diff options
Diffstat (limited to 'include/linux')
59 files changed, 739 insertions, 439 deletions
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9ebb53f031cd..aba9c24486aa 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -28,7 +28,7 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ -enum { +enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ @@ -852,21 +852,39 @@ static inline bool blk_mq_is_reserved_rq(struct request *rq) return rq->rq_flags & RQF_RESV; } -/* +/** + * blk_mq_add_to_batch() - add a request to the completion batch + * @req: The request to add to batch + * @iob: The batch to add the request + * @is_error: Specify true if the request failed with an error + * @complete: The completaion handler for the request + * * Batched completions only work when there is no I/O error and no special * ->end_io handler. + * + * Return: true when the request was added to the batch, otherwise false */ static inline bool blk_mq_add_to_batch(struct request *req, - struct io_comp_batch *iob, int ioerror, + struct io_comp_batch *iob, bool is_error, void (*complete)(struct io_comp_batch *)) { /* - * blk_mq_end_request_batch() can't end request allocated from - * sched tags + * Check various conditions that exclude batch processing: + * 1) No batch container + * 2) Has scheduler data attached + * 3) Not a passthrough request and end_io set + * 4) Not a passthrough request and failed with an error */ - if (!iob || (req->rq_flags & RQF_SCHED_TAGS) || ioerror || - (req->end_io && !blk_rq_is_passthrough(req))) + if (!iob) + return false; + if (req->rq_flags & RQF_SCHED_TAGS) return false; + if (!blk_rq_is_passthrough(req)) { + if (req->end_io) + return false; + if (is_error) + return false; + } if (!iob->complete) iob->complete = complete; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a97428e8bbbe..1c0cf6af392c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -196,10 +196,11 @@ struct gendisk { unsigned int zone_capacity; unsigned int last_zone_capacity; unsigned long __rcu *conv_zones_bitmap; - unsigned int zone_wplugs_hash_bits; - spinlock_t zone_wplugs_lock; + unsigned int zone_wplugs_hash_bits; + atomic_t nr_zone_wplugs; + spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; - struct hlist_head *zone_wplugs_hash; + struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -373,6 +374,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_user_sectors; unsigned int max_segment_size; + unsigned int min_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; diff --git a/include/linux/call_once.h b/include/linux/call_once.h index 6261aa0b3fb0..13cd6469e7e5 100644 --- a/include/linux/call_once.h +++ b/include/linux/call_once.h @@ -26,20 +26,41 @@ do { \ __once_init((once), #once, &__key); \ } while (0) -static inline void call_once(struct once *once, void (*cb)(struct once *)) +/* + * call_once - Ensure a function has been called exactly once + * + * @once: Tracking struct + * @cb: Function to be called + * + * If @once has never completed successfully before, call @cb and, if + * it returns a zero or positive value, mark @once as completed. Return + * the value returned by @cb + * + * If @once has completed succesfully before, return 0. + * + * The call to @cb is implicitly surrounded by a mutex, though for + * efficiency the * function avoids taking it after the first call. + */ +static inline int call_once(struct once *once, int (*cb)(struct once *)) { - /* Pairs with atomic_set_release() below. */ - if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) - return; - - guard(mutex)(&once->lock); - WARN_ON(atomic_read(&once->state) == ONCE_RUNNING); - if (atomic_read(&once->state) != ONCE_NOT_STARTED) - return; - - atomic_set(&once->state, ONCE_RUNNING); - cb(once); - atomic_set_release(&once->state, ONCE_COMPLETED); + int r, state; + + /* Pairs with atomic_set_release() below. */ + if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) + return 0; + + guard(mutex)(&once->lock); + state = atomic_read(&once->state); + if (unlikely(state != ONCE_NOT_STARTED)) + return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0; + + atomic_set(&once->state, ONCE_RUNNING); + r = cb(once); + if (r < 0) + atomic_set(&once->state, ONCE_NOT_STARTED); + else + atomic_set_release(&once->state, ONCE_COMPLETED); + return r; } #endif /* _LINUX_CALL_ONCE_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1b20d2d8ef7c..17960a1e858d 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -71,9 +71,6 @@ enum { /* Cgroup is frozen. */ CGRP_FROZEN, - - /* Control group has to be killed. */ - CGRP_KILL, }; /* cgroup_root->flags */ @@ -461,6 +458,9 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ + /* sequence number for cgroup.kill, serialized by css_set_lock. */ + unsigned int kill_seq; + struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index ec00e3f7af2b..ee2614adb785 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -212,7 +212,7 @@ const volatile void * __must_check_fn(const volatile void *val) { return val; } #define no_free_ptr(p) \ - ((typeof(p)) __must_check_fn(__get_and_null(p, NULL))) + ((typeof(p)) __must_check_fn((__force const volatile void *)__get_and_null(p, NULL))) #define return_ptr(p) return no_free_ptr(p) diff --git a/include/linux/compaction.h b/include/linux/compaction.h index e94776496049..7bf0c521db63 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order) return 2UL << order; } +static inline int current_is_kcompactd(void) +{ + return current->flags & PF_KCOMPACTD; +} + #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b087de2f3e94..155385754824 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Unreachable code */ #ifdef CONFIG_OBJTOOL /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") +#define __annotate_jump_table __section(".data.rel.ro.c_jump_table") #else /* !CONFIG_OBJTOOL */ #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ @@ -191,6 +191,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) +#else /* __CHECKER__ */ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) +#endif /* __CHECKER__ */ + +/* &a[0] degrades to a pointer: a different type from an array */ +#define __is_array(a) (!__same_type((a), &(a)[0])) +#define __must_be_array(a) __BUILD_BUG_ON_ZERO_MSG(!__is_array(a), \ + "must be array") + +#define __is_byte_array(a) (__is_array(a) && sizeof((a)[0]) == 1) +#define __must_be_byte_array(a) __BUILD_BUG_ON_ZERO_MSG(!__is_byte_array(a), \ + "must be byte array") + +/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ +#define __must_be_cstr(p) \ + __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") + #endif /* __KERNEL__ */ /** @@ -231,19 +250,6 @@ static inline void *offset_to_ptr(const int *off) #define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) -#ifdef __CHECKER__ -#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) -#else /* __CHECKER__ */ -#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) -#endif /* __CHECKER__ */ - -/* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) __BUILD_BUG_ON_ZERO_MSG(__same_type((a), &(a)[0]), "must be array") - -/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ -#define __must_be_cstr(p) \ - __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") - /* * This returns a constant expression while determining if an argument is * a constant expression, most importantly without evaluating the argument. diff --git a/include/linux/cred.h b/include/linux/cred.h index 0c3c4b16b469..5658a3bfe803 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -172,18 +172,12 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) static inline const struct cred *override_creds(const struct cred *override_cred) { - const struct cred *old = current->cred; - - rcu_assign_pointer(current->cred, override_cred); - return old; + return rcu_replace_pointer(current->cred, override_cred, 1); } static inline const struct cred *revert_creds(const struct cred *revert_cred) { - const struct cred *override_cred = current->cred; - - rcu_assign_pointer(current->cred, revert_cred); - return override_cred; + return rcu_replace_pointer(current->cred, revert_cred, 1); } /** diff --git a/include/linux/damon.h b/include/linux/damon.h index af525252b853..c9074d569596 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -470,6 +470,11 @@ struct damos { unsigned long next_apply_sis; /* informs if ongoing DAMOS walk for this scheme is finished */ bool walk_completed; + /* + * If the current region in the filtering stage is allowed by core + * layer-handled filters. If true, operations layer allows it, too. + */ + bool core_filters_allowed; /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 4afb60365675..45bff10d3773 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -203,34 +203,34 @@ struct dentry_operations { #define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ -#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) +#define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(13) /* Parent inode is watched by some fsnotify listener */ -#define DCACHE_DENTRY_KILLED BIT(15) +#define DCACHE_DENTRY_KILLED BIT(14) -#define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ -#define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ -#define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ +#define DCACHE_MOUNTED BIT(15) /* is a mountpoint */ +#define DCACHE_NEED_AUTOMOUNT BIT(16) /* handle automount on this dir */ +#define DCACHE_MANAGE_TRANSIT BIT(17) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) -#define DCACHE_LRU_LIST BIT(19) +#define DCACHE_LRU_LIST BIT(18) -#define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ -#define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ -#define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ -#define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ -#define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ -#define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ -#define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ -#define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ +#define DCACHE_ENTRY_TYPE (7 << 19) /* bits 19..21 are for storing type: */ +#define DCACHE_MISS_TYPE (0 << 19) /* Negative dentry */ +#define DCACHE_WHITEOUT_TYPE (1 << 19) /* Whiteout dentry (stop pathwalk) */ +#define DCACHE_DIRECTORY_TYPE (2 << 19) /* Normal directory */ +#define DCACHE_AUTODIR_TYPE (3 << 19) /* Lookupless directory (presumed automount) */ +#define DCACHE_REGULAR_TYPE (4 << 19) /* Regular file type */ +#define DCACHE_SPECIAL_TYPE (5 << 19) /* Other file type */ +#define DCACHE_SYMLINK_TYPE (6 << 19) /* Symlink */ -#define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ -#define DCACHE_OP_REAL BIT(26) +#define DCACHE_NOKEY_NAME BIT(22) /* Encrypted name encoded without key */ +#define DCACHE_OP_REAL BIT(23) -#define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ -#define DCACHE_DENTRY_CURSOR BIT(29) -#define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ +#define DCACHE_PAR_LOOKUP BIT(24) /* being looked up (with parent locked shared) */ +#define DCACHE_DENTRY_CURSOR BIT(25) +#define DCACHE_NORCU BIT(26) /* No RCU delay for freeing */ extern seqlock_t rename_lock; @@ -253,7 +253,6 @@ extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); -extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); diff --git a/include/linux/device/faux.h b/include/linux/device/faux.h new file mode 100644 index 000000000000..9f43c0e46aa4 --- /dev/null +++ b/include/linux/device/faux.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2025 The Linux Foundation + * + * A "simple" faux bus that allows devices to be created and added + * automatically to it. This is to be used whenever you need to create a + * device that is not associated with any "real" system resources, and do + * not want to have to deal with a bus/driver binding logic. It is + * intended to be very simple, with only a create and a destroy function + * available. + */ +#ifndef _FAUX_DEVICE_H_ +#define _FAUX_DEVICE_H_ + +#include <linux/container_of.h> +#include <linux/device.h> + +/** + * struct faux_device - a "faux" device + * @dev: internal struct device of the object + * + * A simple faux device that can be created/destroyed. To be used when a + * driver only needs to have a device to "hang" something off. This can be + * used for downloading firmware or other basic tasks. Use this instead of + * a struct platform_device if the device has no resources assigned to + * it at all. + */ +struct faux_device { + struct device dev; +}; +#define to_faux_device(x) container_of_const((x), struct faux_device, dev) + +/** + * struct faux_device_ops - a set of callbacks for a struct faux_device + * @probe: called when a faux device is probed by the driver core + * before the device is fully bound to the internal faux bus + * code. If probe succeeds, return 0, otherwise return a + * negative error number to stop the probe sequence from + * succeeding. + * @remove: called when a faux device is removed from the system + * + * Both @probe and @remove are optional, if not needed, set to NULL. + */ +struct faux_device_ops { + int (*probe)(struct faux_device *faux_dev); + void (*remove)(struct faux_device *faux_dev); +}; + +struct faux_device *faux_device_create(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops); +struct faux_device *faux_device_create_with_groups(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops, + const struct attribute_group **groups); +void faux_device_destroy(struct faux_device *faux_dev); + +static inline void *faux_device_get_drvdata(const struct faux_device *faux_dev) +{ + return dev_get_drvdata(&faux_dev->dev); +} + +static inline void faux_device_set_drvdata(struct faux_device *faux_dev, void *data) +{ + dev_set_drvdata(&faux_dev->dev, data); +} + +#endif /* _FAUX_DEVICE_H_ */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 053c57e61869..7d63d1d75f22 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -114,21 +114,22 @@ typedef struct { #define EFI_MAX_MEMORY_TYPE 16 /* Attribute values: */ -#define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ -#define EFI_MEMORY_WC ((u64)0x0000000000000002ULL) /* write-coalescing */ -#define EFI_MEMORY_WT ((u64)0x0000000000000004ULL) /* write-through */ -#define EFI_MEMORY_WB ((u64)0x0000000000000008ULL) /* write-back */ -#define EFI_MEMORY_UCE ((u64)0x0000000000000010ULL) /* uncached, exported */ -#define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ -#define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ -#define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ -#define EFI_MEMORY_NV ((u64)0x0000000000008000ULL) /* non-volatile */ -#define EFI_MEMORY_MORE_RELIABLE \ - ((u64)0x0000000000010000ULL) /* higher reliability */ -#define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ -#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ -#define EFI_MEMORY_CPU_CRYPTO ((u64)0x0000000000080000ULL) /* supports encryption */ -#define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ +#define EFI_MEMORY_UC BIT_ULL(0) /* uncached */ +#define EFI_MEMORY_WC BIT_ULL(1) /* write-coalescing */ +#define EFI_MEMORY_WT BIT_ULL(2) /* write-through */ +#define EFI_MEMORY_WB BIT_ULL(3) /* write-back */ +#define EFI_MEMORY_UCE BIT_ULL(4) /* uncached, exported */ +#define EFI_MEMORY_WP BIT_ULL(12) /* write-protect */ +#define EFI_MEMORY_RP BIT_ULL(13) /* read-protect */ +#define EFI_MEMORY_XP BIT_ULL(14) /* execute-protect */ +#define EFI_MEMORY_NV BIT_ULL(15) /* non-volatile */ +#define EFI_MEMORY_MORE_RELIABLE BIT_ULL(16) /* higher reliability */ +#define EFI_MEMORY_RO BIT_ULL(17) /* read-only */ +#define EFI_MEMORY_SP BIT_ULL(18) /* soft reserved */ +#define EFI_MEMORY_CPU_CRYPTO BIT_ULL(19) /* supports encryption */ +#define EFI_MEMORY_HOT_PLUGGABLE BIT_ULL(20) /* supports unplugging at runtime */ +#define EFI_MEMORY_RUNTIME BIT_ULL(63) /* range requires runtime mapping */ + #define EFI_MEMORY_DESCRIPTOR_VERSION 1 #define EFI_PAGE_SHIFT 12 diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 0c0d00fcd131..ccb478eb174b 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -25,6 +25,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long t /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); +/* Copy ready events to userspace */ +int epoll_sendevents(struct file *file, struct epoll_event __user *events, + int maxevents); + /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 78f660ebc318..3c817dc6292e 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ #define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) -#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) +#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT) /* * fanotify_init() flags that require CAP_SYS_ADMIN. @@ -38,7 +38,8 @@ FAN_REPORT_PIDFD | \ FAN_REPORT_FD_ERROR | \ FAN_UNLIMITED_QUEUE | \ - FAN_UNLIMITED_MARKS) + FAN_UNLIMITED_MARKS | \ + FAN_REPORT_MNT) /* * fanotify_init() flags that are allowed for user without CAP_SYS_ADMIN. @@ -58,7 +59,7 @@ #define FANOTIFY_INTERNAL_GROUP_FLAGS (FANOTIFY_UNPRIV) #define FANOTIFY_MARK_TYPE_BITS (FAN_MARK_INODE | FAN_MARK_MOUNT | \ - FAN_MARK_FILESYSTEM) + FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS) #define FANOTIFY_MARK_CMD_BITS (FAN_MARK_ADD | FAN_MARK_REMOVE | \ FAN_MARK_FLUSH) @@ -109,10 +110,13 @@ /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ #define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) +#define FANOTIFY_MOUNT_EVENTS (FAN_MNT_ATTACH | FAN_MNT_DETACH) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ FANOTIFY_INODE_EVENTS | \ - FANOTIFY_ERROR_EVENTS) + FANOTIFY_ERROR_EVENTS | \ + FANOTIFY_MOUNT_EVENTS) /* Extra flags that may be reported with event or control handling of events */ #define FANOTIFY_EVENT_FLAGS (FAN_EVENT_ON_CHILD | FAN_ONDIR) diff --git