Merge 4.2-rc6 into char-misc-next

We want the fixes in Linus's tree in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

38 files changed, 367 insertions, 187 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 862fbc206755..564a7de17d99 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -378,7 +378,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 
 	ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_error(root->fs_info, ret, "kobj add dev failed");
+		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
 
 	printk_in_rcu(KERN_INFO
 		      "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a9aadb2ad525..f556c3732c2c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2842,6 +2842,7 @@ int open_ctree(struct super_block *sb,
 	    !extent_buffer_uptodate(chunk_root->node)) {
 		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
+		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
 	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
@@ -2879,7 +2880,7 @@ retry_root_backup:
 	    !extent_buffer_uptodate(tree_root->node)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
 		       sb->s_id);
-
+		tree_root->node = NULL;
 		goto recovery_tree_root;
 	}
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 171312d51799..07204bf601ed 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4227,6 +4227,24 @@ out:
 	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
 	mutex_unlock(&fs_info->chunk_mutex);
+	/*
+	 * When we allocate a new chunk we reserve space in the chunk block
+	 * reserve to make sure we can COW nodes/leafs in the chunk tree or
+	 * add new nodes/leafs to it if we end up needing to do it when
+	 * inserting the chunk item and updating device items as part of the
+	 * second phase of chunk allocation, performed by
+	 * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
+	 * large number of new block groups to create in our transaction
+	 * handle's new_bgs list to avoid exhausting the chunk block reserve
+	 * in extreme cases - like having a single transaction create many new
+	 * block groups when starting to write out the free space caches of all
+	 * the block groups that were made dirty during the lifetime of the
+	 * transaction.
+	 */
+	if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+		btrfs_create_pending_block_groups(trans, trans->root);
+		btrfs_trans_release_chunk_metadata(trans);
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e9ace099162c..8a8202956576 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1651,6 +1651,11 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 				/* Exclusive -> exclusive, nothing changed */
 			}
 		}
+
+		/* For exclusive extent, free its reserved bytes too */
+		if (nr_old_roots == 0 && nr_new_roots == 1 &&
+		    cur_new_count == nr_new_roots)
+			qg->reserved -= num_bytes;
 		if (dirty)
 			qgroup_dirty(fs_info, qg);
 	}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 51e0f0d0053e..f5021fcb154e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2152,7 +2152,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	if (current != root->fs_info->transaction_kthread)
+	if (current != root->fs_info->transaction_kthread &&
+	    current != root->fs_info->cleaner_kthread)
 		btrfs_run_delayed_iputs(root);
 
 	return ret;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index dc10c9dd36c1..ddd5e9471290 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1506,7 +1506,6 @@ static int __mark_caps_flushing(struct inode *inode,
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
-	cf->kick = false;
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
@@ -2123,8 +2122,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc,
 
 static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 				struct ceph_mds_session *session,
-				struct ceph_inode_info *ci,
-				bool kick_all)
+				struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
@@ -2150,9 +2148,7 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
 			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			if (cf->tid < first_tid)
-				continue;
-			if (kick_all || cf->kick)
+			if (cf->tid >= first_tid)
 				break;
 		}
 		if (!n) {
@@ -2161,7 +2157,6 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 		}
 
 		cf = rb_entry(n, struct ceph_cap_flush, i_node);
-		cf->kick = false;
 
 		first_tid = cf->tid + 1;
 
@@ -2181,8 +2176,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 {
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
 
 	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
@@ -2205,16 +2198,11 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
 			spin_unlock(&ci->i_ceph_lock);
-			if (!__kick_flushing_caps(mdsc, session, ci, true))
+			if (!__kick_flushing_caps(mdsc, session, ci))
 				continue;
 			spin_lock(&ci->i_ceph_lock);
 		}
 
-		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			cf->kick = true;
-		}
-
 		spin_unlock(&ci->i_ceph_lock);
 	}
 }
@@ -2228,7 +2216,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		int delayed = __kick_flushing_caps(mdsc, session, ci, false);
+		int delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
@@ -2261,7 +2249,7 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
 
 		spin_unlock(&ci->i_ceph_lock);
 
