diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-11-10 07:25:09 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-11-10 07:25:09 -0800 |
| commit | 5f5be6584cf5af0d70ee2fd40aa6264da18617ec (patch) | |
| tree | 5b2f567c11ea7081c399653185e20bda19957440 /include/linux | |
| parent | 05e72bd3385972828b30354be4917fcd5ab2d6d2 (diff) | |
| parent | 1448959fe3d013ffdb8302d17e4a8fdad2d2da95 (diff) | |
Merge tag 'vfs-7.4-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs
Pull vfs fixes from Christian Brauner:
- libfs: Make readdir on tmpfs walk the offset tree in offset order
instead of d_children to avoid skipping entries or relisting the
whole directory
It's faster too. Listing a million entries takes 114ms instead of
146ms, and 113ms instead of 470ms with four processes listing in
parallel
- iomap: Finish the ->iomap_next() conversion that started in v7.3
The nilfs2 and fuse ext_map iomap code added this merge window is
converted so now we can remove the ->iomap_begin()/->iomap_end()
fallback. We waited until the new iomap users from other trees were
in mainline otherwise this would have been very messy
- errseq: Retry with the current value when the cmpxchg() in
errseq_check_and_advance() fails to avoid an old value coming back
later hiding the errors
- aio: Hold an extra count for exit_aio() itself so it can't return
before the last free_ioctx_reqs() callback has called complete()
- pidfd: Fail the namespace ioctls with EREMOTE unless the target is
visible in the caller's pid namespace like PIDFD_GET_INFO does
- eventpoll: Wake the next waiter when a woken waiter returns early
because of a fatal signal to avoid sleeping forever
- backing-file: Pass RWF_NOAPPEND on to synchronous writes to the
backing file
- initrd: Flush the deferred fput() of the ramdisk file before mounting
root
- iov_iter: Take an unsigned long segment count in import_iovec()
The upper 32 bits of the count passed to readv(), writev() and
friends were dropped before the UIO_MAXIOV check
- splice: Advance the pipe tail before checking for a full bvec array
in splice_to_socket(). The last buffer was counted again, so MSG_MORE
was set although the pipe was empty and small TCP transfers waited
for the cork timeout
- vfs:
- Reject negative offsets for SEEK_DATA and SEEK_HOLE in
default_llseek() and use must_set_pos() for its whence handling
- Only clear tv_nsec in timestamp_truncate() when clamping changed
the seconds. Timestamps whose seconds were exactly at a
filesystem time limit lost their subsecond part
- Don't leak the kernel-internal STATX_ATTR_CHANGE_MONOTONIC in
stx_attributes_mask
- Clamp the FIONREAD result to the int range so a file with 4 GiB
left isn't reported as empty
- Fix the SEEK_CUR f_lock check
- selftests: Fix the statmount and mount_setattr tests on 32-bit and
s390, build the fchmodat2 and openat2 tests without sanitizers when
the toolchain lacks the runtimes and fix a clang warning in the
mount-notify test
- docs: Fix a docutils warning in porting.rst
* tag 'vfs-7.4-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (28 commits)
fs: fix the SEEK_CUR f_lock condition
splice, net: avoid MSG_MORE when the bvec array fills
aio: don't let exit_aio() return before complete() is done
fs: porting.rst: use literal string to avoid warning
selftests/fs/mount-notify: fix the indentation in the fsmount test
selftests: probe for sanitizer support in fchmodat2 and openat2
selftests/mount_setattr: build with a 64-bit off_t
selftests/statmount: fix format warnings on 32-bit and s390
fs: use must_set_pos() in default_llseek()
fs: reject negative offsets for SEEK_DATA and SEEK_HOLE in default_llseek()
pidfd: restrict task access ioctls to the caller's pid namespace
fs: clamp FIONREAD result to int range
eventpoll: wake the next waiter when a woken waiter is killed
statx: don't leak STATX_ATTR_CHANGE_MONOTONIC in stx_attributes_mask
vfs: preserve subsecond timestamps at filesystem time limits
iov_iter: take an unsigned long segment count in import_iovec()
lib/tests: errseq: add a concurrent check_and_advance test
errseq: don't let errseq_check_and_advance() hide later errors
backing-file: pass RWF_NOAPPEND to synchronous writes
initrd: flush deferred fput() before mounting root
...
