Merge branch 'upstream/linaro-3.1' into linaro-android-3.1-agreen-rebase

30 files changed, 263 insertions, 210 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index dd0fdfc56d3..21ac5ee4b43 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -795,7 +795,16 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			 * might try to exec.  This is because the brk will
 			 * follow the loader, and is not movable.  */
 #if defined(CONFIG_X86) || defined(CONFIG_ARM)
-			load_bias = 0;
+			/* Memory randomization might have been switched off
+			 * in runtime via sysctl.
+			 * If that is the case, retain the original non-zero
+			 * load_bias value in order to establish proper
+			 * non-randomized mappings.
+			 */
+			if (current->flags & PF_RANDOMIZE)
+				load_bias = 0;
+			else
+				load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #else
 			load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
 #endif
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 95f786ec7f0..1c44b8d5450 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1085,6 +1085,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
+	struct module *owner;
 	int ret;
 	int partno;
 	int perm = 0;
@@ -1110,6 +1111,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out;
+	owner = disk->fops->owner;
 
 	disk_block_events(disk);
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
@@ -1137,8 +1139,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 					bdev->bd_disk = NULL;
 					mutex_unlock(&bdev->bd_mutex);
 					disk_unblock_events(disk);
-					module_put(disk->fops->owner);
 					put_disk(disk);
+					module_put(owner);
 					goto restart;
 				}
 			}
@@ -1194,8 +1196,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_unlock_bdev;
 		}
 		/* only one opener holds refs to the module and disk */
-		module_put(disk->fops->owner);
 		put_disk(disk);
+		module_put(owner);
 	}
 	bdev->bd_openers++;
 	if (for_part)
@@ -1215,8 +1217,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
 	disk_unblock_events(disk);
-	module_put(disk->fops->owner);
 	put_disk(disk);
+	module_put(owner);
  out:
 	bdput(bdev);
 
@@ -1442,14 +1444,15 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
 
-		put_disk(disk);
-		module_put(owner);
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;
+
+		put_disk(disk);
+		module_put(owner);
 	}
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 71beb020197..28bba5791d9 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2807,10 +2807,10 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
 
 /*
  * When the server doesn't allow large posix writes, only allow a wsize of
- * 128k minus the size of the WRITE_AND_X header. That allows for a write up
+ * 2^17-1 minus the size of the WRITE_AND_X header. That allows for a write up
  * to the maximum size described by RFC1002.
  */
-#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4)
+#define CIFS_MAX_RFC1002_WSIZE ((1<<17) - 1 - sizeof(WRITE_REQ) + 4)
 
 /*
  * The default wsize is 1M. find_get_pages seems to return a maximum of 256
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a7b2dcd4a53..745e5cdca8f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -562,7 +562,16 @@ int cifs_get_file_info(struct file *filp)
 
 	xid = GetXid();
 	rc = CIFSSMBQFileInfo(xid, tcon, cfile->netfid, &find_data);
-	if (rc == -EOPNOTSUPP || rc == -EINVAL) {
+	switch (rc) {
+	case 0:
+		cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
+		break;
+	case -EREMOTE:
+		cifs_create_dfs_fattr(&fattr, inode->i_sb);
+		rc = 0;
+		break;
+	case -EOPNOTSUPP:
+	case -EINVAL:
 		/*
 		 * FIXME: legacy server -- fall back to path-based call?
 		 * for now, just skip revalidating and mark inode for
@@ -570,18 +579,14 @@ int cifs_get_file_info(struct file *filp)
 		 */
 		rc = 0;
 		CIFS_I(inode)->time = 0;
+	default:
 		goto cgfi_exit;
-	} else if (rc == -EREMOTE) {
-		cifs_create_dfs_fattr(&fattr, inode->i_sb);
-		rc = 0;
-	} else if (rc)
-		goto cgfi_exit;
+	}
 
 	/*
 	 * don't bother with SFU junk here -- just mark inode as needing
 	 * revalidation.
 	 */
-	cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false);
 	fattr.cf_uniqueid = CIFS_I(inode)->uniqueid;
 	fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
 	cifs_fattr_to_inode(inode, &fattr);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index fe047d966dc..2d1744ab5bc 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -70,6 +70,15 @@
  * simultaneous inserts (A into B and B into A) from racing and
  * constructing a cycle without either insert observing that it is
  * going to.
+ * It is necessary to acquire multiple "ep->mtx"es at once in the
+ * case when one epoll fd is added to another. In this case, we
+ * always acquire the locks in the order of nesting (i.e. after
+ * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
+ * before e2->mtx). Since we disallow cycles of epoll file
+ * descriptors, this ensures that the mutexes are well-ordered. In
+ * order to communicate this nesting to lockdep, when walking a tree
+ * of epoll file descriptors, we use the current recursion depth as
+ * the lockdep subkey.
  * It is possible to drop the "ep->mtx" and to use the global
  * mutex "epmutex" (together with "ep->lock") to have it working,
  * but having "ep->mtx" will make the interface more scalable.
@@ -464,13 +473,15 @@ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
  * @ep: Pointer to the epoll private data structure.
  * @sproc: Pointer to the scan callback.
  * @priv: Private opaque data passed to the @sproc callback.
+ * @depth: The current depth of recursive f_op->poll calls.
  *
  * Returns: The same integer error code returned by the @sproc callback.
  */
 static int ep_scan_ready_list(struct eventpoll *ep,
 			      int (*sproc)(struct eventpoll *,
 					   struct list_head *, void *),
-			      void *priv)
+			      void *priv,
+			      int depth)
 {
 	int error, pwake = 0;
 	unsigned long flags;
@@ -481,7 +492,7 @@ static int ep_scan_ready_list(struct eventpoll *ep,
 	 * We need to lock this because we could be hit by
 	 * eventpoll_release_file() and epoll_ctl().
 	 */
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, depth);
 
