Merge branch 'master' into gfs2

38 files changed, 821 insertions, 348 deletions

diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index ba1c88af49fe..82011019494c 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -308,7 +308,7 @@ static struct adfs_discmap *adfs_read_map(struct super_block *sb, struct adfs_di
 	if (adfs_checkmap(sb, dm))
 		return dm;
 
-	adfs_error(sb, NULL, "map corrupted");
+	adfs_error(sb, "map corrupted");
 
 error_free:
 	while (--zone >= 0)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 37534573960b..045f98854f14 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -884,6 +884,61 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
+static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
+{
+	int ret = 0;
+	struct inode *bd_inode = bdev->bd_inode;
+	struct gendisk *disk = bdev->bd_disk;
+
+	mutex_lock_nested(&bdev->bd_mutex, subclass);
+	lock_kernel();
+	if (!--bdev->bd_openers) {
+		sync_blockdev(bdev);
+		kill_bdev(bdev);
+	}
+	if (bdev->bd_contains == bdev) {
+		if (disk->fops->release)
+			ret = disk->fops->release(bd_inode, NULL);
+	} else {
+		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
+				  subclass + 1);
+		bdev->bd_contains->bd_part_count--;
+		mutex_unlock(&bdev->bd_contains->bd_mutex);
+	}
+	if (!bdev->bd_openers) {
+		struct module *owner = disk->fops->owner;
+
+		put_disk(disk);
+		module_put(owner);
+
+		if (bdev->bd_contains != bdev) {
+			kobject_put(&bdev->bd_part->kobj);
+			bdev->bd_part = NULL;
+		}
+		bdev->bd_disk = NULL;
+		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
+		if (bdev != bdev->bd_contains)
+			__blkdev_put(bdev->bd_contains, subclass + 1);
+		bdev->bd_contains = NULL;
+	}
+	unlock_kernel();
+	mutex_unlock(&bdev->bd_mutex);
+	bdput(bdev);
+	return ret;
+}
+
+int blkdev_put(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
+}
+EXPORT_SYMBOL(blkdev_put);
+
+int blkdev_put_partition(struct block_device *bdev)
+{
+	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
+}
+EXPORT_SYMBOL(blkdev_put_partition);
+
 static int
 blkdev_get_whole(struct block_device *bdev, mode_t mode, unsigned flags);
 
@@ -980,7 +1035,7 @@ out_first:
 	bdev->bd_disk = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		blkdev_put(bdev->bd_contains);
+		__blkdev_put(bdev->bd_contains, BD_MUTEX_WHOLE);
 	bdev->bd_contains = NULL;
 	put_disk(disk);
 	module_put(owner);
@@ -1079,63 +1134,6 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	return res;
 }
 
-static int __blkdev_put(struct block_device *bdev, unsigned int subclass)
-{
-	int ret = 0;
-	struct inode *bd_inode = bdev->bd_inode;
-	struct gendisk *disk = bdev->bd_disk;
-
-	mutex_lock_nested(&bdev->bd_mutex, subclass);
-	lock_kernel();
-	if (!--bdev->bd_openers) {
-		sync_blockdev(bdev);
-		kill_bdev(bdev);
-	}
-	if (bdev->bd_contains == bdev) {
-		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
-	} else {
-		mutex_lock_nested(&bdev->bd_contains->bd_mutex,
-				  subclass + 1);
-		bdev->bd_contains->bd_part_count--;
-		mutex_unlock(&bdev->bd_contains->bd_mutex);
-	}
-	if (!bdev->bd_openers) {
-		struct module *owner = disk->fops->owner;
-
-		put_disk(disk);
-		module_put(owner);
-
-		if (bdev->bd_contains != bdev) {
-			kobject_put(&bdev->bd_part->kobj);
-			bdev->bd_part = NULL;
-		}
-		bdev->bd_disk = NULL;
-		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
-		if (bdev != bdev->bd_contains)
-			__blkdev_put(bdev->bd_contains, subclass + 1);
-		bdev->bd_contains = NULL;
-	}
-	unlock_kernel();
-	mutex_unlock(&bdev->bd_mutex);
-	bdput(bdev);
-	return ret;
-}
-
-int blkdev_put(struct block_device *bdev)
-{
-	return __blkdev_put(bdev, BD_MUTEX_NORMAL);
-}
-
-EXPORT_SYMBOL(blkdev_put);
-
-int blkdev_put_partition(struct block_device *bdev)
-{
-	return __blkdev_put(bdev, BD_MUTEX_PARTITION);
-}
-
-EXPORT_SYMBOL(blkdev_put_partition);
-
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 19ffb043abbc..3a3567433b92 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1168,7 +1168,7 @@ static int ep_unlink(struct eventpoll *ep, struct epitem *epi)
 eexit_1:
 
