Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

27 files changed, 197 insertions, 177 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 4ab67e8cb776..873b4ca82ccb 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1085,7 +1085,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2)
 		 * Tell lockdep we inherited freeze protection from submission
 		 * thread.
 		 */
-		__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		if (S_ISREG(file_inode(file)->i_mode))
+			__sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 		file_end_write(file);
 	}
 
@@ -1525,7 +1526,8 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 		 * by telling it the lock got released so that it doesn't
 		 * complain about held lock when we return to userspace.
 		 */
-		__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+		if (S_ISREG(file_inode(file)->i_mode))
+			__sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE);
 	}
 	kfree(iovec);
 	return ret;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 29a02daf08a9..422370293cfd 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -2298,6 +2298,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 				goto end_coredump;
 		}
 	}
+	dump_truncate(cprm);
 
 	if (!elf_core_write_extra_data(cprm))
 		goto end_coredump;
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 63d197724519..ff0b0be92d61 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -273,6 +273,8 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 	unsigned long flags;
 
 	while (1) {
+		void *wtag;
+
 		spin_lock_irqsave(lock, flags);
 		if (list_empty(list))
 			break;
@@ -299,11 +301,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 		spin_unlock_irqrestore(lock, flags);
 
 		/*
-		 * we don't want to call the ordered free functions
-		 * with the lock held though
+		 * We don't want to call the ordered free functions with the
+		 * lock held though. Save the work as tag for the trace event,
+		 * because the callback could free the structure.
 		 */
+		wtag = work;
 		work->ordered_free(work);
-		trace_btrfs_all_work_done(work);
+		trace_btrfs_all_work_done(wq->fs_info, wtag);
 	}
 	spin_unlock_irqrestore(lock, flags);
 }
@@ -311,6 +315,7 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 static void normal_work_helper(struct btrfs_work *work)
 {
 	struct __btrfs_workqueue *wq;
+	void *wtag;
 	int need_order = 0;
 
 	/*
@@ -324,6 +329,8 @@ static void normal_work_helper(struct btrfs_work *work)
 	if (work->ordered_func)
 		need_order = 1;
 	wq = work->wq;
+	/* Safe for tracepoints in case work gets freed by the callback */
+	wtag = work;
 
 	trace_btrfs_work_sched(work);
 	thresh_exec_hook(wq);
@@ -333,7 +340,7 @@ static void normal_work_helper(struct btrfs_work *work)
 		run_ordered_work(wq);
 	}
 	if (!need_order)
-		trace_btrfs_all_work_done(work);
+		trace_btrfs_all_work_done(wq->fs_info, wtag);
 }
 
 void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e97302f437a1..dcd2e798767e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2522,11 +2522,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		if (ref && ref->seq &&
 		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
-			btrfs_delayed_ref_unlock(locked_ref);
 			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
 			delayed_refs->num_heads_ready++;
 			spin_unlock(&delayed_refs->lock);
+			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 			cond_resched();
 			count++;
@@ -2572,7 +2572,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 					 */
 					if (must_insert_reserved)
 						locked_ref->must_insert_reserved = 1;
+					spin_lock(&delayed_refs->lock);
 					locked_ref->processing = 0;
+					delayed_refs->num_heads_ready++;
+					spin_unlock(&delayed_refs->lock);
 					btrfs_debug(fs_info,
 						    "run_delayed_extent_op returned %d",
 						    ret);
@@ -7384,7 +7387,8 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 
 		spin_unlock(&cluster->refill_lock);
 
-		down_read(&used_bg->data_rwsem);
+		/* We should only have one-level nested. */
+		down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING);
 
 		spin_lock(&cluster->refill_lock);
 		if (used_bg == cluster->block_group)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f2b281ad7af6..4e024260ad71 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7059,7 +7059,7 @@ insert:
 	write_unlock(&em_tree->lock);
 out:
 
-	trace_btrfs_get_extent(root, em);
+	trace_btrfs_get_extent(root, inode, em);
 
 	btrfs_free_path(path);
 	if (trans) {
@@ -7623,11 +7623,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode,
 	 * within our reservation, otherwise we need to adjust our inode
 	 * counter appropriately.
 	 */
-	if (dio_data->outstanding_extents) {
+	if (dio_data->outstanding_extents >= num_extents) {
 		dio_data->outstanding_extents -= num_extents;
 	} else {
+		/*
+		 * If dio write length has been split due to no large enough
+		 * contiguous space, we need to compensate our inode counter
+		 * appropriately.
+		 */
+		u64 num_needed = num_extents - dio_data->outstanding_extents;
+
 		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->outstanding_extents += num_extents;
+		BTRFS_I(inode)->outstanding_extents += num_needed;
 		spin_unlock(&BTRFS_I(inode)->lock);
 	}
 }
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f10bf5213ed8..eeffff84f280 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -37,6 +37,7 @@
  */
 #define LOG_INODE_ALL 0
 #define LOG_INODE_EXISTS 1
+#define LOG_OTHER_INODE 2
 
