ceph: include dirty xattrs state in snapped caps
When we snapshot dirty metadata that needs to be written back to the MDS,
include dirty xattr metadata. Make the capsnap reference the encoded
xattr blob so that it will be written back in the FLUSHSNAP op.
Also fix the capsnap creation guard to include dirty auth or file bits,
not just tests specific to dirty file data or file writes in progress
(this fixes auth metadata writeback).
Signed-off-by: Sage Weil <sage@newdream.net>
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0ac2703..ba5bbf3 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1282,7 +1282,7 @@
&capsnap->mtime, &capsnap->atime,
capsnap->time_warp_seq,
capsnap->uid, capsnap->gid, capsnap->mode,
- 0, NULL,
+ capsnap->xattr_version, capsnap->xattr_blob,
capsnap->follows);
next_follows = capsnap->follows + 1;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index c0b26b6..2cb190c 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -435,7 +435,7 @@
{
struct inode *inode = &ci->vfs_inode;
struct ceph_cap_snap *capsnap;
- int used;
+ int used, dirty;
capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
if (!capsnap) {
@@ -445,6 +445,7 @@
spin_lock(&inode->i_lock);
used = __ceph_caps_used(ci);
+ dirty = __ceph_caps_dirty(ci);
if (__ceph_have_pending_cap_snap(ci)) {
/* there is no point in queuing multiple "pending" cap_snaps,
as no new writes are allowed to start when pending, so any
@@ -452,11 +453,13 @@
cap_snap. lucky us. */
dout("queue_cap_snap %p already pending\n", inode);
kfree(capsnap);
- } else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) {
+ } else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR) ||
+ (dirty & (CEPH_CAP_AUTH_EXCL|CEPH_CAP_XATTR_EXCL|
+ CEPH_CAP_FILE_EXCL|CEPH_CAP_FILE_WR))) {
struct ceph_snap_context *snapc = ci->i_head_snapc;
igrab(inode);
-
+
atomic_set(&capsnap->nref, 1);
capsnap->ci = ci;
INIT_LIST_HEAD(&capsnap->ci_item);
@@ -464,15 +467,21 @@
capsnap->follows = snapc->seq - 1;
capsnap->issued = __ceph_caps_issued(ci, NULL);
- capsnap->dirty = __ceph_caps_dirty(ci);
+ capsnap->dirty = dirty;
capsnap->mode = inode->i_mode;
capsnap->uid = inode->i_uid;
capsnap->gid = inode->i_gid;
- /* fixme? */
- capsnap->xattr_blob = NULL;
- capsnap->xattr_len = 0;
+ if (dirty & CEPH_CAP_XATTR_EXCL) {
+ __ceph_build_xattrs_blob(ci);
+ capsnap->xattr_blob =
+ ceph_buffer_get(ci->i_xattrs.blob);
+ capsnap->xattr_version = ci->i_xattrs.version;
+ } else {
+ capsnap->xattr_blob = NULL;
+ capsnap->xattr_version = 0;
+ }
/* dirty page count moved from _head to this cap_snap;
all subsequent writes page dirties occur _after_ this
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2482d69..b33929d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -216,8 +216,7 @@
uid_t uid;
gid_t gid;
- void *xattr_blob;
- int xattr_len;
+ struct ceph_buffer *xattr_blob;
u64 xattr_version;
u64 size;
@@ -229,8 +228,11 @@
static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
{
- if (atomic_dec_and_test(&capsnap->nref))
+ if (atomic_dec_and_test(&capsnap->nref)) {
+ if (capsnap->xattr_blob)
+ ceph_buffer_put(capsnap->xattr_blob);
kfree(capsnap);
+ }
}
/*
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 097a265..9578af6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -485,6 +485,7 @@
ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = NULL;
ci->i_xattrs.dirty = false;
+ ci->i_xattrs.version++;
}
}