracehook_report_syscall_entry() tracehook_report_syscall_entry() is called not only if %TIF_SYSCALL_TRACE is set, but also if %TIF_SYSCALL_EMU is set, as appears from x86's entry code. Signed-off-by: Elvira Khabirova Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ldv@altlinux.org Cc: oleg@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20181110042209.26333972@akathisia Signed-off-by: Ingo Molnar --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. -- cgit v1.2.3-71-gd317 From eff896288872d687d9662000ec9ae11b6d61766f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Nov 2018 09:55:43 -0800 Subject: efi/arm: Defer persistent reservations until after paging_init() The new memory EFI reservation feature we introduced to allow memory reservations to persist across kexec may trigger an unbounded number of calls to memblock_reserve(). The memblock subsystem can deal with this fine, but not before memblock resizing is enabled, which we can only do after paging_init(), when the memory we reallocate the array into is actually mapped. So break out the memreserve table processing into a separate routine and call it after paging_init() on arm64. On ARM, because of limited reviewing bandwidth of the maintainer, we cannot currently fix this, so instead, disable the EFI persistent memreserve entirely on ARM so we can fix it later. Tested-by: Marc Zyngier Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20181114175544.12860-5-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- arch/arm64/kernel/setup.c | 1 + drivers/firmware/efi/efi.c | 4 ++++ drivers/firmware/efi/libstub/arm-stub.c | 3 +++ include/linux/efi.h | 7 +++++++ 4 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 953e316521fc..f4fc1e0544b7 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -313,6 +313,7 @@ void __init setup_arch(char **cmdline_p) arm64_memblock_init(); paging_init(); + efi_apply_persistent_mem_reservations(); acpi_table_upgrade(); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 249eb70691b0..72a4da76d274 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -592,7 +592,11 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, early_memunmap(tbl, sizeof(*tbl)); } + return 0; +} +int __init efi_apply_persistent_mem_reservations(void) +{ if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) { unsigned long prsv = efi.mem_reserve; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index 30ac0c975f8a..3d36142cf812 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -75,6 +75,9 @@ void install_memreserve_table(efi_system_table_t *sys_table_arg) efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID; efi_status_t status; + if (IS_ENABLED(CONFIG_ARM)) + return; + status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv), (void **)&rsv); if (status != EFI_SUCCESS) { diff --git a/include/linux/efi.h b/include/linux/efi.h index 845174e113ce..100ce4a4aff6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1167,6 +1167,8 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); + +extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1185,6 +1187,11 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } + +static inline int efi_apply_persistent_mem_reservations(void) +{ + return 0; +} #endif extern int efi_status_to_err(efi_status_t status); -- cgit v1.2.3-71-gd317 From 0145b50566e7de5637e80ecba96c7f0e6fff1aad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 31 Oct 2018 15:20:05 +0100 Subject: iio/hid-sensors: Fix IIO_CHAN_INFO_RAW returning wrong values for signed numbers Before this commit sensor_hub_input_attr_get_raw_value() failed to take the signedness of 16 and 8 bit values into account, returning e.g. 65436 instead of -100 for the z-axis reading of an accelerometer. This commit adds a new is_signed parameter to the function and makes all callers pass the appropriate value for this. While at it, this commit also fixes up some neighboring lines where statements were needlessly split over 2 lines to improve readability. Signed-off-by: Hans de Goede Acked-by: Srinivas Pandruvada Acked-by: Benjamin Tissoires Cc: Signed-off-by: Jonathan Cameron --- drivers/hid/hid-sensor-custom.c | 2 +- drivers/hid/hid-sensor-hub.c | 13 ++++++++++--- drivers/iio/accel/hid-sensor-accel-3d.c | 5 ++++- drivers/iio/gyro/hid-sensor-gyro-3d.c | 5 ++++- drivers/iio/humidity/hid-sensor-humidity.c | 3 ++- drivers/iio/light/hid-sensor-als.c | 8 +++++--- drivers/iio/light/hid-sensor-prox.c | 8 +++++--- drivers/iio/magnetometer/hid-sensor-magn-3d.c | 8 +++++--- drivers/iio/orientation/hid-sensor-incl-3d.c | 8 +++++--- drivers/iio/pressure/hid-sensor-press.c | 8 +++++--- drivers/iio/temperature/hid-sensor-temperature.c | 3 ++- drivers/rtc/rtc-hid-sensor-time.c | 2 +- include/linux/hid-sensor-hub.h | 4 +++- 13 files changed, 52 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index e8a114157f87..bb012bc032e0 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -358,7 +358,7 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr, sensor_inst->hsdev, sensor_inst->hsdev->usage, usage, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, false); } else if (!strncmp(name, "units", strlen("units"))) value = sensor_inst->fields[field_index].attribute.units; else if (!strncmp(name, "unit-expo", strlen("unit-expo"))) diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 2b63487057c2..4256fdc5cd6d 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -299,7 +299,8 @@ EXPORT_SYMBOL_GPL(sensor_hub_get_feature); int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag) + enum sensor_hub_read_flags flag, + bool is_signed) { struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev); unsigned long flags; @@ -331,10 +332,16 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, &hsdev->pending.ready, HZ*5); switch (hsdev->pending.raw_size) { case 1: - ret_val = *(u8 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s8 *)hsdev->pending.raw_data; + else + ret_val = *(u8 *)hsdev->pending.raw_data; break; case 2: - ret_val = *(u16 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s16 *)hsdev->pending.raw_data; + else + ret_val = *(u16 *)hsdev->pending.raw_data; break; case 4: ret_val = *(u32 *)hsdev->pending.raw_data; diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index 41d97faf5013..38ff374a3ca4 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -149,6 +149,7 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; struct hid_sensor_hub_device *hsdev = accel_state->common_attributes.hsdev; @@ -158,12 +159,14 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&accel_state->common_attributes, true); report_id = accel_state->accel[chan->scan_index].report_id; + min = accel_state->accel[chan->scan_index].logical_minimum; address = accel_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( accel_state->common_attributes.hsdev, hsdev->usage, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&accel_state->common_attributes, diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 36941e69f959..88e857c4baf4 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -111,6 +111,7 