 /*
  * directory trouble cases
@@ -4641,7 +4642,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	if (S_ISDIR(inode->i_mode) ||
 	    (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 		       &BTRFS_I(inode)->runtime_flags) &&
-	     inode_only == LOG_INODE_EXISTS))
+	     inode_only >= LOG_INODE_EXISTS))
 		max_key.type = BTRFS_XATTR_ITEM_KEY;
 	else
 		max_key.type = (u8)-1;
@@ -4665,7 +4666,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	if (inode_only == LOG_OTHER_INODE) {
+		inode_only = LOG_INODE_EXISTS;
+		mutex_lock_nested(&BTRFS_I(inode)->log_mutex,
+				  SINGLE_DEPTH_NESTING);
+	} else {
+		mutex_lock(&BTRFS_I(inode)->log_mutex);
+	}
 
 	/*
 	 * a brute force approach to making sure we get the most uptodate
@@ -4817,7 +4824,7 @@ again:
 				 * unpin it.
 				 */
 				err = btrfs_log_inode(trans, root, other_inode,
-						      LOG_INODE_EXISTS,
+						      LOG_OTHER_INODE,
 						      0, LLONG_MAX, ctx);
 				iput(other_inode);
 				if (err)
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 161342b73ce5..726f928238d0 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -352,7 +352,5 @@ skip:
 
 out:
 	btrfs_free_path(path);
-	if (ret)
-		btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret);
-	return 0;
+	return ret;
 }
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 9cd0c0ea7cdb..e4b066cd912a 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -502,9 +502,9 @@ static struct ceph_snap_context *get_oldest_context(struct inode *inode,
 		dout(" head snapc %p has %d dirty pages\n",
 		     snapc, ci->i_wrbuffer_ref_head);
 		if (truncate_size)
-			*truncate_size = capsnap->truncate_size;
+			*truncate_size = ci->i_truncate_size;
 		if (truncate_seq)
-			*truncate_seq = capsnap->truncate_seq;
+			*truncate_seq = ci->i_truncate_seq;
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	return snapc;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4f49253387a0..ec6b35e9f966 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2106,6 +2106,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
 			dout("do_request mdsmap err %d\n", err);
 			goto finish;
 		}
+		if (mdsc->mdsmap->m_epoch == 0) {
+			dout("do_request no mdsmap, waiting for map\n");
+			list_add(&req->r_wait, &mdsc->waiting_for_map);
+			goto finish;
+		}
 		if (!(mdsc->fsc->mount_options->flags &
 		      CEPH_MOUNT_OPT_MOUNTWAIT) &&
 		    !ceph_mdsmap_is_cluster_available(mdsc->mdsmap)) {
diff --git a/fs/coredump.c b/fs/coredump.c
index e525b6017cdf..ae6b05629ca1 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -833,3 +833,21 @@ int dump_align(struct coredump_params *cprm, int align)
 	return mod ? dump_skip(cprm, align - mod) : 1;
 }
 EXPORT_SYMBOL(dump_align);
+
+/*
+ * Ensures that file size is big enough to contain the current file
+ * postion. This prevents gdb from complaining about a truncated file
+ * if the last "write" to the file was dump_skip.
+ */
+void dump_truncate(struct coredump_params *cprm)
+{
+	struct file *file = cprm->file;
+	loff_t offset;
+
+	if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
+		offset = file->f_op->llseek(file, 0, SEEK_CUR);
+		if (i_size_read(file->f_mapping->host) < offset)
+			do_truncate(file->f_path.dentry, offset, 0, file);
+	}
+}
+EXPORT_SYMBOL(dump_truncate);
diff --git a/fs/dcache.c b/fs/dcache.c
index 769903dbc19d..95d71eda8142 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1336,8 +1336,11 @@ int d_set_mounted(struct dentry *dentry)
 	}
 	spin_lock(&dentry->d_lock);
 	if (!d_unlinked(dentry)) {
-		dentry->d_flags |= DCACHE_MOUNTED;
-		ret = 0;
+		ret = -EBUSY;
+		if (!d_mountpoint(dentry)) {
+			dentry->d_flags |= DCACHE_MOUNTED;
+			ret = 0;
+		}
 	}
  	spin_unlock(&dentry->d_lock);
 out:
diff --git a/fs/direct-io.c b/fs/direct-io.c
index aeae8c063451..c87bae4376b8 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -906,6 +906,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
 			struct buffer_head *map_bh)
 {
 	const unsigned blkbits = sdio->blkbits;
+	const unsigned i_blkbits = blkbits + sdio->blkfactor;
 	int ret = 0;
 
