ceph: check POOL_FLAG_FULL/NEARFULL in addition to OSDMAP_FULL/NEARFULL

CEPH_OSDMAP_FULL/NEARFULL aren't set since mimic, so we need to consult
per-pool flags as well.  Unfortunately the backwards compatibility here
is lacking:

- the change that deprecated OSDMAP_FULL/NEARFULL went into mimic, but
  was guarded by require_osd_release >= RELEASE_LUMINOUS
- it was subsequently backported to luminous in v12.2.2, but that makes
  no difference to clients that only check OSDMAP_FULL/NEARFULL because
  require_osd_release is not client-facing -- it is for OSDs

Since all kernels are affected, the best we can do here is just start
checking both map flags and pool flags and send that to stable.

These checks are best effort, so take osdc->lock and look up pool flags
just once.  Remove the FIXME, since filesystem quotas are checked above
and RADOS quotas are reflected in POOL_FLAG_FULL: when the pool reaches
its quota, both POOL_FLAG_FULL and POOL_FLAG_FULL_QUOTA are set.

Cc: stable@vger.kernel.org
Reported-by: Yanhu Cao <gmayyyha@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Sage Weil <sage@redhat.com>

1 files changed, 11 insertions, 3 deletions

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 7e0190b1f821..5a478cd06e11 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1415,10 +1415,13 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+	struct ceph_osd_client *osdc = &fsc->client->osdc;
 	struct ceph_cap_flush *prealloc_cf;
 	ssize_t count, written = 0;
 	int err, want, got;
 	bool direct_lock = false;
+	u32 map_flags;
+	u64 pool_flags;
 	loff_t pos;
 	loff_t limit = max(i_size_read(inode), fsc->max_file_size);
 
@@ -1481,8 +1484,12 @@ retry_snap:
 			goto out;
 	}
 
-	/* FIXME: not complete since it doesn't account for being at quota */
-	if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL)) {
+	down_read(&osdc->lock);
+	map_flags = osdc->osdmap->flags;
+	pool_flags = ceph_pg_pool_flags(osdc->osdmap, ci->i_layout.pool_id);
+	up_read(&osdc->lock);
+	if ((map_flags & CEPH_OSDMAP_FULL) ||
+	    (pool_flags & CEPH_POOL_FLAG_FULL)) {
 		err = -ENOSPC;
 		goto out;
 	}
@@ -1575,7 +1582,8 @@ retry_snap:
 	}
 
 	if (written >= 0) {
-		if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_NEARFULL))
+		if ((map_flags & CEPH_OSDMAP_NEARFULL) ||
+		    (pool_flags & CEPH_POOL_FLAG_NEARFULL))
 			iocb->ki_flags |= IOCB_DSYNC;
 		written = generic_write_sync(iocb, written);
 	}