Merge branch 'globalheartbeat-2' of git://oss.oracle.com/git/smushran/linux-2.6 into ocfs2-merge-window

Conflicts:
	fs/ocfs2/ocfs2.h

75 files changed, 1612 insertions, 864 deletions

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 16c8a2a98c1..899f168fd19 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -292,9 +292,11 @@ int v9fs_dir_release(struct inode *inode, struct file *filp)
 
 	fid = filp->private_data;
 	P9_DPRINTK(P9_DEBUG_VFS,
-			"inode: %p filp: %p fid: %d\n", inode, filp, fid->fid);
+			"v9fs_dir_release: inode: %p filp: %p fid: %d\n",
+			inode, filp, fid ? fid->fid : -1);
 	filemap_write_and_wait(inode->i_mapping);
-	p9_client_clunk(fid);
+	if (fid)
+		p9_client_clunk(fid);
 	return 0;
 }
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index c7c23eab944..9e670d52764 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -730,7 +730,10 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, int mode,
 		P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
 		goto error;
 	}
-	dentry->d_op = &v9fs_cached_dentry_operations;
+	if (v9ses->cache)
+		dentry->d_op = &v9fs_cached_dentry_operations;
+	else
+		dentry->d_op = &v9fs_dentry_operations;
 	d_instantiate(dentry, inode);
 	err = v9fs_fid_add(dentry, fid);
 	if (err < 0)
@@ -1128,6 +1131,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	v9fs_stat2inode(st, dentry->d_inode, dentry->d_inode->i_sb);
 		generic_fillattr(dentry->d_inode, stat);
 
+	p9stat_free(st);
 	kfree(st);
 	return 0;
 }
@@ -1489,6 +1493,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 
 	retval = strnlen(buffer, buflen);
 done:
+	p9stat_free(st);
 	kfree(st);
 	return retval;
 }
@@ -1942,7 +1947,7 @@ static const struct inode_operations v9fs_dir_inode_operations_dotu = {
 	.unlink = v9fs_vfs_unlink,
 	.mkdir = v9fs_vfs_mkdir,
 	.rmdir = v9fs_vfs_rmdir,
-	.mknod = v9fs_vfs_mknod_dotl,
+	.mknod = v9fs_vfs_mknod,
 	.rename = v9fs_vfs_rename,
 	.getattr = v9fs_vfs_getattr,
 	.setattr = v9fs_vfs_setattr,
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index f9311077de6..1d12ba0ed3d 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -122,6 +122,10 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 	fid = v9fs_session_init(v9ses, dev_name, data);
 	if (IS_ERR(fid)) {
 		retval = PTR_ERR(fid);
+		/*
+		 * we need to call session_close to tear down some
+		 * of the data structure setup by session_init
+		 */
 		goto close_session;
 	}
 
@@ -144,7 +148,6 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		retval = -ENOMEM;
 		goto release_sb;
 	}
-
 	sb->s_root = root;
 
 	if (v9fs_proto_dotl(v9ses)) {
@@ -152,7 +155,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		st = p9_client_getattr_dotl(fid, P9_STATS_BASIC);
 		if (IS_ERR(st)) {
 			retval = PTR_ERR(st);
-			goto clunk_fid;
+			goto release_sb;
 		}
 
 		v9fs_stat2inode_dotl(st, root->d_inode);
@@ -162,7 +165,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		st = p9_client_stat(fid);
 		if (IS_ERR(st)) {
 			retval = PTR_ERR(st);
-			goto clunk_fid;
+			goto release_sb;
 		}
 
 		root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
@@ -174,19 +177,24 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 
 	v9fs_fid_add(root, fid);
 
-P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
+	P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
 	simple_set_mnt(mnt, sb);
 	return 0;
 
 clunk_fid:
 	p9_client_clunk(fid);
-
 close_session:
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
 	return retval;
-
 release_sb:
+	/*
+	 * we will do the session_close and root dentry release
+	 * in the below call. But we need to clunk fid, because we haven't
+	 * attached the fid to dentry so it won't get clunked
+	 * automatically.
+	 */
+	p9_client_clunk(fid);
 	deactivate_locked_super(sb);
 	return retval;
 }
diff --git a/fs/aio.c b/fs/aio.c
index 3006b5bc33d..250b0a73c8a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -712,8 +712,16 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
 	 */
 	ret = retry(iocb);
 