 	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n",
-		     current, ep, epi->file, error));
+		     current, ep, epi->ffd.file, error));
 
 	return error;
 }
@@ -1236,7 +1236,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	struct eventpoll *ep = epi->ep;
 
 	DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
-		     current, epi->file, epi, ep));
+		     current, epi->ffd.file, epi, ep));
 
 	write_lock_irqsave(&ep->lock, flags);
 
diff --git a/fs/exec.c b/fs/exec.c
index 8344ba73a2a6..54135df2a966 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -486,8 +486,6 @@ struct file *open_exec(const char *name)
 		if (!(nd.mnt->mnt_flags & MNT_NOEXEC) &&
 		    S_ISREG(inode->i_mode)) {
 			int err = vfs_permission(&nd, MAY_EXEC);
-			if (!err && !(inode->i_mode & 0111))
-				err = -EACCES;
 			file = ERR_PTR(err);
 			if (!err) {
 				file = nameidata_to_filp(&nd, O_RDONLY);
@@ -753,7 +751,7 @@ no_thread_group:
 
 		write_lock_irq(&tasklist_lock);
 		spin_lock(&oldsighand->siglock);
-		spin_lock(&newsighand->siglock);
+		spin_lock_nested(&newsighand->siglock, SINGLE_DEPTH_NESTING);
 
 		rcu_assign_pointer(current->sighand, newsighand);
 		recalc_sigpending();
@@ -922,12 +920,6 @@ int prepare_binprm(struct linux_binprm *bprm)
 	int retval;
 
 	mode = inode->i_mode;
-	/*
-	 * Check execute perms again - if the caller has CAP_DAC_OVERRIDE,
-	 * generic_permission lets a non-executable through
-	 */
-	if (!(mode & 0111))	/* with at least _one_ execute bit set */
-		return -EACCES;
 	if (bprm->file->f_op == NULL)
 		return -EACCES;
 
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index f2702cda9779..681dea8f9532 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -775,7 +775,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	if (EXT2_INODE_SIZE(sb) == 0)
 		goto cantfind_ext2;
 	sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
-	if (sbi->s_inodes_per_block == 0)
+	if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
 		goto cantfind_ext2;
 	sbi->s_itb_per_group = sbi->s_inodes_per_group /
 					sbi->s_inodes_per_block;
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index a504a40d6d29..063d994bda0b 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -1269,12 +1269,12 @@ ext3_fsblk_t ext3_new_blocks(handle_t *handle, struct inode *inode,
 		goal = le32_to_cpu(es->s_first_data_block);
 	group_no = (goal - le32_to_cpu(es->s_first_data_block)) /
 			EXT3_BLOCKS_PER_GROUP(sb);
+	goal_group = group_no;
+retry_alloc:
 	gdp = ext3_get_group_desc(sb, group_no, &gdp_bh);
 	if (!gdp)
 		goto io_error;
 
