Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client

Pull Ceph changes from Sage Weil:
 "Lots of stuff this time around:

   - lots of cleanup and refactoring in the libceph messenger code, and
     many hard to hit races and bugs closed as a result.
   - lots of cleanup and refactoring in the rbd code from Alex Elder,
     mostly in preparation for the layering functionality that will be
     coming in 3.7.
   - some misc rbd cleanups from Josh Durgin that are finally going
     upstream
   - support for CRUSH tunables (used by newer clusters to improve the
     data placement)
   - some cleanup in our use of d_parent that Al brought up a while back
   - a random collection of fixes across the tree

  There is another patch coming that fixes up our ->atomic_open()
  behavior, but I'm going to hammer on it a bit more before sending it."

Fix up conflicts due to commits that were already committed earlier in
drivers/block/rbd.c, net/ceph/{messenger.c, osd_client.c}

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client: (132 commits)
  rbd: create rbd_refresh_helper()
  rbd: return obj version in __rbd_refresh_header()
  rbd: fixes in rbd_header_from_disk()
  rbd: always pass ops array to rbd_req_sync_op()
  rbd: pass null version pointer in add_snap()
  rbd: make rbd_create_rw_ops() return a pointer
  rbd: have __rbd_add_snap_dev() return a pointer
  libceph: recheck con state after allocating incoming message
  libceph: change ceph_con_in_msg_alloc convention to be less weird
  libceph: avoid dropping con mutex before fault
  libceph: verify state after retaking con lock after dispatch
  libceph: revoke mon_client messages on session restart
  libceph: fix handling of immediate socket connect failure
  ceph: update MAINTAINERS file
  libceph: be less chatty about stray replies
  libceph: clear all flags on con_close
  libceph: clean up con flags
  libceph: replace connection state bits with states
  libceph: drop unnecessary CLOSED check in socket state change callback
  libceph: close socket directly from ceph_con_close()
  ...

fs/ceph/dir.c

@@ -51,8 +51,7 @@ int ceph_init_dentry(struct dentry *dentry)
 		goto out_unlock;
 	}
 
-	if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
-	    ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+	if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
 		d_set_d_op(dentry, &ceph_dentry_ops);
 	else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
 		d_set_d_op(dentry, &ceph_snapdir_dentry_ops);
@@ -79,7 +78,7 @@ struct inode *ceph_get_dentry_parent_inode(struct dentry *dentry)
 		return NULL;
 
 	spin_lock(&dentry->d_lock);
-	if (dentry->d_parent) {
+	if (!IS_ROOT(dentry)) {
 		inode = dentry->d_parent->d_inode;
 		ihold(inode);
 	}
@@ -1154,7 +1153,7 @@ static void ceph_d_prune(struct dentry *dentry)
 	dout("ceph_d_prune %p\n", dentry);
 
 	/* do we have a valid parent? */
-	if (!dentry->d_parent || IS_ROOT(dentry))
+	if (IS_ROOT(dentry))
 		return;
 
 	/* if we are not hashed, we don't affect D_COMPLETE */

fs/ceph/mds_client.c

@@ -10,6 +10,7 @@
 #include "super.h"
 #include "mds_client.h"
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/messenger.h>
 #include <linux/ceph/decode.h>
 #include <linux/ceph/pagelist.h>
@@ -394,11 +395,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_seq = 0;
 	mutex_init(&s->s_mutex);
 
-	ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
-	s->s_con.private = s;
-	s->s_con.ops = &mds_con_ops;
-	s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
-	s->s_con.peer_name.num = cpu_to_le64(mds);
+	ceph_con_init(&s->s_con, s, &mds_con_ops, &mdsc->fsc->client->msgr);
 
 	spin_lock_init(&s->s_gen_ttl_lock);
 	s->s_cap_gen = 0;
@@ -440,7 +437,8 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	mdsc->sessions[mds] = s;
 	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
-	ceph_con_open(&s->s_con, ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
+	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
+		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	return s;
 
