Merge tag 'v4.10-rc6' into devel

Linux 4.10-rc6

Resolved conflicts in:
	drivers/pinctrl/pinctrl-amd.c
	drivers/pinctrl/samsung/pinctrl-exynos.c

80 files changed, 761 insertions, 416 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index c2a377cdda2b..83eab52fb3f6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select FS_IOMAP
 	help
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,
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/block_dev.c b/fs/block_dev.c
index 6254cee8f8f3..3c47614a4b32 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -328,9 +328,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = bdev_file_inode(file);
 	struct block_device *bdev = I_BDEV(inode);
+	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
-	bool is_read = (iov_iter_rw(iter) == READ);
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
 	int ret;
@@ -343,7 +344,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	bio_get(bio); /* extra ref for the completion handler */
 
 	dio = container_of(bio, struct blkdev_dio, bio);
-	dio->is_sync = is_sync_kiocb(iocb);
+	dio->is_sync = is_sync = is_sync_kiocb(iocb);
 	if (dio->is_sync)
 		dio->waiter = current;
 	else
@@ -353,6 +354,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	dio->multi_bio = false;
 	dio->should_dirty = is_read && (iter->type == ITER_IOVEC);
 
+	blk_start_plug(&plug);
 	for (;;) {
 		bio->bi_bdev = bdev;
 		bio->bi_iter.bi_sector = pos >> 9;
@@ -394,8 +396,9 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 		submit_bio(bio);
 		bio = bio_alloc(GFP_KERNEL, nr_pages);
 	}
+	blk_finish_plug(&plug);
 
-	if (!dio->is_sync)
+	if (!is_sync)
 		return -EIOCBQUEUED;
 
 	for (;;) {
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..1e861a063721 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3835,10 +3835,7 @@ cache_acl:
 		break;
 	case S_IFDIR:
 		inode->i_fop = &btrfs_dir_file_operations;
-		if (root == fs_info->tree_root)
-			inode->i_op = &btrfs_dir_ro_inode_operations;
-		else
-			inode->i_op = &btrfs_dir_inode_operations;
+		inode->i_op = &btrfs_dir_inode_operations;
 		break;
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
@@ -4505,8 +4502,19 @@ search_again:
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
@@ -5710,6 +5718,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 
 	inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
 	inode->i_op = &btrfs_dir_ro_inode_operations;
+	inode->i_opflags &= ~IOP_XATTR;
 	inode->i_fop = &simple_dir_operations;
 	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
 	inode->i_mtime = current_time(inode);
@@ -7059,7 +7068,7 @@ 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) {
@@ -7215,7 +7224,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	struct extent_map *em = NULL;
 	int ret;
 
-	down_read(&BTRFS_I(inode)->dio_sem);
 	if (type != BTRFS_ORDERED_NOCOW) {
 		em = create_pinned_em(inode, start, len, orig_start,
 				      block_start, block_len, orig_block_len,
@@ -7234,7 +7242,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 		em = ERR_PTR(ret);
 	}
  out:
-	up_read(&BTRFS_I(inode)->dio_sem);
 
 	return em;
 }
@@ -7623,11 +7630,18 @@ 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);
 	}
 }
@@ -8685,6 +8699,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		dio_data.unsubmitted_oe_range_start = (u64)offset;
 		dio_data.unsubmitted_oe_range_end = (u64)offset;
 		current->journal_info = &dio_data;
+		down_read(&BTRFS_I(inode)->dio_sem);
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_end(inode);
@@ -8697,6 +8712,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 				   iter, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
+		up_read(&BTRFS_I(inode)->dio_sem);
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
@@ -9205,6 +9221,7 @@ static int btrfs_truncate(struct inode *inode)
 			break;
 		}
 
+		btrfs_block_rsv_release(fs_info, rsv, -1);
 		ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
 					      rsv, min_size, 0);
 		BUG_ON(ret);	/* shouldn't happen */
@@ -10572,8 +10589,6 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 static const struct inode_operations btrfs_dir_ro_inode_operations = {
 	.lookup		= btrfs_lookup,
 	.permission	= btrfs_permission,
-	.get_acl	= btrfs_get_acl,
-	.set_acl	= btrfs_set_acl,
 	.update_time	= btrfs_update_time,
 };
 
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/buffer.c b/fs/buffer.c
index d21771fcf7d3..0e87401cf335 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1660,7 +1660,7 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len)
 			head = page_buffers(page);
 			bh = head;
 			do {
-				if (!buffer_mapped(bh))
+				if (!buffer_mapped(bh) || (bh->b_blocknr < block))
 					goto next;
 				if (bh->b_blocknr >= block + len)
 					break;
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/caps.c b/fs/ceph/caps.c
index baea866a6751..94fd76d04683 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2591,8 +2591,13 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
 			add_wait_queue(&ci->i_cap_wq, &wait);
 
 			while (!try_get_cap_refs(ci, need, want, endoff,
-						 true, &_got, &err))
+						 true, &_got, &err)) {
+				if (signal_pending(current)) {
+					ret = -ERESTARTSYS;
+					break;
+				}
 				wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+			}
 
 			remove_wait_queue(&ci->i_cap_wq, &wait);
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d7a93696663b..8ab1fdf0bd49 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1230,7 +1230,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 		struct ceph_mds_client *mdsc =
 			ceph_sb_to_client(dir->i_sb)->mdsc;
 		struct ceph_mds_request *req;
-		int op, mask, err;
+		int op, err;
+		u32 mask;
 
 		if (flags & LOOKUP_RCU)
 			return -ECHILD;
@@ -1245,7 +1246,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
 			if (ceph_security_xattr_wanted(dir))
 				mask |= CEPH_CAP_XATTR_SHARED;
-			req->r_args.getattr.mask = mask;
+			req->r_args.getattr.mask = cpu_to_le32(mask);
 
 			err = ceph_mdsc_do_request(mdsc, NULL, req);
 			switch (err) {
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 398e5328b309..5e659d054b40 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -305,7 +305,8 @@ static int frag_tree_split_cmp(const void *l, const void *r)
 {
 	struct ceph_frag_tree_split *ls = (struct ceph_frag_tree_split*)l;
 	struct ceph_frag_tree_split *rs = (struct ceph_frag_tree_split*)r;
-	return ceph_frag_compare(ls->frag, rs->frag);
+	return ceph_frag_compare(le32_to_cpu(ls->frag),
+				 le32_to_cpu(rs->frag));
 }
 
 static bool is_frag_child(u32 f, struct ceph_inode_frag *frag)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 4f49253387a0..c9d2e553a6c4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -288,12 +288,13 @@ static int parse_reply_info_extra(void **p, void *end,
 				  struct ceph_mds_reply_info_parsed *info,
 				  u64 features)
 {
-	if (info->head->op == CEPH_MDS_OP_GETFILELOCK)
+	u32 op = le32_to_cpu(info->head->op);
+
+	if (op == CEPH_MDS_OP_GETFILELOCK)
 		return parse_reply_info_filelock(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_READDIR ||
-		 info->head->op == CEPH_MDS_OP_LSSNAP)
+	else if (op == CEPH_MDS_OP_READDIR || op == CEPH_MDS_OP_LSSNAP)
 		return parse_reply_info_dir(p, end, info, features);
-	else if (info->head->op == CEPH_MDS_OP_CREATE)
+	else if (op == CEPH_MDS_OP_CREATE)
 		return parse_reply_info_create(p, end, info, features);
 	else
 		return -EIO;
@@ -2106,6 +2107,11 @@ 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/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 6eeea1dcba41..95cd4c3b06c3 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -248,7 +248,8 @@ retry:
 		goto out;
 
 	if (fscrypt_dummy_context_enabled(inode)) {
-		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		memset(raw_key, 0x42, keysize/2);
+		memset(raw_key+keysize/2, 0x24, keysize - (keysize/2));
 		goto got_key;
 	}
 