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/dax.h | 18 | ||||
| -rw-r--r-- | include/linux/fs.h | 9 | ||||
| -rw-r--r-- | include/linux/iomap.h | 66 | ||||
| -rw-r--r-- | include/linux/stat.h | 3 | ||||
| -rw-r--r-- | include/linux/uio.h | 8 |
5 files changed, 55 insertions, 49 deletions
diff --git a/include/linux/dax.h b/include/linux/dax.h index a3af0c63c61b..2e0797e4d408 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -3,6 +3,7 @@ #define _LINUX_DAX_H #include <linux/fs.h> +#include <linux/iomap.h> #include <linux/mm.h> #include <linux/radix-tree.h> @@ -10,9 +11,6 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; -struct iomap_ops; -struct iomap_iter; -struct iomap; enum dax_access_mode { DAX_ACCESS, @@ -200,11 +198,11 @@ static inline void dax_unlock_mapping_entry(struct address_space *mapping, #endif int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, - const struct iomap_ops *ops); + iomap_iter_next_fn next); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, - const struct iomap_ops *ops); + iomap_iter_next_fn next); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, - const struct iomap_ops *ops); + iomap_iter_next_fn next); static inline bool dax_page_is_idle(struct page *page) { @@ -253,10 +251,10 @@ int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len, void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops); + iomap_iter_next_fn next); vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order, unsigned long *pfnp, int *errp, - const struct iomap_ops *ops); + iomap_iter_next_fn next); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, unsigned long pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); @@ -275,11 +273,11 @@ void dax_break_layout_final(struct inode *inode); int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same, - const struct iomap_ops *ops); + iomap_iter_next_fn next); int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, - const struct iomap_ops *ops); + iomap_iter_next_fn next); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/fs.h b/include/linux/fs.h index 99caef43ff3c..5b3a100aba77 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -70,7 +70,8 @@ struct fsnotify_mark_connector; struct fs_context; struct fs_parameter_spec; struct file_kattr; -struct iomap_ops; +struct iomap_iter; +struct iomap; struct delegated_inode; extern void __init inode_init(void); @@ -2083,7 +2084,9 @@ int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, - const struct iomap_ops *dax_read_ops); + int (*dax_read_next)(const struct iomap_iter *iter, + struct iomap *iomap, + struct iomap *srcmap)); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); @@ -3332,7 +3335,7 @@ struct offset_ctx { unsigned long next_offset; }; -void simple_offset_init(struct offset_ctx *octx); +void simple_offset_init(struct offset_ctx *octx, struct inode *dir); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5254430844b2..78a1b7603a4f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -195,7 +195,7 @@ struct iomap_write_ops { }; /* - * Flags for iomap_begin / iomap_end. No flag implies a read. + * Flags for iomap_next. No flag implies a read. */ #define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */ #define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */ @@ -239,12 +239,6 @@ typedef int (*iomap_iter_end_fn)(struct inode *inode, loff_t pos, loff_t length, typedef int (*iomap_iter_next_fn)(const struct iomap_iter *iter, struct iomap *iomap, struct iomap *srcmap); -struct iomap_ops { - iomap_iter_begin_fn iomap_begin; - iomap_iter_end_fn iomap_end; - iomap_iter_next_fn iomap_next; -}; - /** * struct iomap_iter - Iterate through a range of a file * @inode: Set at the start of the iteration and should not change. @@ -256,7 +250,7 @@ struct iomap_ops { * incremental iter advance. * @status: Status of the most recent iteration. Zero on success or a negative * errno on error. - * @flags: Zero or more of the iomap_begin flags above. + * @flags: Zero or more of the iomap_iter_next flags above. * @iomap: Map describing the I/O iteration * @srcmap: Source map for COW operations */ @@ -273,7 +267,7 @@ struct iomap_iter { void *private; }; -int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); +int iomap_iter(struct iomap_iter *iter, iomap_iter_next_fn next); int iomap_iter_advance(struct iomap_iter *iter, u64 count); /** @@ -341,7 +335,7 @@ int iomap_iter_continue(const struct iomap_iter *iter, struct iomap *iomap, * @begin: callback that produces a mapping for the current position * @end: optional callback that finishes the previous mapping, or NULL * - * Inline helper that implements the common body of an ->iomap_next() + * Inline helper that implements the common body of an iomap_iter_next_fn * callback: it finishes the previous mapping via @end (if present), decides * via iomap_iter_continue() whether to keep going, and obtains the next * mapping via @begin. @@ -396,6 +390,14 @@ int name(const struct iomap_iter *iter, struct iomap *iomap, \ DEFINE_IOMAP_ITER_NEXT_END(name, begin_fn, NULL) /* + * Forward-declare an iomap_iter_next_fn callback generated by + * DEFINE_IOMAP_ITER_NEXT(). + */ +#define DECLARE_IOMAP_ITER_NEXT(name) \ +int name(const struct iomap_iter *iter, struct