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

Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f9524
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e61 (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

22 files changed, 436 insertions, 185 deletions

diff --git a/fs/aio.c b/fs/aio.c
index a062d75109cb..6bcd3fb5265a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -68,9 +68,9 @@ struct aio_ring {
 #define AIO_RING_PAGES	8
 
 struct kioctx_table {
-	struct rcu_head	rcu;
-	unsigned	nr;
-	struct kioctx	*table[];
+	struct rcu_head		rcu;
+	unsigned		nr;
+	struct kioctx __rcu	*table[];
 };
 
 struct kioctx_cpu {
@@ -115,7 +115,8 @@ struct kioctx {
 	struct page		**ring_pages;
 	long			nr_pages;
 
-	struct work_struct	free_work;
+	struct rcu_head		free_rcu;
+	struct work_struct	free_work;	/* see free_ioctx() */
 
 	/*
 	 * signals when all in-flight requests are done
@@ -329,7 +330,7 @@ static int aio_ring_mremap(struct vm_area_struct *vma)
 	for (i = 0; i < table->nr; i++) {
 		struct kioctx *ctx;
 
-		ctx = table->table[i];
+		ctx = rcu_dereference(table->table[i]);
 		if (ctx && ctx->aio_ring_file == file) {
 			if (!atomic_read(&ctx->dead)) {
 				ctx->user_id = ctx->mmap_base = vma->vm_start;
@@ -588,6 +589,12 @@ static int kiocb_cancel(struct aio_kiocb *kiocb)
 	return cancel(&kiocb->common);
 }
 
+/*
+ * free_ioctx() should be RCU delayed to synchronize against the RCU
+ * protected lookup_ioctx() and also needs process context to call
+ * aio_free_ring(), so the double bouncing through kioctx->free_rcu and
+ * ->free_work.
+ */
 static void free_ioctx(struct work_struct *work)
 {
 	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
@@ -601,6 +608,14 @@ static void free_ioctx(struct work_struct *work)
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
+static void free_ioctx_rcufn(struct rcu_head *head)
+{
+	struct kioctx *ctx = container_of(head, struct kioctx, free_rcu);
+
+	INIT_WORK(&ctx->free_work, free_ioctx);
+	schedule_work(&ctx->free_work);
+}
+
 static void free_ioctx_reqs(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
@@ -609,8 +624,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 	if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
 		complete(&ctx->rq_wait->comp);
 
-	INIT_WORK(&ctx->free_work, free_ioctx);
-	schedule_work(&ctx->free_work);
+	/* Synchronize against RCU protected table->table[] dereferences */
+	call_rcu(&ctx->free_rcu, free_ioctx_rcufn);
 }
 
 /*
@@ -651,9 +666,9 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 	while (1) {
 		if (table)
 			for (i = 0; i < table->nr; i++)
-				if (!table->table[i]) {
+				if (!rcu_access_pointer(table->table[i])) {
 					ctx->id = i;
-					table->table[i] = ctx;
+					rcu_assign_pointer(table->table[i], ctx);
 					spin_unlock(&mm->ioctx_lock);
 
 					/* While kioctx setup is in progress,
@@ -834,11 +849,11 @@ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
 	}
 
 	table = rcu_dereference_raw(mm->ioctx_table);
-	WARN_ON(ctx != table->table[ctx->id]);
-	table->table[ctx->id] = NULL;
+	WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id]));
+	RCU_INIT_POINTER(table->table[ctx->id], NULL);
 	spin_unlock(&mm->ioctx_lock);
 
-	/* percpu_ref_kill() will do the necessary call_rcu() */
+	/* free_ioctx_reqs() will do the necessary RCU synchronization */
 	wake_up_all(&ctx->wait);
 
 	/*
@@ -880,7 +895,8 @@ void exit_aio(struct mm_struct *mm)
 
 	skipped = 0;
 	for (i = 0; i < table->nr; ++i) {
-		struct kioctx *ctx = table->table[i];
+		struct kioctx *ctx =
+			rcu_dereference_protected(table->table[i], true);
 
 		if (!ctx) {
 			skipped++;
@@ -1069,7 +1085,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
 	if (!table || id >= table->nr)
 		goto out;
 
-	ctx = table->table[id];
+	ctx = rcu_dereference(table->table[id]);
 	if (ctx && ctx->user_id == ctx_id) {
 		percpu_ref_get(&ctx->users);
 		ret = ctx;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index f94b2d8c744a..26484648d090 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1519,6 +1519,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
 		if (!node)
 			break;
 		bytenr = node->val;
+		shared.share_count = 0;
 		cond_resched();
 	}
 
