X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fceph%2Fsnap.c;h=e6f9bc57d4722b3ed10522d002df36d5edccdf1b;hb=5a0e3ad6af8660be21ca98a971cd00f331318c05;hp=52f46a1208f5ea34864d7ae0bf837e27d75c0269;hpb=75eb3592811028e5b01835126483d115532a3aa1;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 52f46a1..e6f9bc5 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,7 +1,7 @@
 #include "ceph_debug.h"
 
-#include <linux/radix-tree.h>
 #include <linux/sort.h>
+#include <linux/slab.h>
 
 #include "super.h"
 #include "decode.h"
@@ -77,6 +77,28 @@ void ceph_get_snap_realm(struct ceph_mds_client *mdsc,
 	atomic_inc(&realm->nref);
 }
 
+static void __insert_snap_realm(struct rb_root *root,
+				struct ceph_snap_realm *new)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct ceph_snap_realm *r = NULL;
+
+	while (*p) {
+		parent = *p;
+		r = rb_entry(parent, struct ceph_snap_realm, node);
+		if (new->ino < r->ino)
+			p = &(*p)->rb_left;
+		else if (new->ino > r->ino)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&new->node, parent, p);
+	rb_insert_color(&new->node, root);
+}
+
 /*
  * create and get the realm rooted at @ino and bump its ref count.
  *
@@ -92,8 +114,6 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	if (!realm)
 		return ERR_PTR(-ENOMEM);
 
-	radix_tree_insert(&mdsc->snap_realms, ino, realm);
-
 	atomic_set(&realm->nref, 0);    /* tree does not take a ref */
 	realm->ino = ino;
 	INIT_LIST_HEAD(&realm->children);
@@ -101,24 +121,34 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	INIT_LIST_HEAD(&realm->empty_item);
 	INIT_LIST_HEAD(&realm->inodes_with_caps);
 	spin_lock_init(&realm->inodes_with_caps_lock);
+	__insert_snap_realm(&mdsc->snap_realms, realm);
 	dout("create_snap_realm %llx %p\n", realm->ino, realm);
 	return realm;
 }
 
 /*
- * find and get (if found) the realm rooted at @ino and bump its ref count.
+ * lookup the realm rooted at @ino.
  *
  * caller must hold snap_rwsem for write.
  */
 struct ceph_snap_realm *ceph_lookup_snap_realm(struct ceph_mds_client *mdsc,
 					       u64 ino)
 {
-	struct ceph_snap_realm *realm;
-
-	realm = radix_tree_lookup(&mdsc->snap_realms, ino);
-	if (realm)
-		dout("lookup_snap_realm %llx %p\n", realm->ino, realm);
-	return realm;
+	struct rb_node *n = mdsc->snap_realms.rb_node;
+	struct ceph_snap_realm *r;
+
+	while (n) {
+		r = rb_entry(n, struct ceph_snap_realm, node);
+		if (ino < r->ino)
+			n = n->rb_left;
+		else if (ino > r->ino)
+			n = n->rb_right;
+		else {
+			dout("lookup_snap_realm %llx %p\n", r->ino, r);
+			return r;
+		}
+	}
+	return NULL;
 }
 
 static void __put_snap_realm(struct ceph_mds_client *mdsc,
@@ -132,7 +162,7 @@ static void __destroy_snap_realm(struct ceph_mds_client *mdsc,
 {
 	dout("__destroy_snap_realm %p %llx\n", realm, realm->ino);
 
-	radix_tree_delete(&mdsc->snap_realms, realm->ino);
+	rb_erase(&realm->node, &mdsc->snap_realms);
 
 	if (realm->parent) {
 		list_del_init(&realm->child_item);
@@ -285,9 +315,9 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 	   because we rebuild_snap_realms() works _downward_ in
 	   hierarchy after each update.) */
 	if (realm->cached_context &&
-	    realm->cached_context->seq <= realm->seq &&
+	    realm->cached_context->seq == realm->seq &&
 	    (!parent ||
-	     realm->cached_context->seq <= parent->cached_context->seq)) {
+	     realm->cached_context->seq >= parent->cached_context->seq)) {
 		dout("build_snap_context %llx %p: %p seq %lld (%d snaps)"
 		     " (unchanged)\n",
 		     realm->ino, realm, realm->cached_context,
@@ -684,11 +714,11 @@ static void flush_snaps(struct ceph_mds_client *mdsc)
  * directory into another realm.
  */
 void ceph_handle_snap(struct ceph_mds_client *mdsc,
+		      struct ceph_mds_session *session,
 		      struct ceph_msg *msg)
 {
 	struct super_block *sb = mdsc->client->sb;
-	struct ceph_mds_session *session;
-	int mds;
+	int mds = session->s_mds;
 	u64 split;
 	int op;
 	int trace_len;
@@ -701,10 +731,6 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 	int i;
 	int locked_rwsem = 0;
 
-	if (msg->hdr.src.name.type != CEPH_ENTITY_TYPE_MDS)
-		return;
-	mds = le64_to_cpu(msg->hdr.src.name.num);
-
 	/* decode */
 	if (msg->front.iov_len < sizeof(*h))
 		goto bad;
@@ -720,15 +746,6 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 	dout("handle_snap from mds%d op %s split %llx tracelen %d\n", mds,
 	     ceph_snap_op_name(op), split, trace_len);
 
-	/* find session */
-	mutex_lock(&mdsc->mutex);
-	session = __ceph_lookup_mds_session(mdsc, mds);
-	mutex_unlock(&mdsc->mutex);
-	if (!session) {
-		dout("WTF, got snap but no session for mds%d\n", mds);
-		return;
-	}
-
 	mutex_lock(&session->s_mutex);
 	session->s_seq++;
 	mutex_unlock(&session->s_mutex);
@@ -802,7 +819,9 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			 * queued (again) by ceph_update_snap_trace()
 			 * below.  Queue it _now_, under the old context.
 			 */
+			spin_lock(&realm->inodes_with_caps_lock);
 			list_del_init(&ci->i_snap_realm_item);
+			spin_unlock(&realm->inodes_with_caps_lock);
 			spin_unlock(&inode->i_lock);
 
 			ceph_queue_cap_snap(ci,
@@ -877,6 +896,7 @@ split_skip_inode:
 
 bad:
 	pr_err("corrupt snap message from mds%d\n", mds);
+	ceph_msg_dump(msg);
 out:
 	if (locked_rwsem)
 		up_write(&mdsc->snap_rwsem);