@@ -1472,11 +1470,6 @@ retry:
 		else
 			len += 1 + temp->d_name.len;
 		temp = temp->d_parent;
-		if (temp == NULL) {
-			rcu_read_unlock();
-			pr_err("build_path corrupt dentry %p\n", dentry);
-			return ERR_PTR(-EINVAL);
-		}
 	}
 	rcu_read_unlock();
 	if (len)
@@ -1513,12 +1506,6 @@ retry:
 		if (pos)
 			path[--pos] = '/';
 		temp = temp->d_parent;
-		if (temp == NULL) {
-			rcu_read_unlock();
-			pr_err("build_path corrupt dentry\n");
-			kfree(path);
-			return ERR_PTR(-EINVAL);
-		}
 	}
 	rcu_read_unlock();
 	if (pos != 0 || read_seqretry(&rename_lock, seq)) {
@@ -2531,7 +2518,9 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
 	session->s_seq = 0;
 
+	ceph_con_close(&session->s_con);
 	ceph_con_open(&session->s_con,
+		      CEPH_ENTITY_TYPE_MDS, mds,
 		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
 
 	/* replay unsafe requests */

fs/ceph/snap.c

@@ -296,8 +296,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	struct ceph_snap_realm *parent = realm->parent;
 	struct ceph_snap_context *snapc;
 	int err = 0;
-	int i;
-	int num = realm->num_prior_parent_snaps + realm->num_snaps;
+	u32 num = realm->num_prior_parent_snaps + realm->num_snaps;
 
 	/*
 	 * build parent context, if it hasn't been built.
@@ -321,11 +320,11 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	    realm->cached_context->seq == realm->seq &&
 	    (!parent ||
 	     realm->cached_context->seq >= parent->cached_context->seq)) {
-		dout("build_snap_context %llx %p: %p seq %lld (%d snaps)"
+		dout("build_snap_context %llx %p: %p seq %lld (%u snaps)"
 		     " (unchanged)\n",
 		     realm->ino, realm, realm->cached_context,
 		     realm->cached_context->seq,
-		     realm->cached_context->num_snaps);
+		     (unsigned int) realm->cached_context->num_snaps);
 		return 0;
 	}
 
@@ -342,6 +341,8 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	num = 0;
 	snapc->seq = realm->seq;
 	if (parent) {
+		u32 i;
+
 		/* include any of parent's snaps occurring _after_ my
 		   parent became my parent */
 		for (i = 0; i < parent->cached_context->num_snaps; i++)
@@ -361,8 +362,9 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 
 	sort(snapc->snaps, num, sizeof(u64), cmpu64_rev, NULL);
 	snapc->num_snaps = num;
-	dout("build_snap_context %llx %p: %p seq %lld (%d snaps)\n",
-	     realm->ino, realm, snapc, snapc->seq, snapc->num_snaps);
+	dout("build_snap_context %llx %p: %p seq %lld (%u snaps)\n",
+	     realm->ino, realm, snapc, snapc->seq,
+	     (unsigned int) snapc->num_snaps);
 
 	if (realm->cached_context)
 		ceph_put_snap_context(realm->cached_context);
@@ -402,9 +404,9 @@ static void rebuild_snap_realms(struct ceph_snap_realm *realm)
  * helper to allocate and decode an array of snapids.  free prior
  * instance, if any.
  */
-static int dup_array(u64 **dst, __le64 *src, int num)
+static int dup_array(u64 **dst, __le64 *src, u32 num)
 {
-	int i;
+	u32 i;
 
 	kfree(*dst);
 	if (num) {

fs/ceph/super.c

@@ -18,6 +18,7 @@
 #include "super.h"
 #include "mds_client.h"
 
+#include <linux/ceph/ceph_features.h>
 #include <linux/ceph/decode.h>
 #include <linux/ceph/mon_client.h>
 #include <linux/ceph/auth.h>

fs/ceph/super.h

@@ -612,9 +612,9 @@ struct ceph_snap_realm {
 	u64 parent_since;   /* snapid when our current parent became so */
 
 	u64 *prior_parent_snaps;      /* snaps inherited from any parents we */
-	int num_prior_parent_snaps;   /*  had prior to parent_since */
+	u32 num_prior_parent_snaps;   /*  had prior to parent_since */
 	u64 *snaps;                   /* snaps specific to this realm */
-	int num_snaps;
+	u32 num_snaps;
 
 	struct ceph_snap_realm *parent;
 	struct list_head children;       /* list of child realms */

fs/ceph/xattr.c

@@ -457,6 +457,7 @@ start:
 			for (i = 0; i < numattr; i++)
 				kfree(xattrs[i]);
 			kfree(xattrs);
+			xattrs = NULL;
 			goto start;
 		}
 		err = -EIO;