linux-kernel - [PATCH v6 06/10] block: Add atomic write support for statx

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240326133813.3224593-7-john.g.garry@oracle.com>
Date: Tue, 26 Mar 2024 13:38:09 +0000
From: John Garry <john.g.garry@...cle.com>
To: axboe@...nel.dk, kbusch@...nel.org, hch@....de, sagi@...mberg.me,
        jejb@...ux.ibm.com, martin.petersen@...cle.com, djwong@...nel.org,
        viro@...iv.linux.org.uk, brauner@...nel.org, dchinner@...hat.com,
        jack@...e.cz
Cc: linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-nvme@...ts.infradead.org, linux-fsdevel@...r.kernel.org,
        tytso@....edu, jbongio@...gle.com, linux-scsi@...r.kernel.org,
        ojaswin@...ux.ibm.com, linux-aio@...ck.org,
        linux-btrfs@...r.kernel.org, io-uring@...r.kernel.org,
        nilay@...ux.ibm.com, ritesh.list@...il.com, willy@...radead.org,
        Prasad Singamsetty <prasad.singamsetty@...cle.com>,
        John Garry <john.g.garry@...cle.com>
Subject: [PATCH v6 06/10] block: Add atomic write support for statx

From: Prasad Singamsetty <prasad.singamsetty@...cle.com>

Extend statx system call to return additional info for atomic write support
support if the specified file is a block device.

Signed-off-by: Prasad Singamsetty <prasad.singamsetty@...cle.com>
Signed-off-by: John Garry <john.g.garry@...cle.com>
---
 block/bdev.c           | 36 ++++++++++++++++++++++++++----------
 fs/stat.c              | 16 +++++++++-------
 include/linux/blkdev.h |  6 ++++--
 3 files changed, 39 insertions(+), 19 deletions(-)

diff --git a/block/bdev.c b/block/bdev.c
index 7a5f611c3d2e..f3dd9f3c8838 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -1182,23 +1182,39 @@ 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 83aaa555711d..0e296925a56b 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 @@ static int vfs_statx(int dfd, struct filename *filename, int flags,
 		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 07145b0acbc8..d16b0c451b27 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1594,7 +1594,8 @@ 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
@@ -1612,7 +1613,8 @@ 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)
-- 
2.31.1