 	/*
 	 * Steal the ready list, and re-init the original one to the
@@ -670,7 +681,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
 
 static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
 {
-	return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
+	return ep_scan_ready_list(priv, ep_read_events_proc, NULL, call_nests + 1);
 }
 
 static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
@@ -737,7 +748,7 @@ void eventpoll_release_file(struct file *file)
 
 		ep = epi->ep;
 		list_del_init(&epi->fllink);
-		mutex_lock(&ep->mtx);
+		mutex_lock_nested(&ep->mtx, 0);
 		ep_remove(ep, epi);
 		mutex_unlock(&ep->mtx);
 	}
@@ -1134,7 +1145,7 @@ static int ep_send_events(struct eventpoll *ep,
 	esed.maxevents = maxevents;
 	esed.events = events;
 
-	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
+	return ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0);
 }
 
 static inline struct timespec ep_set_mstimeout(long ms)
@@ -1267,7 +1278,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests)
 	struct rb_node *rbp;
 	struct epitem *epi;
 
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, call_nests + 1);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		epi = rb_entry(rbp, struct epitem, rbn);
 		if (unlikely(is_file_epoll(epi->ffd.file))) {
@@ -1409,7 +1420,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	}
 
 
-	mutex_lock(&ep->mtx);
+	mutex_lock_nested(&ep->mtx, 0);
 
 	/*
 	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b7d7bd0f066..5c38120c389 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -358,8 +358,7 @@ struct flex_groups {
 
 /* Flags that should be inherited by new inodes from their parent. */
 #define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
-			   EXT4_SYNC_FL | EXT4_IMMUTABLE_FL | EXT4_APPEND_FL |\
-			   EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
+			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL)
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 986e2388f03..89c47f4ee00 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4416,6 +4416,7 @@ retry_alloc:
 			  PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) {
 			unlock_page(page);
 			ret = VM_FAULT_SIGBUS;
+			ext4_journal_stop(handle);
 			goto out;
 		}
 		ext4_set_inode_state(inode, EXT4_STATE_JDATA);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1c924faeb6c..50c72943d7b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1586,7 +1586,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			dxtrace(dx_show_index("node", frames[1].entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
-			err = ext4_handle_dirty_metadata(handle, inode, bh2);
+			err = ext4_handle_dirty_metadata(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
@@ -1612,7 +1612,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			if (err)
 				goto journal_error;
 		}
-		err = ext4_handle_dirty_metadata(handle, inode, frames[0].bh);
+		err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh);
 		if (err) {
 			ext4_std_error(inode->i_sb, err);
 			goto cleanup;
@@ -1863,7 +1863,7 @@ retry:
 	ext4_set_de_type(dir->i_sb, de, S_IFDIR);
 	inode->i_nlink = 2;
 	BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
-	err = ext4_handle_dirty_metadata(handle, dir, dir_block);
+	err = ext4_handle_dirty_metadata(handle, inode, dir_block);
 	if (err)
 		goto out_clear_inode;
 	err = ext4_mark_inode_dirty(handle, inode);
@@ -2530,7 +2530,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
 						cpu_to_le32(new_dir->i_ino);
 		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		retval = ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
+		retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh);
 		if (retval) {
 			ext4_std_error(old_dir->i_sb, retval);
 			goto end_rename;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c757adc9725..19fe4e3d39e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -820,8 +820,14 @@ inserted:
 			if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 				goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
 
+			/*
+			 * take i_data_sem because we will test
+			 * i_delalloc_reserved_flag in ext4_mb_new_blocks
+			 */
+			down_read((&EXT4_I(inode)->i_data_sem));
 			block = ext4_new_meta_blocks(handle, inode, goal, 0,
 						     NULL, &error);
+			up_read((&EXT4_I(inode)->i_data_sem));
 			if (error)
 				goto cleanup;
 
diff --git a/fs/namei.c b/fs/namei.c
index 0b3138de2a3..3d150720c37 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -137,7 +137,7 @@ static int do_getname(const char __user *filename, char *page)
 	return retval;
 }
 