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index dec0907dfb8a..fcfc20de2df3 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1370,6 +1370,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 		stripe_start = stripe->physical;
 		if (physical >= stripe_start &&
 		    physical < stripe_start + rbio->stripe_len &&
+		    stripe->dev->bdev &&
 		    bio->bi_disk == stripe->dev->bdev->bd_disk &&
 		    bio->bi_partno == stripe->dev->bdev->bd_partno) {
 			return i;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index d11c70bff5a9..a8bafed931f4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -423,7 +423,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->nodesize);
+	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->super_copy->nodesize);
 }
 
 BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -433,7 +433,8 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			fs_info->super_copy->sectorsize);
 }
 
 BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -443,7 +444,8 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", fs_info->sectorsize);
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			fs_info->super_copy->sectorsize);
 }
 
 BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9220f004001c..04f07144b45c 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1722,23 +1722,19 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 
 	super = fs_info->super_copy;
 
-	/* update latest btrfs_super_block::chunk_root refs */
 	root_item = &fs_info->chunk_root->root_item;
-	btrfs_set_super_chunk_root(super, root_item->bytenr);
-	btrfs_set_super_chunk_root_generation(super, root_item->generation);
-	btrfs_set_super_chunk_root_level(super, root_item->level);
+	super->chunk_root = root_item->bytenr;
+	super->chunk_root_generation = root_item->generation;
+	super->chunk_root_level = root_item->level;
 
-	/* update latest btrfs_super_block::root refs */
 	root_item = &fs_info->tree_root->root_item;
-	btrfs_set_super_root(super, root_item->bytenr);
-	btrfs_set_super_generation(super, root_item->generation);
-	btrfs_set_super_root_level(super, root_item->level);
-
+	super->root = root_item->bytenr;
+	super->generation = root_item->generation;
+	super->root_level = root_item->level;
 	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		btrfs_set_super_cache_generation(super, root_item->generation);
+		super->cache_generation = root_item->generation;
 	if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
-		btrfs_set_super_uuid_tree_generation(super,
-						     root_item->generation);
+		super->uuid_tree_generation = root_item->generation;
 }
 
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
diff --git a/fs/dcache.c b/fs/dcache.c
index 7c38f39958bc..8945e6cabd93 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -647,11 +647,16 @@ again:
 		spin_unlock(&parent->d_lock);
 		goto again;
 	}
-	rcu_read_unlock();
-	if (parent != dentry)
+	if (parent != dentry) {
 		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	else
+		if (unlikely(dentry->d_lockref.count < 0)) {
+			spin_unlock(&parent->d_lock);
+			parent = NULL;
+		}
+	} else {
 		parent = NULL;
+	}
+	rcu_read_unlock();
 	return parent;
 }
 
@@ -2474,7 +2479,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 
 retry:
 	rcu_read_lock();
-	seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1;
+	seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
 	r_seq = read_seqbegin(&rename_lock);
 	dentry = __d_lookup_rcu(parent, name, &d_seq);
 	if (unlikely(dentry)) {
@@ -2495,8 +2500,14 @@ retry:
 		rcu_read_unlock();
 		goto retry;
 	}
+
+	if (unlikely(seq & 1)) {
+		rcu_read_unlock();
+		goto retry;
+	}
+
 	hlist_bl_lock(b);
-	if (unlikely(parent->d_inode->i_dir_seq != seq)) {
+	if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) {
 		hlist_bl_unlock(b);
 		rcu_read_unlock();
 		goto retry;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 86d6a4435c87..51f940e76c5e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -807,9 +807,6 @@ do_alloc:
 			iomap->length = hole_size(inode, lblock, &mp);
 		else
 			iomap->length = size - pos;
-	} else {
-		if (height <= ip->i_height)
-			iomap->length = hole_size(inode, lblock, &mp);
 	}
 	goto out_release;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 8fe1b0aa2896..b9a254dcc0e7 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -108,6 +108,16 @@ static void huge_pagevec_release(struct pagevec *pvec)
 	pagevec_reinit(pvec);
 }
 
