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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client:
  ceph: avoid picking MDS that is not active
  ceph: avoid immediate cap check after import
  ceph: fix flushing of caps vs cap import
  ceph: fix erroneous cap flush to non-auth mds
  ceph: fix cap_wanted_delay_{min,max} mount option initialization
  ceph: fix xattr rbtree search
  ceph: fix getattr on directory when using norbytes

5 files changed, 54 insertions, 14 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 60d27bc9eb83..6b61ded701e1 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1560,9 +1560,10 @@ retry_locked:
 		/* NOTE: no side-effects allowed, until we take s_mutex */
 
 		revoking = cap->implemented & ~cap->issued;
-		if (revoking)
-			dout(" mds%d revoking %s\n", cap->mds,
-			     ceph_cap_string(revoking));
+		dout(" mds%d cap %p issued %s implemented %s revoking %s\n",
+		     cap->mds, cap, ceph_cap_string(cap->issued),
+		     ceph_cap_string(cap->implemented),
+		     ceph_cap_string(revoking));
 
 		if (cap == ci->i_auth_cap &&
 		    (cap->issued & CEPH_CAP_FILE_WR)) {
@@ -1658,6 +1659,8 @@ ack:
 
 		if (cap == ci->i_auth_cap && ci->i_dirty_caps)
 			flushing = __mark_caps_flushing(inode, session);
+		else
+			flushing = 0;
 
 		mds = cap->mds;  /* remember mds, so we don't repeat */
 		sent++;
@@ -1940,6 +1943,35 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 	}
 }
 
+static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
+				     struct ceph_mds_session *session,
+				     struct inode *inode)
+{
+	struct ceph_inode_info *ci = ceph_inode(inode);
+	struct ceph_cap *cap;
+	int delayed = 0;
+
+	spin_lock(&inode->i_lock);
+	cap = ci->i_auth_cap;
+	dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
+	     ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
+	__ceph_flush_snaps(ci, &session, 1);
+	if (ci->i_flushing_caps) {
+		delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
+				     __ceph_caps_used(ci),
+				     __ceph_caps_wanted(ci),
+				     cap->issued | cap->implemented,
+				     ci->i_flushing_caps, NULL);
+		if (delayed) {
+			spin_lock(&inode->i_lock);
+			__cap_delay_requeue(mdsc, ci);
+			spin_unlock(&inode->i_lock);
+		}
+	} else {
+		spin_unlock(&inode->i_lock);
+	}
+}
+
 
 /*
  * Take references to capabilities we hold, so that we don't release
@@ -2687,7 +2719,7 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
 	ceph_add_cap(inode, session, cap_id, -1,
 		     issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
 		     NULL /* no caps context */);
-	try_flush_caps(inode, session, NULL);
+	kick_flushing_inode_caps(mdsc, session, inode);
 	up_read(&mdsc->snap_rwsem);
 
 	/* make sure we re-request max_size, if necessary */
@@ -2785,8 +2817,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	case CEPH_CAP_OP_IMPORT:
 		handle_cap_import(mdsc, inode, h, session,
 				  snaptrace, snaptrace_len);
-		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_NODELAY,
-				session);
+		ceph_check_caps(ceph_inode(inode), 0, session);
 		goto done_unlocked;
 	}
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e835eff551e3..5625463aa479 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -710,10 +710,6 @@ static int fill_inode(struct inode *inode,
 			ci->i_ceph_flags |= CEPH_I_COMPLETE;
 			ci->i_max_offset = 2;
 		}
-
-		/* it may be better to set st_size in getattr instead? */
-		if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
-			inode->i_size = ci->i_rbytes;
 		break;
 	default:
 		pr_err("fill_inode %llx.%llx BAD mode 0%o\n",
@@ -1819,7 +1815,11 @@ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		else
 			stat->dev = 0;
 		if (S_ISDIR(inode->i_mode)) {
-			stat->size = ci->i_rbytes;
+			if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb),
+						RBYTES))
+				stat->size = ci->i_rbytes;
+			else
+				stat->size = ci->i_files + ci->i_subdirs;
 			stat->blocks = 0;
 			stat->blksize = 65536;
 		}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1e30d194a8e3..a1ee8fa3a8e7 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -693,9 +693,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (%d/%d)\n",
 				     inode, ceph_vinop(inode),
-				     frag.frag, frag.mds,
+				     frag.frag, mds,
 				     (int)r, frag.ndist);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 
 			/* since this file/dir wasn't known to be
@@ -708,7 +710,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				dout("choose_mds %p %llx.%llx "
 				     "frag %u mds%d (auth)\n",
 				     inode, ceph_vinop(inode), frag.frag, mds);
-				return mds;
+				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+				    CEPH_MDS_STATE_ACTIVE)
+					return mds;
 			}
 		}
 	}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bf6f0f34082a..9c5085465a63 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -290,6 +290,8 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
 
         fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
         fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+	fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
+	fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
         fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
         fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
         fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 6e12a6ba5f79..8c9eba6ef9df 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -219,6 +219,7 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct ceph_inode_xattr *xattr = NULL;
+	int name_len = strlen(name);
 	int c;
 
 	p = &ci->i_xattrs.index.rb_node;
@@ -226,6 +227,8 @@ static struct ceph_inode_xattr *__get_xattr(struct ceph_inode_info *ci,
 		parent = *p;
 		xattr = rb_entry(parent, struct ceph_inode_xattr, node);
 		c = strncmp(name, xattr->name, xattr->name_len);
+		if (c == 0 && name_len > xattr->name_len)
+			c = 1;
 		if (c < 0)
 			p = &(*p)->rb_left;
 		else if (c > 0)