 	while (sdio->block_in_file < sdio->final_block_in_request) {
@@ -949,7 +950,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
 					clean_bdev_aliases(
 						map_bh->b_bdev,
 						map_bh->b_blocknr,
-						map_bh->b_size >> blkbits);
+						map_bh->b_size >> i_blkbits);
 				}
 
 				if (!sdio->blkfactor)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0738f48293cc..0d8802453758 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -713,8 +713,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 	}
 	sector = SECTOR_FROM_BLOCK(blkstart);
 
-	if (sector & (bdev_zone_size(bdev) - 1) ||
-				nr_sects != bdev_zone_size(bdev)) {
+	if (sector & (bdev_zone_sectors(bdev) - 1) ||
+	    nr_sects != bdev_zone_sectors(bdev)) {
 		f2fs_msg(sbi->sb, KERN_INFO,
 			"(%d) %s: Unaligned discard attempted (block %x + %x)",
 			devi, sbi->s_ndevs ? FDEV(devi).path: "",
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 702638e21c76..46fd30d8af77 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1553,16 +1553,16 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
 		return 0;
 
 	if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
-				SECTOR_TO_BLOCK(bdev_zone_size(bdev)))
+				SECTOR_TO_BLOCK(bdev_zone_sectors(bdev)))
 		return -EINVAL;
-	sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev));
+	sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_sectors(bdev));
 	if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
 				__ilog2_u32(sbi->blocks_per_blkz))
 		return -EINVAL;
 	sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
 	FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
 					sbi->log_blocks_per_blkz;
-	if (nr_sectors & (bdev_zone_size(bdev) - 1))
+	if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
 		FDEV(devi).nr_blkz++;
 
 	FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
diff --git a/fs/libfs.c b/fs/libfs.c
index e973cd51f126..28d6f35feed6 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -245,7 +245,8 @@ struct dentry *mount_pseudo_xattr(struct file_system_type *fs_type, char *name,
 	struct inode *root;
 	struct qstr d_name = QSTR_INIT(name, strlen(name));
 
-	s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL);
+	s = sget_userns(fs_type, NULL, set_anon_super, MS_KERNMOUNT|MS_NOUSER,
+			&init_user_ns, NULL);
 	if (IS_ERR(s))
 		return ERR_CAST(s);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index b5b1259e064f..487ba30bb5c6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -742,26 +742,50 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
 	return NULL;
 }
 
-static struct mountpoint *new_mountpoint(struct dentry *dentry)
+static struct mountpoint *get_mountpoint(struct dentry *dentry)
 {
-	struct hlist_head *chain = mp_hash(dentry);
-	struct mountpoint *mp;
+	struct mountpoint *mp, *new = NULL;
 	int ret;
 
-	mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
-	if (!mp)
+	if (d_mountpoint(dentry)) {
+mountpoint:
+		read_seqlock_excl(&mount_lock);
+		mp = lookup_mountpoint(dentry);
+		read_sequnlock_excl(&mount_lock);
+		if (mp)
+			goto done;
+	}
+
+	if (!new)
+		new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
+	if (!new)
 		return ERR_PTR(-ENOMEM);
 
+
+	/* Exactly one processes may set d_mounted */
 	ret = d_set_mounted(dentry);
-	if (ret) {
-		kfree(mp);
-		return ERR_PTR(ret);
-	}
 