-static char *getname_flags(const char __user * filename, int flags)
+static char *getname_flags(const char __user *filename, int flags, int *empty)
 {
 	char *tmp, *result;
 
@@ -148,6 +148,8 @@ static char *getname_flags(const char __user * filename, int flags)
 
 		result = tmp;
 		if (retval < 0) {
+			if (retval == -ENOENT && empty)
+				*empty = 1;
 			if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
 				__putname(tmp);
 				result = ERR_PTR(retval);
@@ -160,7 +162,7 @@ static char *getname_flags(const char __user * filename, int flags)
 
 char *getname(const char __user * filename)
 {
-	return getname_flags(filename, 0);
+	return getname_flags(filename, 0, 0);
 }
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -850,7 +852,7 @@ static int follow_managed(struct path *path, unsigned flags)
 		mntput(path->mnt);
 	if (ret == -EISDIR)
 		ret = 0;
-	return ret;
+	return ret < 0 ? ret : need_mntput;
 }
 
 int follow_down_one(struct path *path)
@@ -898,6 +900,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			break;
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
+		nd->flags |= LOOKUP_JUMPED;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
 		/*
 		 * Update the inode too. We don't need to re-check the
@@ -1211,6 +1214,8 @@ retry:
 		path_put_conditional(path, nd);
 		return err;
 	}
+	if (err)
+		nd->flags |= LOOKUP_JUMPED;
 	*inode = path->dentry->d_inode;
 	return 0;
 }
@@ -1798,11 +1803,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	return __lookup_hash(&this, base, NULL);
 }
 
-int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
+int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
+		 struct path *path, int *empty)
 {
 	struct nameidata nd;
-	char *tmp = getname_flags(name, flags);
+	char *tmp = getname_flags(name, flags, empty);
 	int err = PTR_ERR(tmp);
 	if (!IS_ERR(tmp)) {
 
@@ -1816,6 +1821,12 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
 	return err;
 }
 
+int user_path_at(int dfd, const char __user *name, unsigned flags,
+		 struct path *path)
+{
+	return user_path_at_empty(dfd, name, flags, path, 0);
+}
+
 static int user_path_parent(int dfd, const char __user *path,
 			struct nameidata *nd, char **name)
 {
@@ -2141,6 +2152,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	}
 
 	/* create side of things */
+	/*
+	 * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
+	 * cleared when we got to the last component we are about to look up
+	 */
 	error = complete_walk(nd);
 	if (error)
 		return ERR_PTR(error);
@@ -2209,6 +2224,9 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 	if (error < 0)
 		goto exit_dput;
 
+	if (error)
+		nd->flags |= LOOKUP_JUMPED;
+
 	error = -ENOENT;
 	if (!path->dentry->d_inode)
 		goto exit_dput;
@@ -2218,6 +2236,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path,
 
 	path_to_nameidata(path, nd);
 	nd->inode = path->dentry->d_inode;
+	/* Why this, you ask?  _Now_ we might have grown LOOKUP_JUMPED... */
+	error = complete_walk(nd);
+	if (error)
+		goto exit;
 	error = -EISDIR;
 	if (S_ISDIR(nd->inode->i_mode))
 		goto exit;
diff --git a/fs/namespace.c b/fs/namespace.c
index b4febb29d3b..e5e1c7d1839 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1109,6 +1109,7 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* device */
 	if (mnt->mnt_sb->s_op->show_devname) {
+		seq_puts(m, "device ");
 		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
 	} else {
 		if (mnt->mnt_devname) {
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 9561c8fc8bd..281ae95932c 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -176,17 +176,6 @@ retry:
 	return bio;
 }
 