-	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED)
+	if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
+		/*
+		 * There's no easy way to restart the syscall since other AIO's
+		 * may be already running. Just fail this IO with EINTR.
+		 */
+		if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR ||
+			     ret == -ERESTARTNOHAND || ret == -ERESTART_RESTARTBLOCK))
+			ret = -EINTR;
 		aio_complete(iocb, ret, 0);
+	}
 out:
 	spin_lock_irq(&ctx->ctx_lock);
 
@@ -1659,6 +1667,9 @@ long do_io_submit(aio_context_t ctx_id, long nr,
 	if (unlikely(nr < 0))
 		return -EINVAL;
 
+	if (unlikely(nr > LONG_MAX/sizeof(*iocbpp)))
+		nr = LONG_MAX/sizeof(*iocbpp);
+
 	if (unlikely(!access_ok(VERIFY_READ, iocbpp, (nr*sizeof(*iocbpp)))))
 		return -EFAULT;
 
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index a7528b91393..fd0cc0bf9a4 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -724,7 +724,7 @@ static int __init init_misc_binfmt(void)
 {
 	int err = register_filesystem(&bm_fs_type);
 	if (!err) {
-		err = register_binfmt(&misc_format);
+		err = insert_binfmt(&misc_format);
 		if (err)
 			unregister_filesystem(&bm_fs_type);
 	}
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 612a5c38d3c..4d0ff5ee27b 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -413,10 +413,10 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Allocate kernel buffer for protection data */
 	len = sectors * blk_integrity_tuple_size(bi);
-	buf = kmalloc(len, GFP_NOIO | __GFP_NOFAIL | q->bounce_gfp);
+	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
-		return -EIO;
+		return -ENOMEM;
 	}
 
 	end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index bc87b9c1d27..0fcd2640c23 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -3,6 +3,7 @@ config CEPH_FS
 	depends on INET && EXPERIMENTAL
 	select LIBCRC32C
 	select CRYPTO_AES
+	select CRYPTO
 	help
 	  Choose Y or M here to include support for mounting the
 	  experimental Ceph distributed file system.  Ceph is an extremely
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4cfce1ee31f..efbc604001c 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -411,8 +411,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	if (i_size < page_off + len)
 		len = i_size - page_off;
 
-	dout("writepage %p page %p index %lu on %llu~%u\n",
-	     inode, page, page->index, page_off, len);
+	dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",
+	     inode, page, page->index, page_off, len, snapc);
 
 	writeback_stat = atomic_long_inc_return(&client->writeback_count);
 	if (writeback_stat >
@@ -766,7 +766,8 @@ get_more_pages:
 			/* ok */
 			if (locked_pages == 0) {
 				/* prepare async write request */
-				offset = page->index << PAGE_CACHE_SHIFT;
+				offset = (unsigned long long)page->index
+					<< PAGE_CACHE_SHIFT;
 				len = wsize;
 				req = ceph_osdc_new_request(&client->osdc,
 					    &ci->i_layout,
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a2069b6680a..73c153092f7 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -814,7 +814,7 @@ int __ceph_caps_used(struct ceph_inode_info *ci)
 		used |= CEPH_CAP_PIN;
 	if (ci->i_rd_ref)
 		used |= CEPH_CAP_FILE_RD;
-	if (ci->i_rdcache_ref || ci->i_rdcache_gen)
+	if (ci->i_rdcache_ref || ci->vfs_inode.i_data.nrpages)
 		used |= CEPH_CAP_FILE_CACHE;
 	if (ci->i_wr_ref)
 		used |= CEPH_CAP_FILE_WR;
@@ -1195,10 +1195,14 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
  * asynchronously back to the MDS once sync writes complete and dirty
  * data is written out.
  *
+ * Unless @again is true, skip cap_snaps that were already sent to
+ * the MDS (i.e., during this session).
+ *
  * Called under i_lock.  Takes s_mutex as needed.
  */
 void __ceph_flush_snaps(struct ceph_inode_info *ci,
-			struct ceph_mds_session **psession)
+			struct ceph_mds_session **psession,
+			int again)
 		__releases(ci->vfs_inode->i_lock)
 		__acquires(ci->vfs_inode->i_lock)
 {
@@ -1227,7 +1231,7 @@ retry:
 		 * pages to be written out.
 		 */
 		if (capsnap->dirty_pages || capsnap->writing)
-			continue;
+			break;
 