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -118,13 +119,15 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&gyro_state->common_attributes, true); report_id = gyro_state->gyro[chan->scan_index].report_id; + min = gyro_state->gyro[chan->scan_index].logical_minimum; address = gyro_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( gyro_state->common_attributes.hsdev, HID_USAGE_SENSOR_GYRO_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&gyro_state->common_attributes, diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c index beab6d6fd6e1..4bc95f31c730 100644 --- a/drivers/iio/humidity/hid-sensor-humidity.c +++ b/drivers/iio/humidity/hid-sensor-humidity.c @@ -75,7 +75,8 @@ static int humidity_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_HUMIDITY, HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY, humid_st->humidity_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + humid_st->humidity_attr.logical_minimum < 0); hid_sensor_power_state(&humid_st->common_attributes, false); return IIO_VAL_INT; diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index 406caaee9a3c..94f33250ba5a 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -93,6 +93,7 @@ static int als_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -102,8 +103,8 @@ static int als_read_raw(struct iio_dev *indio_dev, case CHANNEL_SCAN_INDEX_INTENSITY: case CHANNEL_SCAN_INDEX_ILLUM: report_id = als_state->als_illum.report_id; - address = - HID_USAGE_SENSOR_LIGHT_ILLUM; + min = als_state->als_illum.logical_minimum; + address = HID_USAGE_SENSOR_LIGHT_ILLUM; break; default: report_id = -1; @@ -116,7 +117,8 @@ static int als_read_raw(struct iio_dev *indio_dev, als_state->common_attributes.hsdev, HID_USAGE_SENSOR_ALS, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&als_state->common_attributes, false); } else { diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 45107f7537b5..cf5a0c242609 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -73,6 +73,7 @@ static int prox_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -81,8 +82,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESENCE: report_id = prox_state->prox_attr.report_id; - address = - HID_USAGE_SENSOR_HUMAN_PRESENCE; + min = prox_state->prox_attr.logical_minimum; + address = HID_USAGE_SENSOR_HUMAN_PRESENCE; break; default: report_id = -1; @@ -95,7 +96,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, prox_state->common_attributes.hsdev, HID_USAGE_SENSOR_PROX, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&prox_state->common_attributes, false); } else { diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c index d55c4885211a..f3c0d41e5a8c 100644 --- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c +++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c @@ -163,21 +163,23 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&magn_state->magn_flux_attributes, true); - report_id = - magn_state->magn[chan->address].report_id; + report_id = magn_state->magn[chan->address].report_id; + min = magn_state->magn[chan->address].logical_minimum; address = magn_3d_addresses[chan->address]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( magn_state->magn_flux_attributes.hsdev, HID_USAGE_SENSOR_COMPASS_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state( diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c index 1e5451d1ff88..bdc5e4554ee4 100644 --- a/drivers/iio/orientation/hid-sensor-incl-3d.c +++ b/drivers/iio/orientation/hid-sensor-incl-3d.c @@ -111,21 +111,23 @@ static int incl_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&incl_state->common_attributes, true); - report_id = - incl_state->incl[chan->scan_index].report_id; + report_id = incl_state->incl[chan->scan_index].report_id; + min = incl_state->incl[chan->scan_index].logical_minimum; address = incl_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( incl_state->common_attributes.hsdev, HID_USAGE_SENSOR_INCLINOMETER_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { hid_sensor_power_state(&incl_state->common_attributes, false); diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c index 4c437918f1d2..d7b1c00ceb4d 100644 --- a/drivers/iio/pressure/hid-sensor-press.c +++ b/drivers/iio/pressure/hid-sensor-press.c @@ -77,6 +77,7 @@ static int press_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -85,8 +86,8 @@ static int press_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESSURE: report_id = press_state->press_attr.report_id; - address = - HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; + min = press_state->press_attr.logical_minimum; + address = HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; break; default: report_id = -1; @@ -99,7 +100,8 @@ static int press_read_raw(struct iio_dev *indio_dev, press_state->common_attributes.hsdev, HID_USAGE_SENSOR_PRESSURE, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&press_state->common_attributes, false); } else { diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c index beaf6fd3e337..b592fc4f007e 100644 --- a/drivers/iio/temperature/hid-sensor-temperature.c +++ b/drivers/iio/temperature/hid-sensor-temperature.c @@ -76,7 +76,8 @@ static int temperature_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_TEMPERATURE, HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE, temp_st->temperature_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + temp_st->temperature_attr.logical_minimum < 0); hid_sensor_power_state( &temp_st->common_attributes, false); diff --git a/drivers/rtc/rtc-hid-sensor-time.c b/drivers/rtc/rtc-hid-sensor-time.c index 2751dba850c6..3e1abb455472 100644 --- a/drivers/rtc/rtc-hid-sensor-time.c +++ b/drivers/rtc/rtc-hid-sensor-time.c @@ -213,7 +213,7 @@ static int hid_rtc_read_time(struct device *dev, struct rtc_time *tm) /* get a report with all values through requesting one value */ sensor_hub_input_attr_get_raw_value(time_state->common_attributes.hsdev, HID_USAGE_SENSOR_TIME, hid_time_addresses[0], - time_state->info[0].report_id, SENSOR_HUB_SYNC); + time_state->info[0].report_id, SENSOR_HUB_SYNC, false); /* wait for all values (event) */ ret = wait_for_completion_killable_timeout( &time_state->comp_last_time, HZ*6); diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** -- cgit v1.2.3-71-gd317 From b34087157dd76e8d96e5e52808134a791ac61e57 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 21 Nov 2018 16:00:50 +0000 Subject: dma-direct: Make DIRECT_MAPPING_ERROR viable for SWIOTLB With the overflow buffer removed, we no longer have a unique address which is guaranteed not to be a valid DMA target to use as an error token. The DIRECT_MAPPING_ERROR value of 0 tries to at least represent an unlikely DMA target, but unfortunately there are already SWIOTLB users with DMA-able memory at physical address 0 which now gets falsely treated as a mapping failure and leads to all manner of misbehaviour. The best we can do to mitigate that is flip DIRECT_MAPPING_ERROR to the other commonly-used error value of all-bits-set, since the last single byte of memory is by far the least-likely-valid DMA target. Fixes: dff8d6c1ed58 ("swiotlb: remove the overflow buffer") Reported-by: John Stultz Tested-by: John Stultz Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- include/linux/dma-direct.