-static void bl_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 /* This is basically copied from mpage_end_io_read */
 static void bl_end_io_read(struct bio *bio, int err)
 {
@@ -206,7 +195,7 @@ static void bl_end_io_read(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!rdata->pnfs_error)
 			rdata->pnfs_error = -EIO;
-		bl_set_lo_fail(rdata->lseg);
+		pnfs_set_lo_fail(rdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -303,6 +292,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 						 bl_end_io_read, par);
 			if (IS_ERR(bio)) {
 				rdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 		}
@@ -370,7 +360,7 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -386,7 +376,7 @@ static void bl_end_io_write(struct bio *bio, int err)
 	if (!uptodate) {
 		if (!wdata->pnfs_error)
 			wdata->pnfs_error = -EIO;
-		bl_set_lo_fail(wdata->lseg);
+		pnfs_set_lo_fail(wdata->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -543,6 +533,11 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 fill_invalid_ext:
 		dprintk("%s need to zero %d pages\n", __func__, npg_zero);
 		for (;npg_zero > 0; npg_zero--) {
+			if (bl_is_sector_init(be->be_inval, isect)) {
+				dprintk("isect %llu already init\n",
+					(unsigned long long)isect);
+				goto next_page;
+			}
 			/* page ref released in bl_end_io_write_zero */
 			index = isect >> PAGE_CACHE_SECTOR_SHIFT;
 			dprintk("%s zero %dth page: index %lu isect %llu\n",
@@ -562,8 +557,7 @@ fill_invalid_ext:
 			 * PageUptodate: It was read before
 			 * sector_initialized: already written out
 			 */
-			if (PageDirty(page) || PageWriteback(page) ||
-			    bl_is_sector_init(be->be_inval, isect)) {
+			if (PageDirty(page) || PageWriteback(page)) {
 				print_page(page);
 				unlock_page(page);
 				page_cache_release(page);
@@ -592,6 +586,7 @@ fill_invalid_ext:
 						 bl_end_io_write_zero, par);
 			if (IS_ERR(bio)) {
 				wdata->pnfs_error = PTR_ERR(bio);
+				bio = NULL;
 				goto out;
 			}
 			/* FIXME: This should be done in bi_end_io */
@@ -640,6 +635,7 @@ next_page:
 					 bl_end_io_write, par);
 		if (IS_ERR(bio)) {
 			wdata->pnfs_error = PTR_ERR(bio);
+			bio = NULL;
 			goto out;
 		}
 		isect += PAGE_CACHE_SECTORS;
@@ -805,7 +801,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 			struct nfs4_deviceid *d_id)
 {
 	struct pnfs_device *dev;
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	u32 max_resp_sz;
 	int max_pages;
 	struct page **pages = NULL;
@@ -823,18 +819,20 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dev = kmalloc(sizeof(*dev), GFP_NOFS);
 	if (!dev) {
 		dprintk("%s kmalloc failed\n", __func__);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
 		kfree(dev);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	for (i = 0; i < max_pages; i++) {
 		pages[i] = alloc_page(GFP_NOFS);
-		if (!pages[i])
+		if (!pages[i]) {
+			rv = ERR_PTR(-ENOMEM);
 			goto out_free;
+		}
 	}
 
 	memcpy(&dev->dev_id, d_id, sizeof(*d_id));
@@ -847,8 +845,10 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh,
 	dprintk("%s: dev_id: %s\n", __func__, dev->dev_id.data);
 	rc = nfs4_proc_getdeviceinfo(server, dev);
 	dprintk("%s getdevice info returns %d\n", __func__, rc);
-	if (rc)
+	if (rc) {
+		rv = ERR_PTR(rc);
 		goto out_free;
+	}
 
 	rv = nfs4_blk_decode_device(server, dev);
  out_free:
@@ -866,7 +866,7 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 	struct pnfs_devicelist *dlist = NULL;
 	struct pnfs_block_dev *bdev;
 	LIST_HEAD(block_disklist);
-	int status = 0, i;
+	int status, i;
 
 	dprintk("%s enter\n", __func__);
 
@@ -898,8 +898,8 @@ bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh)
 		for (i = 0; i < dlist->num_devs; i++) {
 			bdev = nfs4_blk_get_deviceinfo(server, fh,
 						       &dlist->dev_id[i]);
-			if (!bdev) {
-				status = -ENODEV;
+			if (IS_ERR(bdev)) {
+				status = PTR_ERR(bdev);
 				goto out_error;
 			}
 			spin_lock(&b_mt_id->bm_lock);
@@ -960,7 +960,7 @@ static struct pnfs_layoutdriver_type blocklayout_type = {
 };
 
 static const struct rpc_pipe_ops bl_upcall_ops = {
-	.upcall		= bl_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= bl_pipe_downcall,
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
@@ -989,17 +989,20 @@ static int __init nfs4blocklayout_init(void)
 			      mnt,
 			      NFS_PIPE_DIRNAME, 0, &path);
 	if (ret)
-		goto out_remove;
+		goto out_putrpc;
 
 	bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL,
 				    &bl_upcall_ops, 0);
+	path_put(&path);
 	if (IS_ERR(bl_device_pipe)) {
 		ret = PTR_ERR(bl_device_pipe);
-		goto out_remove;
+		goto out_putrpc;
 	}
 out:
 	return ret;
 
+out_putrpc:
+	rpc_put_mount();
 out_remove:
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	return ret;
@@ -1012,6 +1015,7 @@ static void __exit nfs4blocklayout_exit(void)
 
 	pnfs_unregister_layoutdriver(&blocklayout_type);
 	rpc_unlink(bl_device_pipe);
+	rpc_put_mount();
 }
 
 MODULE_ALIAS("nfs-layouttype4-3");
diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index f27d827960a..42acf7ef599 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -150,7 +150,7 @@ BLK_LSEG2EXT(struct pnfs_layout_segment *lseg)
 }
 
 struct bl_dev_msg {
-	int status;
+	int32_t status;
 	uint32_t major, minor;
 };
 
@@ -169,8 +169,6 @@ extern wait_queue_head_t bl_wq;
 #define BL_DEVICE_REQUEST_ERR          0x2 /* User level process fails */
 