-	goal_group = group_no;
-retry:
 	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
 	/*
 	 * if there is not enough free blocks to make a new resevation
@@ -1349,7 +1349,7 @@ retry:
 	if (my_rsv) {
 		my_rsv = NULL;
 		group_no = goal_group;
-		goto retry;
+		goto retry_alloc;
 	}
 	/* No space left on the device */
 	*errp = -ENOSPC;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 63614ed16336..5c4fcd1dbf59 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -395,14 +395,16 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
 	struct fuse_readpages_data data;
 	int err;
 
+	err = -EIO;
 	if (is_bad_inode(inode))
-		return -EIO;
+		goto clean_pages_up;
 
 	data.file = file;
 	data.inode = inode;
 	data.req = fuse_get_req(fc);
+	err = PTR_ERR(data.req);
 	if (IS_ERR(data.req))
-		return PTR_ERR(data.req);
+		goto clean_pages_up;
 
 	err = read_cache_pages(mapping, pages, fuse_readpages_fill, &data);
 	if (!err) {
@@ -412,6 +414,10 @@ static int fuse_readpages(struct file *file, struct address_space *mapping,
 			fuse_put_request(fc, data.req);
 	}
 	return err;
+
+clean_pages_up:
+	put_pages_list(pages);
+	return err;
 }
 
 static size_t fuse_send_write(struct fuse_req *req, struct file *file,
diff --git a/fs/ioprio.c b/fs/ioprio.c
index 93aa5715f224..78b1deae3fa2 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -44,6 +44,9 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
 	task->ioprio = ioprio;
 
 	ioc = task->io_context;
+	/* see wmb() in current_io_context() */
+	smp_read_barrier_depends();
+
 	if (ioc && ioc->set_ioprio)
 		ioc->set_ioprio(ioc, ioprio);
 
@@ -111,9 +114,9 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 					continue;
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
-					break;
+					goto free_uid;
 			} while_each_thread(g, p);
-
+free_uid:
 			if (who)
 				free_uid(user);
 			break;
@@ -137,6 +140,29 @@ out:
 	return ret;
 }
 
+int ioprio_best(unsigned short aprio, unsigned short bprio)
+{
+	unsigned short aclass = IOPRIO_PRIO_CLASS(aprio);
+	unsigned short bclass = IOPRIO_PRIO_CLASS(bprio);
+
+	if (!ioprio_valid(aprio))
+		return bprio;
+	if (!ioprio_valid(bprio))
+		return aprio;
+
+	if (aclass == IOPRIO_CLASS_NONE)
+		aclass = IOPRIO_CLASS_BE;
+	if (bclass == IOPRIO_CLASS_NONE)
+		bclass = IOPRIO_CLASS_BE;
+
+	if (aclass == bclass)
+		return min(aprio, bprio);
+	if (aclass > bclass)
+		return bprio;
+	else
+		return aprio;
+}
+
 asmlinkage long sys_ioprio_get(int which, int who)
 {
 	struct task_struct *g, *p;
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 0971814c38b8..42da60784311 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -261,7 +261,7 @@ void journal_commit_transaction(journal_t *journal)
 			struct buffer_head *bh = jh2bh(jh);
 
 			jbd_lock_bh_state(bh);
-			kfree(jh->b_committed_data);
+			jbd_slab_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			jbd_unlock_bh_state(bh);
 		}
@@ -745,14 +745,14 @@ restart_loop:
 		 * Otherwise, we can just throw away the frozen data now.
 		 */
 		if (jh->b_committed_data) {
-			kfree(jh->b_committed_data);
+			jbd_slab_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
 			}
 		} else if (jh->b_frozen_data) {
-			kfree(jh->b_frozen_data);
+			jbd_slab_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
 		}
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 8c9b28dff119..f66724ce443a 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -84,6 +84,7 @@ EXPORT_SYMBOL(journal_force_commit);
 
 static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
 static void __journal_abort_soft (journal_t *journal, int errno);
+static int journal_create_jbd_slab(size_t slab_size);
 