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index bd73e7a91410..9e66bfe369aa 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,7 +5,7 @@ #include #include -#define DIRECT_MAPPING_ERROR 0 +#define DIRECT_MAPPING_ERROR (~(dma_addr_t)0) #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include -- cgit v1.2.3-71-gd317 From 86de5921a3d5dd246df661e09bdd0a6131b39ae3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Nov 2018 05:53:59 -0800 Subject: tcp: defer SACK compression after DupThresh Jean-Louis reported a TCP regression and bisected to recent SACK compression. After a loss episode (receiver not able to keep up and dropping packets because its backlog is full), linux TCP stack is sending a single SACK (DUPACK). Sender waits a full RTO timer before recovering losses. While RFC 6675 says in section 5, "Algorithm Details", (2) If DupAcks < DupThresh but IsLost (HighACK + 1) returns true -- indicating at least three segments have arrived above the current cumulative acknowledgment point, which is taken to indicate loss -- go to step (4). ... (4) Invoke fast retransmit and enter loss recovery as follows: there are old TCP stacks not implementing this strategy, and still counting the dupacks before starting fast retransmit. While these stacks probably perform poorly when receivers implement LRO/GRO, we should be a little more gentle to them. This patch makes sure we do not enable SACK compression unless 3 dupacks have been sent since last rcv_nxt update. Ideally we should even rearm the timer to send one or two more DUPACK if no more packets are coming, but that will be work aiming for linux-4.21. Many thanks to Jean-Louis for bisecting the issue, providing packet captures and testing this patch. Fixes: 5d9f4262b7ea ("tcp: add SACK compression") Reported-by: Jean-Louis Dupond Tested-by: Jean-Louis Dupond Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + net/ipv4/tcp_input.c | 14 ++++++++++++-- net/ipv4/tcp_output.c | 6 +++--- net/ipv4/tcp_timer.c | 2 +- 4 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8ed77bb4ed86..a9b0280687d5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -196,6 +196,7 @@ struct tcp_sock { u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */ + u32 compressed_ack_rcv_nxt; u32 tsoffset; /* timestamp offset */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e695584bb33f..1e37c1388189 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4268,7 +4268,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq) * If the sack array is full, forget about the last one. */ if (this_sack >= TCP_NUM_SACKS) { - if (tp->compressed_ack) + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) tcp_send_ack(sk); this_sack--; tp->rx_opt.num_sacks--; @@ -5189,7 +5189,17 @@ send_now: if (!tcp_is_sack(tp) || tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) goto send_now; - tp->compressed_ack++; + + if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { + tp->compressed_ack_rcv_nxt = tp->rcv_nxt; + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, + tp->compressed_ack - TCP_FASTRETRANS_THRESH); + tp->compressed_ack = 0; + } + + if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH) + goto send_now; if (hrtimer_is_queued(&tp->compressed_ack_timer)) return; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9c34b97d365d..3f510cad0b3e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -180,10 +180,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, { struct tcp_sock *tp = tcp_sk(sk); - if (unlikely(tp->compressed_ack)) { + if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, - tp->compressed_ack); - tp->compressed_ack = 0; + tp->compressed_ack - TCP_FASTRETRANS_THRESH); + tp->compressed_ack = TCP_FASTRETRANS_THRESH; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 676020663ce8..5f8b6d3cd855 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -740,7 +740,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { - if (tp->compressed_ack) + if (tp->compressed_ack > TCP_FASTRETRANS_THRESH) tcp_send_ack(sk); } else { if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, -- cgit v1.2.3-71-gd317 From f1539a0c2545d7bd82e451bd1464f2a820f55de4 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 21 Nov 2018 16:27:11 +0100 Subject: Revert "HID: input: Create a utility class for counting scroll events" This reverts commit 1ff2e1a44e02d4bdbb9be67c7d9acc240a67141f. It turns out the current API is not that compatible with some Microsoft mice, so better start again from scratch. Signed-off-by: Benjamin Tissoires Acked-by: Harry Cutts Acked-by: Dmitry Torokhov Acked-by: Jiri Kosina --- drivers/hid/hid-input.c | 45 --------------------------------------------- include/linux/hid.h | 28 ---------------------------- 2 files changed, 73 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 28ee2ed88a1a..d6fab5798487 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1841,48 +1841,3 @@ void hidinput_disconnect(struct hid_device *hid) } EXPORT_SYMBOL_GPL(hidinput_disconnect); -/** - * hid_scroll_counter_handle_scroll() - Send high- and low-resolution scroll - * events given a high-resolution wheel - * movement. - * @counter: a hid_scroll_counter struct describing the wheel. - * @hi_res_value: the movement of the wheel, in the mouse's high-resolution - * units. - * - * Given a high-resolution movement, this function converts the movement into - * microns and emits high-resolution scroll events for the input device. It also - * uses the multiplier from &struct hid_scroll_counter to emit low-resolution - * scroll events when appropriate for backwards-compatibility with userspace - * input libraries. - */ -void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, - int hi_res_value) -{ - int low_res_scroll_amount; - /* Some wheels will rest 7/8ths of a notch from the previous notch - * after slow movement, so we want the threshold for low-res events to - * be in the middle of the notches (e.g. after 4/8ths) as opposed to on - * the notches themselves (8/8ths). - */ - int threshold = counter->resolution_multiplier / 2; - - input_report_rel(counter->dev, REL_WHEEL_HI_RES, - hi_res_value * counter->microns_per_hi_res_unit); - - counter->remainder += hi_res_value; - if (abs(counter->remainder) >= threshold) { - /* Add (or subtract) 1 because we want to trigger when the wheel - * is half-way to the next notch (i.e. scroll 1 notch after a - * 1/2 notch movement, 2 notches after a 1 1/2 notch movement, - * etc.). - */ - low_res_scroll_amount = - counter->remainder / counter->resolution_multiplier - + (hi_res_value > 0 ? 