Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
From:   Ojaswin Mujoo <ojaswin@linux.ibm.com>
To:     linux-ext4@vger.kernel.org, "Theodore Ts'o" <tytso@mit.edu>
Cc:     Ritesh Harjani <ritesh.list@gmail.com>,
        linux-kernel@vger.kernel.org,
        "Darrick J . Wong" <djwong@kernel.org>,
        linux-block@vger.kernel.org, linux-xfs@vger.kernel.org,
        linux-fsdevel@vger.kernel.org,
        John Garry <john.g.garry@oracle.com>, dchinner@redhat.com
Subject: [RFC 7/7] ext4: Support atomic write for statx
Date:   Thu, 30 Nov 2023 19:23:16 +0530
Message-Id: <e299f66d5b8f77c8e17970868d83fa1ff7655faa.1701339358.git.ojaswin@linux.ibm.com>
In-Reply-To: <cover.1701339358.git.ojaswin@linux.ibm.com>
References: <cover.1701339358.git.ojaswin@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Support providing info on atomic write unit min and max for an inode.

For simplicity, currently we limit the min at the FS block size, but a
lower limit could be supported in future.

Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
---
 fs/ext4/inode.c | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d185ec54ffa3..c8f974d0f113 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5621,6 +5621,7 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 	struct ext4_inode *raw_inode;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
+	struct block_device *bdev = inode->i_sb->s_bdev;
 
 	if ((request_mask & STATX_BTIME) &&
 	    EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
@@ -5639,8 +5640,6 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 
 		stat->result_mask |= STATX_DIOALIGN;
 		if (dio_align == 1) {
-			struct block_device *bdev = inode->i_sb->s_bdev;
-
 			/* iomap defaults */
 			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
 			stat->dio_offset_align = bdev_logical_block_size(bdev);
@@ -5650,6 +5649,41 @@ int ext4_getattr(struct mnt_idmap *idmap, const struct path *path,
 		}
 	}
 
+	if ((request_mask & STATX_WRITE_ATOMIC)) {
+		unsigned int awumin, awumax;
+		unsigned int blocksize = 1 << inode->i_blkbits;
+
+		awumin = queue_atomic_write_unit_min_bytes(bdev->bd_queue);
+		awumax = queue_atomic_write_unit_max_bytes(bdev->bd_queue);
+
+		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ||
+		    EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) {
+			/*
+			 * Currently not supported for non extent files or
+			 * with bigalloc
+			 */
+			stat->atomic_write_unit_min = 0;
+			stat->atomic_write_unit_max = 0;
+		} else if (awumin && awumax) {
+			/*
+			 * For now we support atomic writes which are
+			 * at least block size bytes. If that exceeds the
+			 * max atomic unit, then don't advertise support
+			 */
+			stat->atomic_write_unit_min = max(awumin, blocksize);
+
+			if (awumax < stat->atomic_write_unit_min) {
+				stat->atomic_write_unit_min = 0;
+				stat->atomic_write_unit_max = 0;
+			} else {
+				stat->atomic_write_unit_max = awumax;
+				stat->attributes |= STATX_ATTR_WRITE_ATOMIC;
+			}
+		}
+		stat->attributes_mask |= STATX_ATTR_WRITE_ATOMIC;
+		stat->result_mask |= STATX_WRITE_ATOMIC;
+	}
+
 	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 	if (flags & EXT4_APPEND_FL)
 		stat->attributes |= STATX_ATTR_APPEND;
-- 
2.39.3