-		delayed = __kick_flushing_caps(mdsc, session, ci, true);
+		delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 4347039ecc18..6706bde9ad1b 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -287,7 +287,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode,
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 860cc016e70d..2f2460d23a06 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -189,7 +189,6 @@ static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
 struct ceph_cap_flush {
 	u64 tid;
 	int caps;
-	bool kick;
 	struct rb_node g_node; // global
 	union {
 		struct rb_node i_node; // inode
diff --git a/fs/dax.c b/fs/dax.c
index c3e21ccfc358..a7f77e1fa18c 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -319,6 +319,12 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
+ * @complete_unwritten: The filesystem method used to convert unwritten blocks
+ *	to written so the data written to them is exposed. This is required for
+ *	required by write faults for filesystems that will return unwritten
+ *	extent mappings from @get_block, but it is optional for reads as
+ *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
+ *	not support unwritten extents, the it should pass NULL.
  *
  * When a page fault occurs, filesystems may call this helper in their
  * fault handler for DAX files. __dax_fault() assumes the caller has done all
@@ -437,8 +443,12 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	 * as for normal BH based IO completions.
 	 */
 	error = dax_insert_mapping(inode, &bh, vma, vmf);
-	if (buffer_unwritten(&bh))
-		complete_unwritten(&bh, !error);
+	if (buffer_unwritten(&bh)) {
+		if (complete_unwritten)
+			complete_unwritten(&bh, !error);
+		else
+			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
+	}
 
  out:
 	if (error == -ENOMEM)
diff --git a/fs/dcache.c b/fs/dcache.c
index 5c8ea15e73a5..9b5fe503f6cb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void)
 	inode_init_early();
 }
 
-void __init vfs_caches_init(unsigned long mempages)
+void __init vfs_caches_init(void)
 {
-	unsigned long reserve;
-
-	/* Base hash sizes on available memory, with a reserve equal to
-           150% of current kernel size */
-
-	reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
-	mempages -= reserve;
-
 	names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	dcache_init();
 	inode_init();
-	files_init(mempages);
+	files_init();
+	files_maxfiles_init();
 	mnt_init();
 	bdev_cache_init();
 	chrdev_init();
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9bedfa8dd3a5..f71e19a9dd3c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2072,8 +2072,6 @@ static int f2fs_set_data_page_dirty(struct page *page)
 		return 1;
 	}
 
-	mark_inode_dirty(inode);
-
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ada2a3dd701a..b0f38c3b37f4 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1331,12 +1331,13 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 	if (ret)
 		return ret;
 
-	if (f2fs_is_atomic_file(inode))
+	if (f2fs_is_atomic_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 		commit_inmem_pages(inode, false);
+	}
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -1387,8 +1388,8 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 	f2fs_balance_fs(F2FS_I_SB(inode));
 
 	if (f2fs_is_atomic_file(inode)) {
-		commit_inmem_pages(inode, false);
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+		commit_inmem_pages(inode, false);
 	}
 
 	if (f2fs_is_volatile_file(inode))
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e1e73617d13b..22fb5ef37966 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -556,27 +556,39 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	if (!fio.encrypted_page)
 		goto put_out;
 
-	f2fs_submit_page_bio(&fio);
+	err = f2fs_submit_page_bio(&fio);
+	if (err)
+		goto put_page_out;
+
+	/* write page */
+	lock_page(fio.encrypted_page);
+
+	if (unlikely(!PageUptodate(fio.encrypted_page)))
+		goto put_page_out;
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+		goto put_page_out;
+
+	set_page_dirty(fio.encrypted_page);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, META);
+	if (clear_page_dirty_for_io(fio.encrypted_page))
+		dec_page_count(fio.sbi, F2FS_DIRTY_META);
+
+	set_page_writeback(fio.encrypted_page);
 
 	/* allocate block address */
 	f2fs_wait_on_page_writeback(dn.node_page, NODE);
-
 	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
 					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
-	dn.data_blkaddr = fio.blk_addr;
-
-	/* write page */
-	lock_page(fio.encrypted_page);
-	set_page_writeback(fio.encrypted_page);
 	fio.rw = WRITE_SYNC;
 	f2fs_submit_page_mbio(&fio);
 