-	mp->m_dentry = dentry;
-	mp->m_count = 1;
-	hlist_add_head(&mp->m_hash, chain);
-	INIT_HLIST_HEAD(&mp->m_list);
+	/* Someone else set d_mounted? */
+	if (ret == -EBUSY)
+		goto mountpoint;
+
+	/* The dentry is not available as a mountpoint? */
+	mp = ERR_PTR(ret);
+	if (ret)
+		goto done;
+
+	/* Add the new mountpoint to the hash table */
+	read_seqlock_excl(&mount_lock);
+	new->m_dentry = dentry;
+	new->m_count = 1;
+	hlist_add_head(&new->m_hash, mp_hash(dentry));
+	INIT_HLIST_HEAD(&new->m_list);
+	read_sequnlock_excl(&mount_lock);
+
+	mp = new;
+	new = NULL;
+done:
+	kfree(new);
 	return mp;
 }
 
@@ -1595,11 +1619,11 @@ void __detach_mounts(struct dentry *dentry)
 	struct mount *mnt;
 
 	namespace_lock();
+	lock_mount_hash();
 	mp = lookup_mountpoint(dentry);
 	if (IS_ERR_OR_NULL(mp))
 		goto out_unlock;
 
-	lock_mount_hash();
 	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
@@ -1609,9 +1633,9 @@ void __detach_mounts(struct dentry *dentry)
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
-	unlock_mount_hash();
 	put_mountpoint(mp);
 out_unlock:
+	unlock_mount_hash();
 	namespace_unlock();
 }
 
@@ -2038,9 +2062,7 @@ retry:
 	namespace_lock();
 	mnt = lookup_mnt(path);
 	if (likely(!mnt)) {
-		struct mountpoint *mp = lookup_mountpoint(dentry);
-		if (!mp)
-			mp = new_mountpoint(dentry);
+		struct mountpoint *mp = get_mountpoint(dentry);
 		if (IS_ERR(mp)) {
 			namespace_unlock();
 			inode_unlock(dentry->d_inode);
@@ -2059,7 +2081,11 @@ retry:
 static void unlock_mount(struct mountpoint *where)
 {
 	struct dentry *dentry = where->m_dentry;
+
+	read_seqlock_excl(&mount_lock);
 	put_mountpoint(where);
+	read_sequnlock_excl(&mount_lock);
+
 	namespace_unlock();
 	inode_unlock(dentry->d_inode);
 }
@@ -3135,9 +3161,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
+	put_mountpoint(root_mp);
 	unlock_mount_hash();
 	chroot_fs_refs(&root, &new);
-	put_mountpoint(root_mp);
 	error = 0;
 out4:
 	unlock_mount(old_mp);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6dcbc5defb7a..ecc151697fd4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -38,7 +38,6 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
-#include <linux/file.h>
 #include <linux/string.h>
 #include <linux/ratelimit.h>
 #include <linux/printk.h>
@@ -1083,7 +1082,8 @@ int nfs4_call_sync(struct rpc_clnt *clnt,
 	return nfs4_call_sync_sequence(clnt, server, msg, args, res);
 }
 
-static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
+static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo,
+		unsigned long timestamp)
 {
 	struct nfs_inode *nfsi = NFS_I(dir);
 
@@ -1099,6 +1099,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 				NFS_INO_INVALID_ACL;
 	}
 	dir->i_version = cinfo->after;
+	nfsi->read_cache_jiffies = timestamp;
 	nfsi->attr_gencount = nfs_inc_attr_generation_counter();
 	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
@@ -2391,11 +2392,13 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 	nfs_fattr_map_and_free_names(server, &data->f_attr);
 
 	if (o_arg->open_flags & O_CREAT) {
-		update_changeattr(dir, &o_res->cinfo);
 		if (o_arg->open_flags & O_EXCL)
 			data->file_created = 1;
 		else if (o_res->cinfo.before != o_res->cinfo.after)
 			data->file_created = 1;
+		if (data->file_created || dir->i_version != o_res->cinfo.after)
+			update_changeattr(dir, &o_res->cinfo,
+					o_res->f_attr->time_start);
 	}
 	if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
 		server->caps &= ~NFS_CAP_POSIX_LOCK;
@@ -4073,11 +4076,12 @@ static int _nfs4_proc_remove(struct inode *dir, const struct qstr *name)
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
+	unsigned long timestamp = jiffies;
 	int status;
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
 	if (status == 0)
-		update_changeattr(dir, &res.cinfo);
+		update_changeattr(dir, &res.cinfo, timestamp);
 	return status;
 }
 
@@ -4125,7 +4129,8 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 	if (nfs4_async_handle_error(task, res->server, NULL,
 				    &data->timeout) == -EAGAIN)
 		return 0;
-	update_changeattr(dir, &res->cinfo);
+	if (task->tk_status == 0)
+		update_changeattr(dir, &res->cinfo, res->dir_attr->time_start);
 	return 1;
 }
 