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 6ed7c2eebeec..d6cd7ea4851d 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -179,6 +179,11 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 		BUG_ON(1);
 	}
 
+	/* No restrictions on file types which are never encrypted */
+	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+	    !S_ISLNK(child->i_mode))
+		return 1;
+
 	/* no restrictions if the parent directory is not encrypted */
 	if (!parent->i_sb->s_cop->is_encrypted(parent))
 		return 1;
diff --git a/fs/dax.c b/fs/dax.c
index 5c74f60d0a50..3af2da5e64ce 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -691,8 +691,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 				      pgoff_t index, unsigned long pfn)
 {
 	struct vm_area_struct *vma;
-	pte_t *ptep;
-	pte_t pte;
+	pte_t pte, *ptep = NULL;
+	pmd_t *pmdp = NULL;
 	spinlock_t *ptl;
 	bool changed;
 
@@ -707,21 +707,42 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
 
 		address = pgoff_address(index, vma);
 		changed = false;
-		if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
+		if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
 			continue;
-		if (pfn != pte_pfn(*ptep))
-			goto unlock;
-		if (!pte_dirty(*ptep) && !pte_write(*ptep))
-			goto unlock;
 
-		flush_cache_page(vma, address, pfn);
-		pte = ptep_clear_flush(vma, address, ptep);
-		pte = pte_wrprotect(pte);
-		pte = pte_mkclean(pte);
-		set_pte_at(vma->vm_mm, address, ptep, pte);
-		changed = true;
-unlock:
-		pte_unmap_unlock(ptep, ptl);
+		if (pmdp) {
+#ifdef CONFIG_FS_DAX_PMD
+			pmd_t pmd;
+
+			if (pfn != pmd_pfn(*pmdp))
+				goto unlock_pmd;
+			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
+				goto unlock_pmd;
+
+			flush_cache_page(vma, address, pfn);
+			pmd = pmdp_huge_clear_flush(vma, address, pmdp);
+			pmd = pmd_wrprotect(pmd);
+			pmd = pmd_mkclean(pmd);
+			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+			changed = true;
+unlock_pmd:
+			spin_unlock(ptl);
+#endif
+		} else {
+			if (pfn != pte_pfn(*ptep))
+				goto unlock_pte;
+			if (!pte_dirty(*ptep) && !pte_write(*ptep))
+				goto unlock_pte;
+
+			flush_cache_page(vma, address, pfn);
+			pte = ptep_clear_flush(vma, address, ptep);
+			pte = pte_wrprotect(pte);
+			pte = pte_mkclean(pte);
+			set_pte_at(vma->vm_mm, address, ptep, pte);
+			changed = true;
+unlock_pte:
+			pte_unmap_unlock(ptep, ptl);
+		}
 
 		if (changed)
 			mmu_notifier_invalidate_page(vma->vm_mm, address);
@@ -969,7 +990,6 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
-#ifdef CONFIG_FS_IOMAP
 static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
 {
 	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
@@ -1407,4 +1427,3 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
 #endif /* CONFIG_FS_DAX_PMD */
-#endif /* CONFIG_FS_IOMAP */
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/ext2/Kconfig b/fs/ext2/Kconfig
index 36bea5adcaba..c634874e12d9 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -1,6 +1,5 @@
 config EXT2_FS
 	tristate "Second extended fs support"
-	select FS_IOMAP if FS_DAX
 	help
 	  Ext2 is a standard Linux file system for hard disks.
 
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 7b90691e98c4..e38039fd96ff 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -37,7 +37,6 @@ config EXT4_FS
 	select CRC16
 	select CRYPTO
 	select CRYPTO_CRC32C
-	select FS_IOMAP if FS_DAX
 	help
 	  This is the next generation of the ext3 filesystem.
 
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/fuse/dev.c b/fs/fuse/dev.c
index 70ea57c7b6bb..4e06a27ed7f8 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2025,7 +2025,6 @@ static void end_requests(struct fuse_conn *fc, struct list_head *head)
 		struct fuse_req *req;
 		req = list_entry(head->next, struct fuse_req, list);
 		req->out.h.error = -ECONNABORTED;
-		clear_bit(FR_PENDING, &req->flags);
 		clear_bit(FR_SENT, &req->flags);
 		list_del_init(&req->list);
 		request_end(fc, req);
@@ -2103,6 +2102,8 @@ void fuse_abort_conn(struct fuse_conn *fc)
 		spin_lock(&fiq->waitq.lock);
 		fiq->connected = 0;
 		list_splice_init(&fiq->pending, &to_end2);
+		list_for_each_entry(req, &to_end2, list)
+			clear_bit(FR_PENDING, &req->flags);
 		while (forget_pending(fiq))
 			kfree(dequeue_forget(fiq, 1, NULL));
 		wake_up_all_locked(&fiq->waitq);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 1f7c732f32b0..811fd8929a18 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -68,7 +68,7 @@ static u64 time_to_jiffies(u64 sec, u32 nsec)
 	if (sec || nsec) {
 		struct timespec64 ts = {
 			sec,
-			max_t(u32, nsec, NSEC_PER_SEC - 1)
+			min_t(u32, nsec, NSEC_PER_SEC - 1)
 		};
 
 		return get_jiffies_64() + timespec64_to_jiffies(&ts);
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..0a0eaecf9676 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;
@@ -2697,7 +2700,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata,
 		sattr->ia_valid |= ATTR_MTIME;
 
 	/* Except MODE, it seems harmless of setting twice. */
-	if ((attrset[1] & FATTR4_WORD1_MODE))
+	if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
+		attrset[1] & FATTR4_WORD1_MODE)
 		sattr->ia_valid &= ~ATTR_MODE;
 
 	if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -4073,11 +4077,12 @@ 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 +4130,8 @@ 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 +4165,11 @@ 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 +4206,7 @@ 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 +4281,8 @@ 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 +6137,6 @@ 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 +6249,6 @@ 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__);
 }
@@ -8483,6 +8491,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		goto out;
 	}
 