+/*
+ * Mask used when checking the page offset value passed in via system
+ * calls.  This value will be converted to a loff_t which is signed.
+ * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the
+ * value.  The extra bit (- 1 in the shift value) is to take the sign
+ * bit into account.
+ */
+#define PGOFF_LOFFT_MAX \
+	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file_inode(file);
@@ -127,12 +137,13 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_ops = &hugetlb_vm_ops;
 
 	/*
-	 * Offset passed to mmap (before page shift) could have been
-	 * negative when represented as a (l)off_t.
+	 * page based offset in vm_pgoff could be sufficiently large to
+	 * overflow a (l)off_t when converted to byte offset.
 	 */
-	if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+	if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
 		return -EINVAL;
 
+	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
diff --git a/fs/namei.c b/fs/namei.c
index 921ae32dbc80..cafa365eeb70 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -559,9 +559,10 @@ static int __nd_alloc_stack(struct nameidata *nd)
 static bool path_connected(const struct path *path)
 {
 	struct vfsmount *mnt = path->mnt;
+	struct super_block *sb = mnt->mnt_sb;
 
-	/* Only bind mounts can have disconnected paths */
-	if (mnt->mnt_root == mnt->mnt_sb->s_root)
+	/* Bind mounts and multi-root filesystems can have disconnected paths */
+	if (!(sb->s_iflags & SB_I_MULTIROOT) && (mnt->mnt_root == sb->s_root))
 		return true;
 
 	return is_subdir(path->dentry, mnt->mnt_root);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 8c10b0562e75..621c517b325c 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -86,10 +86,10 @@ struct nfs_direct_req {
 	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
 	int			mirror_count;
 
+	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
 				bytes_left,	/* bytes left to be sent */
-				io_start,	/* start of IO */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index c13e826614b5..ee723aa153a3 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -292,8 +292,11 @@ pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
 void
 pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
 {
-	struct inode *inode = lo->plh_inode;
+	struct inode *inode;
 
+	if (!lo)
+		return;
+	inode = lo->plh_inode;
 	pnfs_layoutreturn_before_put_layout_hdr(lo);
 
 	if (refcount_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
@@ -1241,10 +1244,12 @@ retry:
 	spin_lock(&ino->i_lock);
 	lo = nfsi->layout;
 	if (!lo || !pnfs_layout_is_valid(lo) ||
-	    test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags))
+	    test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
+		lo = NULL;
 		goto out_noroc;
+	}
+	pnfs_get_layout_hdr(lo);
 	if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) {
-		pnfs_get_layout_hdr(lo);
 		spin_unlock(&ino->i_lock);
 		wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN,
 				TASK_UNINTERRUPTIBLE);
@@ -1312,10 +1317,12 @@ out_noroc:
 		struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
 		if (ld->prepare_layoutreturn)
 			ld->prepare_layoutreturn(args);
+		pnfs_put_layout_hdr(lo);
 		return true;
 	}
 	if (layoutreturn)
 		pnfs_send_layoutreturn(lo, &stateid, iomode, true);
+	pnfs_put_layout_hdr(lo);
 	return false;
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 29bacdc56f6a..5e470e233c83 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2631,6 +2631,8 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		/* initial superblock/root creation */
 		mount_info->fill_super(s, mount_info);
 		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
+		if (!(server->flags & NFS_MOUNT_UNSHARED))
+			s->s_iflags |= SB_I_MULTIROOT;
 	}
 
 	mntroot = nfs_get_root(s, mount_info->mntfh, dev_name);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7428a669d7a7..e7d8ceae8f26 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1876,40 +1876,43 @@ int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 	return status;
 }
 
-int nfs_commit_inode(struct inode *inode, int how)
+static int __nfs_commit_inode(struct inode *inode, int how,
+		struct writeback_control *wbc)
 {
 	LIST_HEAD(head);
 	struct nfs_commit_info cinfo;
 	int may_wait = how & FLUSH_SYNC;
-	int error = 0;
-	int res;
+	int ret, nscan;
 