+	dn.data_blkaddr = fio.blk_addr;
 	set_data_blkaddr(&dn);
 	f2fs_update_extent_cache(&dn);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
-
+put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
 put_out:
 	f2fs_put_dnode(&dn);
@@ -605,8 +617,8 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.page = page,
 			.encrypted_page = NULL,
 		};
+		set_page_dirty(page);
 		f2fs_wait_on_page_writeback(page, DATA);
-
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 38e75fb1e488..a13ffcc32992 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -141,6 +141,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	kunmap_atomic(dst_addr);
 	SetPageUptodate(page);
 no_update:
+	set_page_dirty(page);
+
 	/* clear dirty state */
 	dirty = clear_page_dirty_for_io(page);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1eb343768781..61b97f9cb9f6 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -257,6 +257,7 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 		if (!abort) {
 			lock_page(cur->page);
 			if (cur->page->mapping == inode->i_mapping) {
+				set_page_dirty(cur->page);
 				f2fs_wait_on_page_writeback(cur->page, DATA);
 				if (clear_page_dirty_for_io(cur->page))
 					inode_dec_dirty_pages(inode);
diff --git a/fs/file_table.c b/fs/file_table.c
index 7f9d407c7595..ad17e05ebf95 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
+#include <linux/swap.h>
 
 #include <linux/atomic.h>
 
@@ -308,19 +309,24 @@ void put_filp(struct file *file)
 	}
 }
 
-void __init files_init(unsigned long mempages)
+void __init files_init(void)
 { 
-	unsigned long n;
-
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
 
-	/*
-	 * One file with associated inode and dcache is very roughly 1K.
-	 * Per default don't use more than 10% of our memory for files. 
-	 */ 
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+	unsigned long n;
+	unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
+
+	memreserve = min(memreserve, totalram_pages - 1);
+	n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
 
-	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 } 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cf74df68617..973c24ce59ad 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1010,6 +1010,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
+	if (creat_flags == HUGETLB_SHMFS_INODE)
+		inode->i_flags |= S_PRIVATE;
 
 	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
diff --git a/fs/namei.c b/fs/namei.c
index ae4e4c18b2ac..fbbcf0993312 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1954,8 +1954,13 @@ OK:
 				continue;
 			}
 		}
-		if (unlikely(!d_can_lookup(nd->path.dentry)))
+		if (unlikely(!d_can_lookup(nd->path.dentry))) {
+			if (nd->flags & LOOKUP_RCU) {
+				if (unlazy_walk(nd, NULL, 0))
+					return -ECHILD;
+			}
 			return -ENOTDIR;
+		}
 	}
 }
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ecebb406cc1a..4a90c9bb3135 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -775,7 +775,7 @@ static int nfs_init_server(struct nfs_server *server,
 	server->options = data->options;
 	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
 		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
-		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR;
+		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index c12951b9551e..b3289d701eea 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1852,7 +1852,7 @@ ff_layout_mirror_prepare_stats(struct nfs42_layoutstat_args *args,
 	struct nfs42_layoutstat_devinfo *devinfo;
 	int i;
 
-	for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) {
+	for (i = 0; i < FF_LAYOUT_MIRROR_COUNT(pls); i++) {
 		if (*dev_count >= dev_limit)
 			break;
 		mirror = FF_LAYOUT_COMP(pls, i);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b77b328a06d7..0adc7d245b3d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -442,8 +442,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode->i_version = fattr->change_attr;
-		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
-			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
+		else
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_PAGECACHE);
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
 		else
@@ -1244,9 +1245,11 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
 		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize && nfsi->nrequests == 0)
+		if (cur_size != new_isize)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	}
+	if (nfsi->nrequests != 0)
+		invalid &= ~NFS_INO_REVAL_PAGECACHE;
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
@@ -1684,13 +1687,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			invalid |= NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_DATA
 				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL
-				| NFS_INO_REVAL_PAGECACHE;
+				| NFS_INO_INVALID_ACL;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
 		}
-	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
+	} else
 		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
@@ -1717,7 +1719,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-				invalid &= ~NFS_INO_REVAL_PAGECACHE;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7e3c4604bea8..9b372b845f6a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -296,6 +296,22 @@ extern struct rpc_procinfo nfs4_procedures[];
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	if (!dst || !src)
+		return NULL;
+
+	if (src->len > NFS4_MAXLABELLEN)
+		return NULL;
+
+	dst->lfs = src->lfs;
+	dst->pi = src->pi;
+	dst->len = src->len;
+	memcpy(dst->label, src->label, src->len);
+
+	return dst;
+}
 static inline void nfs4_label_free(struct nfs4_label *label)
 {
 	if (label) {
@@ -316,6 +332,11 @@ static inline void nfs4_label_free(void *label) {}
 static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
 {
 }
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	return NULL;
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index f486b80f927a..d731bbf974aa 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -135,7 +135,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
 	return err;
 }
 
-loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -171,6 +171,23 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
 }
 
+loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(filep));
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err == -ENOTSUPP)
+			return -EOPNOTSUPP;
+		err = nfs4_handle_exception(server, err, &exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+
 static void
 nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
 {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8bee93469617..3acb1eb72930 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -467,7 +467,10 @@ static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp)
 
 static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
 {
-	do_renew_lease(server->nfs_client, timestamp);
+	struct nfs_client *clp = server->nfs_client;
+
+	if (!nfs4_has_session(clp))
+		do_renew_lease(clp, timestamp);
 }
 
 struct nfs4_call_sync_data {
@@ -616,8 +619,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
-		if (res->sr_status_flags != 0)
-			nfs4_schedule_lease_recovery(clp);
+		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
 		nfs41_update_target_slotid(slot->table, slot, res);
 		break;
 	case 1:
@@ -910,6 +912,7 @@ struct nfs4_opendata {
 	struct nfs_open_confirmres c_res;
 	struct nfs4_string owner_name;
 	struct nfs4_string group_name;
+	struct nfs4_label *a_label;
 	struct nfs_fattr f_attr;
 	struct nfs4_label *f_label;
 	struct dentry *dir;
@@ -1013,6 +1016,10 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	if (IS_ERR(p->f_label))
 		goto err_free_p;
 
+	p->a_label = nfs4_label_alloc(server, gfp_mask);
+	if (IS_ERR(p->a_label))
+		goto err_free_f;
+
 	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
 	p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask);
 	if (IS_ERR(p->o_arg.seqid))
@@ -1041,7 +1048,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.server = server;
 	p->o_arg.bitmask = nfs4_bitmask(server, label);
 	p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
-	p->o_arg.label = label;
+	p->o_arg.label = nfs4_label_copy(p->a_label, label);
 	p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
 	switch (p->o_arg.claim) {
 	case NFS4_OPEN_CLAIM_NULL:
@@ -1074,6 +1081,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	return p;
 
 err_free_label:
+	nfs4_label_free(p->a_label);
+err_free_f:
 	nfs4_label_free(p->f_label);
 err_free_p:
 	kfree(p);
@@ -1093,6 +1102,7 @@ static void nfs4_opendata_free(struct kref *kref)
 		nfs4_put_open_state(p->state);
 	nfs4_put_state_owner(p->owner);
 
+	nfs4_label_free(p->a_label);
 	nfs4_label_free(p->f_label);
 
 	dput(p->dir);
@@ -1198,12 +1208,15 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state,
 
 static void nfs_resync_open_stateid_locked(struct nfs4_state *state)
 {
+	if (!(state->n_wronly || state->n_rdonly || state->n_rdwr))
+		return;
 	if (state->n_wronly)
 		set_bit(NFS_O_WRONLY_STATE, &state->flags);
 	if (state->n_rdonly)
 		set_bit(NFS_O_RDONLY_STATE, &state->flags);
 	if (state->n_rdwr)
 		set_bit(NFS_O_RDWR_STATE, &state->flags);
+	set_bit(NFS_OPEN_STATE, &state->flags);
 }
 
 static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
@@ -7571,13 +7584,8 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
 		goto out;
 	}
 	ret = rpc_wait_for_completion_task(task);
-	if (!ret) {
-		struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
-
-		if (task->tk_status == 0)
-			nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+	if (!ret)
 		ret = task->tk_status;
-	}
 	rpc_put_task(task);
 out:
 	dprintk("<-- %s status=%d\n", __func__, ret);
@@ -7965,16 +7973,17 @@ static void nfs4_layoutreturn_release(void *calldata)
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct pnfs_layout_hdr *lo = lrp->args.layout;
+	LIST_HEAD(freeme);
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
 	pnfs_clear_layoutreturn_waitbit(lo);
-	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
-	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
+	pnfs_free_lseg_list(&freeme);
 	pnfs_put_layout_hdr(lrp->args.layout);
 	nfs_iput_and_deactive(lrp->inode);
 	kfree(calldata);
@@ -8588,7 +8597,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
 	.minor_version = 0,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK,
 	.init_client = nfs40_init_client,
 	.shutdown_client = nfs40_shutdown_client,
@@ -8614,7 +8622,6 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1,
@@ -8637,7 +8644,6 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 	.minor_version = 2,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 605840dc89cf..f2e2ad894461 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2191,25 +2191,35 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp)
 	}
 }
 