+	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	err = nfs4_handle_exception(server, nfs4err, exception);
 	if (!status) {
 		if (exception->retry)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 1d152f4470cd..daeb94e3acd4 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1091,6 +1091,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 		case -NFS4ERR_BADXDR:
 		case -NFS4ERR_RESOURCE:
 		case -NFS4ERR_NOFILEHANDLE:
+		case -NFS4ERR_MOVED:
 			/* Non-seqid mutating errors */
 			return;
 	};
@@ -1729,7 +1730,6 @@ 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/nfs/pnfs.c b/fs/nfs/pnfs.c
index 59554f3adf29..dd042498ce7c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1200,10 +1200,10 @@ _pnfs_return_layout(struct inode *ino)
 
 	send = pnfs_prepare_layoutreturn(lo, &stateid, NULL);
 	spin_unlock(&ino->i_lock);
-	pnfs_free_lseg_list(&tmp_list);
 	if (send)
 		status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
 out_put_layout_hdr:
+	pnfs_free_lseg_list(&tmp_list);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
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/notify/mark.c b/fs/notify/mark.c
index d3fea0bd89e2..6043306e8e21 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -510,18 +510,6 @@ void fsnotify_detach_group_marks(struct fsnotify_group *group)
 	}
 }
 
-void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old)
-{
-	assert_spin_locked(&old->lock);
-	new->inode = old->inode;
-	new->mnt = old->mnt;
-	if (old->group)
-		fsnotify_get_group(old->group);
-	new->group = old->group;
-	new->mask = old->mask;
-	new->free_mark = old->free_mark;
-}
-
 /*
  * Nothing fancy, just initialize lists and locks and counters.
  */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 83d576f6a287..77d1632e905d 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3303,6 +3303,16 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	mlog(ML_BASTS, "lockres %s, level %d => %d\n", lockres->l_name,
 	     lockres->l_level, new_level);
 
+	/*
+	 * On DLM_LKF_VALBLK, fsdlm behaves differently with o2cb. It always
+	 * expects DLM_LKF_VALBLK being set if the LKB has LVB, so that
+	 * we can recover correctly from node failure. Otherwise, we may get
+	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
+	 */
+	if (!ocfs2_is_o2cb_active() &&
+	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
+		lvb = 1;
+
 	if (lvb)
 		dlm_flags |= DLM_LKF_VALBLK;
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 52c07346bea3..820359096c7a 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -48,6 +48,12 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
+inline int ocfs2_is_o2cb_active(void)
+{
+	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
+}
+EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
+
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index f2dce10fae54..e3036e1790e8 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,6 +298,9 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
+/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
+int ocfs2_is_o2cb_active(void);
+
 extern struct kset *ocfs2_kset;
 
 #endif  /* STACKGLUE_H */
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 9ad48d9202a9..023bb0b03352 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -154,29 +154,38 @@ out_err:
 static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
 			    struct dentry **ret)
 {
-	const char *s = d->name.name;
+	/* Counting down from the end, since the prefix can change */
+	size_t rem = d->name.len - 1;
 	struct dentry *dentry = NULL;
 	int err;
 
-	if (*s != '/')
+	if (d->name.name[0] != '/')
 		return ovl_lookup_single(base, d, d->name.name, d->name.len,
 					 0, "", ret);
 
-	while (*s++ == '/' && !IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+	while (!IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+		const char *s = d->name.name + d->name.len - rem;
 		const char *next = strchrnul(s, '/');
-		size_t slen = strlen(s);
+		size_t thislen = next - s;
+		bool end = !next[0];
 
-		if (WARN_ON(slen > d->name.len) ||
-		    WARN_ON(strcmp(d->name.name + d->name.len - slen, s)))
+		/* Verify we did not go off the rails */
+		if (WARN_ON(s[-1] != '/'))
 			return -EIO;
 
-		err = ovl_lookup_single(base, d, s, next - s,
-					d->name.len - slen, next, &base);
+		err = ovl_lookup_single(base, d, s, thislen,
+					d->name.len - rem, next, &base);
 		dput(dentry);
 		if (err)
 			return err;
 		dentry = base;
-		s = next;
+		if (end)
+			break;
+
+		rem -= thislen + 1;
+
+		if (WARN_ON(rem >= d->name.len))
+			return -EIO;
 	}
 	*ret = dentry;
 	return 0;
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/base.c b/fs/proc/base.c
index 8e7e61b28f31..87c9a9aacda3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3179,6 +3179,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
 		char name[PROC_NUMBUF];
 		int len;
+
+		cond_resched();
 		if (!has_pid_permissions(ns, iter.task, 2))
 			continue;
 
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/romfs/super.c b/fs/romfs/super.c
index d0f8a38dfafa..0186fe6d39f3 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/major.h>
 #include "internal.h"
 
 static struct kmem_cache *romfs_inode_cachep;
@@ -416,7 +417,22 @@ static void romfs_destroy_inode(struct inode *inode)
 static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	u64 id = 0;
+
+	/* When calling huge_encode_dev(),
+	 * use sb->s_bdev->bd_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK defined
+	 * use sb->s_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD defined
+	 * leave id as 0 when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD undefined
+	 */
+	if (sb->s_bdev)
+		id = huge_encode_dev(sb->s_bdev->bd_dev);
+	else if (sb->s_dev)
+		id = huge_encode_dev(sb->s_dev);
 
 	buf->f_type = ROMFS_MAGIC;
 	buf->f_namelen = ROMFS_MAXFN;
@@ -489,6 +505,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags |= MS_RDONLY | MS_NOATIME;
 	sb->s_op = &romfs_super_ops;
 
+#ifdef CONFIG_ROMFS_ON_MTD
+	/* Use same dev ID from the underlying mtdblock device */
+	if (sb->s_mtd)
+		sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
 	/* read the image superblock and check it */
 	rsb = kmalloc(512, GFP_KERNEL);
 	if (!rsb)
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index 0a908ae7af13..b0d0623c83ed 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -53,7 +53,7 @@ config UBIFS_ATIME_SUPPORT
 
 config UBIFS_FS_ENCRYPTION
 	bool "UBIFS Encryption"
-	depends on UBIFS_FS
+	depends on UBIFS_FS && BLOCK
 	select FS_ENCRYPTION
 	default n
 	help
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 1c5331ac9614..528369f3e472 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -390,16 +390,6 @@ static int do_tmpfile(struct inode *dir, struct dentry *dentry,
 	dbg_gen("dent '%pd', mode %#hx in dir ino %lu",
 		dentry, mode, dir->i_ino);
 
-	if (ubifs_crypt_is_encrypted(dir)) {
-		err = fscrypt_get_encryption_info(dir);
-		if (err)
-			return err;
-
-		if (!fscrypt_has_encryption_key(dir)) {
-			return -EPERM;
-		}
-	}
-
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
 	if (err)
 		return err;
@@ -741,17 +731,9 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 	ubifs_assert(inode_is_locked(dir));
 	ubifs_assert(inode_is_locked(inode));
 
-	if (ubifs_crypt_is_encrypted(dir)) {
-		if (!fscrypt_has_permitted_context(dir, inode))
-			return -EPERM;
-
-		err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return err;
-
-		if (!fscrypt_has_encryption_key(inode))
-			return -EPERM;
-	}
+	if (ubifs_crypt_is_encrypted(dir) &&
+	    !fscrypt_has_permitted_context(dir, inode))
+		return -EPERM;
 
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
 	if (err)
@@ -1000,17 +982,6 @@ static int ubifs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		return err;
 