 /* blocklayoutdev.c */
-ssize_t bl_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-		       char __user *, size_t);
 ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
 struct block_device *nfs4_blkdev_get(dev_t dev);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index a83b393fb01..d08ba9107fd 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -79,28 +79,6 @@ int nfs4_blkdev_put(struct block_device *bdev)
 	return blkdev_put(bdev, FMODE_READ);
 }
 
-/*
- * Shouldn't there be a rpc_generic_upcall() to do this for us?
- */
-ssize_t bl_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		       char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len - msg->copied, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static struct bl_dev_msg bl_mount_reply;
 
 ssize_t bl_pipe_downcall(struct file *filp, const char __user *src,
@@ -131,7 +109,7 @@ struct pnfs_block_dev *
 nfs4_blk_decode_device(struct nfs_server *server,
 		       struct pnfs_device *dev)
 {
-	struct pnfs_block_dev *rv = NULL;
+	struct pnfs_block_dev *rv;
 	struct block_device *bd = NULL;
 	struct rpc_pipe_msg msg;
 	struct bl_msg_hdr bl_msg = {
@@ -141,7 +119,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
 	struct bl_dev_msg *reply = &bl_mount_reply;
-	int offset, len, i;
+	int offset, len, i, rc;
 
 	dprintk("%s CREATING PIPEFS MESSAGE\n", __func__);
 	dprintk("%s: deviceid: %s, mincount: %d\n", __func__, dev->dev_id.data,
@@ -168,8 +146,10 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	dprintk("%s CALLING USERSPACE DAEMON\n", __func__);
 	add_wait_queue(&bl_wq, &wq);
-	if (rpc_queue_upcall(bl_device_pipe->d_inode, &msg) < 0) {
+	rc = rpc_queue_upcall(bl_device_pipe->d_inode, &msg);
+	if (rc < 0) {
 		remove_wait_queue(&bl_wq, &wq);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
@@ -187,8 +167,9 @@ nfs4_blk_decode_device(struct nfs_server *server,
 
 	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
 	if (IS_ERR(bd)) {
-		dprintk("%s failed to open device : %ld\n",
-			__func__, PTR_ERR(bd));
+		rc = PTR_ERR(bd);
+		dprintk("%s failed to open device : %d\n", __func__, rc);
+		rv = ERR_PTR(rc);
 		goto out;
 	}
 
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index f20801ae0a1..47d1c6ff2d8 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -336,8 +336,6 @@ struct idmap {
 	struct idmap_hashtable	idmap_group_hash;
 };
 
-static ssize_t idmap_pipe_upcall(struct file *, struct rpc_pipe_msg *,
-				 char __user *, size_t);
 static ssize_t idmap_pipe_downcall(struct file *, const char __user *,
 				   size_t);
 static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
@@ -345,7 +343,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 static unsigned int fnvhash32(const void *, size_t);
 
 static const struct rpc_pipe_ops idmap_upcall_ops = {
-	.upcall		= idmap_pipe_upcall,
+	.upcall		= rpc_pipe_generic_upcall,
 	.downcall	= idmap_pipe_downcall,
 	.destroy_msg	= idmap_pipe_destroy_msg,
 };
@@ -595,27 +593,6 @@ nfs_idmap_name(struct idmap *idmap, struct idmap_hashtable *h,
 	return ret;
 }
 
-/* RPC pipefs upcall/downcall routines */
-static ssize_t
-idmap_pipe_upcall(struct file *filp, struct rpc_pipe_msg *msg,
-		  char __user *dst, size_t buflen)
-{
-	char *data = (char *)msg->data + msg->copied;
-	size_t mlen = min(msg->len, buflen);
-	unsigned long left;
-
-	left = copy_to_user(dst, data, mlen);
-	if (left == mlen) {
-		msg->errno = -EFAULT;
-		return -EFAULT;
-	}
-
-	mlen -= left;
-	msg->copied += mlen;
-	msg->errno = 0;
-	return mlen;
-}
-
 static ssize_t
 idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index e8915d4840a..4c78c62639e 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -77,19 +77,6 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
 	BUG();
 }
 