-static void nfs41_handle_state_revoked(struct nfs_client *clp)
+static void nfs41_handle_all_state_revoked(struct nfs_client *clp)
 {
 	nfs4_reset_all_state(clp);
 	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
 }
 
+static void nfs41_handle_some_state_revoked(struct nfs_client *clp)
+{
+	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
+	nfs4_schedule_state_manager(clp);
+
+	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
+}
+
 static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
 {
-	/* This will need to handle layouts too */
-	nfs_expire_all_delegations(clp);
+	/* FIXME: For now, we destroy all layouts. */
+	pnfs_destroy_all_layouts(clp);
+	/* FIXME: For now, we test all delegations+open state+locks. */
+	nfs41_handle_some_state_revoked(clp);
 	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
 			clp->cl_hostname);
 }
 
 static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
 {
-	nfs_expire_all_delegations(clp);
-	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-		nfs4_schedule_state_manager(clp);
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+
 	dprintk("%s: server %s declared a backchannel fault\n", __func__,
 			clp->cl_hostname);
 }
@@ -2231,10 +2241,11 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
 
 	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
-	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
-			    SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
+	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED))
+		nfs41_handle_all_state_revoked(clp);
+	if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
 			    SEQ4_STATUS_ADMIN_STATE_REVOKED))
-		nfs41_handle_state_revoked(clp);
+		nfs41_handle_some_state_revoked(clp);
 	if (flags & SEQ4_STATUS_LEASE_MOVED)
 		nfs4_schedule_lease_moved_recovery(clp);
 	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1da68d3b1eda..4984bbe55ff1 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1100,8 +1100,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 		mirror->pg_base = 0;
 		mirror->pg_recoalesce = 0;
 
-		desc->pg_moreio = 0;
-
 		while (!list_empty(&head)) {
 			struct nfs_page *req;
 
@@ -1109,8 +1107,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
 			nfs_list_remove_request(req);
 			if (__nfs_pageio_add_request(desc, req))
 				continue;
-			if (desc->pg_error < 0)
+			if (desc->pg_error < 0) {
+				list_splice_tail(&head, &mirror->pg_list);
+				mirror->pg_recoalesce = 1;
 				return 0;
+			}
 			break;
 		}
 	} while (mirror->pg_recoalesce);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0ba9a02c9566..70bf706b1090 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -352,7 +352,7 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
 {
 	struct pnfs_layout_segment *s;
 
-	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+	if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
 		return false;
 
 	list_for_each_entry(s, &lo->plh_segs, pls_list)
@@ -362,6 +362,18 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
 	return true;
 }
 
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return false;
+	lo->plh_return_iomode = 0;
+	lo->plh_block_lgets++;
+	pnfs_get_layout_hdr(lo);
+	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
+	return true;
+}
+
 static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
 		struct pnfs_layout_hdr *lo, struct inode *inode)
 {
@@ -372,17 +384,16 @@ static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
 	if (pnfs_layout_need_return(lo, lseg)) {
 		nfs4_stateid stateid;
 		enum pnfs_iomode iomode;
+		bool send;
 
 		stateid = lo->plh_stateid;
 		iomode = lo->plh_return_iomode;
-		/* decreased in pnfs_send_layoutreturn() */
-		lo->plh_block_lgets++;
-		lo->plh_return_iomode = 0;
+		send = pnfs_prepare_layoutreturn(lo);
 		spin_unlock(&inode->i_lock);
-		pnfs_get_layout_hdr(lo);
-
-		/* Send an async layoutreturn so we dont deadlock */
-		pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		if (send) {
+			/* Send an async layoutreturn so we dont deadlock */
+			pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		}
 	} else
 		spin_unlock(&inode->i_lock);
 }
@@ -411,6 +422,10 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 		pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
 