 	nfs_init_cinfo_from_inode(&cinfo, inode);
 	nfs_commit_begin(cinfo.mds);
-	res = nfs_scan_commit(inode, &head, &cinfo);
-	if (res)
-		error = nfs_generic_commit_list(inode, &head, how, &cinfo);
+	for (;;) {
+		ret = nscan = nfs_scan_commit(inode, &head, &cinfo);
+		if (ret <= 0)
+			break;
+		ret = nfs_generic_commit_list(inode, &head, how, &cinfo);
+		if (ret < 0)
+			break;
+		ret = 0;
+		if (wbc && wbc->sync_mode == WB_SYNC_NONE) {
+			if (nscan < wbc->nr_to_write)
+				wbc->nr_to_write -= nscan;
+			else
+				wbc->nr_to_write = 0;
+		}
+		if (nscan < INT_MAX)
+			break;
+		cond_resched();
+	}
 	nfs_commit_end(cinfo.mds);
-	if (res == 0)
-		return res;
-	if (error < 0)
-		goto out_error;
-	if (!may_wait)
-		goto out_mark_dirty;
-	error = wait_on_commit(cinfo.mds);
-	if (error < 0)
-		return error;
-	return res;
-out_error:
-	res = error;
-	/* Note: If we exit without ensuring that the commit is complete,
-	 * we must mark the inode as dirty. Otherwise, future calls to
-	 * sync_inode() with the WB_SYNC_ALL flag set will fail to ensure
-	 * that the data is on the disk.
-	 */
-out_mark_dirty:
-	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-	return res;
+	if (ret || !may_wait)
+		return ret;
+	return wait_on_commit(cinfo.mds);
+}
+
+int nfs_commit_inode(struct inode *inode, int how)
+{
+	return __nfs_commit_inode(inode, how, NULL);
 }
 EXPORT_SYMBOL_GPL(nfs_commit_inode);
 
@@ -1919,11 +1922,11 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	int flags = FLUSH_SYNC;
 	int ret = 0;
 
-	/* no commits means nothing needs to be done */
-	if (!atomic_long_read(&nfsi->commit_info.ncommit))
-		return ret;
-
 	if (wbc->sync_mode == WB_SYNC_NONE) {
+		/* no commits means nothing needs to be done */
+		if (!atomic_long_read(&nfsi->commit_info.ncommit))
+			goto check_requests_outstanding;
+
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
 		 */
@@ -1934,16 +1937,16 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		flags = 0;
 	}
 
-	ret = nfs_commit_inode(inode, flags);
-	if (ret >= 0) {
-		if (wbc->sync_mode == WB_SYNC_NONE) {
-			if (ret < wbc->nr_to_write)
-				wbc->nr_to_write -= ret;
-			else
-				wbc->nr_to_write = 0;
-		}
-		return 0;
-	}
+	ret = __nfs_commit_inode(inode, flags, wbc);
+	if (!ret) {
+		if (flags & FLUSH_SYNC)
+			return 0;
+	} else if (atomic_long_read(&nfsi->commit_info.ncommit))
+		goto out_mark_dirty;
+
+check_requests_outstanding:
+	if (!atomic_read(&nfsi->commit_info.rpcs_out))
+		return ret;
 out_mark_dirty:
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 	return ret;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 150521c9671b..61b770e39809 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -268,6 +268,35 @@ free_blocked_lock(struct nfsd4_blocked_lock *nbl)
 	kfree(nbl);
 }
 
+static void
+remove_blocked_locks(struct nfs4_lockowner *lo)
+{
+	struct nfs4_client *clp = lo->lo_owner.so_client;
+	struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+	struct nfsd4_blocked_lock *nbl;
+	LIST_HEAD(reaplist);
+
+	/* Dequeue all blocked locks */
+	spin_lock(&nn->blocked_locks_lock);
+	while (!list_empty(&lo->lo_blocked)) {
+		nbl = list_first_entry(&lo->lo_blocked,
+					struct nfsd4_blocked_lock,
+					nbl_list);
+		list_del_init(&nbl->nbl_list);
+		list_move(&nbl->nbl_lru, &reaplist);
+	}
+	spin_unlock(&nn->blocked_locks_lock);
+
+	/* Now free them */
+	while (!list_empty(&reaplist)) {
+		nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
+					nbl_lru);
+		list_del_init(&nbl->nbl_lru);
+		posix_unblock_lock(&nbl->nbl_lock);
+		free_blocked_lock(nbl);
+	}
+}
+
 static int
 nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
@@ -1866,6 +1895,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
 static void
 __destroy_client(struct nfs4_client *clp)
 {
+	int i;
 	struct nfs4_openowner *oo;
 	struct nfs4_delegation *dp;
 	struct list_head reaplist;
@@ -1895,6 +1925,16 @@ __destroy_client(struct nfs4_client *clp)
 		nfs4_get_stateowner(&oo->oo_owner);
 		release_openowner(oo);
 	}
+	for (i = 0; i < OWNER_HASH_SIZE; i++) {
+		struct nfs4_stateowner *so, *tmp;
+
+		list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i],
+					 so_strhash) {
+			/* Should be no openowners at this point */
+			WARN_ON_ONCE(so->so_is_open_owner);
+			remove_blocked_locks(lockowner(so));
+		}
+	}
 	nfsd4_return_all_client_layouts(clp);
 	nfsd4_shutdown_callback(clp);
 	if (clp->cl_cb_conn.cb_xprt)
@@ -6355,6 +6395,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 	}
 	spin_unlock(&clp->cl_lock);
 	free_ol_stateid_reaplist(&reaplist);
+	remove_blocked_locks(lo);
 	nfs4_put_stateowner(&lo->lo_owner);
 