-/* For data server errors we don't recover from */
-static void
-filelayout_set_lo_fail(struct pnfs_layout_segment *lseg)
-{
-	if (lseg->pls_range.iomode == IOMODE_RW) {
-		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-	} else {
-		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
-	}
-}
-
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
@@ -145,7 +132,7 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_read(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		}
@@ -221,7 +208,7 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 			nfs4_reset_write(task, data);
 			clp = NFS_SERVER(data->inode)->nfs_client;
 		} else
@@ -256,7 +243,7 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 			__func__, data->ds_clp, data->ds_clp->cl_session);
 		if (reset) {
 			prepare_to_resend_writes(data);
-			filelayout_set_lo_fail(data->lseg);
+			pnfs_set_lo_fail(data->lseg);
 		} else
 			nfs_restart_rpc(task, data->ds_clp);
 		return -EAGAIN;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index e550e8836c3..ee73d9a4f70 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1168,23 +1168,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_write_done(struct nfs_write_data *data)
+void pnfs_ld_write_done(struct nfs_write_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		pnfs_set_layoutcommit(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_write(data, NFS_CLIENT(data->inode),
-				    data->mds_ops, NFS_FILE_SYNC);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
@@ -1268,23 +1262,17 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 /*
  * Called by non rpc-based layout drivers
  */
-int
-pnfs_ld_read_done(struct nfs_read_data *data)
+void pnfs_ld_read_done(struct nfs_read_data *data)
 {
-	int status;
-
-	if (!data->pnfs_error) {
+	if (likely(!data->pnfs_error)) {
 		__nfs4_read_done_cb(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-		data->mds_ops->rpc_release(data);
-		return 0;
+	} else {
+		put_lseg(data->lseg);
+		data->lseg = NULL;
+		dprintk("pnfs write error = %d\n", data->pnfs_error);
 	}
-
-	dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
-		data->pnfs_error);
-	status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
-				   data->mds_ops);
-	return status ? : -EAGAIN;
+	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
@@ -1381,6 +1369,18 @@ static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
 	}
 }
 
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
+{
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		dprintk("%s Setting layout IOMODE_RW fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
+	} else {
+		dprintk("%s Setting layout IOMODE_READ fail bit\n", __func__);
+		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
+
 void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 01cbfd54f3c..1509530cb11 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -178,6 +178,7 @@ int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
+void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
@@ -200,8 +201,8 @@ void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
 int _pnfs_return_layout(struct inode *);
-int pnfs_ld_write_done(struct nfs_write_data *);
-int pnfs_ld_read_done(struct nfs_read_data *);
+void pnfs_ld_write_done(struct nfs_write_data *);
+void pnfs_ld_read_done(struct nfs_read_data *);
 struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       struct nfs_open_context *ctx,
 					       loff_t pos,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 2171c043ab0..bfc20b16024 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -541,13 +541,23 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
 static void nfs_readpage_release_full(void *calldata)
 {
 	struct nfs_read_data *data = calldata;
+	struct nfs_pageio_descriptor pgio;
 
+	if (data->pnfs_error) {
+		nfs_pageio_init_read_mds(&pgio, data->inode);
+		pgio.pg_recoalesce = 1;
+	}
 	while (!list_empty(&data->pages)) {
 		struct nfs_page *req = nfs_list_entry(data->pages.next);
 
 		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
+		if (!data->pnfs_error)
+			nfs_readpage_release(req);
+		else
+			nfs_pageio_add_request(&pgio, req);
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_readdata_release(calldata);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c9bd2a6b7d4..106fd0634ab 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -428,7 +428,6 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
 	__set_page_dirty_nobuffers(req->wb_page);
-	__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -762,6 +761,8 @@ int nfs_updatepage(struct file *file, struct page *page,
 	status = nfs_writepage_setup(ctx, page, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(page);
+	else
+		__set_page_dirty_nobuffers(page);
 
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
@@ -1165,7 +1166,13 @@ static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
 static void nfs_writeback_release_full(void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
-	int status = data->task.tk_status;
+	int ret, status = data->task.tk_status;
+	struct nfs_pageio_descriptor pgio;
+
+	if (data->pnfs_error) {
+		nfs_pageio_init_write_mds(&pgio, data->inode, FLUSH_STABLE);
+		pgio.pg_recoalesce = 1;
+	}
 
 	/* Update attributes as result of writeback. */
 	while (!list_empty(&data->pages)) {
@@ -1181,6 +1188,11 @@ static void nfs_writeback_release_full(void *calldata)
 			req->wb_bytes,
 			(long long)req_offset(req));
 
+		if (data->pnfs_error) {
+			dprintk(", pnfs error = %d\n", data->pnfs_error);
+			goto next;
+		}
+
 		if (status < 0) {
 			nfs_set_pageerror(page);
 			nfs_context_set_write_error(req->wb_context, status);
@@ -1200,7 +1212,19 @@ remove_request:
 	next:
 		nfs_clear_page_tag_locked(req);
 		nfs_end_page_writeback(page);
+		if (data->pnfs_error) {
+			lock_page(page);
+			nfs_pageio_cond_complete(&pgio, page->index);
+			ret = nfs_page_async_flush(&pgio, page, 0);
+			if (ret) {
+				nfs_set_pageerror(page);
+				dprintk("rewrite to MDS error = %d\n", ret);
+			}
+			unlock_page(page);
+		}
 	}
+	if (data->pnfs_error)
+		nfs_pageio_complete(&pgio);
 	nfs_writedata_release(calldata);
 }
 