1 : -1); - input_report_rel(counter->dev, REL_WHEEL, - low_res_scroll_amount); - counter->remainder -= - low_res_scroll_amount * counter->resolution_multiplier; - } -} -EXPORT_SYMBOL_GPL(hid_scroll_counter_handle_scroll); diff --git a/include/linux/hid.h b/include/linux/hid.h index 387c70df6f29..a355d61940f2 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1139,34 +1139,6 @@ static inline u32 hid_report_len(struct hid_report *report) int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); - -/** - * struct hid_scroll_counter - Utility class for processing high-resolution - * scroll events. - * @dev: the input device for which events should be reported. - * @microns_per_hi_res_unit: the amount moved by the user's finger for each - * high-resolution unit reported by the mouse, in - * microns. - * @resolution_multiplier: the wheel's resolution in high-resolution mode as a - * multiple of its lower resolution. For example, if - * moving the wheel by one "notch" would result in a - * value of 1 in low-resolution mode but 8 in - * high-resolution, the multiplier is 8. - * @remainder: counts the number of high-resolution units moved since the last - * low-resolution event (REL_WHEEL or REL_HWHEEL) was sent. Should - * only be used by class methods. - */ -struct hid_scroll_counter { - struct input_dev *dev; - int microns_per_hi_res_unit; - int resolution_multiplier; - - int remainder; -}; - -void hid_scroll_counter_handle_scroll(struct hid_scroll_counter *counter, - int hi_res_value); - /* HID quirks API */ unsigned long hid_lookup_quirk(const struct hid_device *hdev); int hid_quirks_init(char **quirks_param, __u16 bus, int count); -- cgit v1.2.3-71-gd317 From 0211dda68a4f6531923a2f72d8e8959207f59fba Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Wed, 21 Nov 2018 16:28:23 +0200 Subject: net/dim: Update DIM start sample after each DIM iteration On every iteration of net_dim, the algorithm may choose to check for the system state by comparing current data sample with previous data sample. After each of these comparison, regardless of the action taken, the sample used as baseline is needed to be updated. This patch fixes a bug that causes DIM to take wrong decisions, due to never updating the baseline sample for comparison between iterations. This way, DIM always compares current sample with zeros. Although this is a functional fix, it also improves and stabilizes performance as the algorithm works properly now. Performance: Tested single UDP TX stream with pktgen: samples/pktgen/pktgen_sample03_burst_single_flow.sh -i p4p2 -d 1.1.1.1 -m 24:8a:07:88:26:8b -f 3 -b 128 ConnectX-5 100GbE packet rate improved from 15-19Mpps to 19-20Mpps. Also, toggling between profiles is less frequent with the fix. Fixes: 8115b750dbcb ("net/dim: use struct net_dim_sample as arg to net_dim") Signed-off-by: Tal Gilboa Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/net_dim.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index c79e859408e6..fd458389f7d1 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -406,6 +406,8 @@ static inline void net_dim(struct net_dim *dim, } /* fall through */ case NET_DIM_START_MEASURE: + net_dim_sample(end_sample.event_ctr, end_sample.pkt_ctr, end_sample.byte_ctr, + &dim->start_sample); dim->state = NET_DIM_MEASURE_IN_PROGRESS; break; case NET_DIM_APPLY_NEW_PROFILE: -- cgit v1.2.3-71-gd317 From 5cd8d46ea1562be80063f53c7c6a5f40224de623 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 20 Nov 2018 13:00:18 -0500 Subject: packet: copy user buffers before orphan or clone tpacket_snd sends packets with user pages linked into skb frags. It notifies that pages can be reused when the skb is released by setting skb->destructor to tpacket_destruct_skb. This can cause data corruption if the skb is orphaned (e.g., on transmit through veth) or cloned (e.g., on mirror to another psock). Create a kernel-private copy of data in these cases, same as tun/tap zerocopy transmission. Reuse that infrastructure: mark the skb as SKBTX_ZEROCOPY_FRAG, which will trigger copy in skb_orphan_frags(_rx). Unlike other zerocopy packets, do not set shinfo destructor_arg to struct ubuf_info. tpacket_destruct_skb already uses that ptr to notify when the original skb is released and a timestamp is recorded. Do not change this timestamp behavior. The ubuf_info->callback is not needed anyway, as no zerocopy notification is expected. Mark destructor_arg as not-a-uarg by setting the lower bit to 1. The resulting value is not a valid ubuf_info pointer, nor a valid tpacket_snd frame address. Add skb_zcopy_.._nouarg helpers for this. The fix relies on features introduced in commit 52267790ef52 ("sock: add MSG_ZEROCOPY"), so can be backported as is only to 4.14. Tested with from `./in_netns.sh ./txring_overwrite` from http://github.com/wdebruij/kerneltools/tests Fixes: 69e3c75f4d54 ("net: TX_RING and packet mmap") Reported-by: Anand H. Krishnan Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 18 +++++++++++++++++- net/packet/af_packet.c | 4 ++-- 2 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0ba687454267..0d1b2c3f127b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1326,6 +1326,22 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) } } +static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) +{ + skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; +} + +static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) +{ + return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; +} + +static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) +{ + return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); +} + /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) { @@ -1335,7 +1351,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) if (uarg->callback == sock_zerocopy_callback) { uarg->zerocopy = uarg->zerocopy && zerocopy; sock_zerocopy_put(uarg); - } else { + } else if (!skb_zcopy_is_nouarg(skb)) { uarg->callback(uarg, zerocopy); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ec3095f13aae..a74650e98f42 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb) void *ph; __u32 ts; - ph = skb_shinfo(skb)->destructor_arg; + ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); @@ -2461,7 +2461,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); - skb_shinfo(skb)->destructor_arg = ph.raw; + skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); -- cgit v1.2.3-71-gd317 From 89259088c1b7fecb43e8e245dc931909132a4e03 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 17 Nov 2018 11:32:29 +0100 Subject: netfilter: nfnetlink_cttimeout: fetch timeouts for udplite and gre, too syzbot was able to trigger the WARN in cttimeout_default_get() by passing UDPLITE as l4protocol. Alias UDPLITE to UDP, both use same timeout values. Furthermore, also fetch GRE timeouts. GRE is a bit more complicated, as it still can be a module and its netns_proto_gre struct layout isn't visible outside of the gre module. Can't move timeouts around, it appears conntrack sysctl unregister assumes net_generic() returns nf_proto_net, so we get crash. Expose layout of netns_proto_gre instead. A followup nf-next patch could make gre tracker be built-in as well if needed, its not that large. Last, make the WARN() mention the missing protocol value in case anything else is missing. Reported-by: syzbot+2fae8fa157dd92618cae@syzkaller.appspotmail.com Fixes: 8866df9264a3 ("netfilter: nfnetlink_cttimeout: pass default timeout policy to