 	return status;
@@ -7140,6 +7181,8 @@ nfs4_state_destroy_net(struct net *net)
 		}
 	}
 
+	WARN_ON(!list_empty(&nn->blocked_locks_lru));
+
 	for (i = 0; i < CLIENT_HASH_SIZE; i++) {
 		while (!list_empty(&nn->unconf_id_hashtbl[i])) {
 			clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash);
@@ -7206,7 +7249,6 @@ nfs4_state_shutdown_net(struct net *net)
 	struct nfs4_delegation *dp = NULL;
 	struct list_head *pos, *next, reaplist;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	struct nfsd4_blocked_lock *nbl;
 
 	cancel_delayed_work_sync(&nn->laundromat_work);
 	locks_end_grace(&nn->nfsd4_manager);
@@ -7227,24 +7269,6 @@ nfs4_state_shutdown_net(struct net *net)
 		nfs4_put_stid(&dp->dl_stid);
 	}
 
-	BUG_ON(!list_empty(&reaplist));
-	spin_lock(&nn->blocked_locks_lock);
-	while (!list_empty(&nn->blocked_locks_lru)) {
-		nbl = list_first_entry(&nn->blocked_locks_lru,
-					struct nfsd4_blocked_lock, nbl_lru);
-		list_move(&nbl->nbl_lru, &reaplist);
-		list_del_init(&nbl->nbl_list);
-	}
-	spin_unlock(&nn->blocked_locks_lock);
-
-	while (!list_empty(&reaplist)) {
-		nbl = list_first_entry(&reaplist,
-					struct nfsd4_blocked_lock, nbl_lru);
-		list_del_init(&nbl->nbl_lru);
-		posix_unblock_lock(&nbl->nbl_lock);
-		free_blocked_lock(nbl);
-	}
-
 	nfsd4_client_tracking_exit(net);
 	nfs4_state_destroy_net(net);
 }
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index 406e72de88f6..ce6ff5a0a6e4 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -24,6 +24,8 @@ config OVERLAY_FS_REDIRECT_DIR
 	  an overlay which has redirects on a kernel that doesn't support this
 	  feature will have unexpected results.
 
+	  If unsure, say N.
+
 config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW
 	bool "Overlayfs: follow redirects even if redirects are turned off"
 	default y
@@ -32,8 +34,13 @@ config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW
 	  Disable this to get a possibly more secure configuration, but that
 	  might not be backward compatible with previous kernels.
 
+	  If backward compatibility is not an issue, then it is safe and
+	  recommended to say N here.
+
 	  For more information, see Documentation/filesystems/overlayfs.txt
 
+	  If unsure, say Y.
+
 config OVERLAY_FS_INDEX
 	bool "Overlayfs: turn on inodes index feature by default"
 	depends on OVERLAY_FS
@@ -51,6 +58,8 @@ config OVERLAY_FS_INDEX
 	  That is, mounting an overlay which has an inodes index on a kernel
 	  that doesn't support this feature will have unexpected results.
 
+	  If unsure, say N.
+
 config OVERLAY_FS_NFS_EXPORT
 	bool "Overlayfs: turn on NFS export feature by default"
 	depends on OVERLAY_FS
@@ -72,3 +81,8 @@ config OVERLAY_FS_NFS_EXPORT
 	  Note, that the NFS export feature is not backward compatible.
 	  That is, mounting an overlay which has a full index on a kernel
 	  that doesn't support this feature will have unexpected results.
+
+	  Most users should say N here and enable this feature on a case-by-
+	  case basis with the "nfs_export=on" mount option.
+
+	  Say N unless you fully understand the consequences.
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index bb94ce9da5c8..87bd4148f4fb 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -19,6 +19,142 @@
 #include <linux/ratelimit.h>
 #include "overlayfs.h"
 