-	if (ubifs_crypt_is_encrypted(dir)) {
-		err = fscrypt_get_encryption_info(dir);
-		if (err)
-			goto out_budg;
-
-		if (!fscrypt_has_encryption_key(dir)) {
-			err = -EPERM;
-			goto out_budg;
-		}
-	}
-
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
 	if (err)
 		goto out_budg;
@@ -1096,17 +1067,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 		return err;
 	}
 
-	if (ubifs_crypt_is_encrypted(dir)) {
-		err = fscrypt_get_encryption_info(dir);
-		if (err)
-			goto out_budg;
-
-		if (!fscrypt_has_encryption_key(dir)) {
-			err = -EPERM;
-			goto out_budg;
-		}
-	}
-
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
 	if (err)
 		goto out_budg;
@@ -1231,18 +1191,6 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry,
 			goto out_inode;
 		}
 
-		err = fscrypt_get_encryption_info(inode);
-		if (err) {
-			kfree(sd);
-			goto out_inode;
-		}
-
-		if (!fscrypt_has_encryption_key(inode)) {
-			kfree(sd);
-			err = -EPERM;
-			goto out_inode;
-		}
-
 		ostr.name = sd->encrypted_path;
 		ostr.len = disk_link.len;
 
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 78d713644df3..da519ba205f6 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -217,6 +217,9 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_SETFLAGS:
 		cmd = FS_IOC_SETFLAGS;
 		break;
+	case FS_IOC_SET_ENCRYPTION_POLICY:
+	case FS_IOC_GET_ENCRYPTION_POLICY:
+		break;
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index a459211a1c21..294519b98874 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -744,6 +744,7 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
 
 	} else {
 		data->compr_size = 0;
+		out_len = compr_len;
 	}
 
 	dlen = UBIFS_DATA_NODE_SZ + out_len;
@@ -1319,6 +1320,7 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in
 	dn->compr_type = cpu_to_le16(compr_type);
 	dn->size = cpu_to_le32(*new_len);
 	*new_len = UBIFS_DATA_NODE_SZ + out_len;
+	err = 0;
 out:
 	kfree(buf);
 	return err;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 74ae2de949df..709aa098dd46 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -34,6 +34,11 @@
 #include <linux/slab.h>
 #include "ubifs.h"
 
+static int try_read_node(const struct ubifs_info *c, void *buf, int type,
+			 int len, int lnum, int offs);
+static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key,
+			      struct ubifs_zbranch *zbr, void *node);
+
 /*
  * Returned codes of 'matches_name()' and 'fallible_matches_name()' functions.
  * @NAME_LESS: name corresponding to the first argument is less than second
@@ -402,7 +407,19 @@ static int tnc_read_hashed_node(struct ubifs_info *c, struct ubifs_zbranch *zbr,
 		return 0;
 	}
 
-	err = ubifs_tnc_read_node(c, zbr, node);
+	if (c->replaying) {
+		err = fallible_read_node(c, &zbr->key, zbr, node);
+		/*
+		 * When the node was not found, return -ENOENT, 0 otherwise.
+		 * Negative return codes stay as-is.
+		 */
+		if (err == 0)
+			err = -ENOENT;
+		else if (err == 1)
+			err = 0;
+	} else {
+		err = ubifs_tnc_read_node(c, zbr, node);
+	}
 	if (err)
 		return err;
 
@@ -2857,7 +2874,11 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c,
 	if (fname_len(nm) > 0) {
 		if (err) {
 			/* Handle collisions */
-			err = resolve_collision(c, key, &znode, &n, nm);
+			if (c->replaying)
+				err = fallible_resolve_collision(c, key, &znode, &n,
+							 nm, 0);
+			else
+				err = resolve_collision(c, key, &znode, &n, nm);
 			dbg_tnc("rc returned %d, znode %p, n %d",
 				err, znode, n);
 			if (unlikely(err < 0))
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d96e2f30084b..43953e03c356 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -63,6 +63,7 @@ struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
 	wait_queue_t wq;
 	struct userfaultfd_ctx *ctx;
+	bool waken;
 };
 
 struct userfaultfd_wake_range {
@@ -86,6 +87,12 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
 	if (len && (start > uwq->msg.arg.pagefault.address ||
 		    start + len <= uwq->msg.arg.pagefault.address))
 		goto out;
+	WRITE_ONCE(uwq->waken, true);
+	/*
+	 * The implicit smp_mb__before_spinlock in try_to_wake_up()
+	 * renders uwq->waken visible to other CPUs before the task is
+	 * waken.
+	 */
 	ret = wake_up_state(wq->private, mode);
 	if (ret)
 		/*
@@ -264,6 +271,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	struct userfaultfd_wait_queue uwq;
 	int ret;
 	bool must_wait, return_to_userland;
+	long blocking_state;
 
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
@@ -334,10 +342,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	uwq.wq.private = current;
 	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
 	uwq.ctx = ctx;
+	uwq.waken = false;
 
 	return_to_userland =
 		(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
+	blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
+			 TASK_KILLABLE;
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/*
@@ -350,8 +361,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	 * following the spin_unlock to happen before the list_add in
 	 * __add_wait_queue.
 	 */
-	set_current_state(return_to_userland ? TASK_INTERRUPTIBLE :
-			  TASK_KILLABLE);
+	set_current_state(blocking_state);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
@@ -364,6 +374,29 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		wake_up_poll(&ctx->fd_wqh, POLLIN);
 		schedule();
 		ret |= VM_FAULT_MAJOR;
+
+		/*
+		 * False wakeups can orginate even from rwsem before
+		 * up_read() however userfaults will wait either for a
+		 * targeted wakeup on the specific uwq waitqueue from
+		 * wake_userfault() or for signals or for uffd
+		 * release.
+		 */
+		while (!READ_ONCE(uwq.waken)) {
+			/*
+			 * This needs the full smp_store_mb()
+			 * guarantee as the state write must be
+			 * visible to other CPUs before reading
+			 * uwq.waken from other CPUs.
+			 */
+			set_current_state(blocking_state);
+			if (READ_ONCE(uwq.waken) ||
+			    READ_ONCE(ctx->released) ||
+			    (return_to_userland ? signal_pending(current) :
+			     fatal_signal_pending(current)))
+				break;
+			schedule();
+		}
 	}
 
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index e5ebc3770460..33db69be4832 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -39,6 +39,7 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_ialloc_btree.h"
 
 /*
  * Per-AG Block Reservations
@@ -200,22 +201,30 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
+	xfs_extlen_t			reserved;
 
-	resv = xfs_perag_resv(pag, type);
 	if (used > ask)
 		ask = used;
-	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = ask - used;
-	mp->m_ag_max_usable -= ask;
+	reserved = ask - used;
 
-	trace_xfs_ag_resv_init(pag, type, ask);
-
-	error = xfs_mod_fdblocks(mp, -(int64_t)resv->ar_reserved, true);
-	if (error)
+	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
+		xfs_warn(mp,
+"Per-AG reservation for AG %u failed.  Filesystem may run out of space.",
+				pag->pag_agno);
+		return error;
+	}
 
-	return error;
+	mp->m_ag_max_usable -= ask;
+
+	resv = xfs_perag_resv(pag, type);
+	resv->ar_asked = ask;
+	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+
+	trace_xfs_ag_resv_init(pag, type, ask);
+	return 0;
 }
 