obj_to_nlattr") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 13 +++++++++++++ net/netfilter/nf_conntrack_proto_gre.c | 14 ++------------ net/netfilter/nfnetlink_cttimeout.c | 15 +++++++++++++-- 3 files changed, 28 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index b8d95564bd53..14edb795ab43 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -21,6 +21,19 @@ struct nf_ct_gre_keymap { struct nf_conntrack_tuple tuple; }; +enum grep_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct netns_proto_gre { + struct nf_proto_net nf; + rwlock_t keymap_lock; + struct list_head keymap_list; + unsigned int gre_timeouts[GRE_CT_MAX]; +}; + /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 9b48dc8b4b88..2a5e56c6d8d9 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -43,24 +43,12 @@ #include #include -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_UNREPLIED] = 30*HZ, [GRE_CT_REPLIED] = 180*HZ, }; static unsigned int proto_gre_net_id __read_mostly; -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; static inline struct netns_proto_gre *gre_pernet(struct net *net) { @@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void) { int ret; + BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); + ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a518eb162344..109b0d27345a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -455,7 +455,8 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, case IPPROTO_TCP: timeouts = nf_tcp_pernet(net)->timeouts; break; - case IPPROTO_UDP: + case IPPROTO_UDP: /* fallthrough */ + case IPPROTO_UDPLITE: timeouts = nf_udp_pernet(net)->timeouts; break; case IPPROTO_DCCP: @@ -469,13 +470,23 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, case IPPROTO_SCTP: #ifdef CONFIG_NF_CT_PROTO_SCTP timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case IPPROTO_GRE: +#ifdef CONFIG_NF_CT_PROTO_GRE + if (l4proto->net_id) { + struct netns_proto_gre *net_gre; + + net_gre = net_generic(net, *l4proto->net_id); + timeouts = net_gre->gre_timeouts; + } #endif break; case 255: timeouts = &nf_generic_pernet(net)->timeout; break; default: - WARN_ON_ONCE(1); + WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); break; } -- cgit v1.2.3-71-gd317 From 786a9ab1330169f2602238822b4df5d5c4c98f6c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Nov 2018 10:35:17 +0100 Subject: gpio: davinci: restore a way to manually specify the GPIO base Commit 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") broke the network support in legacy boot mode for da850-evm since we can no longer request the MDIO clock GPIO. Other boards may be broken too, which I haven't tested. The problem is in the fact that most board files still use the legacy GPIO API where lines are requested by numbers rather than descriptors. While this should be fixed eventually, in order to unbreak the board for now - provide a way to manually specify the GPIO base in platform data. Fixes: 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Acked-by: Linus Walleij Signed-off-by: Sekhar Nori --- drivers/gpio/gpio-davinci.c | 2 +- include/linux/platform_data/gpio-davinci.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 5c1564fcc24e..bdb29e51b417 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -258,7 +258,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.set = davinci_gpio_set; chips->chip.ngpio = ngpio; - chips->chip.base = -1; + chips->chip.base = pdata->no_auto_base ? pdata->base : -1; #ifdef CONFIG_OF_GPIO chips->chip.of_gpio_n_cells = 2; diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; -- cgit v1.2.3-71-gd317 From 8114865ff82e200b383e46821c25cb0625b842b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 17:10:15 -0500 Subject: function_graph: Create function_graph_enter() to consolidate architecture code Currently all the architectures do basically the same thing in preparing the function graph tracer on entry to a function. This code can be pulled into a generic location and then this will allow the function graph tracer to be fixed, as well as extended. Create a new function graph helper function_graph_enter() that will call the hook function (ftrace_graph_entry) and the shadow stack operation (ftrace_push_return_trace), and remove the need of the architecture code to manage the shadow stack. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ kernel/trace/trace_functions_graph.c | 16 ++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..5717e8f81c59 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -779,6 +779,9 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp); +extern int +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..28f2602435d0 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -182,6 +182,22 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, return 0; } +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return -EBUSY; + + return ftrace_push_return_trace(ret, func, &trace.depth, + frame_pointer, retp); +} + /* Retrieve a function return address to the trace stack on thread info.*/ static void ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, -- cgit v1.2.3-71-gd317 From e2c95a61656d29ceaac97b6a975c8a1f26e26f15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Nov 2018 14:05:38 +0100 Subject: bpf, ppc64: generalize fetching subprog into bpf_jit_get_func_addr Make fetching of the BPF call address from ppc64 JIT generic. ppc64 was using a slightly different variant rather than through the insns' imm field encoding as the target address would not fit into that space. Therefore, the target subprog number was encoded into the insns' offset and fetched through fp->aux->func[off]->bpf_func instead. Given there are other JITs with this issue and the mechanism of fetching the address is JIT-generic, move it into the core as a helper instead. On the JIT side, we get information on whether the retrieved address is a fixed one, that is, not changing through JIT passes, or a dynamic one. For the former, JITs can optimize their imm emission because this doesn't change jump offsets throughout JIT process. Signed-off-by: Daniel Borkmann Reviewed-by: Sandipan Das Tested-by: Sandipan Das Signed-off-by: Alexei Starovoitov --- arch/powerpc/net/bpf_jit_comp64.c | 57 ++++++++++++++++++++++++++------------- include/linux/filter.h | 4 +++ kernel/bpf/core.c | 34 +++++++++++++++++++++++ 3 files changed, 76 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 50b129785aee..17482f5de3e2 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) PPC_BLR(); } -static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func) +static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, + u64 func) +{ +#ifdef PPC64_ELF_ABI_v1 + /* func points to the function descriptor */ + PPC_LI64(b2p[TMP_REG_2], func); + /* Load actual entry point from function descriptor */ + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); + /* ... and move it to LR */ + PPC_MTLR(b2p[TMP_REG_1]); + /* + * Load TOC from function descriptor at offset 8. + * We can clobber r2 since we get called through a + * function pointer (so caller will save/restore r2) + * and since we don't use a