ceph: supply snapshot context in ceph_uninline_data()

[ Upstream commit 305ff6b3a03c230d3c07b61457e961406d979693 ]

The ceph_uninline_data function was missing proper snapshot context
handling for its OSD write operations. Both CEPH_OSD_OP_CREATE and
CEPH_OSD_OP_WRITE requests were passing NULL instead of the appropriate
snapshot context, which could lead to unnecessary object clone.

Reproducer:
../src/vstart.sh --new -x --localhost --bluestore
// turn on cephfs inline data
./bin/ceph fs set a inline_data true --yes-i-really-really-mean-it
// allow fs_a client to take snapshot
./bin/ceph auth caps client.fs_a mds 'allow rwps fsname=a' mon 'allow r fsname=a' osd 'allow rw tag cephfs data=a'
// mount cephfs with fuse, since kernel cephfs doesn't support inline write
ceph-fuse --id fs_a -m 127.0.0.1:40318 --conf ceph.conf -d /mnt/mycephfs/
// bump snapshot seq
mkdir /mnt/mycephfs/.snap/snap1
echo "foo" > /mnt/mycephfs/test
// umount and mount it again using kernel cephfs client
umount /mnt/mycephfs
mount -t ceph fs_a@.a=/ /mnt/mycephfs/ -o conf=./ceph.conf
echo "bar" >> /mnt/mycephfs/test
./bin/rados listsnaps -p cephfs.a.data $(printf "%x\n" $(stat -c %i /mnt/mycephfs/test)).00000000

will see this object does unnecessary clone
1000000000a.00000000 (seq:2):
cloneid snaps   size    overlap
2       2       4       []
head    -       8

but it's expected to see
10000000000.00000000 (seq:2):
cloneid snaps   size    overlap
head    -       8

since there's no snapshot between these 2 writes

clone happened because the first osd request CEPH_OSD_OP_CREATE doesn't
pass snap context so object is created with snap seq 0, but later data
writeback is equipped with snapshot context.
snap.seq(1) > object snap seq(0), so osd does object clone.

This fix properly acquiring the snapshot context before performing
write operations.

Signed-off-by: ethanwu <ethanwu@synology.com>
Reviewed-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Tested-by: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 22 insertions, 2 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 2c92de964c5a..db4d11604e9d 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1833,6 +1833,7 @@ int ceph_uninline_data(struct file *file)
 	struct ceph_osd_request *req = NULL;
 	struct ceph_cap_flush *prealloc_cf = NULL;
 	struct folio *folio = NULL;
+	struct ceph_snap_context *snapc = NULL;
 	u64 inline_version = CEPH_INLINE_NONE;
 	struct page *pages[1];
 	int err = 0;
@@ -1860,6 +1861,24 @@ int ceph_uninline_data(struct file *file)
 	if (inline_version == 1) /* initial version, no data */
 		goto out_uninline;
 
+	down_read(&fsc->mdsc->snap_rwsem);
+	spin_lock(&ci->i_ceph_lock);
+	if (__ceph_have_pending_cap_snap(ci)) {
+		struct ceph_cap_snap *capsnap =
+				list_last_entry(&ci->i_cap_snaps,
+						struct ceph_cap_snap,
+						ci_item);
+		snapc = ceph_get_snap_context(capsnap->context);
+	} else {
+		if (!ci->i_head_snapc) {
+			ci->i_head_snapc = ceph_get_snap_context(
+				ci->i_snap_realm->cached_context);
+		}
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
+	}
+	spin_unlock(&ci->i_ceph_lock);
+	up_read(&fsc->mdsc->snap_rwsem);
+
 	folio = read_mapping_folio(inode->i_mapping, 0, file);
 	if (IS_ERR(folio)) {
 		err = PTR_ERR(folio);
@@ -1875,7 +1894,7 @@ int ceph_uninline_data(struct file *file)
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 0, 1,
 				    CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,
-				    NULL, 0, 0, false);
+				    snapc, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
 		goto out_unlock;
@@ -1891,7 +1910,7 @@ int ceph_uninline_data(struct file *file)
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 1, 3,
 				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
-				    NULL, ci->i_truncate_seq,
+				    snapc, ci->i_truncate_seq,
 				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -1954,6 +1973,7 @@ out_unlock:
 		folio_put(folio);
 	}
 out:
+	ceph_put_snap_context(snapc);
 	ceph_free_cap_flush(prealloc_cf);
 	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
 	     inode, ceph_vinop(inode), inline_version, err);