@@ -4159,8 +4164,11 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	if (nfs4_async_handle_error(task, res->server, NULL, &data->timeout) == -EAGAIN)
 		return 0;
 
-	update_changeattr(old_dir, &res->old_cinfo);
-	update_changeattr(new_dir, &res->new_cinfo);
+	if (task->tk_status == 0) {
+		update_changeattr(old_dir, &res->old_cinfo, res->old_fattr->time_start);
+		if (new_dir != old_dir)
+			update_changeattr(new_dir, &res->new_cinfo, res->new_fattr->time_start);
+	}
 	return 1;
 }
 
@@ -4197,7 +4205,7 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct
 
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	if (!status) {
-		update_changeattr(dir, &res.cinfo);
+		update_changeattr(dir, &res.cinfo, res.fattr->time_start);
 		status = nfs_post_op_update_inode(inode, res.fattr);
 		if (!status)
 			nfs_setsecurity(inode, res.fattr, res.label);
@@ -4272,7 +4280,8 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
 	int status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &data->msg,
 				    &data->arg.seq_args, &data->res.seq_res, 1);
 	if (status == 0) {
-		update_changeattr(dir, &data->res.dir_cinfo);
+		update_changeattr(dir, &data->res.dir_cinfo,
+				data->res.fattr->time_start);
 		status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label);
 	}
 	return status;
@@ -6127,7 +6136,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->server = server;
 	atomic_inc(&lsp->ls_count);
 	p->ctx = get_nfs_open_context(ctx);
-	get_file(fl->fl_file);
 	memcpy(&p->fl, fl, sizeof(p->fl));
 	return p;
 out_free_seqid:
@@ -6240,7 +6248,6 @@ static void nfs4_lock_release(void *calldata)
 		nfs_free_seqid(data->arg.lock_seqid);
 	nfs4_put_lock_state(data->lsp);
 	put_nfs_open_context(data->ctx);
-	fput(data->fl.fl_file);
 	kfree(data);
 	dprintk("%s: done!\n", __func__);
 }
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1d152f4470cd..90e6193ce6be 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1729,7 +1729,6 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 			break;
 		case -NFS4ERR_STALE_CLIENTID:
 			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
-			nfs4_state_clear_reclaim_reboot(clp);
 			nfs4_state_start_reclaim_reboot(clp);
 			break;
 		case -NFS4ERR_EXPIRED:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 7ecf16be4a44..8fae53ce21d1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2440,7 +2440,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	p++;                /* to be backfilled later */
 
 	if (bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
-		u32 *supp = nfsd_suppattrs[minorversion];
+		u32 supp[3];
+
+		memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp));
 
 		if (!IS_POSIXACL(dentry->d_inode))
 			supp[0] &= ~FATTR4_WORD0_ACL;
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 595522022aca..c9d48dc78495 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -922,11 +922,10 @@ int simple_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	int error;
 
 	if (type == ACL_TYPE_ACCESS) {
-		error = posix_acl_equiv_mode(acl, &inode->i_mode);
-		if (error < 0)
-			return 0;
-		if (error == 0)
-			acl = NULL;
+		error = posix_acl_update_mode(inode,
+				&inode->i_mode, &acl);
+		if (error)
+			return error;
 	}
 
 	inode->i_ctime = current_time(inode);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 55313d994895..d4e37acd4821 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -709,7 +709,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 	ctl_dir = container_of(head, struct ctl_dir, header);
 
 	if (!dir_emit_dots(file, ctx))
-		return 0;
+		goto out;
 
 	pos = 2;
 
@@ -719,6 +719,7 @@ static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 			break;
 		}
 	}
+out:
 	sysctl_head_finish(head);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 5050056a0b06..9f06a211e157 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -95,10 +95,7 @@ unsigned int
 xfs_alloc_set_aside(
 	struct xfs_mount	*mp)
 {
-	unsigned int		blocks;
-
-	blocks = 4 + (mp->m_sb.sb_agcount * XFS_ALLOC_AGFL_RESERVE);
-	return blocks;
+	return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4);
 }
 
 /*
@@ -365,36 +362,12 @@ xfs_alloc_fix_len(
 		return;
 	ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
 	ASSERT(rlen % args->prod == args->mod);
+	ASSERT(args->pag->pagf_freeblks + args->pag->pagf_flcount >=
+		rlen + args->minleft);
 	args->len = rlen;
 }
 