 /*
  * Helper function used to manage commit timeouts
@@ -328,10 +329,10 @@ repeat:
 		char *tmp;
 
 		jbd_unlock_bh_state(bh_in);
-		tmp = jbd_rep_kmalloc(bh_in->b_size, GFP_NOFS);
+		tmp = jbd_slab_alloc(bh_in->b_size, GFP_NOFS);
 		jbd_lock_bh_state(bh_in);
 		if (jh_in->b_frozen_data) {
-			kfree(tmp);
+			jbd_slab_free(tmp, bh_in->b_size);
 			goto repeat;
 		}
 
@@ -1069,17 +1070,17 @@ static int load_superblock(journal_t *journal)
 int journal_load(journal_t *journal)
 {
 	int err;
+	journal_superblock_t *sb;
 
 	err = load_superblock(journal);
 	if (err)
 		return err;
 
+	sb = journal->j_superblock;
 	/* If this is a V2 superblock, then we have to check the
 	 * features flags on it. */
 
 	if (journal->j_format_version >= 2) {
-		journal_superblock_t *sb = journal->j_superblock;
-
 		if ((sb->s_feature_ro_compat &
 		     ~cpu_to_be32(JFS_KNOWN_ROCOMPAT_FEATURES)) ||
 		    (sb->s_feature_incompat &
@@ -1090,6 +1091,13 @@ int journal_load(journal_t *journal)
 		}
 	}
 
+	/*
+	 * Create a slab for this blocksize
+	 */
+	err = journal_create_jbd_slab(cpu_to_be32(sb->s_blocksize));
+	if (err)
+		return err;
+
 	/* Let the recovery code check whether it needs to recover any
 	 * data from the journal. */
 	if (journal_recover(journal))
@@ -1612,6 +1620,77 @@ void * __jbd_kmalloc (const char *where, size_t size, gfp_t flags, int retry)
 }
 
 /*
+ * jbd slab management: create 1k, 2k, 4k, 8k slabs as needed
+ * and allocate frozen and commit buffers from these slabs.
+ *
+ * Reason for doing this is to avoid, SLAB_DEBUG - since it could
+ * cause bh to cross page boundary.
+ */
+
+#define JBD_MAX_SLABS 5
+#define JBD_SLAB_INDEX(size)  (size >> 11)
+
+static kmem_cache_t *jbd_slab[JBD_MAX_SLABS];
+static const char *jbd_slab_names[JBD_MAX_SLABS] = {
+	"jbd_1k", "jbd_2k", "jbd_4k", NULL, "jbd_8k"
+};
+
+static void journal_destroy_jbd_slabs(void)
+{
+	int i;
+
+	for (i = 0; i < JBD_MAX_SLABS; i++) {
+		if (jbd_slab[i])
+			kmem_cache_destroy(jbd_slab[i]);
+		jbd_slab[i] = NULL;
+	}
+}
+
+static int journal_create_jbd_slab(size_t slab_size)
+{
+	int i = JBD_SLAB_INDEX(slab_size);
+
+	BUG_ON(i >= JBD_MAX_SLABS);
+
+	/*
+	 * Check if we already have a slab created for this size
+	 */
+	if (jbd_slab[i])
+		return 0;
+
+	/*
+	 * Create a slab and force alignment to be same as slabsize -
+	 * this will make sure that allocations won't cross the page
+	 * boundary.
+	 */
+	jbd_slab[i] = kmem_cache_create(jbd_slab_names[i],
+				slab_size, slab_size, 0, NULL, NULL);
+	if (!jbd_slab[i]) {
+		printk(KERN_EMERG "JBD: no memory for jbd_slab cache\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void * jbd_slab_alloc(size_t size, gfp_t flags)
+{
+	int idx;
+
+	idx = JBD_SLAB_INDEX(size);
+	BUG_ON(jbd_slab[idx] == NULL);
+	return kmem_cache_alloc(jbd_slab[idx], flags | __GFP_NOFAIL);
+}
+
+void jbd_slab_free(void *ptr,  size_t size)
+{
+	int idx;
+
+	idx = JBD_SLAB_INDEX(size);
+	BUG_ON(jbd_slab[idx] == NULL);
+	kmem_cache_free(jbd_slab[idx], ptr);
+}
+
+/*
  * Journal_head storage management
  */
 static kmem_cache_t *journal_head_cache;
@@ -1799,13 +1878,13 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 				printk(KERN_WARNING "%s: freeing "
 						"b_frozen_data\n",
 						__FUNCTION__);
-				kfree(jh->b_frozen_data);
+				jbd_slab_free(jh->b_frozen_data, bh->b_size);
 			}
 			if (jh->b_committed_data) {
 				printk(KERN_WARNING "%s: freeing "
 						"b_committed_data\n",
 						__FUNCTION__);
-				kfree(jh->b_committed_data);
+				jbd_slab_free(jh->b_committed_data, bh->b_size);
 			}
 			bh->b_private = NULL;
 			jh->b_bh = NULL;	/* debug, really */
@@ -1961,6 +2040,7 @@ static void journal_destroy_caches(void)
 	journal_destroy_revoke_caches();
 	journal_destroy_journal_head_cache();
 	journal_destroy_handle_cache();
+	journal_destroy_jbd_slabs();
 }
 