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
+			spin_unlock(&inode->i_lock);
+			return;
+		}
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		spin_unlock(&inode->i_lock);
@@ -451,6 +466,8 @@ pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg)
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	if (atomic_dec_and_test(&lseg->pls_refcount)) {
 		struct pnfs_layout_hdr *lo = lseg->pls_layout;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			return;
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		pnfs_free_lseg_async(lseg);
@@ -924,6 +941,7 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
 	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	smp_mb__after_atomic();
 	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
 static int
@@ -978,6 +996,7 @@ _pnfs_return_layout(struct inode *ino)
 	LIST_HEAD(tmp_list);
 	nfs4_stateid stateid;
 	int status = 0, empty;
+	bool send;
 
 	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
@@ -1007,17 +1026,18 @@ _pnfs_return_layout(struct inode *ino)
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
 		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out;
+		goto out_put_layout_hdr;
 	}
 
 	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	lo->plh_block_lgets++;
+	send = pnfs_prepare_layoutreturn(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
-
-	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+	if (send)
+		status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+out_put_layout_hdr:
+	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
@@ -1097,13 +1117,9 @@ bool pnfs_roc(struct inode *ino)
 out_noroc:
 	if (lo) {
 		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
+		if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+			layoutreturn = pnfs_prepare_layoutreturn(lo);
 	}
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
@@ -1146,15 +1162,18 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	struct pnfs_layout_segment *lseg;
 	nfs4_stateid stateid;
 	u32 current_seqid;
-	bool found = false, layoutreturn = false;
+	bool layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
-	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
-		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
-			rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
-			found = true;
-			goto out;
-		}
+	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) {
+		if (!test_bit(NFS_LSEG_ROC, &lseg->pls_flags))
+			continue;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			continue;
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+		spin_unlock(&ino->i_lock);
+		return true;
+	}
 	lo = nfsi->layout;
 	current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
@@ -1162,23 +1181,19 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task)
 	 * a barrier, we choose the worst-case barrier.
 	 */
 	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
-out:
-	if (!found) {
-		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
-	}
+	stateid = lo->plh_stateid;
+	if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+		layoutreturn = pnfs_prepare_layoutreturn(lo);
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
-		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
 		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false);
+		return true;
 	}
-	return found;
+	return false;
 }
 
 /*
@@ -1695,7 +1710,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 	spin_lock(&inode->i_lock);
 	/* set failure bit so that pnfs path will be retried later */
 	pnfs_layout_set_fail_bit(lo, iomode);
-	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	if (lo->plh_return_iomode == 0)
 		lo->plh_return_iomode = range.iomode;
 	else if (lo->plh_return_iomode != range.iomode)
@@ -2207,13 +2221,12 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 	if (ld->prepare_layoutcommit) {
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
+			put_rpccred(data->cred);
 			spin_lock(&inode->i_lock);
 			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
-			spin_unlock(&inode->i_lock);
-			put_rpccred(data->cred);
-			goto clear_layoutcommitting;
+			goto out_unlock;
 		}
 	}
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 65869ca9c851..75a35a1afa79 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1379,24 +1379,27 @@ static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
 {
 	struct nfs_pgio_args *argp = &hdr->args;
 	struct nfs_pgio_res *resp = &hdr->res;
+	u64 size = argp->offset + resp->count;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		fattr->size = size;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) {
+		fattr->valid &= ~NFS_ATTR_FATTR_SIZE;
 		return;
-	if (argp->offset + resp->count != fattr->size)
-		return;
-	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+	}
+	if (size != fattr->size)
 		return;
 	/* Set attribute barrier */
 	nfs_fattr_set_barrier(fattr);
+	/* ...and update size */
+	fattr->valid |= NFS_ATTR_FATTR_SIZE;
 }
 
 void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
 {
-	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct nfs_fattr *fattr = &hdr->fattr;
 	struct inode *inode = hdr->inode;
 
-	if (fattr == NULL)
-		return;
 	spin_lock(&inode->i_lock);
 	nfs_writeback_check_extend(hdr, fattr);
 	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 6904213a4363..ebf90e487c75 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -212,6 +212,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
+		fput(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 61dfb33f0559..95202719a1fd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4396,9 +4396,9 @@ laundromat_main(struct work_struct *laundry)
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
-static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
+static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
-	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4601,9 +4601,6 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags)
 {
 	__be32 status;
 