 /*
- * Fix up length if there is too little space left in the a.g.
- * Return 1 if ok, 0 if too little, should give up.
- */
-STATIC int
-xfs_alloc_fix_minleft(
-	xfs_alloc_arg_t	*args)		/* allocation argument structure */
-{
-	xfs_agf_t	*agf;		/* a.g. freelist header */
-	int		diff;		/* free space difference */
-
-	if (args->minleft == 0)
-		return 1;
-	agf = XFS_BUF_TO_AGF(args->agbp);
-	diff = be32_to_cpu(agf->agf_freeblks)
-		- args->len - args->minleft;
-	if (diff >= 0)
-		return 1;
-	args->len += diff;		/* shrink the allocated space */
-	/* casts to (int) catch length underflows */
-	if ((int)args->len >= (int)args->minlen)
-		return 1;
-	args->agbno = NULLAGBLOCK;
-	return 0;
-}
-
-/*
  * Update the two btrees, logically removing from freespace the extent
  * starting at rbno, rlen blocks.  The extent is contained within the
  * actual (current) free extent fbno for flen blocks.
@@ -689,8 +662,6 @@ xfs_alloc_ag_vextent(
 	xfs_alloc_arg_t	*args)	/* argument structure for allocation */
 {
 	int		error=0;
-	xfs_extlen_t	reservation;
-	xfs_extlen_t	oldmax;
 
 	ASSERT(args->minlen > 0);
 	ASSERT(args->maxlen > 0);
@@ -699,20 +670,6 @@ xfs_alloc_ag_vextent(
 	ASSERT(args->alignment > 0);
 
 	/*
-	 * Clamp maxlen to the amount of free space minus any reservations
-	 * that have been made.
-	 */
-	oldmax = args->maxlen;
-	reservation = xfs_ag_resv_needed(args->pag, args->resv);
-	if (args->maxlen > args->pag->pagf_freeblks - reservation)
-		args->maxlen = args->pag->pagf_freeblks - reservation;
-	if (args->maxlen == 0) {
-		args->agbno = NULLAGBLOCK;
-		args->maxlen = oldmax;
-		return 0;
-	}
-
-	/*
 	 * Branch to correct routine based on the type.
 	 */
 	args->wasfromfl = 0;
@@ -731,8 +688,6 @@ xfs_alloc_ag_vextent(
 		/* NOTREACHED */
 	}
 
-	args->maxlen = oldmax;
-
 	if (error || args->agbno == NULLAGBLOCK)
 		return error;
 
@@ -841,9 +796,6 @@ xfs_alloc_ag_vextent_exact(
 	args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen)
 						- args->agbno;
 	xfs_alloc_fix_len(args);
-	if (!xfs_alloc_fix_minleft(args))
-		goto not_found;
-
 	ASSERT(args->agbno + args->len <= tend);
 
 	/*
@@ -1149,12 +1101,7 @@ restart:
 		XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
 		ASSERT(ltbno + ltlen <= be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length));
 		args->len = blen;
-		if (!xfs_alloc_fix_minleft(args)) {
-			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
-			trace_xfs_alloc_near_nominleft(args);
-			return 0;
-		}
-		blen = args->len;
+
 		/*
 		 * We are allocating starting at bnew for blen blocks.
 		 */
@@ -1346,12 +1293,6 @@ restart:
 	 */
 	args->len = XFS_EXTLEN_MIN(ltlena, args->maxlen);
 	xfs_alloc_fix_len(args);
-	if (!xfs_alloc_fix_minleft(args)) {
-		trace_xfs_alloc_near_nominleft(args);
-		xfs_btree_del_cursor(bno_cur_lt, XFS_BTREE_NOERROR);
-		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
-		return 0;
-	}
 	rlen = args->len;
 	(void)xfs_alloc_compute_diff(args->agbno, rlen, args->alignment,
 				     args->datatype, ltbnoa, ltlena, &ltnew);
@@ -1553,8 +1494,6 @@ restart:
 	}
 	xfs_alloc_fix_len(args);
 
-	if (!xfs_alloc_fix_minleft(args))
-		goto out_nominleft;
 	rlen = args->len;
 	XFS_WANT_CORRUPTED_GOTO(args->mp, rlen <= flen, error0);
 	/*
@@ -2056,7 +1995,7 @@ xfs_alloc_space_available(
 	int			flags)
 {
 	struct xfs_perag	*pag = args->pag;
-	xfs_extlen_t		longest;
+	xfs_extlen_t		alloc_len, longest;
 	xfs_extlen_t		reservation; /* blocks that are still reserved */
 	int			available;
 