@@ -1553,6 +1577,10 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
+	/* no commits means nothing needs to be done */
+	if (!nfsi->ncommit)
+		return ret;
+
 	if (wbc->sync_mode == WB_SYNC_NONE) {
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
@@ -1686,34 +1714,20 @@ out_error:
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 		struct page *page)
 {
-	struct nfs_page *req;
-	int ret;
+	/*
+	 * If PagePrivate is set, then the page is currently associated with
+	 * an in-progress read or write request. Don't try to migrate it.
+	 *
+	 * FIXME: we could do this in principle, but we'll need a way to ensure
+	 *        that we can safely release the inode reference while holding
+	 *        the page lock.
+	 */
+	if (PagePrivate(page))
+		return -EBUSY;
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	req = nfs_find_and_lock_request(page, false);
-	ret = PTR_ERR(req);
-	if (IS_ERR(req))
-		goto out;
-
-	ret = migrate_page(mapping, newpage, page);
-	if (!req)
-		goto out;
-	if (ret)
-		goto out_unlock;
-	page_cache_get(newpage);
-	spin_lock(&mapping->host->i_lock);
-	req->wb_page = newpage;
-	SetPagePrivate(newpage);
-	set_page_private(newpage, (unsigned long)req);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	spin_unlock(&mapping->host->i_lock);
-	page_cache_release(page);
-out_unlock:
-	nfs_clear_page_tag_locked(req);
-out:
-	return ret;
+	return migrate_page(mapping, newpage, page);
 }
 #endif
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index e8077766661..05b397ce70f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -156,6 +156,8 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
 		!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
 		return nfserr_inval;
 
+	accmode |= NFSD_MAY_READ_IF_EXEC;
+
 	if (open->op_share_access & NFS4_SHARE_ACCESS_READ)
 		accmode |= NFSD_MAY_READ;
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
@@ -691,7 +693,7 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	readdir->rd_bmval[1] &= nfsd_suppattrs1(cstate->minorversion);
 	readdir->rd_bmval[2] &= nfsd_suppattrs2(cstate->minorversion);
 
-	if ((cookie > ~(u32)0) || (cookie == 1) || (cookie == 2) ||
+	if ((cookie == 1) || (cookie == 2) ||
 	    (cookie == 0 && memcmp(readdir->rd_verf.data, zeroverf.data, NFS4_VERIFIER_SIZE)))
 		return nfserr_bad_cookie;
 
@@ -930,7 +932,7 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	count = 4 + (verify->ve_attrlen >> 2);
 	buf = kmalloc(count << 2, GFP_KERNEL);
 	if (!buf)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfsd4_encode_fattr(&cstate->current_fh,
 				    cstate->current_fh.fh_export,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 29d77f60585..02eb38ecbfe 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -88,7 +88,7 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 	struct xdr_netobj cksum;
 	struct hash_desc desc;
 	struct scatterlist sg;
-	__be32 status = nfserr_resource;
+	__be32 status = nfserr_jukebox;
 
 	dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
 			clname->len, clname->data);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3787ec11740..6f8bcc733f7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -192,8 +192,15 @@ static void nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
 static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
 {
 	if (atomic_dec_and_test(&fp->fi_access[oflag])) {
-		nfs4_file_put_fd(fp, O_RDWR);
 		nfs4_file_put_fd(fp, oflag);
+		/*
+		 * It's also safe to get rid of the RDWR open *if*
+		 * we no longer have need of the other kind of access
+		 * or if we already have the other kind of open:
+		 */
+		if (fp->fi_fds[1-oflag]
+			|| atomic_read(&fp->fi_access[1 - oflag]) == 0)
+			nfs4_file_put_fd(fp, O_RDWR);
 	}
 }
 
@@ -1946,7 +1953,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * of 5 bullet points, labeled as CASE0 - CASE4 below.
 	 */
 	unconf = find_unconfirmed_client_by_str(dname, strhashval);
-	status = nfserr_resource;
+	status = nfserr_jukebox;
 	if (!conf) {
 		/*
 		 * RFC 3530 14.2.33 CASE 4:
@@ -2483,7 +2490,7 @@ renew:
 	if (open->op_stateowner == NULL) {
 		sop = alloc_init_open_stateowner(strhashval, clp, open);
 		if (sop == NULL)
-			return nfserr_resource;
+			return nfserr_jukebox;
 		open->op_stateowner = sop;
 	}
 	list_del_init(&sop->so_close_lru);
@@ -2619,7 +2626,7 @@ nfs4_new_open(struct svc_rqst *rqstp, struct nfs4_stateid **stpp,
 
 	stp = nfs4_alloc_stateid();
 	if (stp == NULL)
-		return nfserr_resource;
+		return nfserr_jukebox;
 
 	status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open);
 	if (status) {
@@ -2850,7 +2857,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfserr_bad_stateid;
 		if (open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
 			goto out;
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		fp = alloc_init_file(ino);
 		if (fp == NULL)
 			goto out;
@@ -3530,8 +3537,9 @@ static inline void nfs4_file_downgrade(struct nfs4_stateid *stp, unsigned int to
 	int i;
 