a/include/linux/fs.h b/include/linux/fs.h index f47fbe16b101..1a0e23a5d02d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> @@ -222,7 +223,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_FSNOTIFY_HSM(mode) 0 #endif - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -791,6 +791,8 @@ struct inode { static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { + VFS_WARN_ON_INODE(strlen(link) != linklen, inode); + VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; @@ -1055,7 +1057,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_ref: reference count * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations @@ -1065,12 +1066,12 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener + * @f_owner: file owner * @f_path: path of the file * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file - * @f_owner: file owner * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file @@ -1078,9 +1079,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) + * @f_ref: reference count */ struct file { - file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1090,6 +1091,7 @@ struct file { unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; + struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ struct path f_path; union { @@ -1103,7 +1105,6 @@ struct file { void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ - struct fown_struct *f_owner; errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL @@ -1115,6 +1116,7 @@ struct file { struct file_ra_state f_ra; freeptr_t f_freeptr; }; + file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1969,8 +1971,8 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap, */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); -int vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); +struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, @@ -2027,7 +2029,7 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); -extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, @@ -2199,8 +2201,8 @@ struct inode_operations { int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); - int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *, - umode_t); + struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, + struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); @@ -2642,9 +2644,6 @@ static inline bool is_mgtime(const struct inode *inode) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -extern struct dentry *mount_single(struct file_system_type *fs_type, - int flags, void *data, - int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2783,13 +2782,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) return mnt_idmap(mnt) != &nop_mnt_idmap; } -extern long vfs_truncate(const struct path *, loff_t); +int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); -extern long do_sys_open(int dfd, const char __user *filename, int flags, - umode_t mode); +int do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, @@ -2840,7 +2839,10 @@ extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); -extern struct filename *getname(const char __user *); +static inline struct filename *getname(const char __user *name) +{ + return getname_flags(name, 0); +} extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) @@ -2853,6 +2855,13 @@ static inline struct filename *getname_maybe_null(const char __user *name, int f return __getname_maybe_null(name); } extern void putname(struct filename *name); +DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) + +static inline struct filename *refname(struct filename *name) +{ + atomic_inc(&name->refcnt); + return name; +} extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); @@ -2964,8 +2973,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; - filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, - iocb->ki_pos + count); + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; @@ -3141,6 +3150,12 @@ static inline void exe_file_allow_write_access(struct file *exe_file) allow_write_access(exe_file); } +static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) +{ + file->f_mode &= ~FMODE_FSNOTIFY_MASK; + file->f_mode |= mode; +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; @@ -3280,7 +3295,11 @@ static inline void __iget(struct inode *inode) extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); -extern struct inode *new_inode_pseudo(struct super_block *sb); +struct inode *alloc_inode(struct super_block *sb); +static inline struct inode *new_inode_pseudo(struct super_block *sb) +{ + return alloc_inode(sb); +} extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); @@ -3435,6 +3454,8 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); +extern const char *page_get_link_raw(struct dentry *, struct inode *, + struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 4b4bfef6f053..a19e4bd32e4d 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -144,8 +144,6 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); -int reconfigure_single(struct super_block *s, - int flags, void *data); extern int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1a9ef8f6784d..454d8e466958 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -129,7 +129,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS -void file_set_fsnotify_mode(struct file *file); +void file_set_fsnotify_mode_from_watchers(struct file *file); /* * fsnotify_file_area_perm - permission hook before access to file range @@ -171,6 +171,21 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, } /* + * fsnotify_mmap_perm - permission hook before mmap of file range + */ +static inline int fsnotify_mmap_perm(struct file *file, int prot, + const loff_t off, size_t len) +{ + /* + * mmap() generates only pre-content events. + */ + if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode))) + return 0; + + return fsnotify_pre_content(&file->f_path, &off, len); +} + +/* * fsnotify_truncate_perm - permission hook before file truncate */ static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) @@ -213,7 +228,7 @@ static inline int fsnotify_open_perm(struct file *file) } #else -static inline void file_set_fsnotify_mode(struct file *file) +static inline void file_set_fsnotify_mode_from_watchers(struct file *file) { } @@ -223,6 +238,12 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, return 0; } +static inline int fsnotify_mmap_perm(struct file *file, int prot, + const loff_t off, size_t len) +{ + return 0; +} + static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { return 0; @@ -299,6 +320,11 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) __fsnotify_vfsmount_delete(mnt); } +static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns) +{ + __fsnotify_mntns_delete(mntns); +} + /* * fsnotify_inoderemove - an inode is going away */ @@ -507,4 +533,19 @@ static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, NULL, NULL, NULL, 0); } +static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); +} + +static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_DETACH, ns, mnt); +} + +static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt) +{ + fsnotify_mnt(FS_MNT_MOVE, ns, mnt); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 0d24a21a8e60..6cd8d1d28b8b 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -59,6 +59,10 @@ #define FS_PRE_ACCESS 0x00100000 /* Pre-content access hook */ +#define FS_MNT_ATTACH 0x01000000 /* Mount was attached */ +#define FS_MNT_DETACH 0x02000000 /* Mount was detached */ +#define FS_MNT_MOVE (FS_MNT_ATTACH | FS_MNT_DETACH) + /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. @@ -80,6 +84,9 @@ */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) +/* Mount namespace events */ +#define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH) + /* Content events can be used to inspect file content */ #define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \ FS_ACCESS_PERM) @@ -108,6 +115,7 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ + FSNOTIFY_MNT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ @@ -298,6 +306,7 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_MNT, FSNOTIFY_EVENT_ERROR, }; @@ -318,6 +327,11 @@ static inline const struct path *file_range_path(const struct file_range *range) return range->path; } +struct fsnotify_mnt { + const struct mnt_namespace *ns; + u64 mnt_id; +}; + static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { @@ -383,6 +397,24 @@ static inline struct super_block *fsnotify_data_sb(const void *data, } } +static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_MNT: + return data; + default: + return NULL; + } +} + +static inline u64 fsnotify_data_mnt_id(const void *data, int data_type) +{ + const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type); + + return mnt_data ? mnt_data->mnt_id : 0; +} + static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) @@ -420,6 +452,7 @@ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, + FSNOTIFY_ITER_TYPE_MNTNS, FSNOTIFY_ITER_TYPE_COUNT }; @@ -429,6 +462,7 @@ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, + FSNOTIFY_OBJ_TYPE_MNTNS, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; @@ -613,8 +647,10 @@ extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data 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 void __fsnotify_mntns_delete(struct mnt_namespace *mntns); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); +extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { @@ -928,6 +964,9 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void fsnotify_sb_delete(struct super_block *sb) {} +static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns) +{} + static inline void fsnotify_sb_free(struct super_block *sb) {} @@ -942,6 +981,9 @@ static inline u32 fsnotify_get_cookie(void) static inline void fsnotify_unmount_inodes(struct super_block *sb) {} +static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt) +{} + #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h index c3b4b7ed7c16..84a5045f80f3 100644 --- a/include/linux/hrtimer_defs.h +++ b/include/linux/hrtimer_defs.h @@ -125,6 +125,7 @@ struct hrtimer_cpu_base { ktime_t softirq_expires_next; struct hrtimer *softirq_next_timer; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + call_single_data_t csd; } ____cacheline_aligned; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ec8c0ccc8f95..76a75ec03dd6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -682,6 +682,7 @@ struct huge_bootmem_page { int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); +void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, @@ -1004,7 +1005,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif @@ -1066,6 +1069,10 @@ static inline int replace_free_hugepage_folios(unsigned long start_pfn, return 0; } +static inline void wait_for_freed_hugetlb_folios(void) +{ +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c31fd1dba3bd..2b2af24d2a43 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -244,6 +244,7 @@ enum i2c_driver_flags { * @id_table: List of I2C devices supported by this driver * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) + * @clients: List of detected clients we created (for i2c-core use only) * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. @@ -298,6 +299,7 @@ struct i2c_driver { /* Device detection callback for automatic device creation */ int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; + struct list_head clients; u32 flags; }; @@ -313,6 +315,8 @@ struct i2c_driver { * @dev: Driver model device node for the slave. * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) + * @detected: member of an i2c_driver.clients list or i2c-core's + * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. * @devres_group_id: id of the devres group that will be created for resources @@ -332,8 +336,6 @@ struct i2c_client { #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ #define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ -#define I2C_CLIENT_AUTO 0x100 /* client was auto-detected */ -#define I2C_CLIENT_USER 0x200 /* client was userspace-created */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ @@ -345,6 +347,7 @@ struct i2c_client { struct device dev; /* the device structure */ int init_irq; /* irq set at initialization */ int irq; /* irq issued by device */ + struct list_head detected; #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif @@ -751,6 +754,9 @@ struct i2c_adapter { char name[48]; struct completion dev_released; + struct mutex userspace_clients_lock; + struct list_head userspace_clients; + struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 75bf54e76f3b..02fe001feebb 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -56,6 +56,13 @@ struct vm_fault; * * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must * never be merged with the mapping before it. + * + * IOMAP_F_ANON_WRITE indicates that (write) I/O does not have a target block + * assigned to it yet and the file system will do that in the bio submission + * handler, splitting the I/O as needed. + * + * IOMAP_F_ATOMIC_BIO indicates that (write) I/O will be issued as an atomic + * bio, i.e. set REQ_ATOMIC. */ #define IOMAP_F_NEW (1U << 0) #define IOMAP_F_DIRTY (1U << 1) @@ -68,6 +75,8 @@ struct vm_fault; #endif /* CONFIG_BUFFER_HEAD */ #define IOMAP_F_XATTR (1U << 5) #define IOMAP_F_BOUNDARY (1U << 6) +#define IOMAP_F_ANON_WRITE (1U << 7) +#define IOMAP_F_ATOMIC_BIO (1U << 8) /* * Flags set by the core iomap code during operations: @@ -111,6 +120,8 @@ struct iomap { static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos) { + if (iomap->flags & IOMAP_F_ANON_WRITE) + return U64_MAX; /* invalid */ return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT; } @@ -182,7 +193,8 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ -#define IOMAP_ATOMIC (1 << 9) +#define IOMAP_ATOMIC (1 << 9) /* torn-write protection */ +#define IOMAP_DONTCACHE (1 << 10) struct iomap_ops { /* @@ -211,8 +223,10 @@ struct iomap_ops { * calls to iomap_iter(). Treat as read-only in the body. * @len: The remaining length of the file segment we're operating on. * It is updated at the same time as @pos. - * @processed: The number of bytes processed by the body in the most recent - * iteration, or a negative errno. 0 causes the iteration to stop. + * @iter_start_pos: The original start pos for the current iomap. Used for + * incremental iter advance. + * @status: Status of the most recent iteration. Zero on success or a negative + * errno on error. * @flags: Zero or more of the iomap_begin flags above. * @iomap: Map describing the I/O iteration * @srcmap: Source map for COW operations @@ -221,7 +235,8 @@ struct iomap_iter { struct inode *inode; loff_t pos; u64 len; - s64 processed; + loff_t iter_start_pos; + int status; unsigned flags; struct iomap iomap; struct iomap srcmap; @@ -229,20 +244,46 @@ struct iomap_iter { }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); +int iomap_iter_advance(struct iomap_iter *iter, u64 *count); /** - * iomap_length - length of the current iomap iteration + * iomap_length_trim - trimmed length of the current iomap iteration * @iter: iteration structure + * @pos: File position to trim from. + * @len: Length of the mapping to trim to. * - * Returns the length that the operation applies to for the current iteration. + * Returns a trimmed length that the operation applies to for the current + * iteration. */ -static inline u64 iomap_length(const struct iomap_iter *iter) +static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos, + u64 len) { u64 end = iter->iomap.offset + iter->iomap.length; if (iter->srcmap.type != IOMAP_HOLE) end = min(end, iter->srcmap.offset + iter->srcmap.length); - return min(iter->len, end - iter->pos); + return min(len, end - pos); +} + +/** + * iomap_length - length of the current iomap iteration + * @iter: iteration structure + * + * Returns the length that the operation applies to for the current iteration. + */ +static inline u64 iomap_length(const struct iomap_iter *iter) +{ + return iomap_length_trim(iter, iter->pos, iter->len); +} + +/** + * iomap_iter_advance_full - advance by the full length of current map + */ +static inline int iomap_iter_advance_full(struct iomap_iter *iter) +{ + u64 length = iomap_length(iter); + + return iomap_iter_advance(iter, &length); } /** @@ -306,12 +347,11 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, const struct iomap_ops *ops); + bool *did_zero, const struct iomap_ops *ops, void *private); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops); -vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, - const struct iomap_ops *ops); - + const struct iomap_ops *ops, void *private); +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, + void *private); typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, @@ -328,16 +368,42 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops); /* + * Flags for iomap_ioend->io_flags. + */ +/* shared COW extent */ +#define IOMAP_IOEND_SHARED (1U << 0) +/* unwritten extent */ +#define IOMAP_IOEND_UNWRITTEN (1U << 1) +/* don't merge into previous ioend */ +#define IOMAP_IOEND_BOUNDARY (1U << 2) +/* is direct I/O */ +#define IOMAP_IOEND_DIRECT (1U << 3) + +/* + * Flags that if set on either ioend prevent the merge of two ioends. + * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way) + */ +#define IOMAP_IOEND_NOMERGE_FLAGS \ + (IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT) + +/* * Structure for writeback I/O completions. + * + * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io + * for direct I/O) can split a bio generated by iomap. In that case the parent + * ioend it was split from is recorded in ioend->io_parent. */ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ - u16 io_type; - u16 io_flags; /* IOMAP_F_* */ + u16 