@@ -2066,17 +2005,28 @@ xfs_alloc_space_available(
 	reservation = xfs_ag_resv_needed(pag, args->resv);
 
 	/* do we have enough contiguous free space for the allocation? */
+	alloc_len = args->minlen + (args->alignment - 1) + args->minalignslop;
 	longest = xfs_alloc_longest_free_extent(args->mp, pag, min_free,
 			reservation);
-	if ((args->minlen + args->alignment + args->minalignslop - 1) > longest)
+	if (longest < alloc_len)
 		return false;
 
 	/* do we have enough free space remaining for the allocation? */
 	available = (int)(pag->pagf_freeblks + pag->pagf_flcount -
-			  reservation - min_free - args->total);
-	if (available < (int)args->minleft || available <= 0)
+			  reservation - min_free - args->minleft);
+	if (available < (int)max(args->total, alloc_len))
 		return false;
 
+	/*
+	 * Clamp maxlen to the amount of free space available for the actual
+	 * extent allocation.
+	 */
+	if (available < (int)args->maxlen && !(flags & XFS_ALLOC_FLAG_CHECK)) {
+		args->maxlen = available;
+		ASSERT(args->maxlen > 0);
+		ASSERT(args->maxlen >= args->minlen);
+	}
+
 	return true;
 }
 
@@ -2122,7 +2072,8 @@ xfs_alloc_fix_freelist(
 	}
 
 	need = xfs_alloc_min_freelist(mp, pag);
-	if (!xfs_alloc_space_available(args, need, flags))
+	if (!xfs_alloc_space_available(args, need, flags |
+			XFS_ALLOC_FLAG_CHECK))
 		goto out_agbp_relse;
 
 	/*
@@ -2638,12 +2589,10 @@ xfs_alloc_vextent(
 	xfs_agblock_t	agsize;	/* allocation group size */
 	int		error;
 	int		flags;	/* XFS_ALLOC_FLAG_... locking flags */
-	xfs_extlen_t	minleft;/* minimum left value, temp copy */
 	xfs_mount_t	*mp;	/* mount structure pointer */
 	xfs_agnumber_t	sagno;	/* starting allocation group number */
 	xfs_alloctype_t	type;	/* input allocation type */
 	int		bump_rotor = 0;
-	int		no_min = 0;
 	xfs_agnumber_t	rotorstep = xfs_rotorstep; /* inode32 agf stepper */
 
 	mp = args->mp;
@@ -2672,7 +2621,6 @@ xfs_alloc_vextent(
 		trace_xfs_alloc_vextent_badargs(args);
 		return 0;
 	}
-	minleft = args->minleft;
 
 	switch (type) {
 	case XFS_ALLOCTYPE_THIS_AG:
@@ -2683,9 +2631,7 @@ xfs_alloc_vextent(
 		 */
 		args->agno = XFS_FSB_TO_AGNO(mp, args->fsbno);
 		args->pag = xfs_perag_get(mp, args->agno);
-		args->minleft = 0;
 		error = xfs_alloc_fix_freelist(args, 0);
-		args->minleft = minleft;
 		if (error) {
 			trace_xfs_alloc_vextent_nofix(args);
 			goto error0;
@@ -2750,9 +2696,7 @@ xfs_alloc_vextent(
 		 */
 		for (;;) {
 			args->pag = xfs_perag_get(mp, args->agno);
-			if (no_min) args->minleft = 0;
 			error = xfs_alloc_fix_freelist(args, flags);
-			args->minleft = minleft;
 			if (error) {
 				trace_xfs_alloc_vextent_nofix(args);
 				goto error0;
@@ -2792,20 +2736,17 @@ xfs_alloc_vextent(
 			 * or switch to non-trylock mode.
 			 */
 			if (args->agno == sagno) {
-				if (no_min == 1) {
+				if (flags == 0) {
 					args->agbno = NULLAGBLOCK;
 					trace_xfs_alloc_vextent_allfailed(args);
 					break;
 				}
-				if (flags == 0) {
-					no_min = 1;
-				} else {
-					flags = 0;
-					if (type == XFS_ALLOCTYPE_START_BNO) {
-						args->agbno = XFS_FSB_TO_AGBNO(mp,
-							args->fsbno);
-						args->type = XFS_ALLOCTYPE_NEAR_BNO;
-					}
+
+				flags = 0;
+				if (type == XFS_ALLOCTYPE_START_BNO) {
+					args->agbno = XFS_FSB_TO_AGBNO(mp,
+						args->fsbno);
+					args->type = XFS_ALLOCTYPE_NEAR_BNO;
 				}
 			}
 			xfs_perag_put(args->pag);
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 7c404a6b0ae3..1d0f48a501a3 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -56,7 +56,7 @@ typedef unsigned int xfs_alloctype_t;
 #define	XFS_ALLOC_FLAG_FREEING	0x00000002  /* indicate caller is freeing extents*/
 #define	XFS_ALLOC_FLAG_NORMAP	0x00000004  /* don't modify the rmapbt */
 #define	XFS_ALLOC_FLAG_NOSHRINK	0x00000008  /* don't shrink the freelist */
-
+#define	XFS_ALLOC_FLAG_CHECK	0x00000010  /* test only, don't modify args */
 