iomap *iomap, \ + struct iomap *srcmap) + +/* * Return the file offset for the first unchanged block after a short write. * * If nothing was written, round @pos down to point at the first block in @@ -429,15 +431,15 @@ 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, + iomap_iter_next_fn next, const struct iomap_write_ops *write_ops, void *private); int iomap_fsverity_write(struct file *file, loff_t pos, size_t length, - const void *buf, const struct iomap_ops *ops, + const void *buf, iomap_iter_next_fn next, const struct iomap_write_ops *write_ops); -void iomap_read_folio(const struct iomap_ops *ops, - struct iomap_read_folio_ctx *ctx, void *private); -void iomap_readahead(const struct iomap_ops *ops, - struct iomap_read_folio_ctx *ctx, void *private); +void iomap_read_folio(iomap_iter_next_fn next, struct iomap_read_folio_ctx *ctx, + void *private); +void iomap_readahead(iomap_iter_next_fn next, struct iomap_read_folio_ctx *ctx, + void *private); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); @@ -445,17 +447,17 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); void iomap_folio_mark_uptodate(struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, - const struct iomap_ops *ops, + iomap_iter_next_fn next, const struct iomap_write_ops *write_ops); unsigned int iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t *start, loff_t end, unsigned int *iomap_flags); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, - bool *did_zero, const struct iomap_ops *ops, + bool *did_zero, iomap_iter_next_fn next, 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, + iomap_iter_next_fn next, const struct iomap_write_ops *write_ops, void *private); -vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops, +vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, iomap_iter_next_fn next, void *private); typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length, struct iomap *iomap); @@ -464,13 +466,13 @@ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte, iomap_punch_t punch); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, - u64 start, u64 len, const struct iomap_ops *ops); + u64 start, u64 len, iomap_iter_next_fn next); loff_t iomap_seek_hole(struct inode *inode, loff_t offset, - const struct iomap_ops *ops); + iomap_iter_next_fn next); loff_t iomap_seek_data(struct inode *inode, loff_t offset, - const struct iomap_ops *ops); + iomap_iter_next_fn next); sector_t iomap_bmap(struct address_space *mapping, sector_t bno, - const struct iomap_ops *ops); + iomap_iter_next_fn next); /* * Flags for iomap_ioend->io_flags. @@ -711,10 +713,10 @@ struct iomap_dio_ops { #define IOMAP_DIO_BOUNCE (1 << 4) ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + iomap_iter_next_fn next, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, - const struct iomap_ops *ops, const struct iomap_dio_ops *dops, + iomap_iter_next_fn next, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); void iomap_dio_bio_end_io(struct bio *bio); @@ -790,9 +792,9 @@ struct swap_info_struct; int iomap_swapfile_activate(struct swap_info_struct *sis, struct file *swap_file, sector_t *pagespan, - const struct iomap_ops *ops); + iomap_iter_next_fn next); #else -# define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO) +# define iomap_swapfile_activate(sis, swapfile, pagespan, next) (-EIO) #endif /* CONFIG_SWAP */ extern struct bio_set iomap_ioend_bioset; @@ -806,25 +808,25 @@ void iomap_bio_submit_read_endio(const struct iomap_iter *iter, extern const struct iomap_read_ops iomap_bio_read_ops; static inline void iomap_bio_read_folio(struct folio *folio, - const struct iomap_ops *ops) + iomap_iter_next_fn next) { struct iomap_read_folio_ctx ctx = { .ops = &iomap_bio_read_ops, .cur_folio = folio, }; - iomap_read_folio(ops, &ctx, NULL); + iomap_read_folio(next, &ctx, NULL); } static inline void iomap_bio_readahead(struct readahead_control *rac, - const struct iomap_ops *ops) + iomap_iter_next_fn next) { struct iomap_read_folio_ctx ctx = { .ops = &iomap_bio_read_ops, .rac = rac, }; - iomap_readahead(ops, &ctx, NULL); + iomap_readahead(next, &ctx, NULL); } #endif /* CONFIG_BLOCK */ diff --git a/include/linux/stat.h b/include/linux/stat.h index 9c5709132862..4f0a4af7a067 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -69,4 +69,7 @@ struct kstat { /* file attribute values */ #define STATX_ATTR_CHANGE_MONOTONIC 0x8000000000000000ULL /* version monotonically increases */ +/* mask of STATX_ATTR_* bits that is private to the kernel */ +#define STATX_ATTR_INTERNAL_MASK (STATX_ATTR_CHANGE_MONOTONIC) + #endif diff --git a/include/linux/uio.h b/include/linux/uio.h index 638c1116e912..76e4103b9ec4 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -373,11 +373,11 @@ struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, - unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, - struct iov_iter *i); + unsigned long nr_segs, unsigned int fast_segs, + struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, - unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, - struct iov_iter *i, bool compat); + unsigned long nr_segs, unsigned int fast_segs, + struct iovec **iovp, struct iov_iter *i, bool compat); int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, |