io_flags; /* IOMAP_IOEND_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of data within eof */ + size_t io_size; /* size of the extent */ + atomic_t io_remaining; /* completetion defer count */ + int io_error; /* stashed away status */ + struct iomap_ioend *io_parent; /* parent for completions */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ + void *io_private; /* file system private data */ struct bio io_bio; /* MUST BE LAST! */ }; @@ -362,12 +428,14 @@ struct iomap_writeback_ops { loff_t offset, unsigned len); /* - * Optional, allows the file systems to perform actions just before - * submitting the bio and/or override the bio end_io handler for complex - * operations like copy on write extent manipulation or unwritten extent - * conversions. + * Optional, allows the file systems to hook into bio submission, + * including overriding the bi_end_io handler. + * + * Returns 0 if the bio was successfully submitted, or a negative + * error code if status was non-zero or another error happened and + * the bio could not be submitted. */ - int (*prepare_ioend)(struct iomap_ioend *ioend, int status); + int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status); /* * Optional, allows the file system to discard state on a page where @@ -383,6 +451,10 @@ struct iomap_writepage_ctx { u32 nr_folios; /* folios added to the ioend */ }; +struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, + loff_t file_offset, u16 ioend_flags); +struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend, + unsigned int max_len, bool is_append); void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); @@ -454,4 +526,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, # define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO) #endif /* CONFIG_SWAP */ +extern struct bio_set iomap_ioend_bioset; + #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index ed945f42e064..0ea8c9887429 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -537,7 +537,7 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) * * Return: jiffies value */ -#define secs_to_jiffies(_secs) ((_secs) * HZ) +#define secs_to_jiffies(_secs) (unsigned long)((_secs) * HZ) extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) diff --git a/include/linux/key.h b/include/linux/key.h index 074dca3222b9..ba05de8579ec 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -236,6 +236,7 @@ struct key { #define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */ #define KEY_FLAG_KEEP 8 /* set if key should not be removed */ #define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */ +#define KEY_FLAG_FINAL_PUT 10 /* set if final put has happened on key */ /* the key type and key description string * - the desc is used to match a key against search criteria diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3cb9a32a6330..f34f4cfaa513 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1615,7 +1615,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); -int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); diff --git a/include/linux/libata.h b/include/linux/libata.h index c1c57f814b98..e5695998acb0 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -88,6 +88,7 @@ enum ata_quirks { __ATA_QUIRK_MAX_SEC_1024, /* Limit max sects to 1024 */ __ATA_QUIRK_MAX_TRIM_128M, /* Limit max trim size to 128M */ __ATA_QUIRK_NO_NCQ_ON_ATI, /* Disable NCQ on ATI chipset */ + __ATA_QUIRK_NO_LPM_ON_ATI, /* Disable LPM on ATI chipset */ __ATA_QUIRK_NO_ID_DEV_LOG, /* Identify device log missing */ __ATA_QUIRK_NO_LOG_DIR, /* Do not read log directory */ __ATA_QUIRK_NO_FUA, /* Do not use FUA */ @@ -432,6 +433,7 @@ enum { ATA_QUIRK_MAX_SEC_1024 = (1U << __ATA_QUIRK_MAX_SEC_1024), ATA_QUIRK_MAX_TRIM_128M = (1U << __ATA_QUIRK_MAX_TRIM_128M), ATA_QUIRK_NO_NCQ_ON_ATI = (1U << __ATA_QUIRK_NO_NCQ_ON_ATI), + ATA_QUIRK_NO_LPM_ON_ATI = (1U << __ATA_QUIRK_NO_LPM_ON_ATI), ATA_QUIRK_NO_ID_DEV_LOG = (1U << __ATA_QUIRK_NO_ID_DEV_LOG), ATA_QUIRK_NO_LOG_DIR = (1U << __ATA_QUIRK_NO_LOG_DIR), ATA_QUIRK_NO_FUA = (1U << __ATA_QUIRK_NO_FUA), diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c39f119659ba..676721ee878d 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -37,12 +37,13 @@ struct lockref { /** * lockref_init - Initialize a lockref * @lockref: pointer to lockref structure - * @count: initial count + * + * Initializes @lockref->count to 1. */ -static inline void lockref_init(struct lockref *lockref, unsigned int count) +static inline void lockref_init(struct lockref *lockref) { spin_lock_init(&lockref->lock); - lockref->count = count; + lockref->count = 1; } void lockref_get(struct lockref *lockref); diff --git a/include/linux/log2.h b/include/linux/log2.h index 9f30d087a128..1366cb688a6d 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -41,7 +41,7 @@ int __ilog2_u64(u64 n) * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ -static inline __attribute__((const)) +static __always_inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b1068ddcbb7..2edb8d14d165 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1458,7 +1458,10 @@ static inline void folio_get(struct folio *folio) static inline void get_page(struct page *page) { - folio_get(page_folio(page)); + struct folio *folio = page_folio(page); + if (WARN_ON_ONCE(folio_test_slab(folio))) + return; + folio_get(folio); } static inline __must_check bool try_get_page(struct page *page) @@ -1552,6 +1555,9 @@ static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); + if (folio_test_slab(folio)) + return; + /* * For some devmap managed pages we need to catch refcount transition * from 2 to 1: @@ -2549,7 +2555,7 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -struct page *get_dump_page(unsigned long addr); +struct page *get_dump_page(unsigned long addr, int *locked); bool folio_mark_dirty(struct folio *folio); bool folio_mark_dirty_lock(struct folio *folio); @@ -3420,7 +3426,6 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); -extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6b27db7f9496..0234f14f2aa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -875,10 +875,11 @@ struct mm_struct { */ unsigned int nr_cpus_allowed; /** - * @max_nr_cid: Maximum number of concurrency IDs allocated. + * @max_nr_cid: Maximum number of allowed concurrency + * IDs allocated. * - * Track the highest number of concurrency IDs allocated for the - * mm. + * Track the highest number of allowed concurrency IDs + * allocated for the mm. */ atomic_t max_nr_cid; /** diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index b1b219bc3422..e71a6070a8f8 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -25,6 +25,11 @@ static_assert(sizeof(vfsgid_t) == sizeof(kgid_t)); static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val)); static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val)); +static inline bool is_valid_mnt_idmap(const struct mnt_idmap *idmap) +{ + return idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap; +} + #ifdef CONFIG_MULTIUSER static inline uid_t __vfsuid_val(vfsuid_t uid) { diff --git a/include/linux/module.h b/include/linux/module.h index 23792d5d7b74..30e5b19bafa9 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -306,7 +306,10 @@ extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); -#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) +#define symbol_get(x) ({ \ + static const char __notrim[] \ + __used __section(".no_trim_symbol") = __stringify(x); \ + (typeof(&x))(__symbol_get(__stringify(x))); }) /* modules using other modules: kdb wants to see this. */ struct module_use { diff --git a/include/linux/namei.h b/include/linux/namei.h index 8ec8fed3bce8..e3042176cdf4 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -18,35 +18,36 @@ enum { MAX_NESTED_LINKS = 8 }; enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ -#define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ -#define LOOKUP_DIRECTORY 0x0002 /* require a directory */ -#define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ -#define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ -#define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ -#define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ - -#define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ -#define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ +#define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ +#define LOOKUP_DIRECTORY BIT(1) /* require a directory */ +#define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ +#define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ +#define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ +#define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ +#define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ +#define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ +#define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ +#define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ +#define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ +/* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ -#define LOOKUP_OPEN 0x0100 /* ... in open */ -#define LOOKUP_CREATE 0x0200 /* ... in object creation */ -#define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ -#define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ +#define LOOKUP_OPEN BIT(16) /* ... in open */ +#define LOOKUP_CREATE BIT(17) /* ... in object creation */ +#define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ +#define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ -/* internal use only */ -#define LOOKUP_PARENT 0x0010 +/* 4 spare bits for intent */ /* Scoping flags for lookup. */ -#define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ -#define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ -#define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ -#define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ -#define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ -#define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ -#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ +#define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ +#define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ +#define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ +#define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ +#define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) +/* 3 spare bits for scoping */ extern int path_pts(struct path *path); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2a59034a5fa2..ab550a89b9bf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2664,6 +2664,12 @@ struct net *dev_net(const struct net_device *dev) } static inline +struct net *dev_net_rcu(const struct net_device *dev) +{ + return read_pnet_rcu(&dev->nd_net); +} + +static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); @@ -2904,9 +2910,9 @@ struct pcpu_sw_netstats { struct pcpu_dstats { u64_stats_t rx_packets; u64_stats_t rx_bytes; - u64_stats_t rx_drops; u64_stats_t tx_packets; u64_stats_t tx_bytes; + u64_stats_t rx_drops; u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); @@ -3269,6 +3275,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); @@ -4109,7 +4117,6 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 071d05d81d38..c86a11cfc4a3 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -278,7 +278,7 @@ struct netfs_io_request { #define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ -#define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ +#define NETFS_RREQ_RETRYING 14 /* Set if we're in the retry path */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 71fbebfa43c7..9ac83ca88326 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -47,6 +47,7 @@ struct nfs4_acl { struct nfs4_label { uint32_t lfs; uint32_t pi; + u32 lsmid; u32 len; char *label; }; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9155a6ffc370..d66c61cbbd1d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1802,7 +1802,7 @@ struct nfs_rpc_ops { int (*link) (struct inode *, struct inode *, const struct qstr *); int (*symlink) (struct inode *, struct dentry *, struct folio *, unsigned int, struct iattr *); - int (*mkdir) (struct inode *, struct dentry *, struct iattr *); + struct dentry *(*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *); int (*mknod) (struct inode *, struct dentry *, struct iattr *, diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index e07e8978d691..e435250fcb4d 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -13,6 +13,8 @@ #define NVME_TCP_ADMIN_CCSZ SZ_8K #define NVME_TCP_DIGEST_LENGTH 4 #define NVME_TCP_MIN_MAXH2CDATA 4096 +#define NVME_TCP_MIN_C2HTERM_PLEN 24 +#define NVME_TCP_MAX_C2HTERM_PLEN 152 enum nvme_tcp_pfv { NVME_TCP_PFV_1_0 = 0x0, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index fe3b60818fdc..2dc05b1c3283 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -199,28 +199,54 @@ enum { #define NVME_NVM_IOSQES 6 #define NVME_NVM_IOCQES 4 +/* + * Controller Configuration (CC) register (Offset 14h) + */ enum { + /* Enable (EN): bit 0 */ NVME_CC_ENABLE = 1 << 0, NVME_CC_EN_SHIFT = 0, + + /* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */ + + /* I/O Command Set Selected (CSS): bits 06:04 */ NVME_CC_CSS_SHIFT = 4, - NVME_CC_MPS_SHIFT = 7, - NVME_CC_AMS_SHIFT = 11, - NVME_CC_SHN_SHIFT = 14, - NVME_CC_IOSQES_SHIFT = 16, - NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT, NVME_CC_CSS_NVM = 0 << NVME_CC_CSS_SHIFT, NVME_CC_CSS_CSI = 6 << NVME_CC_CSS_SHIFT, - NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT, + + /* Memory Page Size (MPS): bits 10:07 */ + NVME_CC_MPS_SHIFT = 7, + NVME_CC_MPS_MASK = 0xf << NVME_CC_MPS_SHIFT, + + /* Arbitration Mechanism Selected (AMS): bits 13:11 */ + NVME_CC_AMS_SHIFT = 11, + NVME_CC_AMS_MASK = 7 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, + + /* Shutdown Notification (SHN): bits 15:14 */ + NVME_CC_SHN_SHIFT = 14, + NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, - NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, + + /* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */ + NVME_CC_IOSQES_SHIFT = 16, + NVME_CC_IOSQES_MASK = 0xf << NVME_CC_IOSQES_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, + + /* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */ + NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_IOCQES_MASK = 0xf << NVME_CC_IOCQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, + + /* Controller Ready Independent of Media Enable (CRIME): bit 24 */ NVME_CC_CRIME = 1 << 24, + + /* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */ }; enum { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 47bfc6b1b632..f348e7005306 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1044,21 +1044,23 @@ static inline pgoff_t page_pgoff(const struct folio *folio, return folio->index + folio_page_idx(folio, page); } -/* - * Return byte-offset into filesystem object for page. +/** + * folio_pos - Returns the byte position of this folio in its file. + * @folio: The folio. */ -static inline loff_t page_offset(struct page *page) +static inline loff_t folio_pos(const struct folio *folio) { - return ((loff_t)page->index) << PAGE_SHIFT; + return ((loff_t)folio->index) * PAGE_SIZE; } -/** - * folio_pos - Returns the byte position of this folio in its file. - * @folio: The folio. +/* + * Return byte-offset into filesystem object for page. */ -static inline loff_t folio_pos(struct folio *folio) +static inline loff_t page_offset(struct page *page) { - return page_offset(&folio->page); + struct folio *folio = page_folio(page); + + return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index de5deb1a0118..1a2594a38199 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3134,6 +3134,7 @@ #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 #define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 +#define PCI_DEVICE_ID_INTEL_HDA_PTL_H 0xe328 #define PCI_DEVICE_ID_INTEL_HDA_PTL 0xe428 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 7c830d0dec9a..05e6f8f4a026 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -6,6 +6,7 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); void pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); +void pidfs_exit(struct task_struct *tsk); extern const struct dentry_operations pidfs_dentry_operations; #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 8ff23bf5a819..9d42d473d201 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -31,6 +31,33 @@ struct pipe_buffer { unsigned long private; }; +/* + * Really only alpha needs 32-bit fields, but + * might as well do it for 64-bit architectures + * since that's what we've historically done, + * and it makes 'head_tail' always be a simple + * 'unsigned long'. + */ +#ifdef CONFIG_64BIT +typedef unsigned int pipe_index_t; +#else +typedef unsigned short pipe_index_t; +#endif + +/* + * We have to declare this outside 'struct pipe_inode_info', + * but then we can't use 'union pipe_index' for an anonymous + * union, so we end up having to duplicate this declaration + * below. Annoying. + */ +union pipe_index { + unsigned long head_tail; + struct { + pipe_index_t head; + pipe_index_t tail; + }; +}; + /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing @@ -38,6 +65,7 @@ struct pipe_buffer { * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption + * @head_tail: unsigned long union of @head and @tail * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) @@ -58,8 +86,16 @@ struct pipe_buffer { struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; - unsigned int head; - unsigned int tail; + + /* This has to match the 'union pipe_index' above */ + union { + unsigned long head_tail; + struct { + pipe_index_t head; + pipe_index_t tail; + }; + }; + unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; @@ -72,7 +108,7 @@ struct pipe_inode_info { #ifdef CONFIG_WATCH_QUEUE