diff options
Diffstat (limited to 'include/linux')
41 files changed, 563 insertions, 140 deletions
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 1f0a9ff23a2c..941deffc590d 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {} #endif /* Caller should verify both ref and tag to be valid */ -static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { alloc_tag_add_check(ref, tag); if (!ref || !tag) - return; + return false; ref->ct = &tag->ct; + return true; } -static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) { - __alloc_tag_ref_set(ref, tag); + if (unlikely(!__alloc_tag_ref_set(ref, tag))) + return false; + /* * We need in increment the call counter every time we have a new * allocation or when we split a large allocation into smaller ones. @@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t * counter because when we free each part the counter will be decremented. */ this_cpu_inc(tag->counters->calls); + return true; } static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) { - alloc_tag_ref_set(ref, tag); - this_cpu_add(tag->counters->bytes, bytes); + if (likely(alloc_tag_ref_set(ref, tag))) + this_cpu_add(tag->counters->bytes, bytes); } static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b721f360d759..4a952c4885ed 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,10 +11,6 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); -#ifdef CONFIG_ACPI_CPPC_LIB -void topology_init_cpu_capacity_cppc(void); -#endif - struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index f59099a213d0..67f6fdf2e7cd 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -315,8 +315,6 @@ u32 arm_smccc_get_version(void); void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit); -extern u64 smccc_has_sve_hint; - /** * arm_smccc_get_soc_id_version() * @@ -415,15 +413,6 @@ struct arm_smccc_quirk { }; /** - * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls - * - * Sets the SMCCC hint bit to indicate if there is live state in the SVE - * registers, this modifies x0 in place and should never be called from C - * code. - */ -asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); - -/** * __arm_smccc_smc() - make SMC calls * @a0-a7: arguments passed in registers 0 to 7 * @res: result values from registers 0 to 3 @@ -490,20 +479,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #endif -/* nVHE hypervisor doesn't have a current thread so needs separate checks */ -#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__) - -#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n", "bl __arm_smccc_sve_check \n", \ - ARM64_SVE) -#define smccc_sve_clobbers "x16", "x30", "cc", - -#else - -#define SMCCC_SVE_CHECK -#define smccc_sve_clobbers - -#endif - #define __constraint_read_2 "r" (arg0) #define __constraint_read_3 __constraint_read_2, "r" (arg1) #define __constraint_read_4 __constraint_read_3, "r" (arg2) @@ -574,12 +549,11 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, register unsigned long r3 asm("r3"); \ CONCATENATE(__declare_arg_, \ COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__); \ - asm volatile(SMCCC_SVE_CHECK \ - inst "\n" : \ + asm volatile(inst "\n" : \ "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ *___res = (typeof(*___res)){r0, r1, r2, r3}; \ } while (0) @@ -628,7 +602,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, asm ("" : \ : CONCATENATE(__constraint_read_, \ COUNT_ARGS(__VA_ARGS__)) \ - : smccc_sve_clobbers "memory"); \ + : "memory"); \ if (___res) \ ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ } while (0) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 50c3b959da28..c2cc3c146d74 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1674,6 +1674,22 @@ static inline bool bdev_can_atomic_write(struct block_device *bdev) return true; } +static inline unsigned int +bdev_atomic_write_unit_min_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev)); +} + +static inline unsigned int +bdev_atomic_write_unit_max_bytes(struct block_device *bdev) +{ + if (!bdev_can_atomic_write(bdev)) + return 0; + return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev)); +} + #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index aaf004d94322..e45162ef59bb 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +/* Check the allocation size for kmalloc equivalent allocator */ +int bpf_mem_alloc_check_size(bool percpu, size_t size); + /* kmalloc/kfree equivalent: */ void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size); void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index f805adaa316e..cd6f9aae311f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -80,7 +80,11 @@ #define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif +#ifdef __SANITIZE_HWADDRESS__ +#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress"))) +#else #define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#endif #if defined(__SANITIZE_THREAD__) #define __no_sanitize_thread __attribute__((__no_sanitize_thread__)) diff --git a/include/linux/device.h b/include/linux/device.h index b4bde8d22697..667cb6db9019 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); int device_for_each_child_reverse(struct device *dev, void *data, int (*fn)(struct device *dev, void *data)); +int device_for_each_child_reverse_from(struct device *parent, + struct device *from, const void *data, + int (*fn)(struct device *, const void *)); struct device *device_find_child(struct device *dev, void *data, int (*match)(struct device *dev, void *data)); struct device *device_find_child_by_name(struct device *parent, diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 3337745d81bd..0c0d00fcd131 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -42,7 +42,7 @@ static inline void eventpoll_release(struct file *file) * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ - if (likely(!file->f_ep)) + if (likely(!READ_ONCE(file->f_ep))) return; /* diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 893a1d21dc1c..1ab165c2939f 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -250,19 +250,6 @@ struct export_operations { unsigned long flags; }; -/** - * exportfs_lock_op_is_async() - export op supports async lock operation - * @export_ops: the nfs export operations to check - * - * Returns true if the nfs export_operations structure has - * EXPORT_OP_ASYNC_LOCK in their flags set - */ -static inline bool -exportfs_lock_op_is_async(const struct export_operations *export_ops) -{ - return export_ops->flags & EXPORT_OP_ASYNC_LOCK; -} - extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid, int *max_len, struct inode *parent, int flags); diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index b1c5722f2b3c..c45306a9f007 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -92,10 +92,6 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un return files_lookup_fd_raw(files, fd); } -struct file *lookup_fdget_rcu(unsigned int fd); -struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); -struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); - static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) { return test_bit(fd, files_fdtable(files)->close_on_exec); @@ -115,7 +111,6 @@ int iterate_fd(struct files_struct *, unsigned, const void *); extern int close_fd(unsigned int fd); -extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern struct file *file_close_fd(unsigned int fd); extern struct kmem_cache *files_cachep; diff --git a/include/linux/file.h b/include/linux/file.h index f98de143245a..ec4ad5e6a061 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -72,6 +72,7 @@ static inline void fdput(struct fd fd) extern struct file *fget(unsigned int fd); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); +extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd); extern void __f_unlock_pos(struct file *); struct fd fdget(unsigned int fd); diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h new file mode 100644 index 000000000000..9b3a8d9b17ab --- /dev/null +++ b/include/linux/file_ref.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_FILE_REF_H +#define _LINUX_FILE_REF_H + +#include <linux/atomic.h> +#include <linux/preempt.h> +#include <linux/types.h> + +/* + * file_ref is a reference count implementation specifically for use by + * files. It takes inspiration from rcuref but differs in key aspects + * such as support for SLAB_TYPESAFE_BY_RCU type caches. + * + * FILE_REF_ONEREF FILE_REF_MAXREF + * 0x0000000000000000UL 0x7FFFFFFFFFFFFFFFUL + * <-------------------valid -------------------> + * + * FILE_REF_SATURATED + * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL + * <-----------------------saturation zone----------------------> + * + * FILE_REF_RELEASED FILE_REF_DEAD + * 0xC000000000000000UL 0xE000000000000000UL + * <-------------------dead zone-------------------> + * + * FILE_REF_NOREF + * 0xFFFFFFFFFFFFFFFFUL + */ + +#ifdef CONFIG_64BIT +#define FILE_REF_ONEREF 0x0000000000000000UL +#define FILE_REF_MAXREF 0x7FFFFFFFFFFFFFFFUL +#define FILE_REF_SATURATED 0xA000000000000000UL +#define FILE_REF_RELEASED 0xC000000000000000UL +#define FILE_REF_DEAD 0xE000000000000000UL +#define FILE_REF_NOREF 0xFFFFFFFFFFFFFFFFUL +#else +#define FILE_REF_ONEREF 0x00000000U +#define FILE_REF_MAXREF 0x7FFFFFFFU +#define FILE_REF_SATURATED 0xA0000000U +#define FILE_REF_RELEASED 0xC0000000U +#define FILE_REF_DEAD 0xE0000000U +#define FILE_REF_NOREF 0xFFFFFFFFU +#endif + +typedef struct { +#ifdef CONFIG_64BIT + atomic64_t refcnt; +#else + atomic_t refcnt; +#endif +} file_ref_t; + +/** + * file_ref_init - Initialize a file reference count + * @ref: Pointer to the reference count + * @cnt: The initial reference count typically '1' + */ +static inline void file_ref_init(file_ref_t *ref, unsigned long cnt) +{ + atomic_long_set(&ref->refcnt, cnt - 1); +} + +bool __file_ref_put(file_ref_t *ref, unsigned long cnt); + +/** + * file_ref_get - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF. + * + * Provides full memory ordering. + * + * Return: False if the attempt to acquire a reference failed. This happens + * when the last reference has been put already. True if a reference + * was successfully acquired + */ +static __always_inline __must_check bool file_ref_get(file_ref_t *ref) +{ + /* + * Unconditionally increase the reference count with full + * ordering. The saturation and dead zones provide enough + * tolerance for this. + * + * If this indicates negative the file in question the fail can + * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU. + * Hence, unconditionally altering the file reference count to + * e.g., reset the file reference count back to the middle of + * the deadzone risk end up marking someone else's file as dead + * behind their back. + * + * It would be possible to do a careful: + * + * cnt = atomic_long_inc_return(); + * if (likely(cnt >= 0)) + * return true; + * + * and then something like: + * + * if (cnt >= FILE_REF_RELEASE) + * atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD), + * + * to set the value back to the middle of the deadzone. But it's + * practically impossible to go from FILE_REF_DEAD to + * FILE_REF_ONEREF. It would need 2305843009213693952/2^61 + * file_ref_get()s to resurrect such a dead file. + */ + return !atomic_long_add_negative(1, &ref->refcnt); +} + +/** + * file_ref_inc - Acquire one reference on a file + * @ref: Pointer to the reference count + * + * Acquire an additional reference on a file. Warns if the caller didn't + * already hold a reference. + */ +static __always_inline void file_ref_inc(file_ref_t *ref) +{ + long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt); + WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference"); +} + +/** + * file_ref_put -- Release a file reference + * @ref: Pointer to the reference count + * + * Provides release memory ordering, such that prior loads and stores + * are done before, and provides an acquire ordering on success such + * that free() must come after. + * + * Return: True if this was the last reference with no future references + * possible. This signals the caller that it can safely release + * the object which is protected by the reference counter. + * False if there are still active references or the put() raced + * with a concurrent get()/put() pair. Caller is not allowed to + * release the protected object. + */ +static __always_inline __must_check bool file_ref_put(file_ref_t *ref) +{ + long cnt; + + /* + * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put() + * calls don't risk UAFs when a file is recyclyed, it is still + * vulnerable to UAFs caused by freeing the whole slab page once + * it becomes unused. Prevent file_ref_put() from being + * preempted protects against this. + */ + guard(preempt)(); + /* + * Unconditionally decrease the reference count. The saturation + * and dead zones provide enough tolerance for this. If this + * fails then we need to handle the last reference drop and + * cases inside the saturation and dead zones. + */ + cnt = atomic_long_dec_return(&ref->refcnt); + if (cnt >= 0) + return false; + return __file_ref_put(ref, cnt); +} + +/** + * file_ref_read - Read the number of file references + * @ref: Pointer to the reference count + * + * Return: The number of held references (0 ... N) + */ +static inline unsigned long file_ref_read(file_ref_t *ref) +{ + unsigned long c = atomic_long_read(&ref->refcnt); + + /* Return 0 if within the DEAD zone. */ + return c >= FILE_REF_RELEASED ? 0 : c + 1; +} + +#endif diff --git a/include/linux/filelock.h b/include/linux/filelock.h index bb44224c6676..c412ded9171e 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -180,6 +180,11 @@ static inline void locks_wake_up(struct file_lock *fl) wake_up(&fl->c.flc_wait); } +static inline bool locks_can_async_lock(const struct file_operations *fops) +{ + return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK; +} + /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3559446279c1..db4c0d45107a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -45,6 +45,8 @@ #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> +#include <linux/file_ref.h> +#include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -623,6 +625,7 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 +#define IOP_MGTIME 0x0020 /* * Keep mostly read-only and often accessed (especially for @@ -1005,7 +1008,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) /** * struct file - Represents a file - * @f_count: reference count + * @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 @@ -1030,7 +1033,7 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { - atomic_long_t f_count; + file_ref_t f_ref; spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; @@ -1078,15 +1081,14 @@ struct file_handle { static inline struct file *get_file(struct file *f) { - long prior = atomic_long_fetch_inc_relaxed(&f->f_count); - WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); + file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); -#define file_count(x) atomic_long_read(&(x)->f_count) +#define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) @@ -1584,6 +1586,8 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); +struct timespec64 inode_set_ctime_deleg(struct inode *inode, + struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { @@ -1653,6 +1657,17 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, return inode_set_mtime_to_ts(inode, ts); } +/* + * Multigrain timestamps + * + * Conditionally use fine-grained ctime and mtime timestamps when there + * are users actively observing them via getattr. The primary use-case + * for this is NFS clients that use the ctime to distinguish between + * different states of the file, and that are often fooled by multiple + * operations that occur in the same coarse-grained timer tick. + */ +#define I_CTIME_QUERIED ((u32)BIT(31)) + static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; @@ -1660,7 +1675,7 @@ static inline time64_t inode_get_ctime_sec(const struct inode *inode) static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->i_ctime_nsec; + return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) @@ -1671,13 +1686,7 @@ static inline struct timespec64 inode_get_ctime(const struct inode *inode) return ts; } -static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, - struct timespec64 ts) -{ - inode->i_ctime_sec = ts.tv_sec; - inode->i_ctime_nsec = ts.tv_nsec; - return ts; -} +struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode @@ -2116,6 +2125,8 @@ struct file_operations { #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) +/* Supports asynchronous lock callbacks */ +#define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2542,6 +2553,7 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ +#define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2565,6 +2577,17 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) +/** + * is_mgtime: is this inode using multigrain timestamps + * @inode: inode to test for multigrain timestamps + * + * Return true if the inode uses multigrain timestamps, false otherwise. + */ +static inline bool is_mgtime(const struct inode *inode) +{ + return inode->i_opflags & IOP_MGTIME; +} + 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)); @@ -3326,6 +3349,7 @@ extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, @@ -3456,6 +3480,54 @@ extern int generic_ci_match(const struct inode *parent, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); +#if IS_ENABLED(CONFIG_UNICODE) +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *name); + +/** + * generic_ci_validate_strict_name - Check if a given name is suitable + * for a directory + * + * This functions checks if the proposed filename is valid for the + * parent directory. That means that only valid UTF-8 filenames will be + * accepted for casefold directories from filesystems created with the + * strict encoding flag. That also means that any name will be + * accepted for directories that doesn't have casefold enabled, or + * aren't being strict with the encoding. + * + * @dir: inode of the directory where the new file will be created + * @name: name of the new file + * + * Return: + * * True: if the filename is suitable for this directory. It can be + * true if a given name is not suitable for a strict encoding + * directory, but the directory being used isn't strict + * * False if the filename isn't suitable for this directory. This only + * happens when a directory is casefolded and the filesystem is strict + * about its encoding. + */ +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) + return true; + + /* + * A casefold dir must have a encoding set, unless the filesystem + * is corrupted + */ + if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) + return true; + + return !utf8_validate(dir->i_sb->s_encoding, name); +} +#else +static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name) +{ + return true; +} +#endif + static inline bool sb_has_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) @@ -3726,6 +3798,6 @@ static inline bool vfs_empty_path(int dfd, const char __user *path) return !c; } -bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); +int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index c13e99cbbf81..4b4bfef6f053 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc, int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc); + +#define GET_TREE_BDEV_QUIET_LOOKUP 0x0001 +int get_tree_bdev_flags(struct fs_context *fc, + int (*fill_super)(struct super_block *sb, + struct fs_context *fc), unsigned int flags); + extern int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)); diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 6cf713a7e6c6..3cef566088fc 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -28,7 +28,8 @@ typedef int fs_param_type(struct p_log *, */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, - fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid; + fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid, + fs_param_is_file_or_string; /* * Specification of the type of value a parameter wants. @@ -133,6 +134,8 @@ static inline bool fs_validate_description(const char *name, #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +#define fsparam_file_or_string(NAME, OPT) \ + __fsparam(fs_param_is_file_or_string, NAME, OPT, 0, NULL) #define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL) #define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL) diff --git a/include/linux/input.h b/include/linux/input.h index 89a0be6ee0e2..cd866b020a01 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -339,12 +339,16 @@ struct input_handler { * @name: name given to the handle by handler that created it * @dev: input device the handle is attached to * @handler: handler that works with the device through this handle + * @handle_events: event sequence handler. It is set up by the input core + * according to event handling method specified in the @handler. See + * input_handle_setup_event_handler(). + * This method is being called by the input core with interrupts disabled + * and dev->event_lock spinlock held and so it may not