 /* Create a per-AG block reservation. */
@@ -223,6 +232,8 @@ int
 xfs_ag_resv_init(
 	struct xfs_perag		*pag)
 {
+	struct xfs_mount		*mp = pag->pag_mount;
+	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_extlen_t			ask;
 	xfs_extlen_t			used;
 	int				error = 0;
@@ -231,23 +242,45 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(pag->pag_mount,
-				pag->pag_agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
-				ask, used);
+		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
+
+		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+				ask, used);
+		if (error) {
+			/*
+			 * Because we didn't have per-AG reservations when the
+			 * finobt feature was added we might not be able to
+			 * reserve all needed blocks.  Warn and fall back to the
+			 * old and potentially buggy code in that case, but
+			 * ensure we do have the reservation for the refcountbt.
+			 */
+			ask = used = 0;
+
+			mp->m_inotbt_nores = true;
+
+			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+					&used);
+			if (error)
+				goto out;
+
+			error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+					ask, used);
+			if (error)
+				goto out;
+		}
 	}
 
 	/* Create the AGFL metadata reservation */
 	if (pag->pag_agfl_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(pag->pag_mount, pag->pag_agno,
-				&ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -256,6 +289,16 @@ xfs_ag_resv_init(
 			goto out;
 	}
 
+#ifdef DEBUG
+	/* need to read in the AGF for the ASSERT below to work */
+	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	if (error)
+		return error;
+
+	ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
+	       xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
+	       pag->pagf_freeblks + pag->pagf_flcount);
+#endif
 out:
 	return error;
 }
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_attr.c b/fs/xfs/libxfs/xfs_attr.c
index af1ecb19121e..6622d46ddec3 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -131,9 +131,6 @@ xfs_attr_get(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(ip))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, ip, name, flags);
 	if (error)
 		return error;
@@ -392,9 +389,6 @@ xfs_attr_remove(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(dp))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, dp, name, flags);
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 2760bc3b2536..bfc00de5c6f1 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3629,7 +3629,7 @@ xfs_bmap_btalloc(
 		align = xfs_get_cowextsz_hint(ap->ip);
 	else if (xfs_alloc_is_userdata(ap->datatype))
 		align = xfs_get_extsz_hint(ap->ip);
-	if (unlikely(align)) {
+	if (align) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
 						align, 0, ap->eof, 0, ap->conv,
 						&ap->offset, &ap->length);
@@ -3701,7 +3701,7 @@ xfs_bmap_btalloc(
 		args.minlen = ap->minlen;
 	}
 	/* apply extent size hints if obtained earlier */
-	if (unlikely(align)) {
+	if (align) {
 		args.prod = align;
 		if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod)))
 			args.mod = (xfs_extlen_t)(args.prod - args.mod);
@@ -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)
@@ -4517,8 +4514,6 @@ xfs_bmapi_write(
 	int			n;		/* current extent index */
 	xfs_fileoff_t		obno;		/* old block number (offset) */
 	int			whichfork;	/* data or attr fork */
-	char			inhole;		/* current location is hole in file */
-	char			wasdelay;	/* old extent was delayed */
 
 #ifdef DEBUG
 	xfs_fileoff_t		orig_bno;	/* original block number value */
@@ -4606,22 +4601,44 @@ xfs_bmapi_write(
 	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
-		inhole = eof || bma.got.br_startoff > bno;
-		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
+		bool			need_alloc = false, wasdelay = false;
 
-		/*
-		 * Make sure we only reflink into a hole.
-		 */
-		if (flags & XFS_BMAPI_REMAP)
-			ASSERT(inhole);
-		if (flags & XFS_BMAPI_COWFORK)
-			ASSERT(!inhole);
+		/* in hole or beyoned EOF? */
+		if (eof || bma.got.br_startoff > bno) {
+			if (flags & XFS_BMAPI_DELALLOC) {
+				/*
+				 * For the COW fork we can reasonably get a
+				 * request for converting an extent that races
+				 * with other threads already having converted
+				 * part of it, as there converting COW to
+				 * regular blocks is not protected using the
+				 * IOLOCK.
+				 */
+				ASSERT(flags & XFS_BMAPI_COWFORK);
+				if (!(flags & XFS_BMAPI_COWFORK)) {
+					error = -EIO;
+					goto error0;
+				}
+
+				if (eof || bno >= end)
+					break;
+			} else {
+				need_alloc = true;
+			}
+		} else {
+			/*
+			 * Make sure we only reflink into a hole.
+			 */
+			ASSERT(!(flags & XFS_BMAPI_REMAP));
+			if (isnullstartblock(bma.got.br_startblock))
+				wasdelay = true;
+		}
 
 		/*
 		 * First, deal with the hole before the allocated space
 		 * that we found, if any.
 		 */
-		if (inhole || wasdelay) {
+		if (need_alloc || wasdelay) {
 			bma.eof = eof;
 			bma.conv = !!(flags & XFS_BMAPI_CONVERT);
 			bma.wasdel = wasdelay;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index cecd094404cc..cdef87db5262 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -110,6 +110,9 @@ struct xfs_extent_free_item
 /* Map something in the CoW fork. */
 #define XFS_BMAPI_COWFORK	0x200
 
+/* Only convert delalloc space, don't allocate entirely new extents */
+#define XFS_BMAPI_DELALLOC	0x400
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -120,7 +123,8 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
 	{ XFS_BMAPI_REMAP,	"REMAP" }, \
-	{ XFS_BMAPI_COWFORK,	"COWFORK" }
+	{ XFS_BMAPI_COWFORK,	"COWFORK" }, \
+	{ XFS_BMAPI_DELALLOC,	"DELALLOC" }
 
 
 static inline int xfs_bmapi_aflag(int w)
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/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index c58d72c220f5..2f389d366e93 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -36,21 +36,29 @@
 struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
 
 /*
- * @mode, if set, indicates that the type field needs to be set up.
- * This uses the transformation from file mode to DT_* as defined in linux/fs.h
- * for file type specification. This will be propagated into the directory
- * structure if appropriate for the given operation and filesystem config.
+ * Convert inode mode to directory entry filetype
  */
-const unsigned char xfs_mode_to_ftype[S_IFMT >> S_SHIFT] = {
-	[0]			= XFS_DIR3_FT_UNKNOWN,
-	[S_IFREG >> S_SHIFT]    = XFS_DIR3_FT_REG_FILE,
-	[S_IFDIR >> S_SHIFT]    = XFS_DIR3_FT_DIR,
-	[S_IFCHR >> S_SHIFT]    = XFS_DIR3_FT_CHRDEV,
-	[S_IFBLK >> S_SHIFT]    = XFS_DIR3_FT_BLKDEV,
-	[S_IFIFO >> S_SHIFT]    = XFS_DIR3_FT_FIFO,
-	[S_IFSOCK >> S_SHIFT]   = XFS_DIR3_FT_SOCK,
-	[S_IFLNK >> S_SHIFT]    = XFS_DIR3_FT_SYMLINK,
-};
+unsigned char xfs_mode_to_ftype(int mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+		return XFS_DIR3_FT_REG_FILE;
+	case S_IFDIR:
+		return XFS_DIR3_FT_DIR;
+	case S_IFCHR:
+		return XFS_DIR3_FT_CHRDEV;
+	case S_IFBLK:
+		return XFS_DIR3_FT_BLKDEV;
+	case S_IFIFO:
+		return XFS_DIR3_FT_FIFO;
+	case S_IFSOCK:
+		return XFS_DIR3_FT_SOCK;
+	case S_IFLNK:
+		return XFS_DIR3_FT_SYMLINK;
+	default:
+		return XFS_DIR3_FT_UNKNOWN;
+	}
+}
 
