diff options
Diffstat (limited to 'include')
94 files changed, 920 insertions, 293 deletions
diff --git a/include/asm-generic/param.h b/include/asm-generic/param.h index 8d3009dd28ff..8348c116aa3b 100644 --- a/include/asm-generic/param.h +++ b/include/asm-generic/param.h @@ -6,6 +6,6 @@ # undef HZ # define HZ CONFIG_HZ /* Internal kernel timer frequency */ -# define USER_HZ 100 /* some user interfaces are */ +# define USER_HZ __USER_HZ /* some user interfaces are */ # define CLOCKS_PER_SEC (USER_HZ) /* in "ticks" like times() */ #endif /* __ASM_GENERIC_PARAM_H */ diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 9689a7c5dd36..513837632b7d 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -160,6 +160,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm, u64 new_size, struct list_head *blocks); +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear); + void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); void drm_buddy_free_list(struct drm_buddy *mm, diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 5c3b2aa3e69d..d344d41e6cfe 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -300,6 +300,9 @@ struct drm_file { * * Mapping of mm object handles to object pointers. Used by the GEM * subsystem. Protected by @table_lock. + * + * Note that allocated entries might be NULL as a transient state when + * creating or deleting a handle. */ struct idr object_idr; diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h index 668077009fce..38b24fc8978d 100644 --- a/include/drm/drm_framebuffer.h +++ b/include/drm/drm_framebuffer.h @@ -23,6 +23,7 @@ #ifndef __DRM_FRAMEBUFFER_H__ #define __DRM_FRAMEBUFFER_H__ +#include <linux/bits.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/sched.h> @@ -100,6 +101,8 @@ struct drm_framebuffer_funcs { unsigned num_clips); }; +#define DRM_FRAMEBUFFER_HAS_HANDLE_REF(_i) BIT(0u + (_i)) + /** * struct drm_framebuffer - frame buffer object * @@ -189,6 +192,10 @@ struct drm_framebuffer { */ int flags; /** + * @internal_flags: Framebuffer flags like DRM_FRAMEBUFFER_HAS_HANDLE_REF. + */ + unsigned int internal_flags; + /** * @filp_head: Placed on &drm_file.fbs, protected by &drm_file.fbs_lock. */ struct list_head filp_head; diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index b37860f4a895..6d2c08e81101 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -223,6 +223,9 @@ struct mipi_dsi_multi_context { #define to_mipi_dsi_device(__dev) container_of_const(__dev, struct mipi_dsi_device, dev) +extern const struct bus_type mipi_dsi_bus_type; +#define dev_is_mipi_dsi(dev) ((dev)->bus == &mipi_dsi_bus_type) + /** * mipi_dsi_pixel_format_to_bpp - obtain the number of bits per pixel for any * given pixel format defined by the MIPI DSI diff --git a/include/drm/spsc_queue.h b/include/drm/spsc_queue.h index 125f096c88cb..ee9df8cc67b7 100644 --- a/include/drm/spsc_queue.h +++ b/include/drm/spsc_queue.h @@ -70,9 +70,11 @@ static inline bool spsc_queue_push(struct spsc_queue *queue, struct spsc_node *n preempt_disable(); + atomic_inc(&queue->job_count); + smp_mb__after_atomic(); + tail = (struct spsc_node **)atomic_long_xchg(&queue->tail, (long)&node->next); WRITE_ONCE(*tail, node); - atomic_inc(&queue->job_count); /* * In case of first element verify new node will be visible to the consumer diff --git a/include/dt-bindings/clock/sun8i-v3s-ccu.h b/include/dt-bindings/clock/sun8i-v3s-ccu.h index 014ac6123d17..c4055629c9f9 100644 --- a/include/dt-bindings/clock/sun8i-v3s-ccu.h +++ b/include/dt-bindings/clock/sun8i-v3s-ccu.h @@ -96,7 +96,7 @@ #define CLK_TCON0 64 #define CLK_CSI_MISC 65 #define CLK_CSI0_MCLK 66 -#define CLK_CSI1_SCLK 67 +#define CLK_CSI_SCLK 67 #define CLK_CSI1_MCLK 68 #define CLK_VE 69 #define CLK_AC_DIG 70 diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 784ebe4607a4..50b47eba7d01 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -113,7 +113,7 @@ /* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ #define ARM_SMCCC_VENDOR_HYP_UID_KVM UUID_INIT(\ - 0xb66fb428, 0xc52e, 0xe911, \ + 0x28b46fb6, 0x2ec5, 0x11e9, \ 0xa9, 0xca, 0x4b, 0x56, \ 0x4d, 0x00, 0x3a, 0x74) diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 5bded24dc24f..e1634897e159 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -283,6 +283,7 @@ struct ffa_indirect_msg_hdr { u32 offset; u32 send_recv_id; u32 size; + u32 res1; uuid_t uuid; }; diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index c7eae0bfb013..e67a2b6e8f11 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -29,11 +29,13 @@ int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf, ssize_t bytes); +int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, + struct logical_block_metadata_cap __user *argp); static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { - return q->limits.integrity.tuple_size; + return q->limits.integrity.metadata_size; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) @@ -74,7 +76,7 @@ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { - return bio_integrity_intervals(bi, sectors) * bi->tuple_size; + return bio_integrity_intervals(bi, sectors) * bi->metadata_size; } static inline bool blk_integrity_rq(struct request *rq) @@ -92,6 +94,11 @@ static inline struct bio_vec rq_integrity_vec(struct request *rq) rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ +static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd, + struct logical_block_metadata_cap __user *argp) +{ + return -ENOIOCTLCMD; +} static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a51f92b6c340..95886b404b16 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -116,10 +116,11 @@ enum blk_integrity_checksum { struct blk_integrity { unsigned char flags; enum blk_integrity_checksum csum_type; - unsigned char tuple_size; + unsigned char metadata_size; unsigned char pi_offset; unsigned char interval_exp; unsigned char tag_size; + unsigned char pi_tuple_size; }; typedef unsigned int __bitwise blk_mode_t; @@ -269,11 +270,16 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) * however we constrain this to what we can validate and test. */ #define BLK_MAX_BLOCK_SIZE SZ_64K +#else +#define BLK_MAX_BLOCK_SIZE PAGE_SIZE +#endif + /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) @@ -383,6 +389,9 @@ struct queue_limits { unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; + unsigned int max_wzeroes_unmap_sectors; + unsigned int max_hw_wzeroes_unmap_sectors; + unsigned int max_user_wzeroes_unmap_sectors; unsigned int max_hw_zone_append_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -1097,6 +1106,7 @@ static inline void blk_queue_disable_secure_erase(struct request_queue *q) static inline void blk_queue_disable_write_zeroes(struct request_queue *q) { q->limits.max_write_zeroes_sectors = 0; + q->limits.max_wzeroes_unmap_sectors = 0; } /* @@ -1424,6 +1434,12 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) return bdev_limits(bdev)->max_write_zeroes_sectors; } +static inline unsigned int +bdev_write_zeroes_unmap_sectors(struct block_device *bdev) +{ + return bdev_limits(bdev)->max_wzeroes_unmap_sectors; +} + static inline bool bdev_nonrot(struct block_device *bdev) { return blk_queue_nonrot(bdev_get_queue(bdev)); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 0029ff880e27..b16b88bfbc3e 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -262,14 +262,12 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block); int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); -int block_write_end(struct file *, struct address_space *, - loff_t, unsigned len, unsigned copied, - struct folio *, void *); -int generic_write_end(struct file *, struct address_space *, +int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *); +int generic_write_end(const struct kiocb *, struct address_space *, loff_t, unsigned len, unsigned copied, struct folio *, void *); void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to); -int cont_write_begin(struct file *, struct address_space *, loff_t, +int cont_write_begin(const struct kiocb *, struct address_space *, loff_t, unsigned, struct folio **, void **, get_block_t *, loff_t *); int generic_cont_expand_simple(struct inode *inode, loff_t size); diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 7093e1d08af0..bee606bebaca 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -277,6 +277,14 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ class_##_name##_t var __cleanup(class_##_name##_destructor) = \ class_##_name##_constructor +#define scoped_class(_name, var, args) \ + for (CLASS(_name, var)(args); \ + __guard_ptr(_name)(&var) || !__is_cond_ptr(_name); \ + ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ + } else /* * DEFINE_GUARD(name, type, lock, unlock): diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 76e41805b92d..96e8a66da133 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -43,7 +43,7 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -extern void do_coredump(const kernel_siginfo_t *siginfo); +extern void vfs_coredump(const kernel_siginfo_t *siginfo); /* * Logging for the coredump code, ratelimited. @@ -63,7 +63,7 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); #define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__) #else -static inline void do_coredump(const kernel_siginfo_t *siginfo) {} +static inline void vfs_coredump(const kernel_siginfo_t *siginfo) {} #define coredump_report(...) #define coredump_report_failure(...) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 96a3a0d6a60e..6378370a952f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -82,6 +82,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/cred.h b/include/linux/cred.h index 5658a3bfe803..a102a10f833f 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -263,6 +263,8 @@ static inline void put_cred(const struct cred *cred) put_cred_many(cred, 1); } +DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T)) + /** * current_cred - Access the current task's subjective credentials * diff --git a/include/linux/dax.h b/include/linux/dax.h index dcc9fcdf14e4..78891518291d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -65,12 +65,13 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, /* * Check if given mapping is supported by the file / underlying device. */ -static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, - struct dax_device *dax_dev) +static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, + const struct inode *inode, + struct dax_device *dax_dev) { - if (!(vma->vm_flags & VM_SYNC)) + if (!(vm_flags & VM_SYNC)) return true; - if (!IS_DAX(file_inode(vma->vm_file))) + if (!IS_DAX(inode)) return false; return dax_synchronous(dax_dev); } @@ -110,10 +111,11 @@ static inline void set_dax_nomc(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } -static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, - struct dax_device *dax_dev) +static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, + const struct inode *inode, + struct dax_device *dax_dev) { - return !(vma->vm_flags & VM_SYNC); + return !