 static int __init journal_init(void)
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 508b2ea91f43..de2e4cbbf79a 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -666,8 +666,9 @@ repeat:
 			if (!frozen_buffer) {
 				JBUFFER_TRACE(jh, "allocate memory for buffer");
 				jbd_unlock_bh_state(bh);
-				frozen_buffer = jbd_kmalloc(jh2bh(jh)->b_size,
-							    GFP_NOFS);
+				frozen_buffer =
+					jbd_slab_alloc(jh2bh(jh)->b_size,
+							 GFP_NOFS);
 				if (!frozen_buffer) {
 					printk(KERN_EMERG
 					       "%s: OOM for frozen_buffer\n",
@@ -879,7 +880,7 @@ int journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 
 repeat:
 	if (!jh->b_committed_data) {
-		committed_data = jbd_kmalloc(jh2bh(jh)->b_size, GFP_NOFS);
+		committed_data = jbd_slab_alloc(jh2bh(jh)->b_size, GFP_NOFS);
 		if (!committed_data) {
 			printk(KERN_EMERG "%s: No memory for committed data\n",
 				__FUNCTION__);
@@ -906,7 +907,7 @@ repeat:
 out:
 	journal_put_journal_head(jh);
 	if (unlikely(committed_data))
-		kfree(committed_data);
+		jbd_slab_free(committed_data, bh->b_size);
 	return err;
 }
 
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 43e3f566aad6..a223cf4faa9b 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -168,16 +168,15 @@ void jfs_dirty_inode(struct inode *inode)
 	set_cflag(COMMIT_Dirty, inode);
 }
 
-static int
-jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
-			struct buffer_head *bh_result, int create)
+int jfs_get_block(struct inode *ip, sector_t lblock,
+		  struct buffer_head *bh_result, int create)
 {
 	s64 lblock64 = lblock;
 	int rc = 0;
 	xad_t xad;
 	s64 xaddr;
 	int xflag;
-	s32 xlen = max_blocks;
+	s32 xlen = bh_result->b_size >> ip->i_blkbits;
 