sleep. * @d_node: used to put the handle on device's list of attached handles * @h_node: used to put the handle on handler's list of handles from which * it gets events */ struct input_handle { - void *private; int open; @@ -353,6 +357,10 @@ struct input_handle { struct input_dev *dev; struct input_handler *handler; + unsigned int (*handle_events)(struct input_handle *handle, + struct input_value *vals, + unsigned int count); + struct list_head d_node; struct list_head h_node; }; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index d0420e962ffd..27048ec10e1c 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -178,6 +178,7 @@ struct iomap_folio_ops { #else #define IOMAP_DAX 0 #endif /* CONFIG_FS_DAX */ +#define IOMAP_ATOMIC (1 << 9) struct iomap_ops { /* @@ -270,6 +271,25 @@ static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos, return round_up(pos + written, i_blocksize(inode)); } +/* + * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE + * operation. + * + * Don't bother with blocks that are not shared to start with; or mappings that + * cannot be shared, such as inline data, delalloc reservations, holes or + * unwritten extents. + * + * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing + * requires providing a separate source map, and the presence of one is a good + * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set + * for any data that goes into the COW fork for XFS. + */ +static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) +{ + return (iter->iomap.flags & IOMAP_F_SHARED) && + iter->srcmap.type == IOMAP_MAPPED; +} + ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 11690dacd986..ec9c05044d4f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm) return atomic_long_read(&mm->ksm_zero_pages); } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { + /* Adding mm to ksm is best effort on fork. */ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); - - return 0; + __ksm_enter(mm); } static inline int ksm_execve(struct mm_struct *mm) @@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm) return 0; } -static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) +static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - return 0; } static inline int ksm_execve(struct mm_struct *mm) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 34d2da05f2f1..e1b41554a5fb 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1760,8 +1760,9 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { struct mem_cgroup *memcg; @@ -1770,7 +1771,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); - count_memcg_events(memcg, idx, 1); + count_memcg_events(memcg, idx, count); rcu_read_unlock(); } @@ -1825,8 +1826,9 @@ static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) return NULL; } -static inline void count_objcg_event(struct obj_cgroup *objcg, - enum vm_event_item idx) +static inline void count_objcg_events(struct obj_cgroup *objcg, + enum vm_event_item idx, + unsigned long count) { } diff --git a/include/linux/mman.h b/include/linux/mman.h index bcb201ab7a41..a842783ffa62 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H +#include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> @@ -94,7 +95,7 @@ static inline void vm_unacct_memory(long pages) #endif #ifndef arch_calc_vm_flag_bits -#define arch_calc_vm_flag_bits(flags) 0 +#define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot @@ -151,13 +152,13 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey) * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long -calc_vm_flag_bits(unsigned long flags) +calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | - arch_calc_vm_flag_bits(flags); + arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); @@ -188,16 +189,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; - if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true; - if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true; return false; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 17506e4a2835..80bc5640bb60 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -458,9 +458,7 @@ struct lru_gen_folio { enum { MM_LEAF_TOTAL, /* total leaf entries */ - MM_LEAF_OLD, /* old leaf entries */ MM_LEAF_YOUNG, /* young leaf entries */ - MM_NONLEAF_TOTAL, /* total non-leaf entries */ MM_NONLEAF_FOUND, /* non-leaf entries found in Bloom filters */ MM_NONLEAF_ADDED, /* non-leaf entries added to Bloom filters */ NR_MM_STATS @@ -557,7 +555,7 @@ struct lru_gen_memcg { void lru_gen_init_pgdat(struct pglist_data *pgdat); void lru_gen_init_lruvec(struct lruvec *lruvec); -void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); +bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw); void lru_gen_init_memcg(struct mem_cgroup *memcg); void lru_gen_exit_memcg(struct mem_cgroup *memcg); @@ -576,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec) { } -static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw) +static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw) { + return false; } static inline void lru_gen_init_memcg(struct mem_cgroup *memcg) @@ -824,6 +823,7 @@ struct zone { unsigned long watermark_boost; unsigned long nr_reserved_highatomic; + unsigned long nr_free_highatomic; /* * We don't know if the memory that we're going to allocate will be diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h index b0dd9b1eef4f..3982fea79919 100644 --- a/include/linux/nfslocalio.h +++ b/include/linux/nfslocalio.h @@ -32,7 +32,8 @@ typedef struct { struct auth_domain *dom; /* auth_domain for localio */ } nfs_uuid_t; -void nfs_uuid_begin(nfs_uuid_t *); +void nfs_uuid_init(nfs_uuid_t *); +bool nfs_uuid_begin(nfs_uuid_t *); void nfs_uuid_end(nfs_uuid_t *); void nfs_uuid_is_local(const uuid_t *, struct list_head *, struct net *, struct auth_domain *, struct module *); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1b3a76710487..908ee0aad554 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -543,7 +543,7 @@ FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE) * - PG_private and PG_private_2 cause release_folio() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) -PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) +FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE) /* owner_2 can be set on tail pages for anon memory */ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) @@ -554,7 +554,7 @@ FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE) */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) -PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) +FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) @@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \ } \ static __always_inline void __folio_set_##fname(struct folio *folio) \ { \ + if (folio_test_##fname(folio)) \ + return; \ VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX, \ folio); \ folio->page.page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __folio_clear_##fname(struct folio *folio) \ { \ + if (folio->page.page_type == UINT_MAX) \ + return; \ VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ folio->page.page_type = UINT_MAX; \ } @@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page) \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ + if (Page##uname(page)) \ + return; \ VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page); \ page->page_type = (unsigned int)PGTY_##lname << 24; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ + if (page->page_type == UINT_MAX) \ + return; \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type = UINT_MAX; \ } diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index b637ec14025f..cf4b11be3709 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -92,6 +92,10 @@ struct dev_pm_domain_list { * GENPD_FLAG_OPP_TABLE_FW: The genpd provider supports performance states, * but its corresponding OPP tables are not * described in DT, but are given directly by FW. + * + * GENPD_FLAG_DEV_NAME_FW: Instructs genpd to generate an unique device name + * using ida. It is used by genpd providers which + * get their genpd-names directly from FW. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -101,6 +105,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_RPM_ALWAYS_ON (1U << 5) #define GENPD_FLAG_MIN_RESIDENCY (1U << 6) #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) +#define GENPD_FLAG_DEV_NAME_FW (1U << 8) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ @@ -163,6 +168,7 @@ struct generic_pm_domain { atomic_t sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ unsigned int device_count; /* Number of devices */ + unsigned int device_id; /* unique device id */ unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ unsigned int performance_state; /* Aggregated max performance state */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 0e65b3d634d9..e2d47eb1a7f3 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -28,9 +28,9 @@ struct posix_acl_entry { struct posix_acl { refcount_t a_refcount; - struct rcu_head a_rcu; unsigned int a_count; - struct posix_acl_entry a_entries[]; + struct rcu_head a_rcu; + struct posix_acl_entry a_entries[] __counted_by(a_count); }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ @@ -62,7 +62,7 @@ posix_acl_release(struct posix_acl *acl) /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); -extern struct posix_acl *posix_acl_alloc(int, gfp_t); +extern struct posix_acl *posix_acl_alloc(unsigned int count, gfp_t flags); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index bf10bdb487dd..6c2fef89a4fd 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/magic.h> #include <linux/refcount.h> +#include <linux/kasan.h> #ifdef CONFIG_THREAD_INFO_IN_TASK @@ -89,6 +90,7 @@ static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); + obj = kasan_reset_tag(obj); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 515a9a6a3c6f..018da28c01e7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -42,10 +42,10 @@ struct shmem_inode_info { struct inode vfs_inode; }; -#define SHMEM_FL_USER_VISIBLE FS_FL_USER_VISIBLE +#define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL) #define SHMEM_FL_USER_MODIFIABLE \ - (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL) -#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL) + (FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) +#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL) struct shmem_quota_limits { qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */ diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 9e9f528b1370..2f20281d4ad4 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -125,6 +125,7 @@ struct llcc_edac_reg_offset { * @num_banks: Number of llcc banks * @bitmap: Bit map to track the active slice ids * @ecc_irq: interrupt for llcc cache error detection and reporting + * @ecc_irq_configured: 'True' if firmware has already configured the irq propagation * @version: Indicates the LLCC version */ struct llcc_drv_data { @@ -139,6 +140,7 @@ struct llcc_drv_data { u32 num_banks; unsigned long *bitmap; int ecc_irq; + bool ecc_irq_configured; u32 version; }; diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index fc5a206c4043..195debe2b1db 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -77,7 +77,9 @@ static inline int copy_safe_from_sockptr(void *dst, size_t ksize, { if (optlen < ksize) return -EINVAL; - return copy_from_sockptr(dst, optval, ksize); + if (copy_from_sockptr(dst, optval, ksize)) + return -EFAULT; + return 0; } static inline int copy_struct_from_sockptr(void *dst, size_t ksize, diff --git a/include/linux/swap.h b/include/linux/swap.h index ca533b478c21..f3e0ac20c2e8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,6 +335,7 @@ struct swap_info_struct { * list. */ struct work_struct discard_work; /* discard worker */ + struct work_struct reclaim_work; /* reclaim worker */ struct list_head discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one diff --git a/include/linux/tick.h b/include/linux/tick.h index 72744638c5b0..99c9c5a7252a 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk, if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } + static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } + +static inline void tick_dep_init_task(struct task_struct *tsk) +{ + atomic_set(&tsk->tick_dep_mask, 0); +} + static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { @@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } +static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..84a035e86ac8 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,11 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); + void getboottime64(struct timespec64 *ts); /* diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 587b96b4418e..20a40ade8030 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -421,6 +421,7 @@ void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); +void tpm_buf_append_handle(struct tpm_chip *chip, struct tpm_buf *buf, u32 handle); /* * Check if TPM device is in the firmware upgrade mode. @@ -505,6 +506,8 @@ void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, u8 attributes, u8 *passphrase, int passphraselen); +void tpm_buf_append_auth(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, int passphraselen); static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, struct tpm_buf *buf, u8 attributes, diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 39c7cf82b0c2..e9c702c1908d 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -38,6 +38,7 @@ #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define mask_user_address(src) (src) #endif /* @@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); - if (!should_fail_usercopy() && likely(access_ok(from, n))) { + if (should_fail_usercopy()) + goto fail; + if (can_do_masked_user_access()) + from = mask_user_address(from); + else { + if (!access_ok(from, n)) + goto fail; /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); - instrument_copy_from_user_before(to, from, n); - res = raw_copy_from_user(to, from, n); - instrument_copy_from_user_after(to, from, n, res); } - if (unlikely(res)) - memset(to + (n - res), 0, res); + instrument_copy_from_user_before(to, from, n); + res = raw_copy_from_user(to, from, n); + instrument_copy_from_user_after(to, from, n, res); + if (likely(!res)) + return 0; +fail: + memset(to + (n - res), 0, res); return res; } extern __must_check unsigned long @@ -394,6 +403,103 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, return 0; } +/** + * copy_struct_to_user: copy a struct to userspace + * @dst: Destination address, in userspace. This buffer must be @ksize + * bytes long. + * @usize: (Alleged) size of @dst struct. + * @src: Source address, in kernel space. + * @ksize: Size of @src struct. + * @ignored_trailing: Set to %true if there was a non-zero byte in @src that + * userspace cannot see because they are using an smaller struct. + * + * Copies a struct from kernel space to userspace, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * Some syscalls may wish to make sure that userspace knows about everything in + * the struct, and if there is a non-zero value that userspce doesn't know + * about, they want to return an error (such as -EMSGSIZE) or have some other + * fallback (such as adding a "you're missing some information" flag). If + * @ignored_trailing is non-%NULL, it will be set to %true if there was a + * non-zero byte that could not be copied to userspace (ie. was past @usize). + * + * While unconditionally returning an error in this case is the simplest + * solution, for maximum backward compatibility you should try to only return + * -EMSGSIZE if the user explicitly requested the data that couldn't be copied. + * Note that structure sizes can change due to header changes and simple + * recompilations without code changes(!), so if you care about + * @ignored_trailing you probably want to make