(vm_flags & VM_SYNC); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) diff --git a/include/linux/dcache.h b/include/linux/dcache.h index e29823c701ac..cc3e1c1a3454 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -237,7 +237,6 @@ extern void d_instantiate_new(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); -extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); @@ -245,6 +244,9 @@ extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); +/* weird procfs mess; *NOT* exported */ +extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *, + const struct dentry_operations *); 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); @@ -604,4 +606,6 @@ static inline struct dentry *d_next_sibling(const struct dentry *dentry) return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); } +void set_default_d_op(struct super_block *, const struct dentry_operations *); + #endif /* __LINUX_DCACHE_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 25c4a5afbd44..cfb0dd1ea49c 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -230,7 +230,7 @@ struct handle_to_path_ctx { * directory. The name should be stored in the @name (with the * understanding that it is already pointing to a %NAME_MAX+1 sized * buffer. get_name() should return %0 on success, a negative error code - * or error. @get_name will be called without @parent->i_mutex held. + * or error. @get_name will be called without @parent->i_rwsem held. * * get_parent: * @get_parent should find the parent directory for the given @child which @@ -247,7 +247,7 @@ struct handle_to_path_ctx { * @commit_metadata should commit metadata changes to stable storage. * * Locking rules: - * get_parent is called with child->d_inode->i_mutex down + * get_parent is called with child->d_inode->i_rwsem down * get_name is not (which is possibly inconsistent) */ diff --git a/include/linux/falloc.h b/include/linux/falloc.h index 3f49f3df6af5..7c38c6b76b60 100644 --- a/include/linux/falloc.h +++ b/include/linux/falloc.h @@ -36,7 +36,8 @@ struct space_resv { FALLOC_FL_COLLAPSE_RANGE | \ FALLOC_FL_ZERO_RANGE | \ FALLOC_FL_INSERT_RANGE | \ - FALLOC_FL_UNSHARE_RANGE) + FALLOC_FL_UNSHARE_RANGE | \ + FALLOC_FL_WRITE_ZEROES) /* on ia32 l_start is on a 32-bit boundary */ #if defined(CONFIG_X86_64) diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h index 47c05a9851d0..f89dcfad3f8f 100644 --- a/include/linux/fileattr.h +++ b/include/linux/fileattr.h @@ -14,13 +14,33 @@ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT) +/* Read-only inode flags */ +#define FS_XFLAG_RDONLY_MASK \ + (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR) + +/* Flags to indicate valid value of fsx_ fields */ +#define FS_XFLAG_VALUES_MASK \ + (FS_XFLAG_EXTSIZE | FS_XFLAG_COWEXTSIZE) + +/* Flags for directories */ +#define FS_XFLAG_DIRONLY_MASK \ + (FS_XFLAG_RTINHERIT | FS_XFLAG_NOSYMLINKS | FS_XFLAG_EXTSZINHERIT) + +/* Misc settable flags */ +#define FS_XFLAG_MISC_MASK \ + (FS_XFLAG_REALTIME | FS_XFLAG_NODEFRAG | FS_XFLAG_FILESTREAM) + +#define FS_XFLAGS_MASK \ + (FS_XFLAG_COMMON | FS_XFLAG_RDONLY_MASK | FS_XFLAG_VALUES_MASK | \ + FS_XFLAG_DIRONLY_MASK | FS_XFLAG_MISC_MASK) + /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ -struct fileattr { +struct file_kattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ @@ -33,10 +53,10 @@ struct fileattr { bool fsx_valid:1; }; -int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa); +int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa); -void fileattr_fill_xflags(struct fileattr *fa, u32 xflags); -void fileattr_fill_flags(struct fileattr *fa, u32 flags); +void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags); +void fileattr_fill_flags(struct file_kattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes @@ -45,15 +65,19 @@ void fileattr_fill_flags(struct fileattr *fa, u32 flags); * Return: true if any attributes are present that are not represented in * ->flags. */ -static inline bool fileattr_has_fsx(const struct fileattr *fa) +static inline bool fileattr_has_fsx(const struct file_kattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } -int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa); +int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, - struct fileattr *fa); + struct file_kattr *fa); +int ioctl_getflags(struct file *file, unsigned int __user *argp); +int ioctl_setflags(struct file *file, unsigned int __user *argp); +int ioctl_fsgetxattr(struct file *file, void __user *argp); +int ioctl_fssetxattr(struct file *file, void __user *argp); #endif /* _LINUX_FILEATTR_H */ diff --git a/include/linux/filelock.h b/include/linux/filelock.h index c412ded9171e..c2ce8ba05d06 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -175,9 +175,14 @@ static inline bool lock_is_write(struct file_lock *fl) return fl->c.flc_type == F_WRLCK; } +static inline void locks_wake_up_waiter(struct file_lock_core *flc) +{ + wake_up(&flc->flc_wait); +} + static inline void locks_wake_up(struct file_lock *fl) { - wake_up(&fl->c.flc_wait); + locks_wake_up_waiter(&fl->c); } static inline bool locks_can_async_lock(const struct file_operations *fops) diff --git a/include/linux/fs.h b/include/linux/fs.h index b085f161ed22..2ec4807d4ea8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -80,7 +80,7 @@ struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; -struct fileattr; +struct file_kattr; struct iomap_ops; extern void __init inode_init(void); @@ -446,10 +446,10 @@ struct address_space_operations { void (*readahead)(struct readahead_control *); - int (*write_begin)(struct file *, struct address_space *mapping, + int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); - int (*write_end)(struct file *, struct address_space *mapping, + int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); @@ -839,7 +839,7 @@ static inline void inode_fake_hash(struct inode *inode) } /* - * inode->i_mutex nesting subclasses for the lock validator: + * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent @@ -991,7 +991,7 @@ static inline loff_t i_size_read(const struct inode *inode) /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it - * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount + * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) @@ -1402,6 +1402,7 @@ struct super_block { char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; + unsigned int s_d_flags; /* default d_flags for dentries */ /* * The next field is for VFS *only*. No filesystems have any business @@ -1415,7 +1416,7 @@ struct super_block { */ const char *s_subtype; - const struct dentry_operations *s_d_op; /* default d_op for dentries */ + const struct dentry_operations *__s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ @@ -1923,7 +1924,7 @@ static inline void sb_end_intwrite(struct super_block *sb) * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write - * -> i_mutex (write path, truncate, directory ops, ...) + * -> i_rwsem (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) @@ -2006,20 +2007,20 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, /** * struct renamedata - contains all information required for renaming * @old_mnt_idmap: idmap of the old mount the inode was found from - * @old_dir: parent of source + * @old_parent: parent of source * @old_dentry: source * @new_mnt_idmap: idmap of the new mount the inode was found from - * @new_dir: parent of destination + * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *old_mnt_idmap; - struct inode *old_dir; + struct dentry *old_parent; struct dentry *old_dentry; struct mnt_idmap *new_mnt_idmap; - struct inode *new_dir; + struct dentry *new_parent; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; @@ -2256,13 +2257,13 @@ struct inode_operations { int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, - struct dentry *dentry, struct fileattr *fa); - int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa); + struct dentry *dentry, struct file_kattr *fa); + int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; /* Did the driver provide valid mmap hook configuration? */ -static inline bool file_has_valid_mmap_hooks(struct file *file) +static inline bool can_mmap_file(struct file *file) { bool has_mmap = file->f_op->mmap; bool has_mmap_prepare = file->f_op->mmap_prepare; @@ -2278,7 +2279,7 @@ static inline bool file_has_valid_mmap_hooks(struct file *file) int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma); -static inline int call_mmap(struct file *file, struct vm_area_struct *vma) +static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { if (file->f_op->mmap_prepare) return compat_vma_mmap_prepare(file, vma); @@ -2286,8 +2287,7 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -static inline int __call_mmap_prepare(struct file *file, - struct vm_area_desc *desc) +static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) { return file->f_op->mmap_prepare(desc); } @@ -2367,6 +2367,15 @@ struct super_operations { struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); + /* + * If a filesystem can support graceful removal of a device and + * continue read-write operations, implement this callback. + * + * Return 0 if the filesystem can continue read-write. + * Non-zero return value or no such callback means the fs will be shutdown + * as usual. + */ + int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); void (*shutdown)(struct super_block *sb); }; @@ -2868,7 +2877,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); -struct path *backing_file_user_path(struct file *f); +struct path *backing_file_user_path(const struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file @@ -2880,14 +2889,14 @@ struct path *backing_file_user_path(struct file *f); * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ -static inline const struct path *file_user_path(struct file *f) +static inline const struct path *file_user_path(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ -static inline const struct inode *file_user_inode(struct file *f) +static inline const struct inode *file_user_inode(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); @@ -3268,6 +3277,22 @@ static inline bool is_dot_dotdot(const char *name, size_t len) (len == 1 || (len == 2 && name[1] == '.')); } +/** + * name_contains_dotdot - check if a file name contains ".." path components + * + * Search for ".." surrounded by either '/' or start/end of string. + */ +static inline bool name_contains_dotdot(const char *name) +{ + size_t name_len; + + name_len = strlen(name); + return strcmp(name, "..") == 0 || + strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); +} + #include <linux/err.h> /* needed for stackable file system support */ @@ -3396,8 +3421,10 @@ extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); -extern int generic_file_mmap(struct file *, struct vm_area_struct *); -extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap(struct file *, struct vm_area_struct *); +int generic_file_mmap_prepare(struct vm_area_desc *desc); +int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); +int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, @@ -3599,17 +3626,21 @@ extern int simple_rename(struct mnt_idmap *, struct inode *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); +extern void locked_recursive_removal(struct dentry *, + void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, - struct folio **foliop, void **fsdata); +extern int simple_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); +struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, + const struct inode *context_inode); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); -extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); @@ -3623,6 +3654,7 @@ extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); +struct dentry *simple_start_creating(struct dentry *, const char *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index a19e4bd32e4d..7773eb870039 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -200,7 +200,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, */ #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__) #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__) -#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) +#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__) /** * warnf - Store supplementary warning message diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h index 2b1f74b24070..0cc2fa283305 100644 --- a/include/linux/fs_stack.h +++ b/include/linux/fs_stack.h @@ -3,7 +3,7 @@ #define _LINUX_FS_STACK_H /* This file defines generic functions used primarily by stackable - * filesystems; none of these functions require i_mutex to be held. + * filesystems; none of these functions require i_rwsem to be held. */ #include <linux/fs.h> diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index 783b48dedb72..baf200ab5c77 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -8,8 +8,7 @@ struct fs_struct { int users; - spinlock_t lock; - seqcount_spinlock_t seq; + seqlock_t seq; int umask; int in_exec; struct path root, pwd; @@ -26,18 +25,18 @@ extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { - spin_lock(&fs->lock); + read_seqlock_excl(&fs->seq); *root = fs->root; path_get(root); - spin_unlock(&fs->lock); + read_sequnlock_excl(&fs->seq); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { - spin_lock(&fs->lock); + read_seqlock_excl(&fs->seq); *pwd = fs->pwd; path_get(pwd); - spin_unlock(&fs->lock); + read_sequnlock_excl(&fs->seq); } extern bool current_chrooted(void); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 22f39e5e2ff1..996be3c2cff0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -663,18 +663,6 @@ static inline bool ieee80211_s1g_has_cssid(__le16 fc) } /** - * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame is an S1G short beacon, - * i.e. it is an S1G beacon with 'next TBTT' flag set - */ -static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) -{ - return ieee80211_is_s1g_beacon(fc) && - (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); -} - -/** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder * Return: whether or not the frame is an ATIM frame @@ -4901,6 +4889,39 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb) return false; } +/** + * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon + * @fc: frame control bytes in little-endian byteorder + * @variable: pointer to the beacon frame elements + * @variable_len: length of the frame elements + * Return: whether or not the frame is an S1G short beacon. As per + * IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall + * always be present as the first element in beacon frames generated at a + * TBTT (Target Beacon Transmission Time), so any frame not containing + * this element must have been generated at a TSBTT (Target Short Beacon + * Transmission Time) that is not a TBTT. Additionally, short beacons are + * prohibited from containing the S1G beacon compatibility element as per + * IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with + * either no elements or the first element is not the beacon compatibility + * element, we have a short beacon. + */ +static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable, + size_t variable_len) +{ + if (!ieee80211_is_s1g_beacon(fc)) + return false; + + /* + * If the frame does not contain at least 1 element (this is perfectly + * valid in a short beacon) and is an S1G beacon, we have a short + * beacon. + */ + if (variable_len < 2) + return true; + + return variable[0] != WLAN_EID_S1G_BCN_COMPAT; +} + struct element { u8 id; u8 datalen; diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 55cfebc658e6..8a2f652a05ff 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -119,6 +119,7 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create_dyn(void); struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); +int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name); int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node); int icc_link_create(struct icc_node *node, const int dst_id); void icc_node_add(struct icc_node *node, struct icc_provider *provider); @@ -152,6 +153,12 @@ static inline void icc_node_destroy(int id) { } +static inline int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, + const char *name) +{ + return -EOPNOTSUPP; +} + static inline int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node) { return -EOPNOTSUPP; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 53408124c1e5..cfa6d0c0c322 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -8,6 +8,8 @@ /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */ #define IORING_URING_CMD_CANCELABLE (1U << 30) +/* io_uring_cmd is being issued again */ +#define IORING_URING_CMD_REISSUE (1U << 31) struct io_uring_cmd { struct file *file; @@ -19,10 +21,6 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; -struct io_uring_cmd_data { - void *op_data; -}; - static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) { return sqe->cmd; @@ -135,11 +133,6 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd return cmd_to_io_kiocb(cmd)->tctx->task; } -static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd) -{ - return cmd_to_io_kiocb(cmd)->async_data; -} - /* * Return uring_cmd's context reference as its context handle for driver to * track per-context resource, such as registered kernel IO buffer diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 2922635986f5..80a178f3d896 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -26,6 +26,8 @@ enum io_uring_cmd_flags { IO_URING_F_MULTISHOT = 4, /* executed by io-wq */ IO_URING_F_IOWQ = 8, + /* executed inline from syscall */ + IO_URING_F_INLINE = 16, /* int's last bit, sign checks are usually faster than a bit test */ IO_URING_F_NONBLOCK = INT_MIN, @@ -502,6 +504,7 @@ enum { REQ_F_BUF_NODE_BIT, REQ_F_HAS_METADATA_BIT, REQ_F_IMPORT_BUFFER_BIT, + REQ_F_SQE_COPIED_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -591,6 +594,8 @@ enum { * For SEND_ZC, whether to import buffers (i.e. the first issue). */ REQ_F_IMPORT_BUFFER = IO_REQ_FLAG(REQ_F_IMPORT_BUFFER_BIT), + /* ->sqe_copy() has been called, if necessary */ + REQ_F_SQE_COPIED = IO_REQ_FLAG(REQ_F_SQE_COPIED_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, io_tw_token_t tw); @@ -698,6 +703,8 @@ struct io_kiocb { struct hlist_node hash_node; /* For IOPOLL setup queues, with hybrid polling */ u64 iopoll_start; + /* for private io_kiocb freeing */ + struct rcu_head rcu_head; }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 522644d62f30..73dceabc21c8 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -101,8 +101,6 @@ struct vm_fault; */ #define IOMAP_NULL_ADDR -1ULL /* addr is not valid */ -struct iomap_folio_ops; - struct iomap { u64 addr; /* disk offset of mapping, bytes */ loff_t offset; /* file offset of mapping, bytes */ @@ -113,7 +111,6 @@ struct iomap { struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data; void *private; /* filesystem private */ - const struct iomap_folio_ops *folio_ops; u64 validity_cookie; /* used with .iomap_valid() */ }; @@ -143,16 +140,11 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap) } /* - * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio - * and put_folio will be called for each folio written to. This only applies - * to buffered writes as unbuffered writes will not typically have folios - * associated with them. - * * When get_folio succeeds, put_folio will always be called to do any * cleanup work necessary. put_folio is responsible for unlocking and putting * @folio. */ -struct iomap_folio_ops { +struct iomap_write_ops { struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos, unsigned len); void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied, @@ -174,6 +166,16 @@ struct iomap_folio_ops { * locked by the iomap code. */ bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap); + + /* + * Optional if the filesystem wishes to provide a custom handler for + * reading in the contents of a folio, otherwise iomap will default to + * submitting a bio read request. + * + * The read must be done synchronously. + */ + int (*read_folio_range)(const struct iomap_iter *iter, + struct folio *folio, loff_t pos, size_t len); }; /* @@ -335,7 +337,8 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) } ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, - const struct iomap_ops *ops, void *private); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private); int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); @@ -344,11 +347,14 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); 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); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, const struct iomap_ops *ops, void *private); + bool *did_zero, const struct iomap_ops *ops, + const struct iomap_write_ops *write_ops, void *private); int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops, void *private); + const struct iomap_ops *ops, + const struct iomap_write_ops *write_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, @@ -391,8 +397,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno, /* * 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 + * File systems 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 { @@ -416,41 +421,38 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio) struct iomap_writeback_ops { /* - * Required, maps the blocks so that writeback can be performed on - * the range starting at offset. + * Performs writeback on the passed in range * - * Can return arbitrarily large regions, but we need to call into it at + * Can map arbitrarily large regions, but we need to call into it at * least once per folio to allow the file systems to synchronize with * the write path that could be invalidating mappings. * * An existing mapping from a previous call to this method can be reused * by the file system if it is still valid. - */ - int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode, - loff_t offset, unsigned len); - - /* - * 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. + * Returns the number of bytes processed or a negative errno. */ - int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status); + ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc, + struct folio *folio, u64 pos, unsigned int len, + u64 end_pos); /* - * Optional, allows the file system to discard state on a page where - * we failed to submit any I/O. + * Submit a writeback context previously build up by ->writeback_range. + * + * Returns 0 if the context was successfully submitted, or a negative + * error code if not. If @error is non-zero a failure occurred, and + * the writeback context should be completed with an error. */ - void (*discard_folio)(struct folio *folio, loff_t pos); + int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error); }; struct iomap_writepage_ctx { struct iomap iomap; - struct iomap_ioend *ioend; + struct inode *inode; + struct writeback_control *wbc; const struct iomap_writeback_ops *ops; u32 nr_folios; /* folios added to the ioend */ + void *wb_ctx; /* pending writeback context */ }; struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio, @@ -461,9 +463,17 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error); void iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends); void iomap_sort_ioends(struct list_head *ioend_list); -int iomap_writepages(struct address_space *mapping, - struct writeback_control *wbc, struct iomap_writepage_ctx *wpc, - const struct iomap_writeback_ops *ops); +ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, + loff_t pos, loff_t