bool note_loss; #endif - struct page *tmp_page; + struct page *tmp_page[2]; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; struct pipe_buffer *bufs; @@ -141,23 +177,23 @@ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) } /** - * pipe_empty - Return true if the pipe is empty + * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ -static inline bool pipe_empty(unsigned int head, unsigned int tail) +static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { - return head == tail; + return (pipe_index_t)(head - tail); } /** - * pipe_occupancy - Return number of slots used in the pipe + * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ -static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) +static inline bool pipe_empty(unsigned int head, unsigned int tail) { - return head - tail; + return !pipe_occupancy(head, tail); } /** @@ -173,6 +209,33 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, } /** + * pipe_is_full - Return true if the pipe is full + * @pipe: the pipe + */ +static inline bool pipe_is_full(const struct pipe_inode_info *pipe) +{ + return pipe_full(pipe->head, pipe->tail, pipe->max_usage); +} + +/** + * pipe_is_empty - Return true if the pipe is empty + * @pipe: the pipe + */ +static inline bool pipe_is_empty(const struct pipe_inode_info *pipe) +{ + return pipe_empty(pipe->head, pipe->tail); +} + +/** + * pipe_buf_usage - Return how many pipe buffers are in use + * @pipe: the pipe + */ +static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe) +{ + return pipe_occupancy(pipe->head, pipe->tail); +} + +/** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest @@ -245,15 +308,6 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, return buf->ops->try_steal(pipe, buf); } -static inline void pipe_discard_from(struct pipe_inode_info *pipe, - unsigned int old_head) -{ - unsigned int mask = pipe->ring_size - 1; - - while (pipe->head > old_head) - pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); -} - /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index 8ab5b0e8eb2c..8c9df7dadd5d 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -33,6 +33,8 @@ enum platform_profile_option { * @probe: Callback to setup choices available to the new class device. These * choices will only be enforced when setting a new profile, not when * getting the current one. + * @hidden_choices: Callback to setup choices that are not visible to the user + * but can be set by the driver. * @profile_get: Callback that will be called when showing the current platform * profile in sysfs. * @profile_set: Callback that will be called when storing a new platform @@ -40,6 +42,7 @@ enum platform_profile_option { */ struct platform_profile_ops { int (*probe)(void *drvdata, unsigned long *choices); + int (*hidden_choices)(void *drvdata, unsigned long *choices); int (*profile_get)(struct device *dev, enum platform_profile_option *profile); int (*profile_set)(struct device *dev, enum platform_profile_option profile); }; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0b2a89854440..ea62201c74c4 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -20,10 +20,13 @@ enum { * If in doubt, ignore this flag. */ #ifdef MODULE - PROC_ENTRY_PERMANENT = 0U, + PROC_ENTRY_PERMANENT = 0U, #else - PROC_ENTRY_PERMANENT = 1U << 0, + PROC_ENTRY_PERMANENT = 1U << 0, #endif + + PROC_ENTRY_proc_read_iter = 1U << 1, + PROC_ENTRY_proc_compat_ioctl = 1U << 2, }; struct proc_ops { diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 903ddfea8585..f3cad182d4ef 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -815,6 +815,15 @@ struct sev_data_snp_commit { #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** + * sev_module_init - perform PSP SEV module initialization + * + * Returns: + * 0 if the PSP module is successfully initialized + * negative value if the PSP module initialization fails + */ +int sev_module_init(void); + +/** * sev_platform_init - perform SEV INIT command * * @args: struct sev_platform_init_args to pass in arguments diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h index 2c8bfd0f1b6b..6322d8c1c6b4 100644 --- a/include/linux/rcuref.h +++ b/include/linux/rcuref.h @@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref) return rcuref_get_slowpath(ref); } -extern __must_check bool rcuref_put_slowpath(rcuref_t *ref); +extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { + int cnt; + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ - if (likely(!atomic_add_negative_release(-1, &ref->refcnt))) + cnt = atomic_sub_return_release(1, &ref->refcnt); + if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ - return rcuref_put_slowpath(ref); + return rcuref_put_slowpath(ref, cnt); } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 9632e3318e0d..9c15365a30c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1701,7 +1701,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 0f2aeb37bbb0..ca1db4b92c32 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -43,6 +43,7 @@ struct kernel_clone_args { void *fn_arg; struct cgroup *cgrp; struct css_set *cset; + unsigned int kill_seq; }; /* diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 2cbe0c22a32f..0b9095a281b8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -91,6 +91,8 @@ struct sk_psock { struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; + u32 copied_seq; + u32 ingress_bytes; #endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..c3322eb3d686 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,8 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len, + void *data); struct timespec64; struct __kernel_timespec; diff --git a/include/linux/string.h b/include/linux/string.h index 86d5d352068b..f8e21e80942f 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -414,7 +414,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * must be discoverable by the compiler. */ #define strtomem_pad(dest, src, pad) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ @@ -437,7 +438,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * must be discoverable by the compiler. */ #define strtomem(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ @@ -456,7 +458,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ @@ -481,7 +484,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr_pad(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index fec1e8a1570c..eac57914dcf3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -158,7 +158,6 @@ enum { RPC_TASK_NEED_XMIT, RPC_TASK_NEED_RECV, RPC_TASK_MSG_PIN_WAIT, - RPC_TASK_SIGNALLED, }; #define rpc_test_and_set_running(t) \ @@ -171,7 +170,7 @@ enum { #define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate) -#define RPC_SIGNALLED(t) test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate) +#define RPC_SIGNALLED(t) (READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS) /* * Task priorities. diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h index b5ec038069da..91cdf12190a0 100644 --- a/include/linux/swap_cgroup.h +++ b/include/linux/swap_cgroup.h @@ -6,7 +6,7 @@ #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) -extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent); +extern void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent); extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents); extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent); extern int swap_cgroup_swapon(int type, unsigned long max_pages); @@ -15,7 +15,7 @@ extern void swap_cgroup_swapoff(int type); #else static inline -void swap_cgroup_record(struct folio *folio, swp_entry_t ent) +void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent) { } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c6333204d451..e5603cc91963 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -951,6 +951,10 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, asmlinkage long sys_rseq(struct rseq __user *rseq, uint32_t rseq_len, int flags, uint32_t sig); asmlinkage long sys_open_tree(int dfd, const char __user *path, unsigned flags); +asmlinkage long sys_open_tree_attr(int dfd, const char __user *path, + unsigned flags, + struct mount_attr __user *uattr, + size_t usize); asmlinkage long sys_move_mount(int from_dfd, const char __user *from_path, int to_dfd, const char __user *to_path, unsigned int ms_flags); @@ -1266,14 +1270,14 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, AT_SYMLINK_NOFOLLOW); } -extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); +int do_sys_ftruncate(unsigned int fd, loff_t length, int small); static inline long ksys_ftruncate(unsigned int fd, loff_t length) { return do_sys_ftruncate(fd, length, 1); } -extern long do_sys_truncate(const char __user *pathname, loff_t length); +int do_sys_truncate(const char __user *pathname, loff_t length); static inline long ksys_truncate(const char __user *pathname, loff_t length) { diff --git a/include/linux/sysv_fs.h b/include/linux/sysv_fs.h