 		/*
 		 * if cap writeback already occurred, we should have dropped
@@ -1240,6 +1244,13 @@ retry:
 			dout("no auth cap (migrating?), doing nothing\n");
 			goto out;
 		}
+
+		/* only flush each capsnap once */
+		if (!again && !list_empty(&capsnap->flushing_item)) {
+			dout("already flushed %p, skipping\n", capsnap);
+			continue;
+		}
+
 		mds = ci->i_auth_cap->session->s_mds;
 		mseq = ci->i_auth_cap->mseq;
 
@@ -1276,8 +1287,8 @@ retry:
 			      &session->s_cap_snaps_flushing);
 		spin_unlock(&inode->i_lock);
 
-		dout("flush_snaps %p cap_snap %p follows %lld size %llu\n",
-		     inode, capsnap, next_follows, capsnap->size);
+		dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
+		     inode, capsnap, capsnap->follows, capsnap->flush_tid);
 		send_cap_msg(session, ceph_vino(inode).ino, 0,
 			     CEPH_CAP_OP_FLUSHSNAP, capsnap->issued, 0,
 			     capsnap->dirty, 0, capsnap->flush_tid, 0, mseq,
@@ -1314,7 +1325,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci)
 	struct inode *inode = &ci->vfs_inode;
 
 	spin_lock(&inode->i_lock);
-	__ceph_flush_snaps(ci, NULL);
+	__ceph_flush_snaps(ci, NULL, 0);
 	spin_unlock(&inode->i_lock);
 }
 
@@ -1477,7 +1488,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 
 	/* flush snaps first time around only */
 	if (!list_empty(&ci->i_cap_snaps))
-		__ceph_flush_snaps(ci, &session);
+		__ceph_flush_snaps(ci, &session, 0);
 	goto retry_locked;
 retry:
 	spin_lock(&inode->i_lock);
@@ -1894,7 +1905,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
 		if (cap && cap->session == session) {
 			dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
 			     cap, capsnap);
-			__ceph_flush_snaps(ci, &session);
+			__ceph_flush_snaps(ci, &session, 1);
 		} else {
 			pr_err("%p auth cap %p not mds%d ???\n", inode,
 			       cap, session->s_mds);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6e4f43ff23e..a1986eb5204 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1021,11 +1021,15 @@ out_touch:
 static void ceph_dentry_release(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
-	struct inode *parent_inode = dentry->d_parent->d_inode;
-	u64 snapid = ceph_snap(parent_inode);
+	struct inode *parent_inode = NULL;
+	u64 snapid = CEPH_NOSNAP;
 
+	if (!IS_ROOT(dentry)) {
+		parent_inode = dentry->d_parent->d_inode;
+		if (parent_inode)
+			snapid = ceph_snap(parent_inode);
+	}
 	dout("dentry_release %p parent %p\n", dentry, parent_inode);
-
 	if (parent_inode && snapid != CEPH_SNAPDIR) {
 		struct ceph_inode_info *ci = ceph_inode(parent_inode);
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e7cca414da0..62377ec37ed 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -845,7 +845,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
  * the caller) if we fail.
  */
 static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash)
+				    bool *prehash, bool set_offset)
 {
 	struct dentry *realdn;
 