end_pos, unsigned int dirty_len); +int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error); + +void iomap_start_folio_write(struct inode *inode, struct folio *folio, + size_t len); +void iomap_finish_folio_write(struct inode *inode, struct folio *folio, + size_t len); + +int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio); +int iomap_writepages(struct iomap_writepage_ctx *wpc); /* * Flags for direct I/O ->end_io: diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h index dd8d1d138544..224ac28e88d7 100644 --- a/include/linux/irqchip/irq-msi-lib.h +++ b/include/linux/irqchip/irq-msi-lib.h @@ -17,6 +17,7 @@ #define MATCH_PLATFORM_MSI BIT(DOMAIN_BUS_PLATFORM_MSI) +struct msi_domain_info; int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); diff --git a/include/linux/ism.h b/include/linux/ism.h index 5428edd90982..8358b4cd7ba6 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -28,6 +28,7 @@ struct ism_dmb { struct ism_dev { spinlock_t lock; /* protects the ism device */ + spinlock_t cmd_lock; /* serializes cmds */ struct list_head list; struct pci_dev *pdev; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index bf3bbac4e02a..fd11fffdd3c3 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -157,6 +157,8 @@ LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name) LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry, const char *name) +LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct file_kattr *fa) +LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct file_kattr *fa) LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry, diff --git a/include/linux/mm.h b/include/linux/mm.h index 0ef2ba0c667a..fa538feaa8d9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return percpu_counter_read_positive(&mm->rss_stat[member]); } +static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member) +{ + return percpu_counter_sum_positive(&mm->rss_stat[member]); +} + void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) diff --git a/include/linux/mount.h b/include/linux/mount.h index 1a508beba446..5f9c053b0897 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -35,9 +35,6 @@ enum mount_flags { MNT_SHRINKABLE = 0x100, MNT_WRITE_HOLD = 0x200, - MNT_SHARED = 0x1000, /* if the vfsmount is a shared mount */ - MNT_UNBINDABLE = 0x2000, /* if the vfsmount is a unbindable mount */ - MNT_INTERNAL = 0x4000, MNT_LOCK_ATIME = 0x040000, @@ -48,25 +45,15 @@ enum mount_flags { MNT_LOCKED = 0x800000, MNT_DOOMED = 0x1000000, MNT_SYNC_UMOUNT = 0x2000000, - MNT_MARKED = 0x4000000, MNT_UMOUNT = 0x8000000, - /* - * MNT_SHARED_MASK is the set of flags that should be cleared when a - * mount becomes shared. Currently, this is only the flag that says a - * mount cannot be bind mounted, since this is how we create a mount - * that shares events with another mount. If you add a new MNT_* - * flag, consider how it interacts with shared mounts. - */ - MNT_SHARED_MASK = MNT_UNBINDABLE, MNT_USER_SETTABLE_MASK = MNT_NOSUID | MNT_NODEV | MNT_NOEXEC | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME | MNT_READONLY | MNT_NOSYMFOLLOW, MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME, - MNT_INTERNAL_FLAGS = MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | - MNT_LOCKED, + MNT_INTERNAL_FLAGS = MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | + MNT_SYNC_UMOUNT | MNT_LOCKED }; struct vfsmount { @@ -98,6 +85,7 @@ int mnt_get_write_access(struct vfsmount *mnt); void mnt_put_write_access(struct vfsmount *mnt); extern struct vfsmount *fc_mount(struct fs_context *fc); +extern struct vfsmount *fc_mount_longterm(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h index e8462deda6db..f0aa098a395f 100644 --- a/include/linux/mtd/nand-qpic-common.h +++ b/include/linux/mtd/nand-qpic-common.h @@ -237,6 +237,9 @@ * @last_data_desc - last DMA desc in data channel (tx/rx). * @last_cmd_desc - last DMA desc in command channel. * @txn_done - completion for NAND transfer. + * @bam_ce_nitems - the number of elements in the @bam_ce array + * @cmd_sgl_nitems - the number of elements in the @cmd_sgl array + * @data_sgl_nitems - the number of elements in the @data_sgl array * @bam_ce_pos - the index in bam_ce which is available for next sgl * @bam_ce_start - the index in bam_ce which marks the start position ce * for current sgl. It will be used for size calculation @@ -255,6 +258,11 @@ struct bam_transaction { struct dma_async_tx_descriptor *last_data_desc; struct dma_async_tx_descriptor *last_cmd_desc; struct completion txn_done; + + unsigned int bam_ce_nitems; + unsigned int cmd_sgl_nitems; + unsigned int data_sgl_nitems; + struct_group(bam_positions, u32 bam_ce_pos; u32 bam_ce_start; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 065c17385e53..185bd8196503 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -265,21 +265,20 @@ struct netfs_io_request { bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_OFFLOAD_COLLECTION 0 /* Offload collection to workqueue */ -#define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ -#define NETFS_RREQ_FAILED 4 /* The request failed */ -#define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes (has ref) */ -#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 6 /* Copy current folio to cache from read */ -#define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ -#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_IN_PROGRESS 0 /* Unlocked when the request completes (has ref) */ +#define NETFS_RREQ_ALL_QUEUED 1 /* All subreqs are now queued */ +#define NETFS_RREQ_PAUSE 2 /* Pause subrequest generation */ +#define NETFS_RREQ_FAILED 3 /* The request failed */ +#define NETFS_RREQ_RETRYING 4 /* Set if we're in the retry path */ +#define NETFS_RREQ_SHORT_TRANSFER 5 /* Set if we have a short transfer */ +#define NETFS_RREQ_OFFLOAD_COLLECTION 8 /* Offload collection to workqueue */ +#define NETFS_RREQ_NO_UNLOCK_FOLIO 9 /* Don't unlock no_unlock_folio on completion */ +#define NETFS_RREQ_FOLIO_COPY_TO_CACHE 10 /* Copy current folio to cache from read */ +#define NETFS_RREQ_UPLOAD_TO_SERVER 11 /* Need to write to the server */ #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_RETRYING 14 /* Set if we're in the retry path */ -#define NETFS_RREQ_SHORT_TRANSFER 15 /* Set if we have a short transfer */ #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; - void (*cleanup)(struct netfs_io_request *req); }; /* @@ -443,7 +442,6 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error); -void netfs_queue_write_request(struct netfs_io_subrequest *subreq); int netfs_start_io_read(struct inode *inode); void netfs_end_io_read(struct inode *inode); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e63fbfbd5b0f..ce2bcdcadb73 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -751,6 +751,33 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); /** + * write_begin_get_folio - Get folio for write_begin with flags. + * @iocb: The kiocb passed from write_begin (may be NULL). + * @mapping: The address space to search. + * @index: The page cache index. + * @len: Length of data being written. + * + * This is a helper for filesystem write_begin() implementations. + * It wraps __filemap_get_folio(), setting appropriate flags in + * the write begin context. + * + * Return: A folio or an ERR_PTR. + */ +static inline struct folio *write_begin_get_folio(const struct kiocb *iocb, + struct address_space *mapping, pgoff_t index, size_t len) +{ + fgf_t fgp_flags = FGP_WRITEBEGIN; + + fgp_flags |= fgf_set_order(len); + + if (iocb && iocb->ki_flags & IOCB_DONTCACHE) + fgp_flags |= FGP_DONTCACHE; + + return __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); +} + +/** * filemap_get_folio - Find and get a folio. * @mapping: The address_space to search. * @index: The page index. diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 437769e061b7..13add0c2c407 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -154,6 +154,7 @@ struct phy_attrs { * @id: id of the phy device * @ops: function pointers for performing phy operations * @mutex: mutex to protect phy_ops + * @lockdep_key: lockdep information for this mutex * @init_count: used to protect when the PHY is used by multiple consumers * @power_count: used to protect when the PHY is used by multiple consumers * @attrs: used to specify PHY specific attributes @@ -165,6 +166,7 @@ struct phy { int id; const struct phy_ops *ops; struct mutex mutex; + struct lock_class_key lockdep_key; int init_count; int power_count; struct phy_attrs attrs; diff --git a/include/linux/pid.h b/include/linux/pid.h index 453ae6d8a68d..003a1027d219 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -47,19 +47,23 @@ #define RESERVED_PIDS 300 +struct pidfs_attr; + struct upid { int nr; struct pid_namespace *ns; }; -struct pid -{ +struct pid { refcount_t count; unsigned int level; spinlock_t lock; - struct dentry *stashed; - u64 ino; - struct rb_node pidfs_node; + struct { + u64 ino; + struct rb_node pidfs_node; + struct dentry *stashed; + struct pidfs_attr *attr; + }; /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 77e7db194914..3e08c33da2df 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -14,7 +14,6 @@ void pidfs_coredump(const struct coredump_params *cprm); #endif extern const struct dentry_operations pidfs_dentry_operations; int pidfs_register_pid(struct pid *pid); -void pidfs_get_pid(struct pid *pid); -void pidfs_put_pid(struct pid *pid); +void pidfs_free_pid(struct pid *pid); #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/platform_data/x86/amd-fch.h b/include/linux/platform_data/x86/amd-fch.h new file mode 100644 index 000000000000..2cf5153edbc2 --- /dev/null +++ b/include/linux/platform_data/x86/amd-fch.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AMD_FCH_H_ +#define _ASM_X86_AMD_FCH_H_ + +#define FCH_PM_BASE 0xFED80300 + +/* Register offsets from PM base: */ +#define FCH_PM_DECODEEN 0x00 +#define FCH_PM_DECODEEN_SMBUS0SEL GENMASK(20, 19) +#define FCH_PM_SCRATCH 0x80 +#define FCH_PM_S5_RESET_STATUS 0xC0 + +#endif /* _ASM_X86_AMD_FCH_H_ */ diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7803edaa8ff8..0cca01b5607b 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -888,15 +888,23 @@ static inline int power_supply_is_system_supplied(void) { return -ENOSYS; } extern int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val); +int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val); #if IS_ENABLED(CONFIG_POWER_SUPPLY) extern int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); +int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val); #else static inline int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val) { return 0; } +static inline int power_supply_set_property_direct(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val) +{ return 0; } #endif extern void power_supply_external_power_changed(struct power_supply *psy); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index ea62201c74c4..de1d24f19f76 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -27,6 +27,8 @@ enum { PROC_ENTRY_proc_read_iter = 1U << 1, PROC_ENTRY_proc_compat_ioctl = 1U << 2, + + PROC_ENTRY_FORCE_LOOKUP = 1U << 7, }; struct proc_ops { diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 5ea470eb4d76..4b20375f3783 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -6,6 +6,7 @@ #define _LINUX_PROC_NS_H #include <linux/ns_common.h> +#include <uapi/linux/nsfs.h> struct pid_namespace; struct nsset; @@ -39,13 +40,14 @@ extern const struct proc_ns_operations timens_for_children_operations; * We always define these