+static int ovl_encode_maybe_copy_up(struct dentry *dentry)
+{
+	int err;
+
+	if (ovl_dentry_upper(dentry))
+		return 0;
+
+	err = ovl_want_write(dentry);
+	if (!err) {
+		err = ovl_copy_up(dentry);
+		ovl_drop_write(dentry);
+	}
+
+	if (err) {
+		pr_warn_ratelimited("overlayfs: failed to copy up on encode (%pd2, err=%i)\n",
+				    dentry, err);
+	}
+
+	return err;
+}
+
+/*
+ * Before encoding a non-upper directory file handle from real layer N, we need
+ * to check if it will be possible to reconnect an overlay dentry from the real
+ * lower decoded dentry. This is done by following the overlay ancestry up to a
+ * "layer N connected" ancestor and verifying that all parents along the way are
+ * "layer N connectable". If an ancestor that is NOT "layer N connectable" is
+ * found, we need to copy up an ancestor, which is "layer N connectable", thus
+ * making that ancestor "layer N connected". For example:
+ *
+ * layer 1: /a
+ * layer 2: /a/b/c
+ *
+ * The overlay dentry /a is NOT "layer 2 connectable", because if dir /a is
+ * copied up and renamed, upper dir /a will be indexed by lower dir /a from
+ * layer 1. The dir /a from layer 2 will never be indexed, so the algorithm (*)
+ * in ovl_lookup_real_ancestor() will not be able to lookup a connected overlay
+ * dentry from the connected lower dentry /a/b/c.
+ *
+ * To avoid this problem on decode time, we need to copy up an ancestor of
+ * /a/b/c, which is "layer 2 connectable", on encode time. That ancestor is
+ * /a/b. After copy up (and index) of /a/b, it will become "layer 2 connected"
+ * and when the time comes to decode the file handle from lower dentry /a/b/c,
+ * ovl_lookup_real_ancestor() will find the indexed ancestor /a/b and decoding
+ * a connected overlay dentry will be accomplished.
+ *
+ * (*) the algorithm in ovl_lookup_real_ancestor() can be improved to lookup an
+ * entry /a in the lower layers above layer N and find the indexed dir /a from
+ * layer 1. If that improvement is made, then the check for "layer N connected"
+ * will need to verify there are no redirects in lower layers above N. In the
+ * example above, /a will be "layer 2 connectable". However, if layer 2 dir /a
+ * is a target of a layer 1 redirect, then /a will NOT be "layer 2 connectable":
+ *
+ * layer 1: /A (redirect = /a)
+ * layer 2: /a/b/c
+ */
+
+/* Return the lowest layer for encoding a connectable file handle */
+static int ovl_connectable_layer(struct dentry *dentry)
+{
+	struct ovl_entry *oe = OVL_E(dentry);
+
+	/* We can get overlay root from root of any layer */
+	if (dentry == dentry->d_sb->s_root)
+		return oe->numlower;
+
+	/*
+	 * If it's an unindexed merge dir, then it's not connectable with any
+	 * lower layer
+	 */
+	if (ovl_dentry_upper(dentry) &&
+	    !ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+		return 0;
+
+	/* We can get upper/overlay path from indexed/lower dentry */
+	return oe->lowerstack[0].layer->idx;
+}
+
+/*
+ * @dentry is "connected" if all ancestors up to root or a "connected" ancestor
+ * have the same uppermost lower layer as the origin's layer. We may need to
+ * copy up a "connectable" ancestor to make it "connected". A "connected" dentry
+ * cannot become non "connected", so cache positive result in dentry flags.
+ *
+ * Return the connected origin layer or < 0 on error.
+ */
+static int ovl_connect_layer(struct dentry *dentry)
+{
+	struct dentry *next, *parent = NULL;
+	int origin_layer;
+	int err = 0;
+
+	if (WARN_ON(dentry == dentry->d_sb->s_root) ||
+	    WARN_ON(!ovl_dentry_lower(dentry)))
+		return -EIO;
+
+	origin_layer = OVL_E(dentry)->lowerstack[0].layer->idx;
+	if (ovl_dentry_test_flag(OVL_E_CONNECTED, dentry))
+		return origin_layer;
+
+	/* Find the topmost origin layer connectable ancestor of @dentry */
+	next = dget(dentry);
+	for (;;) {
+		parent = dget_parent(next);
+		if (WARN_ON(parent == next)) {
+			err = -EIO;
+			break;
+		}
+
+		/*
+		 * If @parent is not origin layer connectable, then copy up
+		 * @next which is origin layer connectable and we are done.
+		 */
+		if (ovl_connectable_layer(parent) < origin_layer) {
+			err = ovl_encode_maybe_copy_up(next);
+			break;
+		}
+
+		/* If @parent is connected or indexed we are done */
+		if (ovl_dentry_test_flag(OVL_E_CONNECTED, parent) ||
+		    ovl_test_flag(OVL_INDEX, d_inode(parent)))
+			break;
+
+		dput(next);
+		next = parent;
+	}
+
+	dput(parent);
+	dput(next);
+
+	if (!err)
+		ovl_dentry_set_flag(OVL_E_CONNECTED, dentry);
+
+	return err ?: origin_layer;
+}
+
 /*
  * We only need to encode origin if there is a chance that the same object was
  * encoded pre copy up and then we need to stay consistent with the same
@@ -41,73 +177,59 @@
  * L = lower file handle
  *
  * (*) Connecting an overlay dir from real lower dentry is not always
- * possible when there are redirects in lower layers. To mitigate this case,
- * we copy up the lower dir first and then encode an upper dir file handle.
+ * possible when there are redirects in lower layers and non-indexed merge dirs.
+ * To mitigate those case, we may copy up the lower dir ancestor before encode
+ * a lower dir file handle.
+ *
+ * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error.
  */
-static bool ovl_should_encode_origin(struct dentry *dentry)
+static int ovl_check_encode_origin(struct dentry *dentry)
 {
 	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 
+	/* Upper file handle for pure upper */
 	if (!ovl_dentry_lower(dentry))
-		return false;
+		return 0;
 