-	status = nfs4_check_fh(fhp, ols);
-	if (status)
-		return status;
 	status = nfsd4_check_openowner_confirmed(ols);
 	if (status)
 		return status;
@@ -4690,6 +4687,9 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 		status = nfserr_bad_stateid;
 		break;
 	}
+	if (status)
+		goto out;
+	status = nfs4_check_fh(fhp, s);
 
 done:
 	if (!status && filpp)
@@ -4798,7 +4798,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status)
 		return status;
-	return nfs4_check_fh(current_fh, stp);
+	return nfs4_check_fh(current_fh, &stp->st_stid);
 }
 
 /* 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 54633858733a..75e0563c09d1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2143,6 +2143,7 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
 			      FATTR4_WORD0_RDATTR_ERROR)
 #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
+#define WORD2_ABSENT_FS_ATTRS 0
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 static inline __be32
@@ -2171,7 +2172,7 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 { return 0; }
 #endif
 
-static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
+static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err)
 {
 	/* As per referral draft:  */
 	if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS ||
@@ -2184,6 +2185,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
 	}
 	*bmval0 &= WORD0_ABSENT_FS_ATTRS;
 	*bmval1 &= WORD1_ABSENT_FS_ATTRS;
+	*bmval2 &= WORD2_ABSENT_FS_ATTRS;
 	return 0;
 }
 
@@ -2246,8 +2248,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion));
 
 	if (exp->ex_fslocs.migrated) {
-		BUG_ON(bmval[2]);
-		status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
+		status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err);
 		if (status)
 			goto out;
 	}
@@ -2286,8 +2287,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	}
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) ||
-			bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+	if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) ||
+	     bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
 		err = security_inode_getsecctx(d_inode(dentry),
 						&context, &contextlen);
 		contextsupport = (err == 0);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 92e48c70f0f0..39ddcaf0918f 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -412,16 +412,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
+	LIST_HEAD(to_free);
 
+	/*
+	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+	 * to_free list so we have to use mark_mutex even when accessing that
+	 * list. And freeing mark requires us to drop mark_mutex. So we can
+	 * reliably free only the first mark in the list. That's why we first
+	 * move marks to free to to_free list in one go and then free marks in
+	 * to_free list one by one.
+	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags) {
-			fsnotify_get_mark(mark);
-			fsnotify_destroy_mark_locked(mark, group);
-			fsnotify_put_mark(mark);
-		}
+		if (mark->flags & flags)
+			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
+
+	while (1) {
+		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+		if (list_empty(&to_free)) {
+			mutex_unlock(&group->mark_mutex);
+			break;
+		}
+		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		fsnotify_get_mark(mark);
+		fsnotify_destroy_mark_locked(mark, group);
+		mutex_unlock(&group->mark_mutex);
+		fsnotify_put_mark(mark);
+	}
 }
 
 /*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1a35c6139656..0f5fd9db8194 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -685,7 +685,7 @@ static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb,
 
 	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
 		u64 s = i_size_read(inode);
-		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
 			(do_div(s, osb->s_clustersize) >> 9);
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
@@ -910,7 +910,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				p_cpos << (osb->s_clustersize_bits - 9),
+				(u64)p_cpos << (osb->s_clustersize_bits - 9),
 				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8b23aa2f52dd..23157e40dd74 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -4025,9 +4025,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb)
 	osb->dc_work_sequence = osb->dc_wake_sequence;
 
 	processed = osb->blocked_lock_count;
-	while (processed) {
-		BUG_ON(list_empty(&osb->blocked_lock_list));
-
+	/*
+	 * blocked lock processing in this loop might call iput which can
+	 * remove items off osb->blocked_lock_list. Downconvert up to
+	 * 'processed' number of locks, but stop short if we had some
+	 * removed in ocfs2_mark_lockres_freeing when downconverting.
+	 */
+	while (processed && !list_empty(&osb->blocked_lock_list)) {
 		lockres = list_entry(osb->blocked_lock_list.next,
 				     struct ocfs2_lock_res, l_blocked_list);
 		list_del_init(&lockres->l_blocked_list);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 7e412ad74836..270221fcef42 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (kinfo->si_code == BUS_MCEERR_AR ||
-		    kinfo->si_code == BUS_MCEERR_AO)
+		if (kinfo->si_signo == SIGBUS &&
+		    (kinfo->si_code == BUS_MCEERR_AR ||
+		     kinfo->si_code == BUS_MCEERR_AO))
 			err |= __put_user((short) kinfo->si_addr_lsb,
 					  &uinfo->ssi_addr_lsb);
 #endif
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 20de88d1bf86..dd714037c322 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -159,11 +159,10 @@ xfs_attr3_rmt_write_verify(
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+	int		blksize = mp->m_attr_geo->blksize;
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
-	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -175,16 +174,22 @@ xfs_attr3_rmt_write_verify(
 	ASSERT(len >= blksize);
 
 	while (len > 0) {
+		struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
+
 		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, -EFSCORRUPTED);
 			xfs_verifier_error(bp);
 			return;
 		}
-		if (bip) {
-			struct xfs_attr3_rmt_hdr *rmt;
 