sure that any new field data is + * associated with a flag. Otherwise you might assume that a program knows + * about data it does not. + * + * @ksize is just sizeof(*src), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, struct foo __user *, uarg, size_t, usize) + * { + * int err; + * bool ignored_trailing; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * // ... modify karg somehow ... + * + * err = copy_struct_to_user(uarg, usize, &karg, sizeof(karg), + * &ignored_trailing); + * if (err) + * return err; + * if (ignored_trailing) + * return -EMSGSIZE: + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the kernel is trying to pass userspace a newer + * struct than it supports. Thus we only copy the interoperable portions + * (@usize) and ignore the rest (but @ignored_trailing is set to %true if + * any of the trailing (@ksize - @usize) bytes are non-zero). + * * If @usize > @ksize, then the kernel is trying to pass userspace an older + * struct than userspace supports. In order to make sure the + * unknown-to-the-kernel fields don't contain garbage values, we zero the + * trailing (@usize - @ksize) bytes. + * + * Returns (in all cases, some data may have been copied): + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_to_user(void __user *dst, size_t usize, const void *src, + size_t ksize, bool *ignored_trailing) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Double check if ksize is larger than a known object size. */ + if (WARN_ON_ONCE(ksize > __builtin_object_size(src, 1))) + return -E2BIG; + + /* Deal with trailing bytes. */ + if (usize > ksize) { + if (clear_user(dst + size, rest)) + return -EFAULT; + } + if (ignored_trailing) + *ignored_trailing = ksize < usize && + memchr_inv(src + size, 0, rest) != NULL; + /* Copy the interoperable parts of the struct. */ + if (copy_to_user(dst, src, size)) + return -EFAULT; + return 0; +} + bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 4d39e6e11a95..5e6b212a2aed 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -16,6 +16,8 @@ struct utf8data_table; ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ ((unsigned int)(REV))) +#define UTF8_LATEST UNICODE_AGE(12, 1, 0) + static inline u8 unicode_major(unsigned int age) { return (age >> UNICODE_MAJ_SHIFT) & 0xff; @@ -76,4 +78,6 @@ int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); +int utf8_parse_version(char *version); + #endif /* _LINUX_UNICODE_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 3625096d5f85..7183e5aca282 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -141,7 +141,8 @@ static inline long get_rlimit_value(struct ucounts *ucounts, enum rlimit_type ty long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v); -long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type); +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, + bool override_rlimit); void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type); bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long max); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 9fc6ce15c499..cb40f1a1d081 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); +void dup_userfaultfd_fail(struct list_head *); extern void mremap_userfaultfd_prep(struct vm_area_struct *, struct vm_userfaultfd_ctx *); @@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l) { } +static inline void dup_userfaultfd_fail(struct list_head *l) +{ +} + static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *ctx) { diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index aed952d04132..f70d0958095c 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -134,6 +134,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, + SWPIN_ZERO, + SWPOUT_ZERO, #ifdef CONFIG_KSM KSM_SWPIN_COPY, #endif diff --git a/include/linux/wait.h b/include/linux/wait.h index 8aa3372f21a0..2b322a9b88a2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -221,6 +221,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) +#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d6db822e4bb3..d11b903c2edb 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -213,11 +213,8 @@ static inline void wait_on_inode(struct inode *inode) #include <linux/bio.h> void __inode_attach_wb(struct inode *inode, struct folio *folio); -void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); @@ -254,22 +251,8 @@ static inline void inode_detach_wb(struct inode *inode) } } -/** - * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite - * @wbc: writeback_control of interest - * @inode: target inode - * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. - */ -static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, - struct inode *inode) -{ - spin_lock(&inode->i_lock); - inode_attach_wb(inode, NULL); - wbc_attach_and_unlock_inode(wbc, inode); -} +void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode); /** * wbc_init_bio - writeback specific initializtion of bio @@ -303,13 +286,6 @@ static inline void inode_detach_wb(struct inode *inode) { } -static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock) -{ - spin_unlock(&inode->i_lock); -} - static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { @@ -324,7 +300,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, - struct page *page, size_t bytes) + struct folio *folio, size_t bytes) { } |