ceph: supply snapshot context in ceph_zero_partial_object()

The ceph_zero_partial_object function was missing proper snapshot
context for its OSD write operations, which could lead to data
inconsistencies in snapshots.

Reproducer:
../src/vstart.sh --new -x --localhost --bluestore
./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 -t ceph fs_a@.a=/ /mnt/mycephfs/ -o conf=./ceph.conf
dd if=/dev/urandom of=/mnt/mycephfs/foo bs=64K count=1
mkdir /mnt/mycephfs/.snap/snap1
md5sum /mnt/mycephfs/.snap/snap1/foo
fallocate -p -o 0 -l 4096 /mnt/mycephfs/foo
echo 3 > /proc/sys/vm/drop/caches
md5sum /mnt/mycephfs/.snap/snap1/foo # get different md5sum!!

Cc: stable@vger.kernel.org
Fixes: ad7a60de882ac ("ceph: punch hole support")
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>

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 983390069f737254e8c7bcad1718f375499f443e..9152b47227101615be09a1c514b528bbf52a8e2e 100644 (file)
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2568,6 +2568,7 @@ static int ceph_zero_partial_object(struct inode *inode,
        struct ceph_inode_info *ci = ceph_inode(inode);
        struct ceph_fs_client *fsc = ceph_inode_to_fs_client(inode);
        struct ceph_osd_request *req;
+       struct ceph_snap_context *snapc;
        int ret = 0;
        loff_t zero = 0;
        int op;
@@ -2582,12 +2583,25 @@ static int ceph_zero_partial_object(struct inode *inode,
                op = CEPH_OSD_OP_ZERO;
        }
 
+       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 {
+               BUG_ON(!ci->i_head_snapc);
+               snapc = ceph_get_snap_context(ci->i_head_snapc);
+       }
+       spin_unlock(&ci->i_ceph_lock);
+
        req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
                                        ceph_vino(inode),
                                        offset, length,
                                        0, 1, op,
                                        CEPH_OSD_FLAG_WRITE,
-                                       NULL, 0, 0, false);
+                                       snapc, 0, 0, false);
        if (IS_ERR(req)) {
                ret = PTR_ERR(req);
                goto out;
@@ -2601,6 +2615,7 @@ static int ceph_zero_partial_object(struct inode *inode,
        ceph_osdc_put_request(req);
 
 out:
+       ceph_put_snap_context(snapc);
        return ret;
 }