deleted file mode 100644 index 5cf77dbb8d86..000000000000 --- a/include/linux/sysv_fs.h +++ /dev/null @@ -1,214 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_SYSV_FS_H -#define _LINUX_SYSV_FS_H - -#define __packed2__ __attribute__((packed, aligned(2))) - - -#ifndef __KERNEL__ -typedef u16 __fs16; -typedef u32 __fs16; -#endif - -/* inode numbers are 16 bit */ -typedef __fs16 sysv_ino_t; - -/* Block numbers are 24 bit, sometimes stored in 32 bit. - On Coherent FS, they are always stored in PDP-11 manner: the least - significant 16 bits come last. */ -typedef __fs32 sysv_zone_t; - -/* 0 is non-existent */ -#define SYSV_BADBL_INO 1 /* inode of bad blocks file */ -#define SYSV_ROOT_INO 2 /* inode of root directory */ - - -/* Xenix super-block data on disk */ -#define XENIX_NICINOD 100 /* number of inode cache entries */ -#define XENIX_NICFREE 100 /* number of free block list chunk entries */ -struct xenix_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= XENIX_NICFREE */ - sysv_zone_t s_free[XENIX_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= XENIX_NICINOD */ - sysv_ino_t s_inode[XENIX_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_dinfo[4]; /* device information ?? */ - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - char s_clean; /* set to 0x46 when filesystem is properly unmounted */ - char s_fill[371]; - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks - 3 for 2048 byte blocks */ - -}; - -/* - * SystemV FS comes in two variants: - * sysv2: System V Release 2 (e.g. Microport), structure elements aligned(2). - * sysv4: System V Release 4 (e.g. Consensys), structure elements aligned(4). - */ -#define SYSV_NICINOD 100 /* number of inode cache entries */ -#define SYSV_NICFREE 50 /* number of free block list chunk entries */ - -/* SystemV4 super-block data on disk */ -struct sysv4_super_block { - __fs16 s_isize; /* index of first data zone */ - u16 s_pad0; - __fs32 s_fsize; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= SYSV_NICFREE */ - u16 s_pad1; - sysv_zone_t s_free[SYSV_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= SYSV_NICINOD */ - u16 s_pad2; - sysv_ino_t s_inode[SYSV_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time; /* time of last super block update */ - __fs16 s_dinfo[4]; /* device information ?? */ - __fs32 s_tfree; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - u16 s_pad3; - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - s32 s_fill[12]; - __fs32 s_state; /* file system state: 0x7c269d38-s_time means clean */ - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks */ -}; - -/* SystemV2 super-block data on disk */ -struct sysv2_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= SYSV_NICFREE */ - sysv_zone_t s_free[SYSV_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= SYSV_NICINOD */ - sysv_ino_t s_inode[SYSV_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs16 s_dinfo[4]; /* device information ?? */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - s32 s_fill[14]; - __fs32 s_state; /* file system state: 0xcb096f43 means clean */ - s32 s_magic; /* version of file system */ - __fs32 s_type; /* type of file system: 1 for 512 byte blocks - 2 for 1024 byte blocks */ -}; - -/* V7 super-block data on disk */ -#define V7_NICINOD 100 /* number of inode cache entries */ -#define V7_NICFREE 50 /* number of free block list chunk entries */ -struct v7_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= V7_NICFREE */ - sysv_zone_t s_free[V7_NICFREE]; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= V7_NICINOD */ - sysv_ino_t s_inode[V7_NICINOD]; /* some free inodes */ - /* locks, not used by Linux or V7: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - /* the following fields are not maintained by V7: */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_m; /* interleave factor */ - __fs16 s_n; /* interleave factor */ - char s_fname[6]; /* file system name */ - char s_fpack[6]; /* file system pack name */ -}; -/* Constants to aid sanity checking */ -/* This is not a hard limit, nor enforced by v7 kernel. It's actually just - * the limit used by Seventh Edition's ls, though is high enough to assume - * that no reasonable file system would have that much entries in root - * directory. Thus, if we see anything higher, we just probably got the - * endiannes wrong. */ -#define V7_NFILES 1024 -/* The disk addresses are three-byte (despite direct block addresses being - * aligned word-wise in inode). If the most significant byte is non-zero, - * something is most likely wrong (not a filesystem, bad bytesex). */ -#define V7_MAXSIZE 0x00ffffff - -/* Coherent super-block data on disk */ -#define COH_NICINOD 100 /* number of inode cache entries */ -#define COH_NICFREE 64 /* number of free block list chunk entries */ -struct coh_super_block { - __fs16 s_isize; /* index of first data zone */ - __fs32 s_fsize __packed2__; /* total number of zones of this fs */ - /* the start of the free block list: */ - __fs16 s_nfree; /* number of free blocks in s_free, <= COH_NICFREE */ - sysv_zone_t s_free[COH_NICFREE] __packed2__; /* first free block list chunk */ - /* the cache of free inodes: */ - __fs16 s_ninode; /* number of free inodes in s_inode, <= COH_NICINOD */ - sysv_ino_t s_inode[COH_NICINOD]; /* some free inodes */ - /* locks, not used by Linux: */ - char s_flock; /* lock during free block list manipulation */ - char s_ilock; /* lock during inode cache manipulation */ - char s_fmod; /* super-block modified flag */ - char s_ronly; /* flag whether fs is mounted read-only */ - __fs32 s_time __packed2__; /* time of last super block update */ - __fs32 s_tfree __packed2__; /* total number of free zones */ - __fs16 s_tinode; /* total number of free inodes */ - __fs16 s_interleave_m; /* interleave factor */ - __fs16 s_interleave_n; - char s_fname[6]; /* file system volume name */ - char s_fpack[6]; /* file system pack name */ - __fs32 s_unique; /* zero, not used */ -}; - -/* SystemV/Coherent inode data on disk */ -struct sysv_inode { - __fs16 i_mode; - __fs16 i_nlink; - __fs16 i_uid; - __fs16 i_gid; - __fs32 i_size; - u8 i_data[3*(10+1+1+1)]; - u8 i_gen; - __fs32 i_atime; /* time of last access */ - __fs32 i_mtime; /* time of last modification */ - __fs32 i_ctime; /* time of creation */ -}; - -/* SystemV/Coherent directory entry on disk */ -#define SYSV_NAMELEN 14 /* max size of name in struct sysv_dir_entry */ -struct sysv_dir_entry { - sysv_ino_t inode; - char name[SYSV_NAMELEN]; /* up to 14 characters, the rest are zeroes */ -}; - -#define SYSV_DIRSIZE sizeof(struct sysv_dir_entry) /* size of every directory entry */ - -#endif /* _LINUX_SYSV_FS_H */ diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index f85ec5613721..2dc767e08f54 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -132,6 +132,7 @@ static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); +u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count); #else @@ -186,6 +187,11 @@ static inline u32 map_id_down(struct uid_gid_map *map, u32 id) return id; } +static inline u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) +{ + return id; +} + static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; diff --git a/include/linux/vfsdebug.h b/include/linux/vfsdebug.h new file mode 100644 index 000000000000..9cf22d3eb9dd --- /dev/null +++ b/include/linux/vfsdebug.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_VFS_DEBUG_H +#define LINUX_VFS_DEBUG_H 1 + +#include <linux/bug.h> + +struct inode; + +#ifdef CONFIG_DEBUG_VFS +void dump_inode(struct inode *inode, const char *reason); + +#define VFS_BUG_ON(cond) BUG_ON(cond) +#define VFS_WARN_ON(cond) (void)WARN_ON(cond) +#define VFS_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#define VFS_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format) +#define VFS_WARN(cond, format...) (void)WARN(cond, format) + +#define VFS_BUG_ON_INODE(cond, inode) ({ \ + if (unlikely(!!(cond))) { \ + dump_inode(inode, "VFS_BUG_ON_INODE(" #cond")");\ + BUG_ON(1); \ + } \ +}) + +#define VFS_WARN_ON_INODE(cond, inode) ({ \ + int __ret_warn = !!(cond); \ + \ + if (unlikely(__ret_warn)) { \ + dump_inode(inode, "VFS_WARN_ON_INODE(" #cond")");\ + WARN_ON(1); \ + } \ + unlikely(__ret_warn); \ +}) +#else +#define VFS_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) +#define VFS_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) + +#define VFS_BUG_ON_INODE(cond, inode) VFS_BUG_ON(cond) +#define VFS_WARN_ON_INODE(cond, inode) BUILD_BUG_ON_INVALID(cond) +#endif /* CONFIG_DEBUG_VFS */ + +#endif diff --git a/include/linux/wait.h b/include/linux/wait.h index 6d90ad974408..3503fe822e38 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -316,6 +316,9 @@ extern void init_wait_entry(struct wait_queue_entry *wq_entry, int flags); } \ \ cmd; \ + \ + if (condition) \ + break; \ } \ finish_wait(&wq_head, &__wq_entry); \ __out: __ret; \ |