@@ -877,7 +877,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	}
 	if ((!prehash || *prehash) && d_unhashed(dn))
 		d_rehash(dn);
-	ceph_set_dentry_offset(dn);
+	if (set_offset)
+		ceph_set_dentry_offset(dn);
 out:
 	return dn;
 }
@@ -1062,7 +1063,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 				d_delete(dn);
 				goto done;
 			}
-			dn = splice_dentry(dn, in, &have_lease);
+			dn = splice_dentry(dn, in, &have_lease, true);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1105,7 +1106,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			goto done;
 		}
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
-		dn = splice_dentry(dn, in, NULL);
+		dn = splice_dentry(dn, in, NULL, true);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1237,7 +1238,7 @@ retry_lookup:
 				err = PTR_ERR(in);
 				goto out;
 			}
-			dn = splice_dentry(dn, in, NULL);
+			dn = splice_dentry(dn, in, NULL, false);
 			if (IS_ERR(dn))
 				dn = NULL;
 		}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index f091b135178..fad95f8f260 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2374,6 +2374,8 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 						num_fcntl_locks,
 						num_flock_locks);
 		unlock_kernel();
+	} else {
+		err = ceph_pagelist_append(pagelist, &rec, reclen);
 	}
 
 out_free:
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
index b6859f47d36..46a368b6dce 100644
--- a/fs/ceph/pagelist.c
+++ b/fs/ceph/pagelist.c
@@ -5,10 +5,18 @@
 
 #include "pagelist.h"
 
+static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
+{
+	struct page *page = list_entry(pl->head.prev, struct page,
+				       lru);
+	kunmap(page);
+}
+
 int ceph_pagelist_release(struct ceph_pagelist *pl)
 {
 	if (pl->mapped_tail)
-		kunmap(pl->mapped_tail);
+		ceph_pagelist_unmap_tail(pl);
+
 	while (!list_empty(&pl->head)) {
 		struct page *page = list_first_entry(&pl->head, struct page,
 						     lru);
@@ -26,7 +34,7 @@ static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
 	pl->room += PAGE_SIZE;
 	list_add_tail(&page->lru, &pl->head);
 	if (pl->mapped_tail)
-		kunmap(pl->mapped_tail);
+		ceph_pagelist_unmap_tail(pl);
 	pl->mapped_tail = kmap(page);
 	return 0;
 }
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 4868b9dcac5..190b6c4a6f2 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -119,6 +119,7 @@ static struct ceph_snap_realm *ceph_create_snap_realm(
 	INIT_LIST_HEAD(&realm->children);
 	INIT_LIST_HEAD(&realm->child_item);
 	INIT_LIST_HEAD(&realm->empty_item);
+	INIT_LIST_HEAD(&realm->dirty_item);
 	INIT_LIST_HEAD(&realm->inodes_with_caps);
 	spin_lock_init(&realm->inodes_with_caps_lock);
 	__insert_snap_realm(&mdsc->snap_realms, realm);
@@ -467,7 +468,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 		INIT_LIST_HEAD(&capsnap->ci_item);
 		INIT_LIST_HEAD(&capsnap->flushing_item);
 
-		capsnap->follows = snapc->seq - 1;
+		capsnap->follows = snapc->seq;
 		capsnap->issued = __ceph_caps_issued(ci, NULL);
 		capsnap->dirty = dirty;
 
@@ -604,6 +605,7 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc,
 	struct ceph_snap_realm *realm;
 	int invalidate = 0;
 	int err = -ENOMEM;
+	LIST_HEAD(dirty_realms);
 
 	dout("update_snap_trace deletion=%d\n", deletion);
 more:
@@ -626,24 +628,6 @@ more:
 		}
 	}
 
-	if (le64_to_cpu(ri->seq) > realm->seq) {
-		dout("update_snap_trace updating %llx %p %lld -> %lld\n",
-		     realm->ino, realm, realm->seq, le64_to_cpu(ri->seq));
-		/*
-		 * if the realm seq has changed, queue a cap_snap for every
-		 * inode with open caps.  we do this _before_ we update
-		 * the realm info so that we prepare for writeback under the
-		 * _previous_ snap context.
-		 *
-		 * ...unless it's a snap deletion!
-		 */
-		if (!deletion)
-			queue_realm_cap_snaps(realm);
-	} else {
-		dout("update_snap_trace %llx %p seq %lld unchanged\n",
-		     realm->ino, realm, realm->seq);
-	}
-
 	/* ensure the parent is correct */
 	err = adjust_snap_realm_parent(mdsc, realm, le64_to_cpu(ri->parent));
 	if (err < 0)