 	/*
 	 * Take appropriate lock on inode
@@ -188,7 +187,7 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
 		IREAD_LOCK(ip);
 
 	if (((lblock64 << ip->i_sb->s_blocksize_bits) < ip->i_size) &&
-	    (!xtLookup(ip, lblock64, max_blocks, &xflag, &xaddr, &xlen, 0)) &&
+	    (!xtLookup(ip, lblock64, xlen, &xflag, &xaddr, &xlen, 0)) &&
 	    xaddr) {
 		if (xflag & XAD_NOTRECORDED) {
 			if (!create)
@@ -255,13 +254,6 @@ jfs_get_blocks(struct inode *ip, sector_t lblock, unsigned long max_blocks,
 	return rc;
 }
 
-static int jfs_get_block(struct inode *ip, sector_t lblock,
-			 struct buffer_head *bh_result, int create)
-{
-	return jfs_get_blocks(ip, lblock, bh_result->b_size >> ip->i_blkbits,
-			bh_result, create);
-}
-
 static int jfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	return nobh_writepage(page, jfs_get_block, wbc);
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index b5c7da6190dc..1fc48df670c8 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -32,6 +32,7 @@ extern void jfs_truncate_nolock(struct inode *, loff_t);
 extern void jfs_free_zero_link(struct inode *);
 extern struct dentry *jfs_get_parent(struct dentry *dentry);
 extern void jfs_set_inode_flags(struct inode *);
+extern int jfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
 extern const struct address_space_operations jfs_aops;
 extern struct inode_operations jfs_dir_inode_operations;
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 4f6cfebc82db..143bcd1d5eaa 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -26,6 +26,7 @@
 #include <linux/moduleparam.h>
 #include <linux/kthread.h>
 #include <linux/posix_acl.h>
+#include <linux/buffer_head.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 
@@ -298,7 +299,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize,
 			break;
 		}
 
-#if defined(CONFIG_QUOTA)
+#ifdef CONFIG_QUOTA
 		case Opt_quota:
 		case Opt_usrquota:
 			*flag |= JFS_USRQUOTA;
@@ -597,7 +598,7 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (sbi->flag & JFS_NOINTEGRITY)
 		seq_puts(seq, ",nointegrity");
 
-#if defined(CONFIG_QUOTA)
+#ifdef CONFIG_QUOTA
 	if (sbi->flag & JFS_USRQUOTA)
 		seq_puts(seq, ",usrquota");
 
@@ -608,6 +609,113 @@ static int jfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	return 0;
 }
 