 	for (i = 1; i < 4; i++) {
-		if (test_bit(i, &stp->st_access_bmap) && !(i & to_access)) {
-			nfs4_file_put_access(stp->st_file, i);
+		if (test_bit(i, &stp->st_access_bmap)
+					&& ((i & to_access) != i)) {
+			nfs4_file_put_access(stp->st_file, nfs4_access_to_omode(i));
 			__clear_bit(i, &stp->st_access_bmap);
 		}
 	}
@@ -3562,6 +3570,8 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	if (!access_valid(od->od_share_access, cstate->minorversion)
 			|| !deny_valid(od->od_share_deny))
 		return nfserr_inval;
+	/* We don't yet support WANT bits: */
+	od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
 
 	nfs4_lock_state();
 	if ((status = nfs4_preprocess_seqid_op(cstate,
@@ -4035,7 +4045,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		/* XXX: Do we need to check for duplicate stateowners on
 		 * the same file, or should they just be allowed (and
 		 * create new stateids)? */
-		status = nfserr_resource;
+		status = nfserr_jukebox;
 		lock_sop = alloc_init_lock_stateowner(strhashval,
 				open_sop->so_client, open_stp, lock);
 		if (lock_sop == NULL)
@@ -4119,9 +4129,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	case (EDEADLK):
 		status = nfserr_deadlock;
 		break;
-	default:        
+	default:
 		dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err);
-		status = nfserr_resource;
+		status = nfserrno(err);
 		break;
 	}
 out:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c8bf405d19d..f8109960525 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1623,6 +1623,18 @@ static void write_cinfo(__be32 **p, struct nfsd4_change_info *c)
 								\
 	save = resp->p;
 
+static bool seqid_mutating_err(__be32 err)
+{
+	/* rfc 3530 section 8.1.5: */
+	return	err != nfserr_stale_clientid &&
+		err != nfserr_stale_stateid &&
+		err != nfserr_bad_stateid &&
+		err != nfserr_bad_seqid &&
+		err != nfserr_bad_xdr &&
+		err != nfserr_resource &&
+		err != nfserr_nofilehandle;
+}
+
 /*
  * Routine for encoding the result of a "seqid-mutating" NFSv4 operation.  This
  * is where sequence id's are incremented, and the replay cache is filled.
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4eefaf1b42e..5cfebe50405 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -447,12 +447,6 @@ struct nfs4_stateid {
 #define WR_STATE	        0x00000020
 #define CLOSE_STATE             0x00000040
 
-#define seqid_mutating_err(err)                       \
-	(((err) != nfserr_stale_clientid) &&    \
-	((err) != nfserr_bad_seqid) &&          \
-	((err) != nfserr_stale_stateid) &&      \
-	((err) != nfserr_bad_stateid))
-
 struct nfsd4_compound_state;
 
 extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fd0acca5370..acf88aea211 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -2114,7 +2114,8 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 
 	/* Allow read access to binaries even when mode 111 */
 	if (err == -EACCES && S_ISREG(inode->i_mode) &&
-	    acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE))
+	     (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) ||
+	      acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC)))
 		err = inode_permission(inode, MAY_EXEC);
 
 	return err? nfserrno(err) : 0;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index e0bbac04d1d..a22e40e2786 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -25,6 +25,7 @@
 #define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
 #define NFSD_MAY_NOT_BREAK_LEASE 512
 #define NFSD_MAY_BYPASS_GSS	1024
+#define NFSD_MAY_READ_IF_EXEC	2048
 
 #define NFSD_MAY_CREATE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE		(NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5afaa58a863..c7d4ee663f1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1039,6 +1039,9 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " stack");
 	}
 
+	if (is_vm_hugetlb_page(vma))
+		seq_printf(m, " huge");
+
 	walk_page_range(vma->vm_start, vma->vm_end, &walk);
 
 	if (!md->pages)
diff --git a/fs/stat.c b/fs/stat.c
index 78a3aa83c7e..8806b8997d2 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -294,15 +294,16 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 {
 	struct path path;
 	int error;
+	int empty = 0;
 
 	if (bufsiz <= 0)
 		return -EINVAL;
 
-	error = user_path_at(dfd, pathname, LOOKUP_EMPTY, &path);
+	error = user_path_at_empty(dfd, pathname, LOOKUP_EMPTY, &path, &empty);
 	if (!error) {
 		struct inode *inode = path.dentry->d_inode;
 
-		error = -EINVAL;
+		error = empty ? -ENOENT : -EINVAL;
 		if (inode->i_op->readlink) {
 			error = security_inode_readlink(path.dentry);
 			if (!error) {
diff --git a/fs/statfs.c b/fs/statfs.c
index 8244924dec5..9cf04a11896 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -76,7 +76,7 @@ EXPORT_SYMBOL(vfs_statfs);
 int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
 	struct path path;
-	int error = user_path(pathname, &path);
+	int error = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 	if (!error) {
 		error = vfs_statfs(&path, st);
 		path_put(&path);