 /*
  * ASCII case-insensitive (ie. A-Z) support for directories that was
@@ -631,7 +639,8 @@ xfs_dir2_isblock(
 	if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
 		return rval;
 	rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
-	ASSERT(rval == 0 || args->dp->i_d.di_size == args->geo->blksize);
+	if (rval != 0 && args->dp->i_d.di_size != args->geo->blksize)
+		return -EFSCORRUPTED;
 	*vp = rval;
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 0197590fa7d7..d6e6d9d16f6c 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -18,6 +18,9 @@
 #ifndef __XFS_DIR2_H__
 #define __XFS_DIR2_H__
 
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+
 struct xfs_defer_ops;
 struct xfs_da_args;
 struct xfs_inode;
@@ -32,10 +35,9 @@ struct xfs_dir2_data_unused;
 extern struct xfs_name	xfs_name_dotdot;
 
 /*
- * directory filetype conversion tables.
+ * Convert inode mode to directory entry filetype
  */
-#define S_SHIFT 12
-extern const unsigned char xfs_mode_to_ftype[];
+extern unsigned char xfs_mode_to_ftype(int mode);
 
 /*
  * directory operations vector for encode/decode routines
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 0fd086d03d41..7c471881c9a6 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -82,11 +82,12 @@ xfs_finobt_set_root(
 }
 
 STATIC int
-xfs_inobt_alloc_block(
+__xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			*stat)
+	int			*stat,
+	enum xfs_ag_resv_type	resv)
 {
 	xfs_alloc_arg_t		args;		/* block allocation args */
 	int			error;		/* error return value */
@@ -103,6 +104,7 @@ xfs_inobt_alloc_block(
 	args.maxlen = 1;
 	args.prod = 1;
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
+	args.resv = resv;
 
 	error = xfs_alloc_vextent(&args);
 	if (error) {
@@ -123,6 +125,27 @@ xfs_inobt_alloc_block(
 }
 
 STATIC int
+xfs_inobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE);
+}
+
+STATIC int
+xfs_finobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat,
+			XFS_AG_RESV_METADATA);
+}
+
+STATIC int
 xfs_inobt_free_block(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
@@ -328,7 +351,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_finobt_set_root,
-	.alloc_block		= xfs_inobt_alloc_block,
+	.alloc_block		= xfs_finobt_alloc_block,
 	.free_block		= xfs_inobt_free_block,
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
@@ -480,3 +503,64 @@ xfs_inobt_rec_check_count(
 	return 0;
 }
 #endif	/* DEBUG */
+
+static xfs_extlen_t
+xfs_inobt_max_size(
+	struct xfs_mount	*mp)
+{
+	/* Bail out if we're uninitialized, which can happen in mkfs. */
+	if (mp->m_inobt_mxr[0] == 0)
+		return 0;
+
+	return xfs_btree_calc_size(mp, mp->m_inobt_mnr,
+		(uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
+				XFS_INODES_PER_CHUNK);
+}
+
+static int
+xfs_inobt_count_blocks(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_btnum_t		btnum,
+	xfs_extlen_t		*tree_blocks)
+{
+	struct xfs_buf		*agbp;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	if (error)
+		return error;
+
+	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	error = xfs_btree_count_blocks(cur, tree_blocks);
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_buf_relse(agbp);
+
+	return error;
+}
+
+/*
+ * Figure out how many blocks to reserve and how many are used by this btree.
+ */
+int
+xfs_finobt_calc_reserves(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_extlen_t		*ask,
+	xfs_extlen_t		*used)
+{
+	xfs_extlen_t		tree_len = 0;
+	int			error;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return 0;
+
+	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	if (error)
+		return error;
+
+	*ask += xfs_inobt_max_size(mp);
+	*used += tree_len;
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bd88453217ce..aa81e2e63f3f 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -72,4 +72,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
+		xfs_extlen_t *ask, xfs_extlen_t *used);
+
 #endif	/* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index dd483e2767f7..d93f9d918cfc 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -29,6 +29,7 @@
 #include "xfs_icache.h"
 #include "xfs_trans.h"
 #include "xfs_ialloc.h"
+#include "xfs_dir2.h"
 
 /*
  * Check that none of the inode's in the buffer have a next
@@ -386,6 +387,7 @@ xfs_dinode_verify(
 	xfs_ino_t		ino,
 	struct xfs_dinode	*dip)
 {
+	uint16_t		mode;
 	uint16_t		flags;
 	uint64_t		flags2;
 
@@ -396,8 +398,12 @@ xfs_dinode_verify(
 	if (be64_to_cpu(dip->di_size) & (1ULL << 63))
 		return false;
 
-	/* No zero-length symlinks. */
-	if (S_ISLNK(be16_to_cpu(dip->di_mode)) && dip->di_size == 0)
+	mode = be16_to_cpu(dip->di_mode);
+	if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
+		return false;
+
+	/* No zero-length symlinks/dirs. */
+	if ((S_ISLNK(mode) || S_ISDIR(mode)) && dip->di_size == 0)
 		return false;
 
 	/* only version 3 or greater inodes are extensively verified here */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 6fb2215f8ff7..50add5272807 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -409,13 +409,14 @@ xfs_refcountbt_calc_size(
  */
 xfs_extlen_t
 xfs_refcountbt_max_size(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agblocks)
 {
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (mp->m_refc_mxr[0] == 0)
 		return 0;
 
-	return xfs_refcountbt_calc_size(mp, mp->m_sb.sb_agblocks);
+	return xfs_refcountbt_calc_size(mp, agblocks);
 }
 
 /*
@@ -430,22 +431,24 @@ xfs_refcountbt_calc_reserves(
 {
 	struct xfs_buf		*agbp;
 	struct xfs_agf		*agf;
+	xfs_agblock_t		agblocks;
 	xfs_extlen_t		tree_len;
 	int			error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	*ask += xfs_refcountbt_max_size(mp);
 
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
+	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
 	xfs_buf_relse(agbp);
 
+	*ask += xfs_refcountbt_max_size(mp, agblocks);
 	*used += tree_len;
 
 	return error;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index 3be7768bd51a..9db008b955b7 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -66,7 +66,8 @@ extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
 
 extern xfs_extlen_t xfs_refcountbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
-extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
+		xfs_agblock_t agblocks);
 
 extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index de25771764ba..74e5a54bc428 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -550,13 +550,14 @@ xfs_rmapbt_calc_size(
  */
 xfs_extlen_t
 xfs_rmapbt_max_size(
-	struct xfs_mount	*mp)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agblocks)
 {
 	/* Bail out if we're uninitialized, which can happen in mkfs. */
 	if (mp->m_rmap_mxr[0] == 0)
 		return 0;
 