+#ifdef CONFIG_QUOTA
+
+/* Read data from quotafile - avoid pagecache and such because we cannot afford
+ * acquiring the locks... As quota files are never truncated and quota code
+ * itself serializes the operations (and noone else should touch the files)
+ * we don't have to be afraid of races */
+static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
+			      size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	sector_t blk = off >> sb->s_blocksize_bits;
+	int err = 0;
+	int offset = off & (sb->s_blocksize - 1);
+	int tocopy;
+	size_t toread;
+	struct buffer_head tmp_bh;
+	struct buffer_head *bh;
+	loff_t i_size = i_size_read(inode);
+
+	if (off > i_size)
+		return 0;
+	if (off+len > i_size)
+		len = i_size-off;
+	toread = len;
+	while (toread > 0) {
+		tocopy = sb->s_blocksize - offset < toread ?
+				sb->s_blocksize - offset : toread;
+
+		tmp_bh.b_state = 0;
+		tmp_bh.b_size = 1 << inode->i_blkbits;
+		err = jfs_get_block(inode, blk, &tmp_bh, 0);
+		if (err)
+			return err;
+		if (!buffer_mapped(&tmp_bh))	/* A hole? */
+			memset(data, 0, tocopy);
+		else {
+			bh = sb_bread(sb, tmp_bh.b_blocknr);
+			if (!bh)
+				return -EIO;
+			memcpy(data, bh->b_data+offset, tocopy);
+			brelse(bh);
+		}
+		offset = 0;
+		toread -= tocopy;
+		data += tocopy;
+		blk++;
+	}
+	return len;
+}
+
+/* Write to quotafile */
+static ssize_t jfs_quota_write(struct super_block *sb, int type,
+			       const char *data, size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	sector_t blk = off >> sb->s_blocksize_bits;
+	int err = 0;
+	int offset = off & (sb->s_blocksize - 1);
+	int tocopy;
+	size_t towrite = len;
+	struct buffer_head tmp_bh;
+	struct buffer_head *bh;
+
+	mutex_lock(&inode->i_mutex);
+	while (towrite > 0) {
+		tocopy = sb->s_blocksize - offset < towrite ?
+				sb->s_blocksize - offset : towrite;
+
+		tmp_bh.b_state = 0;
+		tmp_bh.b_size = 1 << inode->i_blkbits;
+		err = jfs_get_block(inode, blk, &tmp_bh, 1);
+		if (err)
+			goto out;
+		if (offset || tocopy != sb->s_blocksize)
+			bh = sb_bread(sb, tmp_bh.b_blocknr);
+		else
+			bh = sb_getblk(sb, tmp_bh.b_blocknr);
+		if (!bh) {
+			err = -EIO;
+			goto out;
+		}
+		lock_buffer(bh);
+		memcpy(bh->b_data+offset, data, tocopy);
+		flush_dcache_page(bh->b_page);
+		set_buffer_uptodate(bh);
+		mark_buffer_dirty(bh);
+		unlock_buffer(bh);
+		brelse(bh);
+		offset = 0;
+		towrite -= tocopy;
+		data += tocopy;
+		blk++;
+	}
+out:
+	if (len == towrite)
+		return err;
+	if (inode->i_size < off+len-towrite)
+		i_size_write(inode, off+len-towrite);
+	inode->i_version++;
+	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(inode);
+	mutex_unlock(&inode->i_mutex);
+	return len - towrite;
+}
+
+#endif
+
 static struct super_operations jfs_super_operations = {
 	.alloc_inode	= jfs_alloc_inode,
 	.destroy_inode	= jfs_destroy_inode,
@@ -621,7 +729,11 @@ static struct super_operations jfs_super_operations = {
 	.unlockfs       = jfs_unlockfs,
 	.statfs		= jfs_statfs,
 	.remount_fs	= jfs_remount,
-	.show_options	= jfs_show_options
+	.show_options	= jfs_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= jfs_quota_read,
+	.quota_write	= jfs_quota_write,
+#endif
 };
 
 static struct export_operations jfs_export_operations = {
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index 2a4df9b3779a..01b4db9e5466 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -237,19 +237,22 @@ static int
 nlm_traverse_files(struct nlm_host *host, int action)
 {
 	struct nlm_file	*file, **fp;
-	int		i;
+	int i, ret = 0;
 
 	mutex_lock(&nlm_file_mutex);
 	for (i = 0; i < FILE_NRHASH; i++) {
 		fp = nlm_files + i;
 		while ((file = *fp) != NULL) {
+			file->f_count++;
+			mutex_unlock(&nlm_file_mutex);
+
 			/* Traverse locks, blocks and shares of this file
 			 * and update file->f_locks count */
-			if (nlm_inspect_file(host, file, action)) {
-				mutex_unlock(&nlm_file_mutex);
-				return 1;
-			}
+			if (nlm_inspect_file(host, file, action))
+				ret = 1;
 
+			mutex_lock(&nlm_file_mutex);
+			file->f_count--;
 			/* No more references to this file. Let go of it. */
 			if (!file->f_blocks && !file->f_locks
 			 && !file->f_shares && !file->f_count) {
@@ -262,7 +265,7 @@ nlm_traverse_files(struct nlm_host *host, int action)
 		}
 	}
 	mutex_unlock(&nlm_file_mutex);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/fs/locks.c b/fs/locks.c
index b0b41a64e10b..d7c53392cac1 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1421,8 +1421,9 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp)
 	if (!leases_enable)
 		goto out;
 
-	error = lease_alloc(filp, arg, &fl);
-	if (error)
+	error = -