 /*
  * Argument structure for xfs_alloc routines.
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 2760bc3b2536..44773c9eb957 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3812,7 +3812,6 @@ xfs_bmap_btalloc(
 		args.fsbno = 0;
 		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		args.total = ap->minlen;
-		args.minleft = 0;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 		ap->dfops->dop_low = true;
@@ -4344,8 +4343,6 @@ xfs_bmapi_allocate(
 	if (error)
 		return error;
 
-	if (bma->dfops->dop_low)
-		bma->minleft = 0;
 	if (bma->cur)
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
 	if (bma->blkno == NULLFSBLOCK)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index d6330c297ca0..d9be241fc86f 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -502,12 +502,11 @@ try_another_ag:
 	if (args.fsbno == NULLFSBLOCK && args.minleft) {
 		/*
 		 * Could not find an AG with enough free space to satisfy
-		 * a full btree split.  Try again without minleft and if
+		 * a full btree split.  Try again and if
 		 * successful activate the lowspace algorithm.
 		 */
 		args.fsbno = 0;
 		args.type = XFS_ALLOCTYPE_FIRST_AG;
-		args.minleft = 0;
 		error = xfs_alloc_vextent(&args);
 		if (error)
 			goto error0;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0f56fcd3a5d5..631e7c0e0a29 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1152,19 +1152,22 @@ xfs_vm_releasepage(
 	 * block_invalidatepage() can send pages that are still marked dirty
 	 * but otherwise have invalidated buffers.
 	 *
-	 * We've historically freed buffers on the latter. Instead, quietly
-	 * filter out all dirty pages to avoid spurious buffer state warnings.
-	 * This can likely be removed once shrink_active_list() is fixed.
+	 * We want to release the latter to avoid unnecessary buildup of the
+	 * LRU, skip the former and warn if we've left any lingering
+	 * delalloc/unwritten buffers on clean pages. Skip pages with delalloc
+	 * or unwritten buffers and warn if the page is not dirty. Otherwise
+	 * try to release the buffers.
 	 */
-	if (PageDirty(page))
-		return 0;
-
 	xfs_count_page_state(page, &delalloc, &unwritten);
 
-	if (WARN_ON_ONCE(delalloc))
+	if (delalloc) {
+		WARN_ON_ONCE(!PageDirty(page));
 		return 0;
-	if (WARN_ON_ONCE(unwritten))
+	}
+	if (unwritten) {
+		WARN_ON_ONCE(!PageDirty(page));
 		return 0;
+	}
 
 	return try_to_free_buffers(page);
 }
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c39ac14ff540..b1469f0a91a6 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3317,12 +3317,8 @@ xfs_log_force(
 	xfs_mount_t	*mp,
 	uint		flags)
 {
-	int	error;
-
 	trace_xfs_log_force(mp, 0, _RET_IP_);
-	error = _xfs_log_force(mp, flags, NULL);
-	if (error)
-		xfs_warn(mp, "%s: error %d returned.", __func__, error);
+	_xfs_log_force(mp, flags, NULL);
 }
 
 /*
@@ -3466,12 +3462,8 @@ xfs_log_force_lsn(
 	xfs_lsn_t	lsn,
 	uint		flags)
 {
-	int	error;
-
 	trace_xfs_log_force(mp, lsn, _RET_IP_);
-	error = _xfs_log_force_lsn(mp, lsn, flags, NULL);
-	if (error)
-		xfs_warn(mp, "%s: error %d returned.", __func__, error);
+	_xfs_log_force_lsn(mp, lsn, flags, NULL);
 }
 
 /*