-			rmt = (struct xfs_attr3_rmt_hdr *)ptr;
-			rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+		/*
+		 * Ensure we aren't writing bogus LSNs to disk. See
+		 * xfs_attr3_rmt_hdr_set() for the explanation.
+		 */
+		if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
+			xfs_buf_ioerror(bp, -EFSCORRUPTED);
+			xfs_verifier_error(bp);
+			return;
 		}
 		xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
 
@@ -221,6 +226,18 @@ xfs_attr3_rmt_hdr_set(
 	rmt->rm_owner = cpu_to_be64(ino);
 	rmt->rm_blkno = cpu_to_be64(bno);
 
+	/*
+	 * Remote attribute blocks are written synchronously, so we don't
+	 * have an LSN that we can stamp in them that makes any sense to log
+	 * recovery. To ensure that log recovery handles overwrites of these
+	 * blocks sanely (i.e. once they've been freed and reallocated as some
+	 * other type of metadata) we need to ensure that the LSN has a value
+	 * that tells log recovery to ignore the LSN and overwrite the buffer
+	 * with whatever is in it's log. To do this, we use the magic
+	 * NULLCOMMITLSN to indicate that the LSN is invalid.
+	 */
+	rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN);
+
 	return sizeof(struct xfs_attr3_rmt_hdr);
 }
 
@@ -434,14 +451,21 @@ xfs_attr_rmtval_set(
 
 		/*
 		 * Allocate a single extent, up to the size of the value.
+		 *
+		 * Note that we have to consider this a data allocation as we
+		 * write the remote attribute without logging the contents.
+		 * Hence we must ensure that we aren't using blocks that are on
+		 * the busy list so that we don't overwrite blocks which have
+		 * recently been freed but their transactions are not yet
+		 * committed to disk. If we overwrite the contents of a busy
+		 * extent and then crash then the block may not contain the
+		 * correct metadata after log recovery occurs.
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt,
-				  XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
-				  args->firstblock, args->total, &map, &nmap,
-				  args->flist);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
+				  args->total, &map, &nmap, args->flist);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
 						&committed);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f0e8249722d4..db4acc1c3e73 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1514,18 +1514,27 @@ xfs_filemap_fault(
 	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct xfs_inode	*ip = XFS_I(file_inode(vma->vm_file));
+	struct inode		*inode = file_inode(vma->vm_file);
 	int			ret;
 
-	trace_xfs_filemap_fault(ip);
+	trace_xfs_filemap_fault(XFS_I(inode));
 
 	/* DAX can shortcut the normal fault path on write faults! */
-	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip)))
+	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
 		return xfs_filemap_page_mkwrite(vma, vmf);
 
-	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
-	ret = filemap_fault(vma, vmf);
-	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	if (IS_DAX(inode)) {
+		/*
+		 * we do not want to trigger unwritten extent conversion on read
+		 * faults - that is unnecessary overhead and would also require
+		 * changes to xfs_get_blocks_direct() to map unwritten extent
+		 * ioend for conversion on read-only mappings.
+		 */
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+	} else
+		ret = filemap_fault(vma, vmf);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	return ret;
 }
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 01dd228ca05e..480ebba8464f 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1886,9 +1886,14 @@ xlog_recover_get_buf_lsn(
 		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
 		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
-		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
-		break;
+		/*
+		 * Remote attr blocks are written synchronously, rather than
+		 * being logged. That means they do not contain a valid LSN
+		 * (i.e. transactionally ordered) in them, and hence any time we
+		 * see a buffer to replay over the top of a remote attribute
+		 * block we should simply do so.
+		 */
+		goto recover_immediately;
 	case XFS_SB_MAGIC:
 		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
 		uuid = &((struct xfs_dsb *)blk)->sb_uuid;