 	/*
-	 * Decoding a merge dir, whose origin's parent is under a redirected
-	 * lower dir is not always possible. As a simple aproximation, we do
-	 * not encode lower dir file handles when overlay has multiple lower
-	 * layers and origin is below the topmost lower layer.
+	 * Upper file handle for non-indexed upper.
 	 *
-	 * TODO: copy up only the parent that is under redirected lower.
+	 * Root is never indexed, so if there's an upper layer, encode upper for
+	 * root.
 	 */
-	if (d_is_dir(dentry) && ofs->upper_mnt &&
-	    OVL_E(dentry)->lowerstack[0].layer->idx > 1)
-		return false;
-
-	/* Decoding a non-indexed upper from origin is not implemented */
 	if (ovl_dentry_upper(dentry) &&
 	    !ovl_test_flag(OVL_INDEX, d_inode(dentry)))
-		return false;
-
-	return true;
-}
-
-static int ovl_encode_maybe_copy_up(struct dentry *dentry)
-{
-	int err;
-
-	if (ovl_dentry_upper(dentry))
 		return 0;
 
-	err = ovl_want_write(dentry);
-	if (err)
-		return err;
-
-	err = ovl_copy_up(dentry);
+	/*
+	 * Decoding a merge dir, whose origin's ancestor is under a redirected
+	 * lower dir or under a non-indexed upper is not always possible.
+	 * ovl_connect_layer() will try to make origin's layer "connected" by
+	 * copying up a "connectable" ancestor.
+	 */
+	if (d_is_dir(dentry) && ofs->upper_mnt)
+		return ovl_connect_layer(dentry);
 
-	ovl_drop_write(dentry);
-	return err;
+	/* Lower file handle for indexed and non-upper dir/non-dir */
+	return 1;
 }
 
 static int ovl_d_to_fh(struct dentry *dentry, char *buf, int buflen)
 {
-	struct dentry *origin = ovl_dentry_lower(dentry);
 	struct ovl_fh *fh = NULL;
-	int err;
+	int err, enc_lower;
 
 	/*
-	 * If we should not encode a lower dir file handle, copy up and encode
-	 * an upper dir file handle.
+	 * Check if we should encode a lower or upper file handle and maybe
+	 * copy up an ancestor to make lower file handle connectable.
 	 */
-	if (!ovl_should_encode_origin(dentry)) {
-		err = ovl_encode_maybe_copy_up(dentry);
-		if (err)
-			goto fail;
-
-		origin = NULL;
-	}
+	err = enc_lower = ovl_check_encode_origin(dentry);
+	if (enc_lower < 0)
+		goto fail;
 