-	return xfs_rmapbt_calc_size(mp, mp->m_sb.sb_agblocks);
+	return xfs_rmapbt_calc_size(mp, agblocks);
 }
 
 /*
@@ -571,25 +572,24 @@ xfs_rmapbt_calc_reserves(
 {
 	struct xfs_buf		*agbp;
 	struct xfs_agf		*agf;
-	xfs_extlen_t		pool_len;
+	xfs_agblock_t		agblocks;
 	xfs_extlen_t		tree_len;
 	int			error;
 
 	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
 		return 0;
 
-	/* Reserve 1% of the AG or enough for 1 block per record. */
-	pool_len = max(mp->m_sb.sb_agblocks / 100, xfs_rmapbt_max_size(mp));
-	*ask += pool_len;
-
 	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
+	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_rmap_blocks);
 	xfs_buf_relse(agbp);
 
+	/* Reserve 1% of the AG or enough for 1 block per record. */
+	*ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
 	*used += tree_len;
 
 	return error;
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 2a9ac472fb15..19c08e933049 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -60,7 +60,8 @@ extern void xfs_rmapbt_compute_maxlevels(struct xfs_mount *mp);
 
 extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
-extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp);
+extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
+		xfs_agblock_t agblocks);
 
 extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 2580262e4ea0..584ec896a533 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -242,7 +242,7 @@ xfs_mount_validate_sb(
 	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
 	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
 	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
-	    sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG			||
+	    sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
 	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
 	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
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_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index b9abce524c33..c1417919ab0a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -528,7 +528,6 @@ xfs_getbmap(
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
 	xfs_mount_t		*mp;		/* file system mount point */
 	int			nex;		/* # of user extents can do */
-	int			nexleft;	/* # of user extents left */
 	int			subnex;		/* # of bmapi's can do */
 	int			nmap;		/* number of map entries */
 	struct getbmapx		*out;		/* output structure */
@@ -686,10 +685,8 @@ xfs_getbmap(
 		goto out_free_map;
 	}
 
-	nexleft = nex;
-
 	do {
-		nmap = (nexleft > subnex) ? subnex : nexleft;
+		nmap = (nex> subnex) ? subnex : nex;
 		error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
 				       XFS_BB_TO_FSB(mp, bmv->bmv_length),
 				       map, &nmap, bmapi_flags);
@@ -697,8 +694,8 @@ xfs_getbmap(
 			goto out_free_map;
 		ASSERT(nmap <= subnex);
 
-		for (i = 0; i < nmap && nexleft && bmv->bmv_length &&
-				cur_ext < bmv->bmv_count; i++) {
+		for (i = 0; i < nmap && bmv->bmv_length &&
+				cur_ext < bmv->bmv_count - 1; i++) {
 			out[cur_ext].bmv_oflags = 0;
 			if (map[i].br_state == XFS_EXT_UNWRITTEN)
 				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
@@ -760,16 +757,27 @@ xfs_getbmap(
 				continue;
 			}
 
+			/*
+			 * In order to report shared extents accurately,
+			 * we report each distinct shared/unshared part
+			 * of a single bmbt record using multiple bmap
+			 * extents.  To make that happen, we iterate the
+			 * same map array item multiple times, each
+			 * time trimming out the subextent that we just
+			 * reported.
+			 *
+			 * Because of this, we must check the out array
+			 * index (cur_ext) directly against bmv_count-1
+			 * to avoid overflows.
+			 */
 			if (inject_map.br_startblock != NULLFSBLOCK) {
 				map[i] = inject_map;
 				i--;
-			} else
-				nexleft--;
+			}
 			bmv->bmv_entries++;
 			cur_ext++;
 		}
-	} while (nmap && nexleft && bmv->bmv_length &&
-		 cur_ext < bmv->bmv_count);
+	} while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1);
 
  out_free_map:
 	kmem_free(map);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7f0a01f7b592..ac3b4db519df 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -422,6 +422,7 @@ retry:
 out_free_pages:
 	for (i = 0; i < bp->b_page_count; i++)
 		__free_page(bp->b_pages[i]);
+	bp->b_flags &= ~_XBF_PAGES;
 	return error;
 }
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 7a30b8f11db7..9d06cc30e875 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -710,6 +710,10 @@ xfs_dq_get_next_id(
 	/* Simple advance */
 	next_id = *id + 1;
 
+	/* If we'd wrap past the max ID, stop */
+	if (next_id < *id)
+		return -ENOENT;
+
 	/* If new ID is within the current chunk, advancing it sufficed */
 	if (next_id % mp->m_quotainfo->qi_dqperchunk) {
 		*id = next_id;
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 93d12fa2670d..242e8091296d 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -631,6 +631,20 @@ xfs_growfs_data_private(
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
+	/*
+	 * If we expanded the last AG, free the per-AG reservation
+	 * so we can reinitialize it with the new size.
+	 */
+	if (new) {
+		struct xfs_perag	*pag;
+
+		pag = xfs_perag_get(mp, agno);
+		error = xfs_ag_resv_free(pag);
+		xfs_perag_put(pag);
+		if (error)
+			goto out;
+	}
+
 	/* Reserve AG metadata blocks. */
 	error = xfs_fs_reserve_ag_blocks(mp);
 	if (error && error != -ENOSPC)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index ff4d6311c7f4..70ca4f608321 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1597,7 +1597,8 @@ xfs_inode_free_cowblocks(
 	 * If the mapping is dirty or under writeback we cannot touch the
 	 * CoW fork.  Leave it alone if we're in the midst of a directio.
 	 */
-	if (mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
+	if ((VFS_I(ip)->i_state & I_DIRTY_PAGES) ||
+	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_DIRTY) ||
 	    mapping_tagged(VFS_I(ip)->i_mapping, PAGECACHE_TAG_WRITEBACK) ||
 	    atomic_read(&VFS_I(ip)->i_dio_count))
 		return 0;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b9557795eb74..de32f0fe47c8 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1792,22 +1792,23 @@ xfs_inactive_ifree(
 	int			error;
 
 	/*
-	 * The ifree transaction might need to allocate blocks for record
-	 * insertion to the finobt. We don't want to fail here at ENOSPC, so
-	 * allow ifree to dip into the reserved block pool if necessary.
-	 *
-	 * Freeing large sets of inodes generally means freeing inode chunks,
-	 * directory and file data blocks, so this should be relatively safe.
-	 * Only under severe circumstances should it be possible to free enough
-	 * inodes to exhaust the reserve block pool via finobt expansion while
-	 * at the same time not creating free space in the filesystem.
+	 * We try to use a per-AG reservation for any block needed by the finobt
+	 * tree, but as the finobt feature predates the per-AG reservation
+	 * support a degraded file system might not have enough space for the
+	 * reservation at mount time.  In that case try to dip into the reserved
+	 * pool and pray.
 	 *
 	 * Send a warning if the reservation does happen to fail, as the inode
 	 * now remains allocated and sits on the unlinked list until the fs is
 	 * repaired.
 	 */
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
-			XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+	if (unlikely(mp->m_inotbt_nores)) {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
+				XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
+				&tp);
+	} else {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp);
+	}
 	if (error) {
 		if (error == -ENOSPC) {
 			xfs_warn_ratelimited(mp,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0d147428971e..1aa3abd67b36 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -681,7 +681,7 @@ xfs_iomap_write_allocate(
 	xfs_trans_t	*tp;
 	int		nimaps;
 	int		error = 0;
-	int		flags = 0;
+	int		flags = XFS_BMAPI_DELALLOC;
 	int		nres;
 
