From 0f9ca80fa4f9670ba09721e4e36b8baf086a500c Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:53 +0000 Subject: fs: Add initial atomic write support info to statx Extend statx system call to return additional info for atomic write support support for a file. Helper function generic_fill_statx_atomic_writes() can be used by FSes to fill in the relevant statx fields. For now atomic_write_segments_max will always be 1, otherwise some rules would need to be imposed on iovec length and alignment, which we don't want now. Signed-off-by: Prasad Singamsetty jpg: relocate bdev support to another patch Reviewed-by: Darrick J. Wong Reviewed-by: Martin K. Petersen Signed-off-by: John Garry Acked-by: Darrick J. Wong Link: https://lore.kernel.org/r/20240620125359.2684798-5-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- fs/stat.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'fs/stat.c') diff --git a/fs/stat.c b/fs/stat.c index 70bd3e888cfa..72d0e6357b91 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -89,6 +89,37 @@ void generic_fill_statx_attr(struct inode *inode, struct kstat *stat) } EXPORT_SYMBOL(generic_fill_statx_attr); +/** + * generic_fill_statx_atomic_writes - Fill in atomic writes statx attributes + * @stat: Where to fill in the attribute flags + * @unit_min: Minimum supported atomic write length in bytes + * @unit_max: Maximum supported atomic write length in bytes + * + * Fill in the STATX{_ATTR}_WRITE_ATOMIC flags in the kstat structure from + * atomic write unit_min and unit_max values. + */ +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max) +{ + /* Confirm that the request type is known */ + stat->result_mask |= STATX_WRITE_ATOMIC; + + /* Confirm that the file attribute type is known */ + stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC; + + if (unit_min) { + stat->atomic_write_unit_min = unit_min; + stat->atomic_write_unit_max = unit_max; + /* Initially only allow 1x segment */ + stat->atomic_write_segments_max = 1; + + /* Confirm atomic writes are actually supported */ + stat->attributes |= STATX_ATTR_WRITE_ATOMIC; + } +} +EXPORT_SYMBOL_GPL(generic_fill_statx_atomic_writes); + /** * vfs_getattr_nosec - getattr without security checks * @path: file to get attributes from @@ -659,6 +690,9 @@ cp_statx(const struct kstat *stat, struct statx __user *buffer) tmp.stx_dio_mem_align = stat->dio_mem_align; tmp.stx_dio_offset_align = stat->dio_offset_align; tmp.stx_subvol = stat->subvol; + tmp.stx_atomic_write_unit_min = stat->atomic_write_unit_min; + tmp.stx_atomic_write_unit_max = stat->atomic_write_unit_max; + tmp.stx_atomic_write_segments_max = stat->atomic_write_segments_max; return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0; } -- cgit v1.2.3-70-g09d2 From 9abcfbd235f59fb5b6379e5bc0231dad831ebace Mon Sep 17 00:00:00 2001 From: Prasad Singamsetty Date: Thu, 20 Jun 2024 12:53:55 +0000 Subject: block: Add atomic write support for statx Extend statx system call to return additional info for atomic write support support if the specified file is a block device. Reviewed-by: Martin K. Petersen Signed-off-by: Prasad Singamsetty Signed-off-by: John Garry Reviewed-by: Keith Busch Acked-by: Darrick J. Wong Reviewed-by: Darrick J. Wong Reviewed-by: Luis Chamberlain Link: https://lore.kernel.org/r/20240620125359.2684798-7-john.g.garry@oracle.com Signed-off-by: Jens Axboe --- block/bdev.c | 36 ++++++++++++++++++++++++++---------- fs/stat.c | 16 +++++++++------- include/linux/blkdev.h | 6 ++++-- 3 files changed, 39 insertions(+), 19 deletions(-) (limited to 'fs/stat.c') diff --git a/block/bdev.c b/block/bdev.c index ced4ac990ec8..1b4af2cc3b1e 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -1260,23 +1260,39 @@ void sync_bdevs(bool wait) } /* - * Handle STATX_DIOALIGN for block devices. - * - * Note that the inode passed to this is the inode of a block device node file, - * not the block device's internal inode. Therefore it is *not* valid to use - * I_BDEV() here; the block device has to be looked up by i_rdev instead. + * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices. */ -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +void bdev_statx(struct inode *backing_inode, struct kstat *stat, + u32 request_mask) { struct block_device *bdev; - bdev = blkdev_get_no_open(inode->i_rdev); + if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC))) + return; + + /* + * Note that backing_inode is the inode of a block device node file, + * not the block device's internal inode. Therefore it is *not* valid + * to use I_BDEV() here; the block device has to be looked up by i_rdev + * instead. + */ + bdev = blkdev_get_no_open(backing_inode->i_rdev); if (!bdev) return; - stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; - stat->dio_offset_align = bdev_logical_block_size(bdev); - stat->result_mask |= STATX_DIOALIGN; + if (request_mask & STATX_DIOALIGN) { + stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; + stat->dio_offset_align = bdev_logical_block_size(bdev); + stat->result_mask |= STATX_DIOALIGN; + } + + if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) { + struct request_queue *bd_queue = bdev->bd_queue; + + generic_fill_statx_atomic_writes(stat, + queue_atomic_write_unit_min_bytes(bd_queue), + queue_atomic_write_unit_max_bytes(bd_queue)); + } blkdev_put_no_open(bdev); } diff --git a/fs/stat.c b/fs/stat.c index 72d0e6357b91..bd0698dfd7b3 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -265,6 +265,7 @@ static int vfs_statx(int dfd, struct filename *filename, int flags, { struct path path; unsigned int lookup_flags = getname_statx_lookup_flags(flags); + struct inode *backing_inode; int error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT | AT_EMPTY_PATH | @@ -290,13 +291,14 @@ retry: stat->attributes |= STATX_ATTR_MOUNT_ROOT; stat->attributes_mask |= STATX_ATTR_MOUNT_ROOT; - /* Handle STATX_DIOALIGN for block devices. */ - if (request_mask & STATX_DIOALIGN) { - struct inode *inode = d_backing_inode(path.dentry); - - if (S_ISBLK(inode->i_mode)) - bdev_statx_dioalign(inode, stat); - } + /* + * If this is a block device inode, override the filesystem + * attributes with the block device specific parameters that need to be + * obtained from the bdev backing inode. + */ + backing_inode = d_backing_inode(path.dentry); + if (S_ISBLK(backing_inode->i_mode)) + bdev_statx(backing_inode, stat, request_mask); path_put(&path); if (retry_estale(error, lookup_flags)) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4816f3b1d528..2800231046a9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1638,7 +1638,8 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); +void bdev_statx(struct inode *backing_inode, struct kstat *stat, + u32 request_mask); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1656,7 +1657,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +static inline void bdev_statx(struct inode *backing_inode, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) -- cgit v1.2.3-70-g09d2