TOC ourself. + */ + PPC_BPF_LL(2, b2p[TMP_REG_2], 8); +#else + /* We can clobber r12 */ + PPC_FUNC_ADDR(12, func); + PPC_MTLR(12); +#endif + PPC_BLRL(); +} + +static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, + u64 func) { unsigned int i, ctx_idx = ctx->idx; @@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, { const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; - int i; + int i, ret; /* Start of epilogue code - will only be valid 2nd pass onwards */ u32 exit_addr = addrs[flen]; @@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 src_reg = b2p[insn[i].src_reg]; s16 off = insn[i].off; s32 imm = insn[i].imm; + bool func_addr_fixed; + u64 func_addr; u64 imm64; - u8 *func; u32 true_cond; u32 tmp_idx; @@ -711,23 +738,15 @@ emit_clear: case BPF_JMP | BPF_CALL: ctx->seen |= SEEN_FUNC; - /* bpf function call */ - if (insn[i].src_reg == BPF_PSEUDO_CALL) - if (!extra_pass) - func = NULL; - else if (fp->aux->func && off < fp->aux->func_cnt) - /* use the subprog id from the off - * field to lookup the callee address - */ - func = (u8 *) fp->aux->func[off]->bpf_func; - else - return -EINVAL; - /* kernel helper call */ - else - func = (u8 *) __bpf_call_base + imm; - - bpf_jit_emit_func_call(image, ctx, (u64)func); + ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass, + &func_addr, &func_addr_fixed); + if (ret < 0) + return ret; + if (func_addr_fixed) + bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + else + bpf_jit_emit_func_call_rel(image, ctx, func_addr); /* move return value from r3 to BPF_REG_0 */ PPC_MR(b2p[BPF_REG_0], 3); break; diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..448dcc448f1f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed); + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1a796e0799ec..b1a3545d0ec8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) -- cgit v1.2.3-71-gd317 From d125f3f866df88da5a85df00291f88f0baa89f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 07:40:39 -0500 Subject: function_graph: Make ftrace_push_return_trace() static As all architectures now call function_graph_enter() to do the entry work, no architecture should ever call ftrace_push_return_trace(). Make it static. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 --- kernel/trace/trace_functions_graph.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5717e8f81c59..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -776,9 +776,6 @@ struct ftrace_ret_stack { */ extern void return_to_handler(void); -extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 28f2602435d0..88ca787a1cdc 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,7 +118,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int +static int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp) { -- cgit v1.2.3-71-gd317 From 39eb456dacb543de90d3bc6a8e0ac5cf51ac475e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 08:07:12 -0500 Subject: function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack Currently, the depth of the ret_stack is determined by curr_ret_stack index. The issue is that there's a race between setting of the curr_ret_stack and calling of the callback attached to the return of the function. Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") moved the calling of the callback to after the setting of the curr_ret_stack, even stating that it was safe to do so, when in fact, it was the reason there was a barrier() there (yes, I should have commented that barrier()). Not only does the curr_ret_stack keep track of the current call graph depth, it also keeps the ret_stack content from being overwritten by new data. The function profiler, uses the "subtime" variable of ret_stack structure and by moving the curr_ret_stack, it allows for interrupts to use the same structure it was using, corrupting the data, and breaking the profiler. To fix this, there needs to be two variables to handle the call stack depth and the pointer to where the ret_stack is being used, as they need to change at two different locations. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/sched.h | 1 + kernel/trace/ftrace.c | 3 +++ kernel/trace/trace_functions_graph.c | 21 +++++++++++++-------- 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d6183a55e8eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..48513954713c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 88ca787a1cdc..02d4081a7f5a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -119,7 +119,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, /* Add a function return address to the trace stack on thread info.*/ static int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,8 +177,6 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; - return 0; } @@ -188,14 +186,20 @@ int function_graph_enter(unsigned long ret, unsigned long func, struct ftrace_graph_ent trace; trace.func = func; - trace.depth = current->curr_ret_stack + 1; + trace.depth = ++current->curr_ret_depth; /* Only trace if the calling function expects to */ if (!ftrace_graph_entry(&trace)) - return -EBUSY; + goto out; - return ftrace_push_return_trace(ret, func, &trace.depth, - frame_pointer, retp); + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + return 0; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -257,7 +261,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth; } /* @@ -273,6 +277,7 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) trace.rettime = trace_clock_local(); barrier(); current->curr_ret_stack--; + current->curr_ret_depth--; /* * The curr_ret_stack can be less than -1 only if it was * filtered out and it's about to return from the function. -- cgit v1.2.3-71-gd317 From 321a874a7ef85655e93b3206d0f36b4a6097f948 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:38 +0100 Subject: sched/smt: Expose sched_smt_present static key Make the scheduler's 'sched_smt_present' static key globaly available, so it can be used in the x86 speculation control code. Provide a query function and a stub for the CONFIG_SMP=n case. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.430168326@linutronix.de --- include/linux/sched/smt.h | 18 ++++++++++++++++++ kernel/sched/sched.h | 4 +--- 2 files changed, 19 insertions(+), 3 deletions(-) create mode 100644 include/linux/sched/smt.h (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..c9e0be514110 --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 618577fc9aa8..4e524ab589c9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -936,9 +937,6 @@ static inline int cpu_of(struct rq *rq) #ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) -- cgit v1.2.3-71-gd317 From a74cfffb03b73d41e08f84c2e5c87dec0ce3db9f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:39 +0100 Subject: x86/speculation: Rework SMT state change arch_smt_update() is only called when the sysfs SMT control knob is changed. This means that when SMT is enabled in the sysfs control knob the system is considered to have SMT active even if all siblings are offline. To allow finegrained control of the speculation mitigations, the actual SMT state is more interesting than the fact