 	if (whichfork == XFS_COW_FORK)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 308bebb6dfd2..22c16155f1b4 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -98,12 +98,27 @@ xfs_init_security(
 static void
 xfs_dentry_to_name(
 	struct xfs_name	*namep,
+	struct dentry	*dentry)
+{
+	namep->name = dentry->d_name.name;
+	namep->len = dentry->d_name.len;
+	namep->type = XFS_DIR3_FT_UNKNOWN;
+}
+
+static int
+xfs_dentry_mode_to_name(
+	struct xfs_name	*namep,
 	struct dentry	*dentry,
 	int		mode)
 {
 	namep->name = dentry->d_name.name;
 	namep->len = dentry->d_name.len;
-	namep->type = xfs_mode_to_ftype[(mode & S_IFMT) >> S_SHIFT];
+	namep->type = xfs_mode_to_ftype(mode);
+
+	if (unlikely(namep->type == XFS_DIR3_FT_UNKNOWN))
+		return -EFSCORRUPTED;
+
+	return 0;
 }
 
 STATIC void
@@ -119,7 +134,7 @@ xfs_cleanup_inode(
 	 * xfs_init_security we must back out.
 	 * ENOSPC can hit here, among other things.
 	 */
-	xfs_dentry_to_name(&teardown, dentry, 0);
+	xfs_dentry_to_name(&teardown, dentry);
 
 	xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
 }
@@ -154,8 +169,12 @@ xfs_generic_create(
 	if (error)
 		return error;
 
+	/* Verify mode is valid also for tmpfile case */
+	error = xfs_dentry_mode_to_name(&name, dentry, mode);
+	if (unlikely(error))
+		goto out_free_acl;
+
 	if (!tmpfile) {
-		xfs_dentry_to_name(&name, dentry, mode);
 		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
 	} else {
 		error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
@@ -248,7 +267,7 @@ xfs_vn_lookup(
 	if (dentry->d_name.len >= MAXNAMELEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	xfs_dentry_to_name(&name, dentry, 0);
+	xfs_dentry_to_name(&name, dentry);
 	error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
 	if (unlikely(error)) {
 		if (unlikely(error != -ENOENT))
@@ -275,7 +294,7 @@ xfs_vn_ci_lookup(
 	if (dentry->d_name.len >= MAXNAMELEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	xfs_dentry_to_name(&xname, dentry, 0);
+	xfs_dentry_to_name(&xname, dentry);
 	error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name);
 	if (unlikely(error)) {
 		if (unlikely(error != -ENOENT))
@@ -310,7 +329,9 @@ xfs_vn_link(
 	struct xfs_name	name;
 	int		error;
 
-	xfs_dentry_to_name(&name, dentry, inode->i_mode);
+	error = xfs_dentry_mode_to_name(&name, dentry, inode->i_mode);
+	if (unlikely(error))
+		return error;
 
 	error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
 	if (unlikely(error))
@@ -329,7 +350,7 @@ xfs_vn_unlink(
 	struct xfs_name	name;
 	int		error;
 
-	xfs_dentry_to_name(&name, dentry, 0);
+	xfs_dentry_to_name(&name, dentry);
 
 	error = xfs_remove(XFS_I(dir), &name, XFS_I(d_inode(dentry)));
 	if (error)
@@ -359,7 +380,9 @@ xfs_vn_symlink(
 
 	mode = S_IFLNK |
 		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
-	xfs_dentry_to_name(&name, dentry, mode);
+	error = xfs_dentry_mode_to_name(&name, dentry, mode);
+	if (unlikely(error))
+		goto out;
 
 	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
 	if (unlikely(error))
@@ -395,6 +418,7 @@ xfs_vn_rename(
 {
 	struct inode	*new_inode = d_inode(ndentry);
 	int		omode = 0;
+	int		error;
 	struct xfs_name	oname;
 	struct xfs_name	nname;
 
@@ -405,8 +429,14 @@ xfs_vn_rename(
 	if (flags & RENAME_EXCHANGE)
 		omode = d_inode(ndentry)->i_mode;
 
-	xfs_dentry_to_name(&oname, odentry, omode);
-	xfs_dentry_to_name(&nname, ndentry, d_inode(odentry)->i_mode);
+	error = xfs_dentry_mode_to_name(&oname, odentry, omode);
+	if (omode && unlikely(error))
+		return error;
+
+	error = xfs_dentry_mode_to_name(&nname, ndentry,
+					d_inode(odentry)->i_mode);
+	if (unlikely(error))
+		return error;
 
 	return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)),
 			  XFS_I(ndir), &nname,
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index e467218c0098..7a989de224f4 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -331,11 +331,11 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
 }
 
 #define ASSERT_ALWAYS(expr)	\
-	(unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+	(likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
 
 #ifdef DEBUG
 #define ASSERT(expr)	\
-	(unlikely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+	(likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
 
 #ifndef STATIC
 # define STATIC noinline
@@ -346,7 +346,7 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
 #ifdef XFS_WARN
 
 #define ASSERT(expr)	\
-	(unlikely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__))
+	(likely(expr) ? (void)0 : asswarn(#expr, __FILE__, __LINE__))
 
 #ifndef STATIC
 # define STATIC static noinline
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);
 }
 
 /*
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 84f785218907..7f351f706b7a 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -140,6 +140,7 @@ typedef struct xfs_mount {
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
 	__uint64_t		m_flags;	/* global mount flags */
+	bool			m_inotbt_nores; /* no per-AG finobt resv. */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
 	int			m_ialloc_min_blks;/* min blocks in sparse inode
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 45e50ea90769..b669b123287b 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1177,7 +1177,8 @@ xfs_qm_dqusage_adjust(
 	 * the case in all other instances. It's OK that we do this because
 	 * quotacheck is done only at mount time.
 	 */
-	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
+	error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
+			 &ip);
 	if (error) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index fe86a668a57e..6e4c7446c3d4 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -526,13 +526,14 @@ xfs_cui_recover(
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
-		goto abort_error;
+		goto abort_defer;
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
+abort_defer:
 	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 276d3023d60f..de6195e38910 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -396,7 +396,7 @@ max_retries_show(
 	int		retries;
 	struct xfs_error_cfg *cfg = to_error_cfg(kobject);
 
-	if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER)
+	if (cfg->max_retries == XFS_ERR_RETRY_FOREVER)
 		retries = -1;
 	else
 		retries = cfg->max_retries;
@@ -422,7 +422,7 @@ max_retries_store(
 		return -EINVAL;
 
 	if (val == -1)
-		cfg->retry_timeout = XFS_ERR_RETRY_FOREVER;
+		cfg->max_retries = XFS_ERR_RETRY_FOREVER;
 	else
 		cfg->max_retries = val;
 	return count;