enumerators */ enum { - PROC_ROOT_INO = 1, - PROC_IPC_INIT_INO = 0xEFFFFFFFU, - PROC_UTS_INIT_INO = 0xEFFFFFFEU, - PROC_USER_INIT_INO = 0xEFFFFFFDU, - PROC_PID_INIT_INO = 0xEFFFFFFCU, - PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, - PROC_TIME_INIT_INO = 0xEFFFFFFAU, + PROC_IPC_INIT_INO = IPC_NS_INIT_INO, + PROC_UTS_INIT_INO = UTS_NS_INIT_INO, + PROC_USER_INIT_INO = USER_NS_INIT_INO, + PROC_PID_INIT_INO = PID_NS_INIT_INO, + PROC_CGROUP_INIT_INO = CGROUP_NS_INIT_INO, + PROC_TIME_INIT_INO = TIME_NS_INIT_INO, + PROC_NET_INIT_INO = NET_NS_INIT_INO, + PROC_MNT_INIT_INO = MNT_NS_INIT_INO, }; #ifdef CONFIG_PROC_FS diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 0b3a36bdaa90..0f5f94137f6d 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -594,6 +594,7 @@ struct sev_data_snp_addr { * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the * purpose of guest-assisted migration. * @rsvd: reserved + * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest * @gosvw: guest OS-visible workarounds, as defined by hypervisor */ struct sev_data_snp_launch_start { @@ -603,6 +604,7 @@ struct sev_data_snp_launch_start { u32 ma_en:1; /* In */ u32 imi_en:1; /* In */ u32 rsvd:30; + u32 desired_tsc_khz; /* In */ u8 gosvw[16]; /* In */ } __packed; diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index 06cc8888199e..c334f82ed385 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -19,7 +19,7 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb) return &sb->s_dquot; } -/* i_mutex must being held */ +/* i_rwsem must being held */ static inline bool is_quota_modification(struct mnt_idmap *idmap, struct inode *inode, struct iattr *ia) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52..aa9c5be7a632 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -548,10 +548,6 @@ struct sched_statistics { u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; -#ifdef CONFIG_NUMA_BALANCING - u64 numa_task_migrated; - u64 numa_task_swapped; -#endif u64 nr_wakeups; u64 nr_wakeups_sync; diff --git a/include/linux/security.h b/include/linux/security.h index dba349629229..fb72525ddd73 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -451,6 +451,10 @@ int security_inode_listxattr(struct dentry *dentry); int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name); void security_inode_post_removexattr(struct dentry *dentry, const char *name); +int security_inode_file_setattr(struct dentry *dentry, + struct file_kattr *fa); +int security_inode_file_getattr(struct dentry *dentry, + struct file_kattr *fa); int security_inode_need_killpriv(struct dentry *dentry); int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry); int security_inode_getsecurity(struct mnt_idmap *idmap, @@ -1052,6 +1056,18 @@ static inline void security_inode_post_removexattr(struct dentry *dentry, const char *name) { } +static inline int security_inode_file_setattr(struct dentry *dentry, + struct file_kattr *fa) +{ + return 0; +} + +static inline int security_inode_file_getattr(struct dentry *dentry, + struct file_kattr *fa) +{ + return 0; +} + static inline int security_inode_need_killpriv(struct dentry *dentry) { return cap_inode_need_killpriv(dentry); @@ -2211,7 +2227,6 @@ struct dentry *securityfs_create_symlink(const char *name, const char *target, const struct inode_operations *iops); extern void securityfs_remove(struct dentry *dentry); -extern void securityfs_recursive_remove(struct dentry *dentry); #else /* CONFIG_SECURITYFS */ @@ -2243,6 +2258,8 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#define securityfs_recursive_remove securityfs_remove + #ifdef CONFIG_BPF_SYSCALL union bpf_attr; struct bpf_map; diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 4789f91dae94..e9ea43234d9a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -21,7 +21,7 @@ #include <uapi/linux/spi/spi.h> /* Max no. of CS supported per spi device */ -#define SPI_CS_CNT_MAX 16 +#define SPI_CS_CNT_MAX 24 struct dma_chan; struct software_node; diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h index 51cab2def9ec..876130091384 100644 --- a/include/linux/sprintf.h +++ b/include/linux/sprintf.h @@ -4,6 +4,7 @@ #include <linux/compiler_attributes.h> #include <linux/types.h> +#include <linux/stdarg.h> int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h index c4b0eb2b2f04..ada17b57ca44 100644 --- a/include/linux/sunrpc/msg_prot.h +++ b/include/linux/sunrpc/msg_prot.h @@ -69,15 +69,17 @@ enum rpc_reject_stat { }; enum rpc_auth_stat { - RPC_AUTH_OK = 0, - RPC_AUTH_BADCRED = 1, - RPC_AUTH_REJECTEDCRED = 2, - RPC_AUTH_BADVERF = 3, - RPC_AUTH_REJECTEDVERF = 4, - RPC_AUTH_TOOWEAK = 5, + RPC_AUTH_OK = 0, /* success */ + RPC_AUTH_BADCRED = 1, /* bad credential (seal broken) */ + RPC_AUTH_REJECTEDCRED = 2, /* client must begin new session */ + RPC_AUTH_BADVERF = 3, /* bad verifier (seal broken) */ + RPC_AUTH_REJECTEDVERF = 4, /* verifier expired or replayed */ + RPC_AUTH_TOOWEAK = 5, /* rejected for security reasons */ + RPC_AUTH_INVALIDRESP = 6, /* bogus response verifier */ + RPC_AUTH_FAILED = 7, /* reason unknown */ /* RPCSEC_GSS errors */ - RPCSEC_GSS_CREDPROBLEM = 13, - RPCSEC_GSS_CTXPROBLEM = 14 + RPCSEC_GSS_CREDPROBLEM = 13, /* no credentials for user */ + RPCSEC_GSS_CTXPROBLEM = 14 /* problem with context */ }; #define RPC_MAXNETNAMELEN 256 diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 3b35b6f6533a..2cb406f8ff4e 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -98,7 +98,7 @@ static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) { } struct rpc_clnt; -extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); +extern int rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *); extern int rpc_remove_client_dir(struct rpc_clnt *); extern void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh); @@ -127,9 +127,9 @@ extern void rpc_remove_cache_dir(struct dentry *); struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags); void rpc_destroy_pipe_data(struct rpc_pipe *pipe); -extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *, +extern int rpc_mkpipe_dentry(struct dentry *, const char *, void *, struct rpc_pipe *); -extern int rpc_unlink(struct dentry *); +extern void rpc_unlink(struct rpc_pipe *); extern int register_rpc_pipefs(void); extern void unregister_rpc_pipefs(void); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 48666b83fe68..40cbe81360ed 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -245,10 +245,10 @@ struct svc_rqst { * initialisation success. */ - unsigned long bc_to_initval; - unsigned int bc_to_retries; - void ** rq_lease_breaker; /* The v4 client breaking a lease */ + unsigned long bc_to_initval; + unsigned int bc_to_retries; unsigned int rq_status_counter; /* RPC processing counter */ + void **rq_lease_breaker; /* The v4 client breaking a lease */ }; /* bits for rq_flags */ diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h index 2e111153f7cd..4b92fec23a49 100644 --- a/include/linux/sunrpc/svcauth.h +++ b/include/linux/sunrpc/svcauth.h @@ -86,7 +86,6 @@ struct auth_domain { enum svc_auth_status { SVC_GARBAGE = 1, - SVC_SYSERR, SVC_VALID, SVC_NEGATIVE, SVC_OK, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index a2ab813a9800..e3358c630ba1 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -119,6 +119,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) #define rpc_autherr_badverf cpu_to_be32(RPC_AUTH_BADVERF) #define rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF) #define rpc_autherr_tooweak cpu_to_be32(RPC_AUTH_TOOWEAK) +#define rpc_autherr_invalidresp cpu_to_be32(RPC_AUTH_INVALIDRESP) +#define rpc_autherr_failed cpu_to_be32(RPC_AUTH_FAILED) #define rpcsec_gsserr_credproblem cpu_to_be32(RPCSEC_GSS_CREDPROBLEM) #define rpcsec_gsserr_ctxproblem cpu_to_be32(RPCSEC_GSS_CTXPROBLEM) @@ -242,8 +244,7 @@ typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst); -extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, - struct page **pages, struct rpc_rqst *rqst); +void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes); extern void __xdr_commit_encode(struct xdr_stream *xdr); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index b1c76c8f2c82..6a3f92098872 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -446,6 +446,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb); extern void ksys_sync_helper(void); extern void pm_report_hw_sleep_time(u64 t); extern void pm_report_max_hw_sleep(u64 t); +void pm_restrict_gfp_mask(void); +void pm_restore_gfp_mask(void); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ @@ -492,6 +494,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) static inline void pm_report_hw_sleep_time(u64 t) {}; static inline void pm_report_max_hw_sleep(u64 t) {}; +static inline void pm_restrict_gfp_mask(void) {} +static inline void pm_restore_gfp_mask(void) {} + static inline void ksys_sync_helper(void) {} #define pm_notifier(fn, pri) do { (void)(fn); } while (0) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e5603cc91963..77f45e5d4413 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -78,6 +78,7 @@ struct cachestat; struct statmount; struct mnt_id_req; struct xattr_args; +struct file_attr; #include <linux/types.h> #include <linux/aio_abi.h> @@ -371,6 +372,12 @@ asmlinkage long sys_removexattrat(int dfd, const char __user *path, asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); +asmlinkage long sys_file_getattr(int dfd, const char __user *filename, + struct file_attr __user *attr, size_t usize, + unsigned int at_flags); +asmlinkage long sys_file_setattr(int dfd, const char __user *filename, + struct file_attr __user *attr, size_t usize, + unsigned int at_flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_eventfd2(unsigned int count, int flags); asmlinkage long sys_epoll_create1(int flags); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index a3d8305e88a5..9894c104dc93 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -182,7 +182,7 @@ struct tpm_chip { unsigned long duration[TPM_NUM_DURATIONS]; /* jiffies */ bool duration_adjusted; - struct dentry *bios_dir[TPM_NUM_EVENT_LOG_FILES]; + struct dentry *bios_dir; const struct attribute_group *groups[3 + TPM_MAX_HASHES]; unsigned int groups_cnt; diff --git a/include/linux/usb.h b/include/linux/usb.h index 1b2545b4363b..92c752f5446f 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -614,6 +614,7 @@ struct usb3_lpm_parameters { * FIXME -- complete doc * @authenticated: Crypto authentication passed * @tunnel_mode: Connection native or tunneled over USB4 + * @usb4_link: device link to the USB4 host interface * @lpm_capable: device supports LPM * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM @@ -724,6 +725,7 @@ struct usb_device { unsigned reset_resume:1; unsigned port_is_suspended:1; enum usb_link_tunnel_mode tunnel_mode; + struct device_link *usb4_link; int slot_id; struct usb2_lpm_parameters l1_params; diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h index f2da264d9c14..acb0ad03bdac 100644 --- a/include/linux/usb/typec_dp.h +++ b/include/linux/usb/typec_dp.h @@ -57,6 +57,7 @@ enum { DP_PIN_ASSIGN_D, DP_PIN_ASSIGN_E, DP_PIN_ASSIGN_F, /* Not supported after v1.0b */ + DP_PIN_ASSIGN_MAX, }; /* DisplayPort alt mode specific commands */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 91a3ce9a2687..9e15a088ba38 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NUMA_HINT_FAULTS, NUMA_HINT_FAULTS_LOCAL, NUMA_PAGE_MIGRATE, - NUMA_TASK_MIGRATE, - NUMA_TASK_SWAP, #endif #ifdef CONFIG_MIGRATION PGMIGRATE_SUCCESS, PGMIGRATE_FAIL, diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d56e6e135158..d40e978126e3 