that siblings could be enabled. Rework the code, so arch_smt_update() is invoked from each individual CPU hotplug function, and simplify the update function while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.521974984@linutronix.de --- arch/x86/kernel/cpu/bugs.c | 11 +++++------ include/linux/sched/smt.h | 2 ++ kernel/cpu.c | 15 +++++++++------ 3 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index a723af0c4400..5625b323ff32 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -344,16 +345,14 @@ void arch_smt_update(void) return; mutex_lock(&spec_ctrl_mutex); - mask = x86_spec_ctrl_base; - if (cpu_smt_control == CPU_SMT_ENABLED) + + mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP; + if (sched_smt_active()) mask |= SPEC_CTRL_STIBP; - else - mask &= ~SPEC_CTRL_STIBP; if (mask != x86_spec_ctrl_base) { pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n", - cpu_smt_control == CPU_SMT_ENABLED ? - "Enabling" : "Disabling"); + mask & SPEC_CTRL_STIBP ? "Enabling" : "Disabling"); x86_spec_ctrl_base = mask; on_each_cpu(update_stibp_msr, NULL, 1); } diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index c9e0be514110..59d3736c454c 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -15,4 +15,6 @@ static __always_inline bool sched_smt_active(void) static inline bool sched_smt_active(void) { return false; } #endif +void arch_smt_update(void); + #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c7f3b4c453c..91d5c38eb7e5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -367,6 +368,12 @@ static void lockdep_release_cpus_lock(void) #endif /* CONFIG_HOTPLUG_CPU */ +/* + * Architectures that need SMT-specific errata handling during SMT hotplug + * should override this. + */ +void __weak arch_smt_update(void) { } + #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); @@ -1011,6 +1018,7 @@ out: * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); + arch_smt_update(); return ret; } @@ -1139,6 +1147,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); + arch_smt_update(); return ret; } @@ -2055,12 +2064,6 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -/* - * Architectures that need SMT-specific errata handling during SMT hotplug - * should override this. - */ -void __weak arch_smt_update(void) { }; - static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; -- cgit v1.2.3-71-gd317 From 46f7ecb1e7359f183f5bbd1e08b90e10e52164f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:50 +0100 Subject: ptrace: Remove unused ptrace_may_access_sched() and MODE_IBRS The IBPB control code in x86 removed the usage. Remove the functionality which was introduced for this. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.559149393@linutronix.de --- include/linux/ptrace.h | 17 ----------------- kernel/ptrace.c | 10 ---------- 2 files changed, 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 80b34dffdfb9..c2cee9db5204 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -261,9 +261,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - if (mode & PTRACE_MODE_SCHED) - return false; - if (mode & PTRACE_MODE_NOAUDIT) return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); else @@ -331,16 +328,9 @@ ok: !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; - if (mode & PTRACE_MODE_SCHED) - return 0; return security_ptrace_access_check(task, mode); } -bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode) -{ - return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED); -} - bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; -- cgit v1.2.3-71-gd317 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- Documentation/userspace-api/spec_ctrl.rst | 9 +++++ arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 67 +++++++++++++++++++++++++++++++ arch/x86/kernel/process.c | 5 +++ include/linux/sched.h | 9 +++++ include/uapi/linux/prctl.h | 1 + tools/include/uapi/linux/prctl.h | 1 + 7 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index 32f3d55c54b7..c4dbe6f7cdae 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -92,3 +92,12 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + +- PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes + (Mitigate Spectre V2 style attacks against user processes) + + Invocations: + * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index d4d35baf0430..2adbe7b047fa 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -232,6 +232,7 @@ enum spectre_v2_mitigation { enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_PRCTL, }; /* The Speculative Store Bypass disable variants */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9cab538e10f1..74359fff87fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -566,6 +566,8 @@ void arch_smt_update(void) case SPECTRE_V2_USER_STRICT: update_stibp_strict(); break; + case SPECTRE_V2_USER_PRCTL: + break; } mutex_unlock(&spec_ctrl_mutex); @@ -752,12 +754,50 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + switch (ctrl) { + case PR_SPEC_ENABLE: + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return 0; + /* + * Indirect branch speculation is always disabled in strict + * mode. + */ + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return -EPERM; + task_clear_spec_ib_disable(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + /* + * Indirect branch speculation is always allowed when + * mitigation is force disabled. + */ + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return -EPERM; + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return 0; + task_set_spec_ib_disable(task); + if (ctrl == PR_SPEC_FORCE_DISABLE) + task_set_spec_ib_force_disable(task); + task_update_spec_tif(task); + break; + default: + return -ERANGE; + } + return 0; +} + int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, unsigned long ctrl) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_set(task, ctrl); default: return -ENODEV; } @@ -790,11 +830,34 @@ static int ssb_prctl_get(struct task_struct *task) } } +static int ib_prctl_get(struct task_struct *task) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return PR_SPEC_NOT_AFFECTED; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return PR_SPEC_ENABLE; + case SPECTRE_V2_USER_PRCTL: + if (task_spec_ib_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ib_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case SPECTRE_V2_USER_STRICT: + return PR_SPEC_DISABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_get(task); default: return -ENODEV; } @@ -974,6 +1037,8 @@ static char *stibp_state(void) return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: return ", STIBP: forced"; + case SPECTRE_V2_USER_PRCTL: + return ""; } return ""; } @@ -986,6 +1051,8 @@ static char *ibpb_state(void) return ", IBPB: disabled"; case SPECTRE_V2_USER_STRICT: return ", IBPB: always-on"; + case SPECTRE_V2_USER_PRCTL: + return ""; } } return ""; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index afbe2eb4a1c6..7d31192296a8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -450,6 +450,11 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) set_tsk_thread_flag(tsk, TIF_SSBD); else clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); } /* Return the updated threadinfo flags*/ return task_thread_info(tsk)->flags; diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) -- cgit v1.2.3-71-gd317 From 3f2b7b9035107d6096ea438ea3d97dcf0481b6d2 Mon Sep 17 00:00:00 2001 From: "kiran.modukuri" Date: Mon, 26 Nov 2018 15:41:48 +0000 Subject: fscache: Fix race in fscache_op_complete() due to split atomic_sub & read The code in fscache_retrieval_complete is using atomic_sub followed by an atomic_read: atomic_sub(n_pages, &op->n_pages); if (atomic_read(&op->n_pages) <= 0) fscache_op_complete(&op->op, true); This causes two threads doing a decrement of n_pages to race with each other seeing the op->refcount 0 at same time - and they end up calling fscache_op_complete() in both the threads leading to an assertion failure. Fix this by using atomic_sub_return_relaxed() instead of two calls. Note that I'm using 'relaxed' rather than, say, 'release' as there aren't multiple variables that appear to need ordering across the release. The oops looks something like: FS-Cache: Assertion failed FS-Cache: 0 > 0 is false ... kernel BUG at /usr/src/linux-4.4.0/fs/fscache/operation.c:449! ... Workqueue: fscache_operation fscache_op_work_func [fscache] ... RIP: 0010:[] fscache_op_complete+0x10d/0x180 [fscache] ... Call Trace: [] cachefiles_read_copier+0x3a9/0x410 [cachefiles] [] fscache_op_work_func+0x22/0x50 [fscache] [] process_one_work+0x150/0x3f0 [] worker_thread+0x11a/0x470 [] ? __schedule+0x359/0x980 [] ? rescuer_thread+0x310/0x310 [] kthread+0xd6/0xf0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 This seen this in 4.4.x kernels and the same bug affects fscache in latest upstreams kernels. Fixes: 1bb4b7f98f36 ("FS-Cache: The retrieval remaining-pages counter needs to be atomic_t") Signed-off-by: Kiran Kumar Modukuri Signed-off-by: David Howells --- include/linux/fscache-cache.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } -- cgit v1.2.3-71-gd317 From 89d328f637b9904b6d4c9af73c8a608b8dd4d6f8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 16:17:22 -0700 Subject: pstore/ram: Correctly calculate usable PRZ bytes The actual number of bytes stored in a PRZ is smaller than the bytes requested by platform data, since there is a header on each PRZ. Additionally, if ECC is enabled, there are trailing bytes used as well. Normally this mismatch doesn't matter since PRZs are circular buffers and the leading "overflow" bytes are just thrown away. However, in the case of a compressed record, this rather badly corrupts the results. This corruption was visible with "ramoops.mem_size=204800 ramoops.ecc=1". Any stored crashes would not be uncompressable (producing a pstorefs "dmesg-*.enc.z" file), and triggering errors at boot: [ 2.790759] pstore: crypto_comp_decompress failed, ret = -22! Backporting this depends on commit 70ad35db3321 ("pstore: Convert console write to use ->write_buf") Reported-by: Joel Fernandes Fixes: b0aad7a99c1d ("pstore: Add compression support to pstore") Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) --- fs/pstore/ram.c | 15 ++++++--------- include/linux/pstore.h | 5 ++++- 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 712960e117fe..8646fe6e916f 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -816,17 +816,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we - * have to handle dumps, we must have at least record_size buffer. And - * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be - * ZERO_SIZE_PTR). + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). */ - if (cxt->console_size) - cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */ - cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize); - cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore buffer\n"); + pr_err("cannot allocate pstore crash dump buffer\n"); err = -ENOMEM; goto fail_clear; } diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for -- cgit v1.2.3-71-gd317 From 0c7a52e4d4b5c4d35b31f3c3ad32af814f1bf491 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 28 Nov 2018 03:35:23 +0000 Subject: tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique After enabling KVM event tracing, almost all of trace_kvm_exit()'s printk shows "kvm_exit: IRQ: ..." even if the actual exception_type is NOT IRQ. More specifically, trace_kvm_exit() is defined in virt/kvm/arm/trace.h by TRACE_EVENT. This slight problem may have existed after commit e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU"). There are two variables in trace_kvm_exit() and __DO_TRACE() which have the same name, *idx*. Thus the actual value of *idx* will be overwritten when tracing. Fix it by adding a simple prefix. Cc: Joel Fernandes Cc: Wang Haibin Cc: linux-trace-devel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Reviewed-by: Joel Fernandes (Google) Signed-off-by: Zenghui Yu Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ -- cgit v1.2.3-71-gd317 From e0c274472d5d27f277af722e017525e0b33784cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 4 ++++ include/linux/psi.h | 3 ++- init/Kconfig | 9 ++++++++ kernel/sched/psi.c | 30 +++++++++++++++++-------- kernel/sched/stats.h | 8 +++---- 5 files changed, 40 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 675170c36078..5d6ba930d4f4 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3505,6 +3505,10 @@ before loading. See Documentation/blockdev/ramdisk.txt. + psi= [KNL] Enable or disable pressure stall information + tracking. + Format: + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); diff --git a/init/Kconfig b/init/Kconfig index a4112e95724a..cf5b5a0dcbc2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -509,6 +509,15 @@ config PSI Say N if unsure. +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi_enable=1 + on the kernel commandline during boot. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3d7355d7c3e3..fe24de3fbc93 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@ static int psi_bug __read_mostly; -bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); /* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group) void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + } psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; *flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0; cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -637,7 +649,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (psi_disabled) { + if (static_branch_likely(&psi_disabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -673,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; update_stats(group); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 4904c4677000..aa0de240fb41 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -66,7 +66,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!wakeup || p->sched_psi_wake_requeue) { @@ -86,7 +86,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!sleep) { @@ -102,7 +102,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -128,7 +128,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (unlikely(rq->curr->flags & PF_MEMSTALL)) -- cgit v1.2.3-71-gd317