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 <martin.petersen@oracle.com>
Signed-off-by: Prasad Singamsetty <prasad.singamsetty@oracle.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Acked-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20240620125359.2684798-7-john.g.garry@oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/bdev.c b/block/bdev.c
index ced4ac990ec88fc1936217ba300a5c7092ff8cf5..1b4af2cc3b1e6c86fbfef9d8dcc60e543aa4f189 100644 (file)
--- 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 72d0e6357b91f160515576fb1147da5ec3fb8826..bd0698dfd7b36e01722176bb39024c927dfdb744 100644 (file)
--- 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 4816f3b1d5289291c8f43c3aa2fdc4857036ec56..2800231046a98bce7cf18fc632767d924170e577 100644 (file)
--- 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)