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -243,8 +243,8 @@ int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); -#ifdef CONFIG_BPF_SYSCALL extern struct proto vsock_proto; +#ifdef CONFIG_BPF_SYSCALL int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void __init vsock_bpf_build_proto(void); #else diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 82cbd54443ac..c79901f2dc2a 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -377,6 +377,8 @@ enum { * This quirk must be set before hci_register_dev is called. */ HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, + + __HCI_NUM_QUIRKS, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9fc8f544e20e..f79f59e67114 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -464,7 +464,7 @@ struct hci_dev { unsigned int auto_accept_delay; - unsigned long quirks; + DECLARE_BITMAP(quirk_flags, __HCI_NUM_QUIRKS); atomic_t cmd_cnt; unsigned int acl_cnt; @@ -656,6 +656,10 @@ struct hci_dev { u8 (*classify_pkt_type)(struct hci_dev *hdev, struct sk_buff *skb); }; +#define hci_set_quirk(hdev, nr) set_bit((nr), (hdev)->quirk_flags) +#define hci_clear_quirk(hdev, nr) clear_bit((nr), (hdev)->quirk_flags) +#define hci_test_quirk(hdev, nr) test_bit((nr), (hdev)->quirk_flags) + #define HCI_PHY_HANDLE(handle) (handle & 0xff) enum conn_reasons { @@ -829,20 +833,20 @@ extern struct mutex hci_cb_list_lock; #define hci_dev_test_and_clear_flag(hdev, nr) test_and_clear_bit((nr), (hdev)->dev_flags) #define hci_dev_test_and_change_flag(hdev, nr) test_and_change_bit((nr), (hdev)->dev_flags) -#define hci_dev_clear_volatile_flags(hdev) \ - do { \ - hci_dev_clear_flag(hdev, HCI_LE_SCAN); \ - hci_dev_clear_flag(hdev, HCI_LE_ADV); \ - hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);\ - hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); \ - hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); \ +#define hci_dev_clear_volatile_flags(hdev) \ + do { \ + hci_dev_clear_flag((hdev), HCI_LE_SCAN); \ + hci_dev_clear_flag((hdev), HCI_LE_ADV); \ + hci_dev_clear_flag((hdev), HCI_LL_RPA_RESOLUTION); \ + hci_dev_clear_flag((hdev), HCI_PERIODIC_INQ); \ + hci_dev_clear_flag((hdev), HCI_QUALITY_REPORT); \ } while (0) #define hci_dev_le_state_simultaneous(hdev) \ - (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \ - (hdev->le_states[4] & 0x08) && /* Central */ \ - (hdev->le_states[4] & 0x40) && /* Peripheral */ \ - (hdev->le_states[3] & 0x10)) /* Simultaneous */ + (!hci_test_quirk((hdev), HCI_QUIRK_BROKEN_LE_STATES) && \ + ((hdev)->le_states[4] & 0x08) && /* Central */ \ + ((hdev)->le_states[4] & 0x40) && /* Peripheral */ \ + ((hdev)->le_states[3] & 0x10)) /* Simultaneous */ /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); @@ -1350,8 +1354,7 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle, __u16 state) rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) || - c->state != state) + if (c->type != BIS_LINK || c->state != state) continue; if (handle == c->iso_qos.bcast.big) { @@ -1932,8 +1935,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M)) #define le_coded_capable(dev) (((dev)->le_features[1] & HCI_LE_PHY_CODED) && \ - !test_bit(HCI_QUIRK_BROKEN_LE_CODED, \ - &(dev)->quirks)) + !hci_test_quirk((dev), \ + HCI_QUIRK_BROKEN_LE_CODED)) #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) @@ -1941,31 +1944,31 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ - (hdev->commands[39] & 0x04)) + ((dev)->commands[39] & 0x04)) #define read_key_size_capable(dev) \ ((dev)->commands[20] & 0x10 && \ - !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE)) #define read_voice_setting_capable(dev) \ ((dev)->commands[9] & 0x04 && \ - !test_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_READ_VOICE_SETTING)) /* Use enhanced synchronous connection if command is supported and its quirk * has not been set. */ #define enhanced_sync_conn_capable(dev) \ (((dev)->commands[29] & 0x08) && \ - !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ ((dev)->commands[37] & 0x40) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_SCAN)) /* Use ext create connection if command is supported */ #define use_ext_conn(dev) (((dev)->commands[37] & 0x80) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, &(dev)->quirks)) + !hci_test_quirk((dev), HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) @@ -1980,8 +1983,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); */ #define use_enhanced_conn_complete(dev) ((ll_privacy_capable(dev) || \ ext_adv_capable(dev)) && \ - !test_bit(HCI_QUIRK_BROKEN_EXT_CREATE_CONN, \ - &(dev)->quirks)) + !hci_test_quirk((dev), \ + HCI_QUIRK_BROKEN_EXT_CREATE_CONN)) /* Periodic advertising support */ #define per_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_PERIODIC_ADV)) @@ -1998,7 +2001,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ - (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) + (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d1848dc8ec99..10248d527616 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2690,7 +2690,7 @@ struct cfg80211_scan_request { s8 tsf_report_link_id; /* keep last */ - struct ieee80211_channel *channels[] __counted_by(n_channels); + struct ieee80211_channel *channels[]; }; static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 3f02a45773e8..ca26274196b9 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -306,8 +306,19 @@ static inline bool nf_ct_is_expired(const struct nf_conn *ct) /* use after obtaining a reference count */ static inline bool nf_ct_should_gc(const struct nf_conn *ct) { - return nf_ct_is_expired(ct) && nf_ct_is_confirmed(ct) && - !nf_ct_is_dying(ct); + if (!nf_ct_is_confirmed(ct)) + return false; + + /* load ct->timeout after is_confirmed() test. + * Pairs with __nf_conntrack_confirm() which: + * 1. Increases ct->timeout value + * 2. Inserts ct into rcu hlist + * 3. Sets the confirmed bit + * 4. Unlocks the hlist lock + */ + smp_acquire__after_ctrl_dep(); + + return nf_ct_is_expired(ct) && !nf_ct_is_dying(ct); } #define NF_CT_DAY (86400 * HZ) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d711642e78b5..c003cd194fa2 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -370,7 +370,7 @@ static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb) static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto) { - if (!pskb_may_pull(skb, PPPOE_SES_HLEN)) + if (!pskb_may_pull(skb, ETH_HLEN + PPPOE_SES_HLEN)) return false; *inner_proto = __nf_flow_pppoe_proto(skb); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index e4d8e451e935..5e49619ae49c 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1142,11 +1142,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); -struct nft_hook; -void nf_tables_chain_device_notify(const struct nft_chain *chain, - const struct nft_hook *hook, - const struct net_device *dev, int event); - enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, NFT_CHAIN_T_ROUTE, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index d7b7b6cd4aa1..8a75c73fc555 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -114,7 +114,6 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); -void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate); @@ -290,4 +289,28 @@ static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, return true; } +static inline void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc) +{ + if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); + qdisc->flags |= TCQ_F_WARN_NONWC; + } +} + +static inline unsigned int qdisc_peek_len(struct Qdisc *sch) +{ + struct sk_buff *skb; + unsigned int len; + + skb = sch->ops->peek(sch); + if (unlikely(skb == NULL)) { + qdisc_warn_nonwc("qdisc_peek_len", sch); + return 0; + } + len = qdisc_pkt_len(skb); + + return len; +} + #endif diff --git a/include/net/scm.h b/include/net/scm.h index 84c4707e78a5..c52519669349 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -69,7 +69,7 @@ static __inline__ void unix_get_peersec_dgram(struct socket *sock, struct scm_co static __inline__ void scm_set_cred(struct scm_cookie *scm, struct pid *pid, kuid_t uid, kgid_t gid) { - scm->pid = get_pid(pid); + scm->pid = get_pid(pid); scm->creds.pid = pid_vnr(pid); scm->creds.uid = uid; scm->creds.gid = gid; @@ -78,7 +78,7 @@ static __inline__ void scm_set_cred(struct scm_cookie *scm, static __inline__ void scm_destroy_cred(struct scm_cookie *scm) { put_pid(scm->pid); - scm->pid = NULL; + scm->pid = NULL; } static __inline__ void scm_destroy(struct scm_cookie *scm) diff --git a/include/net/sock.h b/include/net/sock.h index 4c37015b7cf7..131f3662426f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2677,6 +2677,10 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); +bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk); +int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, + struct timespec64 *ts); + static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a21e276dbe44..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -441,7 +441,6 @@ int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); -void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { struct module *owner; @@ -474,7 +473,7 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); -void xfrm_set_type_offload(struct xfrm_state *x); +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load); static inline void xfrm_unset_type_offload(struct xfrm_state *x) { if (!x->type_offload) @@ -916,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -926,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1770,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index bebc252db865..d54fe354b390 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -144,7 +144,8 @@ FLUSH_STATES #define EXTENT_FLAGS \ { EXTENT_DIRTY, "DIRTY"}, \ { EXTENT_LOCKED, "LOCKED"}, \ - { EXTENT_NEW, "NEW"}, \ + { EXTENT_DIRTY_LOG1, "DIRTY_LOG1"}, \ + { EXTENT_DIRTY_LOG2, "DIRTY_LOG2"}, \ { EXTENT_DELALLOC, "DELALLOC"}, \ { EXTENT_DEFRAG, "DEFRAG"}, \ { EXTENT_BOUNDARY, "BOUNDARY"}, \ @@ -1095,7 +1096,7 @@ TRACE_EVENT(btrfs_cow_block, TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = btrfs_root_id(root); __entry->buf_start = buf->start; - __entry->refs = atomic_read(&buf->refs); + __entry->refs = refcount_read(&buf->refs); __entry->cow_start = cow->start; __entry->buf_level = btrfs_header_level(buf); __entry->cow_level = btrfs_header_level(cow); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 156908641e68..6f9cf2811733 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -92,7 +92,8 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { FALLOC_FL_KEEP_SIZE, "KEEP_SIZE"}, \ { FALLOC_FL_PUNCH_HOLE, "PUNCH_HOLE"}, \ { FALLOC_FL_COLLAPSE_RANGE, "COLLAPSE_RANGE"}, \ - { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}) + { FALLOC_FL_ZERO_RANGE, "ZERO_RANGE"}, \ + { FALLOC_FL_WRITE_ZEROES, "WRITE_ZEROES"}) TRACE_DEFINE_ENUM(EXT4_FC_REASON_XATTR); TRACE_DEFINE_ENUM(EXT4_FC_REASON_CROSS_RENAME); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 333d2e38dd2c..64a382fbc31a 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -50,12 +50,15 @@ #define netfs_rreq_traces \ EM(netfs_rreq_trace_assess, "ASSESS ") \ - EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_collect, "COLLECT") \ EM(netfs_rreq_trace_complete, "COMPLET") \ + EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ + EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ + EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_abandon, "S-ABNDN") \ @@ -63,13 +66,15 @@ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ + EM(netfs_rreq_trace_unpause, "UNPAUSE") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ - EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ - EM(netfs_rreq_trace_wait_queue, "WAIT-Q ") \ + EM(netfs_rreq_trace_wait_pause, "--PAUSED--") \ + EM(netfs_rreq_trace_wait_quiesce, "WAIT-QUIESCE") \ + EM(netfs_rreq_trace_waited_ip, "DONE-IP") \ + EM(netfs_rreq_trace_waited_pause, "--UNPAUSED--") \ + EM(netfs_rreq_trace_waited_quiesce, "DONE-QUIESCE") \ EM(netfs_rreq_trace_wake_ip, "WAKE-IP") \ EM(netfs_rreq_trace_wake_queue, "WAKE-Q ") \ - EM(netfs_rreq_trace_woke_queue, "WOKE-Q ") \ - EM(netfs_rreq_trace_unpause, "UNPAUSE") \ E_(netfs_rreq_trace_write_done, "WR-DONE") #define netfs_sreq_sources \ @@ -82,6 +87,7 @@ E_(NETFS_WRITE_TO_CACHE, "WRIT") #define netfs_sreq_traces \ + EM(netfs_sreq_trace_abandoned, "ABNDN") \ EM(netfs_sreq_trace_add_donations, "+DON ") \ EM(netfs_sreq_trace_added, "ADD ") \ EM(netfs_sreq_trace_cache_nowrite, "CA-NW") \ @@ -89,6 +95,7 @@ EM(netfs_sreq_trace_cache_write, "CA-WR") \ EM(netfs_sreq_trace_cancel, "CANCL") \ EM(netfs_sreq_trace_clear, "CLEAR") \ + EM(netfs_sreq_trace_consumed, "CONSM") \ EM(netfs_sreq_trace_discard, "DSCRD") \ EM(netfs_sreq_trace_donate_to_prev, "DON-P") \ EM(netfs_sreq_trace_donate_to_next, "DON-N") \ @@ -96,7 +103,12 @@ EM(netfs_sreq_trace_fail, "FAIL ") \ EM(netfs_sreq_trace_free, "FREE ") \ EM(netfs_sreq_trace_hit_eof, "EOF ") \ - EM(netfs_sreq_trace_io_progress, "IO ") \ + EM(netfs_sreq_trace_io_bad, "I-BAD") \ + EM(netfs_sreq_trace_io_malformed, "I-MLF") \ + EM(netfs_sreq_trace_io_unknown, "I-UNK") \ + EM(netfs_sreq_trace_io_progress, "I-OK ") \ + EM(netfs_sreq_trace_io_req_submitted, "I-RSB") \ + EM(netfs_sreq_trace_io_retry_needed, "I-RTR") \ EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_need_clear, "N-CLR") \ EM(netfs_sreq_trace_partial_read, "PARTR") \ @@ -142,8 +154,8 @@ #define netfs_sreq_ref_traces \ EM(netfs_sreq_trace_get_copy_to_cache, "GET COPY2C ") \ - EM(netfs_sreq_trace_get_resubmit, "GET RESUBMIT") \ - EM(netfs_sreq_trace_get_submit, "GET SUBMIT") \ + EM(netfs_sreq_trace_get_resubmit, "GET RESUBMT") \ + EM(netfs_sreq_trace_get_submit, "GET SUBMIT ") \ EM(netfs_sreq_trace_get_short_read, "GET SHORTRD") \ EM(netfs_sreq_trace_new, "NEW ") \ EM(netfs_sreq_trace_put_abandon, "PUT ABANDON") \ @@ -366,7 +378,7 @@ TRACE_EVENT(netfs_sreq, __entry->slot = sreq->io_iter.folioq_slot; ), - TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d", + TP_printk("R=%08x[%x] %s %s f=%03x s=%llx %zx/%zx s=%u e=%d", __entry->rreq, __entry->index, __print_symbolic(__entry->source, netfs_sreq_sources), __print_symbolic(__entry->what, netfs_sreq_traces), @@ -548,6 +560,35 @@ TRACE_EVENT(netfs_write, __entry->start, __entry->start + __entry->len - 1) ); +TRACE_EVENT(netfs_copy2cache, + TP_PROTO(const struct netfs_io_request *rreq, + const struct netfs_io_request *creq), + + TP_ARGS(rreq, creq), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, creq) + __field(unsigned int, cookie) + __field(unsigned int, ino) + ), + + TP_fast_assign( + struct netfs_inode *__ctx = netfs_inode(rreq->inode); + struct fscache_cookie *__cookie = netfs_i_cookie(__ctx); + __entry->rreq = rreq->debug_id; + __entry->creq = creq->debug_id; + __entry->cookie = __cookie ? __cookie->debug_id : 0; + __entry->ino = rreq->inode->i_ino; + ), + + TP_printk("R=%08x CR=%08x c=%08x i=%x ", + __entry->rreq, + __entry->creq, + __entry->cookie, + __entry->ino) + ); + TRACE_EVENT(netfs_collect, TP_PROTO(const struct netfs_io_request *wreq), diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 378d2dfc7392..de6f6d25767c 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -322,20 +322,24 @@ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_release_recvmsg_q, "PUT rls-rcmq") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ - EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ + EM(rxrpc_call_see_already_released, "SEE alrdy-rl") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ EM(rxrpc_call_see_conn_abort, "SEE conn-abt") \ + EM(rxrpc_call_see_discard, "SEE discard ") \ EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_notify_released, "SEE nfy-rlsd") \ + EM(rxrpc_call_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_call_see_release, "SEE release ") \ EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ EM(rxrpc_call_see_waiting_call, "SEE q-conn ") \ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index aad697da1580..750ecce56930 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1691,7 +1691,6 @@ SVC_RQST_FLAG_LIST __print_flags(flags, "|", SVC_RQST_FLAG_LIST) TRACE_DEFINE_ENUM(SVC_GARBAGE); -TRACE_DEFINE_ENUM(SVC_SYSERR); TRACE_DEFINE_ENUM(SVC_VALID); TRACE_DEFINE_ENUM(SVC_NEGATIVE); TRACE_DEFINE_ENUM(SVC_OK); @@ -1704,7 +1703,6 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE); #define show_svc_auth_status(status) \ __print_symbolic(status, \ { SVC_GARBAGE, "SVC_GARBAGE" }, \ - { SVC_SYSERR, "SVC_SYSERR" }, \ { SVC_VALID, "SVC_VALID" }, \ { SVC_NEGATIVE, "SVC_NEGATIVE" }, \ { SVC_OK, "SVC_OK" }, \ @@ -2123,22 +2121,35 @@ TRACE_EVENT(svc_xprt_accept, ) ); -TRACE_EVENT(svc_wake_up, - TP_PROTO(int pid), +DECLARE_EVENT_CLASS(svc_pool_thread_event, + TP_PROTO(const struct svc_pool *pool, pid_t pid), - TP_ARGS(pid), + TP_ARGS(pool, pid), TP_STRUCT__entry( - __field(int, pid) + __field(unsigned int, pool_id) + __field(pid_t, pid) ), TP_fast_assign( + __entry->pool_id = pool->sp_id; __entry->pid = pid; ), - TP_printk("pid=%d", __entry->pid) + TP_printk("pool=%u pid=%d", __entry->pool_id, __entry->pid) ); +#define DEFINE_SVC_POOL_THREAD_EVENT(name) \ + DEFINE_EVENT(svc_pool_thread_event, svc_pool_thread_##name, \ + TP_PROTO( \ + const struct svc_pool *pool, pid_t pid \ + ), \ + TP_ARGS(pool, pid)) + +DEFINE_SVC_POOL_THREAD_EVENT(wake); +DEFINE_SVC_POOL_THREAD_EVENT(running); +DEFINE_SVC_POOL_THREAD_EVENT(noidle); + TRACE_EVENT(svc_alloc_arg_err, TP_PROTO( unsigned int requested, diff --git a/include/uapi/asm-generic/param.h b/include/uapi/asm-generic/param.h index baad02ea7f93..3ed505dfea13 100644 --- a/include/uapi/asm-generic/param.h +++ b/include/uapi/asm-generic/param.h @@ -2,8 +2,12 @@ #ifndef _UAPI__ASM_GENERIC_PARAM_H #define _UAPI__ASM_GENERIC_PARAM_H +#ifndef __USER_HZ +#define __USER_HZ 100 +#endif + #ifndef HZ -#define HZ 100 +#define HZ __USER_HZ #endif #ifndef EXEC_PAGESIZE diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 2892a45023af..04e0077fb4c9 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat) #define __NR_open_tree_attr 467 __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) +/* fs/inode.c */ +#define __NR_file_getattr 468 +__SYSCALL(__NR_file_getattr, sys_file_getattr) +#define __NR_file_setattr 469 +__SYSCALL(__NR_file_setattr, sys_file_setattr) + #undef __NR_syscalls -#define __NR_syscalls 468 +#define __NR_syscalls 470 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h index 682b406e1067..a04afef9efca 100644 --- a/include/uapi/linux/bits.h +++ b/include/uapi/linux/bits.h @@ -4,9 +4,9 @@ #ifndef _UAPI_LINUX_BITS_H #define _UAPI_LINUX_BITS_H -#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h)))) +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) -#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) #define __GENMASK_U128(h, l) \ ((_BIT128((h)) << 1) - (_BIT128(l))) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index dd02160015b2..8e710bbb688e 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -616,8 +616,11 @@ struct btrfs_ioctl_clone_range_args { #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 #define BTRFS_DEFRAG_RANGE_COMPRESS_LEVEL 4 +/* Request no compression on the range (uncompress if necessary). */ +#define BTRFS_DEFRAG_RANGE_NOCOMPRESS 8 #define BTRFS_DEFRAG_RANGE_FLAGS_SUPP (BTRFS_DEFRAG_RANGE_COMPRESS | \ BTRFS_DEFRAG_RANGE_COMPRESS_LEVEL | \ + BTRFS_DEFRAG_RANGE_NOCOMPRESS | \ BTRFS_DEFRAG_RANGE_START_IO) struct btrfs_ioctl_defrag_range_args { diff --git a/include/uapi/linux/coredump.h b/include/uapi/linux/coredump.h new file mode 100644 index 000000000000..dc3789b78af0 --- /dev/null +++ b/include/uapi/linux/coredump.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_COREDUMP_H +#define _UAPI_LINUX_COREDUMP_H + +#include <linux/types.h> + +/** + * coredump_{req,ack} flags + * @COREDUMP_KERNEL: kernel writes coredump + * @COREDUMP_USERSPACE: userspace writes coredump + * @COREDUMP_REJECT: don't generate coredump + * @COREDUMP_WAIT: wait for coredump server + */ +enum { + COREDUMP_KERNEL = (1ULL << 0), + COREDUMP_USERSPACE = (1ULL << 1), + COREDUMP_REJECT = (1ULL << 2), + COREDUMP_WAIT = (1ULL << 3), +}; + +/** + * struct coredump_req - message kernel sends to userspace + * @size: size of struct coredump_req + * @size_ack: known size of struct coredump_ack on this kernel + * @mask: supported features + * + * When a coredump happens the kernel will connect to the coredump + * socket and send a coredump request to the coredump server. The @size + * member is set to the size of struct coredump_req and provides a hint + * to userspace how much data can be read. Userspace may use MSG_PEEK to + * peek the size of struct coredump_req and then choose to consume it in + * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0 + * request. If the size the kernel sends is larger userspace simply + * discards any remaining data. + * + * The coredump_req->mask member is set to the currently know features. + * Userspace may only set coredump_ack->mask to the bits raised by the + * kernel in coredump_req->mask. + * + * The coredump_req->size_ack member is set by the kernel to the size of + * struct coredump_ack the kernel knows. Userspace may only send up to + * coredump_req->size_ack bytes to the kernel and must set + * coredump_ack->size accordingly. + */ +struct coredump_req { + __u32 size; + __u32 size_ack; + __u64 mask; +}; + +enum { + COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * struct coredump_ack - message userspace sends to kernel + * @size: size of the struct + * @spare: unused + * @mask: features kernel is supposed to use + * + * The @size member must be set to the size of struct coredump_ack. It + * may never exceed what the kernel returned in coredump_req->size_ack + * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <= + * coredump_req->size_ack). + * + * The @mask member must be set to the features the coredump server + * wants the kernel to use. Only bits the kernel returned in + * coredump_req->mask may be set. + */ +struct coredump_ack { + __u32 size; + __u32 spare; + __u64 mask; +}; + +enum { + COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * enum coredump_mark - Markers for the coredump socket + * + * The kernel will place a single byte on the coredump socket. The + * markers notify userspace whether the coredump ack succeeded or + * failed. + * + * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small + * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big + * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid + * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options + * @COREDUMP_MARK_REQACK: the coredump request and ack was successful + * @__COREDUMP_MARK_MAX: the maximum coredump mark value + */ +enum coredump_mark { + COREDUMP_MARK_REQACK = 0U, + COREDUMP_MARK_MINSIZE = 1U, + COREDUMP_MARK_MAXSIZE = 2U, + COREDUMP_MARK_UNSUPPORTED = 3U, + COREDUMP_MARK_CONFLICTING = 4U, + __COREDUMP_MARK_MAX = (1U << 31), +}; + +#endif /* _UAPI_LINUX_COREDUMP_H */ diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h index 5810371ed72b..1f9ca757d02d 100644 --- a/include/uapi/linux/falloc.h +++ b/include/uapi/linux/falloc.h @@ -78,4 +78,21 @@ */ #define FALLOC_FL_UNSHARE_RANGE 0x40 +/* + * FALLOC_FL_WRITE_ZEROES zeroes a specified file range in such a way that + * subsequent writes to that range do not require further changes to the file + * mapping metadata. This flag is beneficial for subsequent pure overwriting + * within this range, as it can save on block allocation and, consequently, + * significant metadata changes. Therefore, filesystems that always require + * out-of-place writes should not support this flag. + * + * Different filesystems may implement different limitations on the + * granularity of the zeroing operation. Most will preferably be accelerated + * by submitting write zeroes command if the backing storage supports, which + * may not physically write zeros to the media. + * + * This flag cannot be specified in conjunction with the FALLOC_FL_KEEP_SIZE. + */ +#define FALLOC_FL_WRITE_ZEROES 0x80 + #endif /* _UAPI_FALLOC_H_ */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index a15ac2fa4b20..f291ab4f94eb 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -90,10 +90,28 @@ #define DN_ATTRIB 0x00000020 /* File changed attibutes */ #define DN_MULTISHOT 0x80000000 /* Don't remove notifier */ +/* Reserved kernel ranges [-100], [-10000, -40000]. */ #define AT_FDCWD -100 /* Special value for dirfd used to indicate openat should use the current working directory. */ +/* + * The concept of process and threads in userland and the kernel is a confusing + * one - within the kernel every thread is a 'task' with its own individual PID, + * however from userland's point of view threads are grouped by a single PID, + * which is that of the 'thread group leader', typically the first thread + * spawned. + * + * To cut the Gideon knot, for internal kernel usage, we refer to + * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel + * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread + * group leader... + */ +#define PIDFD_SELF_THREAD -10000 /* Current thread. */ +#define PIDFD_SELF_THREAD_GROUP -10001 /* Current thread group leader. */ + +#define FD_PIDFS_ROOT -10002 /* Root of the pidfs filesystem */ +#define FD_INVALID -10009 /* Invalid file descriptor: -10000 - EBADF = -10009 */ /* Generic flags for the *at(2) family of syscalls. */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 0098b0ce8ccb..0bd678a4a10e 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -60,6 +60,17 @@ #define RENAME_EXCHANGE (1 << 1) /* Exchange source and dest */ #define RENAME_WHITEOUT (1 << 2) /* Whiteout source */ +/* + * The root inode of procfs is guaranteed to always have the same inode number. + * For programs that make heavy use of procfs, verifying that the root is a + * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH}) + * will allow you to make sure you are never tricked into operating on the + * wrong procfs file. + */ +enum procfs_ino { + PROCFS_ROOT_INO = 1, +}; + struct file_clone_range { __s64 src_fd; __u64 src_offset; @@ -91,6 +102,63 @@ struct fs_sysfs_path { __u8 name[128]; }; +/* Protection info capability flags */ +#define LBMD_PI_CAP_INTEGRITY (1 << 0) +#define LBMD_PI_CAP_REFTAG (1 << 1) + +/* Checksum types for Protection Information */ +#define LBMD_PI_CSUM_NONE 0 +#define LBMD_PI_CSUM_IP 1 +#define LBMD_PI_CSUM_CRC16_T10DIF 2 +#define LBMD_PI_CSUM_CRC64_NVME 4 + +/* sizeof first published struct */ +#define LBMD_SIZE_VER0 16 + +/* + * Logical block metadata capability descriptor + * If the device does not support metadata, all the fields will be zero. + * Applications must check lbmd_flags to determine whether metadata is + * supported or not. + */ +struct logical_block_metadata_cap { + /* Bitmask of logical block metadata capability flags */ + __u32 lbmd_flags; + /* + * The amount of data described by each unit of logical block + * metadata + */ + __u16 lbmd_interval; + /* + * Size in bytes of the logical block metadata associated with each + * interval + */ + __u8 lbmd_size; + /* + * Size in bytes of the opaque block tag associated with each + * interval + */ + __u8 lbmd_opaque_size; + /* + * Offset in bytes of the opaque block tag within the logical block + * metadata + */ + __u8 lbmd_opaque_offset; + /* Size in bytes of the T10 PI tuple associated with each interval */ + __u8 lbmd_pi_size; + /* Offset in bytes of T10 PI tuple within the logical block metadata */ + __u8 lbmd_pi_offset; + /* T10 PI guard tag type */ + __u8 lbmd_guard_tag_type; + /* Size in bytes of the T10 PI application tag */ + __u8 lbmd_app_tag_size; + /* Size in bytes of the T10 PI reference tag */ + __u8 lbmd_ref_tag_size; + /* Size in bytes of the T10 PI storage tag */ + __u8 lbmd_storage_tag_size; + __u8 pad; +}; + /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */ #define FILE_DEDUPE_RANGE_SAME 0 #define FILE_DEDUPE_RANGE_DIFFERS 1 @@ -149,6 +217,24 @@ struct fsxattr { }; /* + * Variable size structure for file_[sg]et_attr(). + * + * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'. + * As this structure is passed to/from userspace with its size, this can + * be versioned based on the size. + */ +struct file_attr { + __u64 fa_xflags; /* xflags field value (get/set) */ + __u32 fa_extsize; /* extsize field value (get/set)*/ + __u32 fa_nextents; /* nextents field value (get) */ + __u32 fa_projid; /* project identifier (get/set) */ + __u32 fa_cowextsize; /* CoW extsize field value (get/set) */ +}; + +#define FILE_ATTR_SIZE_VER0 24 +#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0 + +/* * Flags for the fsx_xflags field */ #define FS_XFLAG_REALTIME 0x00000001 /* data in realtime volume */ @@ -247,6 +333,8 @@ struct fsxattr { * also /sys/kernel/debug/ for filesystems with debugfs exports */ #define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path) +/* Get logical block metadata capability details */ +#define FS_IOC_GETLBMD_CAP _IOWR(0x15, 2, struct logical_block_metadata_cap) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index cfd17e382082..b8a0e70ee2fd 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -50,7 +50,7 @@ struct io_uring_sqe { }; __u32 len; /* buffer size or number of iovecs */ union { - __kernel_rwf_t rw_flags; + __u32 rw_flags; __u32 fsync_flags; __u16 poll_events; /* compatibility */ __u32 poll32_events; /* word-reversed for BE */ @@ -449,6 +449,7 @@ enum io_uring_msg_ring_flags { #define IORING_NOP_FILE (1U << 1) #define IORING_NOP_FIXED_FILE (1U << 2) #define IORING_NOP_FIXED_BUFFER (1U << 3) +#define IORING_NOP_TW (1U << 4) /* * IO completion data structure (Completion Queue Entry) @@ -968,6 +969,22 @@ enum io_uring_socket_op { SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, SOCKET_URING_OP_SETSOCKOPT, + SOCKET_URING_OP_TX_TIMESTAMP, +}; + +/* + * SOCKET_URING_OP_TX_TIMESTAMP definitions + */ + +#define IORING_TIMESTAMP_HW_SHIFT 16 +/* The cqe->flags bit from which the timestamp type is stored */ +#define IORING_TIMESTAMP_TYPE_SHIFT (IORING_TIMESTAMP_HW_SHIFT + 1) +/* The cqe->flags flag signifying whether it's a hardware timestamp */ +#define IORING_CQE_F_TSTAMP_HW ((__u32)1 << IORING_TIMESTAMP_HW_SHIFT) + +struct io_timespec { + __u64 tv_sec; + __u64 tv_nsec; }; /* Zero copy receive refill queue entry */ diff --git a/include/uapi/linux/io_uring/mock_file.h b/include/uapi/linux/io_uring/mock_file.h new file mode 100644 index 000000000000..debeee8e4527 --- /dev/null +++ b/include/uapi/linux/io_uring/mock_file.h @@ -0,0 +1,47 @@ +#ifndef LINUX_IO_URING_MOCK_FILE_H +#define LINUX_IO_URING_MOCK_FILE_H + +#include <linux/types.h> + +enum { + IORING_MOCK_FEAT_CMD_COPY, + IORING_MOCK_FEAT_RW_ZERO, + IORING_MOCK_FEAT_RW_NOWAIT, + IORING_MOCK_FEAT_RW_ASYNC, + IORING_MOCK_FEAT_POLL, + + IORING_MOCK_FEAT_END, +}; + +struct io_uring_mock_probe { + __u64 features; + __u64 __resv[9]; +}; + +enum { + IORING_MOCK_CREATE_F_SUPPORT_NOWAIT = 1, + IORING_MOCK_CREATE_F_POLL = 2, +}; + +struct io_uring_mock_create { + __u32 out_fd; + __u32 flags; + __u64 file_size; + __u64 rw_delay_ns; + __u64 __resv[13]; +}; + +enum { + IORING_MOCK_MGR_CMD_PROBE, + IORING_MOCK_MGR_CMD_CREATE, +}; + +enum { + IORING_MOCK_CMD_COPY_REGBUF, +}; + +enum { + IORING_MOCK_COPY_FROM = 1, +}; + +#endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 37891580d05d..7a4c35ff03fe 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -467,6 +467,10 @@ struct kvm_run { __u64 leaf; __u64 r11, r12, r13, r14; } get_tdvmcall_info; + struct { + __u64 ret; + __u64 vector; + } setup_event_notify; }; } tdx; /* Fix the size of the union. */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 518ba144544c..2beb30be2c5f 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -142,8 +142,6 @@ enum nf_tables_msg_types { NFT_MSG_DESTROYOBJ, NFT_MSG_DESTROYFLOWTABLE, NFT_MSG_GETSETELEM_RESET, - NFT_MSG_NEWDEV, - NFT_MSG_DELDEV, NFT_MSG_MAX, }; @@ -1786,18 +1784,10 @@ enum nft_synproxy_attributes { * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) - * @NFTA_DEVICE_TABLE: table containing the flowtable or chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_FLOWTABLE: flowtable hooking into the device (NLA_STRING) - * @NFTA_DEVICE_CHAIN: chain hooking into the device (NLA_STRING) - * @NFTA_DEVICE_SPEC: hook spec matching the device (NLA_STRING) */ enum nft_devices_attributes { NFTA_DEVICE_UNSPEC, NFTA_DEVICE_NAME, - NFTA_DEVICE_TABLE, - NFTA_DEVICE_FLOWTABLE, - NFTA_DEVICE_CHAIN, - NFTA_DEVICE_SPEC, __NFTA_DEVICE_MAX }; #define NFTA_DEVICE_MAX (__NFTA_DEVICE_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 50d807af2649..6cd58cd2a6f0 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -25,8 +25,6 @@ enum nfnetlink_groups { #define NFNLGRP_ACCT_QUOTA NFNLGRP_ACCT_QUOTA NFNLGRP_NFTRACE, #define NFNLGRP_NFTRACE NFNLGRP_NFTRACE - NFNLGRP_NFT_DEV, -#define NFNLGRP_NFT_DEV NFNLGRP_NFT_DEV __NFNLGRP_MAX, }; #define NFNLGRP_MAX (__NFNLGRP_MAX - 1) diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index 34127653fd00..97d8d80d139f 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -42,4 +42,15 @@ struct mnt_ns_info { /* Get previous namespace. */ #define NS_MNT_GET_PREV _IOR(NSIO, 12, struct mnt_ns_info) +enum init_ns_ino { + IPC_NS_INIT_INO = 0xEFFFFFFFU, + UTS_NS_INIT_INO = 0xEFFFFFFEU, + USER_NS_INIT_INO = 0xEFFFFFFDU, + PID_NS_INIT_INO = 0xEFFFFFFCU, + CGROUP_NS_INIT_INO = 0xEFFFFFFBU, + TIME_NS_INIT_INO = 0xEFFFFFFAU, + NET_NS_INIT_INO = 0xEFFFFFF9U, + MNT_NS_INIT_INO = 0xEFFFFFF8U, +}; + #endif /* __LINUX_NSFS_H */ diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index c27a4e238e4b..957db425d459 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -43,21 +43,6 @@ #define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ /* - * The concept of process and threads in userland and the kernel is a confusing - * one - within the kernel every thread is a 'task' with its own individual PID, - * however from userland's point of view threads are grouped by a single PID, - * which is that of the 'thread group leader', typically the first thread - * spawned. - * - * To cut the Gideon knot, for internal kernel usage, we refer to - * PIDFD_SELF_THREAD to refer to the current thread (or task from a kernel - * perspective), and PIDFD_SELF_THREAD_GROUP to refer to the current thread - * group leader... - */ -#define PIDFD_SELF_THREAD -10000 /* Current thread. */ -#define PIDFD_SELF_THREAD_GROUP -20000 /* Current thread group leader. */ - -/* * ...and for userland we make life simpler - PIDFD_SELF refers to the current * thread, PIDFD_SELF_PROCESS refers to the process thread group leader. * |