Merge tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client

Pull Ceph updates from Ilya Dryomov:
 "The highlights are:

   - RADOS namespace support in libceph and CephFS (Zheng Yan and
     myself).  The stopgaps added in 4.5 to deny access to inodes in
     namespaces are removed and CEPH_FEATURE_FS_FILE_LAYOUT_V2 feature
     bit is now fully supported

   - A large rework of the MDS cap flushing code (Zheng Yan)

   - Handle some of ->d_revalidate() in RCU mode (Jeff Layton).  We were
     overly pessimistic before, bailing at the first sight of LOOKUP_RCU

  On top of that we've got a few CephFS bug fixes, a couple of cleanups
  and Arnd's workaround for a weird genksyms issue"

* tag 'ceph-for-4.8-rc1' of git://github.com/ceph/ceph-client: (34 commits)
  ceph: fix symbol versioning for ceph_monc_do_statfs
  ceph: Correctly return NXIO errors from ceph_llseek
  ceph: Mark the file cache as unreclaimable
  ceph: optimize cap flush waiting
  ceph: cleanup ceph_flush_snaps()
  ceph: kick cap flushes before sending other cap message
  ceph: introduce an inode flag to indicates if snapflush is needed
  ceph: avoid sending duplicated cap flush message
  ceph: unify cap flush and snapcap flush
  ceph: use list instead of rbtree to track cap flushes
  ceph: update types of some local varibles
  ceph: include 'follows' of pending snapflush in cap reconnect message
  ceph: update cap reconnect message to version 3
  ceph: mount non-default filesystem by name
  libceph: fsmap.user subscription support
  ceph: handle LOOKUP_RCU in ceph_d_revalidate
  ceph: allow dentry_lease_is_valid to work under RCU walk
  ceph: clear d_fsinfo pointer under d_lock
  ceph: remove ceph_mdsc_lease_release
  ceph: don't use ->d_time
  ...

1 files changed, 48 insertions, 25 deletions

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6e0fedf6713b..c64a0b794d49 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -59,7 +59,7 @@ int ceph_init_dentry(struct dentry *dentry)
 
 	di->dentry = dentry;
 	di->lease_session = NULL;
-	dentry->d_time = jiffies;
+	di->time = jiffies;
 	/* avoid reordering d_fsdata setup so that the check above is safe */
 	smp_mb();
 	dentry->d_fsdata = di;
@@ -1124,7 +1124,7 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 void ceph_invalidate_dentry_lease(struct dentry *dentry)
 {
 	spin_lock(&dentry->d_lock);
-	dentry->d_time = jiffies;
+	ceph_dentry(dentry)->time = jiffies;
 	ceph_dentry(dentry)->lease_shared_gen = 0;
 	spin_unlock(&dentry->d_lock);
 }
@@ -1133,7 +1133,8 @@ void ceph_invalidate_dentry_lease(struct dentry *dentry)
  * Check if dentry lease is valid.  If not, delete the lease.  Try to
  * renew if the least is more than half up.
  */
-static int dentry_lease_is_valid(struct dentry *dentry)
+static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags,
+				 struct inode *dir)
 {
 	struct ceph_dentry_info *di;
 	struct ceph_mds_session *s;
@@ -1141,12 +1142,11 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 	u32 gen;
 	unsigned long ttl;
 	struct ceph_mds_session *session = NULL;
-	struct inode *dir = NULL;
 	u32 seq = 0;
 
 	spin_lock(&dentry->d_lock);
 	di = ceph_dentry(dentry);
-	if (di->lease_session) {
+	if (di && di->lease_session) {
 		s = di->lease_session;
 		spin_lock(&s->s_gen_ttl_lock);
 		gen = s->s_cap_gen;
@@ -1154,17 +1154,24 @@ static int dentry_lease_is_valid(struct dentry *dentry)
 		spin_unlock(&s->s_gen_ttl_lock);
 
 		if (di->lease_gen == gen &&
-		    time_before(jiffies, dentry->d_time) &&
+		    time_before(jiffies, di->time) &&
 		    time_before(jiffies, ttl)) {
 			valid = 1;
 			if (di->lease_renew_after &&
 			    time_after(jiffies, di->lease_renew_after)) {
-				/* we should renew */
-				dir = d_inode(dentry->d_parent);
-				session = ceph_get_mds_session(s);
-				seq = di->lease_seq;
-				di->lease_renew_after = 0;
-				di->lease_renew_from = jiffies;
+				/*
+				 * We should renew. If we're in RCU walk mode
+				 * though, we can't do that so just return
+				 * -ECHILD.
+				 */
+				if (flags & LOOKUP_RCU) {
+					valid = -ECHILD;
+				} else {
+					session = ceph_get_mds_session(s);
+					seq = di->lease_seq;
+					di->lease_renew_after = 0;
+					di->lease_renew_from = jiffies;
+				}
 			}
 		}
 	}
@@ -1207,15 +1214,19 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct dentry *parent;
 	struct inode *dir;
 
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
+	if (flags & LOOKUP_RCU) {
+		parent = ACCESS_ONCE(dentry->d_parent);
+		dir = d_inode_rcu(parent);
+		if (!dir)
+			return -ECHILD;
+	} else {
+		parent = dget_parent(dentry);
+		dir = d_inode(parent);
+	}
 
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
 	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
 
-	parent = dget_parent(dentry);
-	dir = d_inode(parent);
-
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
 		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
@@ -1224,12 +1235,16 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	} else if (d_really_is_positive(dentry) &&
 		   ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
 		valid = 1;
-	} else if (dentry_lease_is_valid(dentry) ||
-		   dir_lease_is_valid(dir, dentry)) {
-		if (d_really_is_positive(dentry))
-			valid = ceph_is_any_caps(d_inode(dentry));
-		else
-			valid = 1;
+	} else {
+		valid = dentry_lease_is_valid(dentry, flags, dir);
+		if (valid == -ECHILD)
+			return valid;
+		if (valid || dir_lease_is_valid(dir, dentry)) {
+			if (d_really_is_positive(dentry))
+				valid = ceph_is_any_caps(d_inode(dentry));
+			else
+				valid = 1;
+		}
 	}
 
 	if (!valid) {
@@ -1238,6 +1253,9 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		struct ceph_mds_request *req;
 		int op, mask, err;
 
+		if (flags & LOOKUP_RCU)
+			return -ECHILD;
+
 		op = ceph_snap(dir) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
 		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
@@ -1273,7 +1291,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		ceph_dir_clear_complete(dir);
 	}
 
-	dput(parent);
+	if (!(flags & LOOKUP_RCU))
+		dput(parent);
 	return valid;
 }
 
@@ -1286,10 +1305,14 @@ static void ceph_d_release(struct dentry *dentry)
 
 	dout("d_release %p\n", dentry);
 	ceph_dentry_lru_del(dentry);
+
+	spin_lock(&dentry->d_lock);
+	dentry->d_fsdata = NULL;
+	spin_unlock(&dentry->d_lock);
+
 	if (di->lease_session)
 		ceph_put_mds_session(di->lease_session);
 	kmem_cache_free(ceph_dentry_cachep, di);
-	dentry->d_fsdata = NULL;
 }
 
 static int ceph_snapdir_d_revalidate(struct dentry *dentry,