-	/* Encode an upper or origin file handle */
-	fh = ovl_encode_fh(origin ?: ovl_dentry_upper(dentry), !origin);
+	/* Encode an upper or lower file handle */
+	fh = ovl_encode_fh(enc_lower ? ovl_dentry_lower(dentry) :
+				       ovl_dentry_upper(dentry), !enc_lower);
 	err = PTR_ERR(fh);
 	if (IS_ERR(fh))
 		goto fail;
@@ -355,8 +477,8 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 		dput(upper);
 	}
 
-	if (!this)
-		return NULL;
+	if (IS_ERR_OR_NULL(this))
+		return this;
 
 	if (WARN_ON(ovl_dentry_real_at(this, layer->idx) != real)) {
 		dput(this);
@@ -498,7 +620,7 @@ static struct dentry *ovl_lookup_real(struct super_block *sb,
 			if (err == -ECHILD) {
 				this = ovl_lookup_real_ancestor(sb, real,
 								layer);
-				err = IS_ERR(this) ? PTR_ERR(this) : 0;
+				err = PTR_ERR_OR_ZERO(this);
 			}
 			if (!err) {
 				dput(connected);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index fcd97b783fa1..3b1bd469accd 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -669,38 +669,59 @@ struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real,
 	return inode;
 }
 
+/*
+ * Does overlay inode need to be hashed by lower inode?
+ */
+static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper,
+			     struct dentry *lower, struct dentry *index)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	/* No, if pure upper */
+	if (!lower)
+		return false;
+
+	/* Yes, if already indexed */
+	if (index)
+		return true;
+
+	/* Yes, if won't be copied up */
+	if (!ofs->upper_mnt)
+		return true;
+
+	/* No, if lower hardlink is or will be broken on copy up */
+	if ((upper || !ovl_indexdir(sb)) &&
+	    !d_is_dir(lower) && d_inode(lower)->i_nlink > 1)
+		return false;
+
+	/* No, if non-indexed upper with NFS export */
+	if (sb->s_export_op && upper)
+		return false;
+
+	/* Otherwise, hash by lower inode for fsnotify */
+	return true;
+}
+
 struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry,
 			    struct dentry *lowerdentry, struct dentry *index,
 			    unsigned int numlower)
 {
-	struct ovl_fs *ofs = sb->s_fs_info;
 	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
 	struct inode *inode;
-	/* Already indexed or could be indexed on copy up? */
-	bool indexed = (index || (ovl_indexdir(sb) && !upperdentry));
-	struct dentry *origin = indexed ? lowerdentry : NULL;
+	bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index);
 	bool is_dir;
 
-	if (WARN_ON(upperdentry && indexed && !lowerdentry))
-		return ERR_PTR(-EIO);
-
 	if (!realinode)
 		realinode = d_inode(lowerdentry);
 
 	/*
-	 * Copy up origin (lower) may exist for non-indexed non-dir upper, but
-	 * we must not use lower as hash key in that case.
-	 * Hash non-dir that is or could be indexed by origin inode.
-	 * Hash dir that is or could be merged by origin inode.
-	 * Hash pure upper and non-indexed non-dir by upper inode.
-	 * Hash non-indexed dir by upper inode for NFS export.
+	 * Copy up origin (lower) may exist for non-indexed upper, but we must
+	 * not use lower as hash key if this is a broken hardlink.
 	 */
 	is_dir = S_ISDIR(realinode->i_mode);
-	if (is_dir && (indexed || !sb->s_export_op || !ofs->upper_mnt))
-		origin = lowerdentry;
-
-	if (upperdentry || origin) {
-		struct inode *key = d_inode(origin ?: upperdentry);
+	if (upperdentry || bylower) {
+		struct inode *key = d_inode(bylower ? lowerdentry :
+						      upperdentry);
 		unsigned int nlink = is_dir ? 1 : realinode->i_nlink;
 
 		inode = iget5_locked(sb, (unsigned long) key,
@@ -728,6 +749,7 @@ struct inode *ovl_get_inode(struct super_block *sb, struct dentry *upperdentry,
 			nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink);
 		set_nlink(inode, nlink);
 	} else {
+		/* Lower hardlink that will be broken on copy up */
 		inode = new_inode(sb);
 		if (!inode)
 			goto out_nomem;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index de3e6da1d5a5..70fcfcc684cc 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -913,9 +913,6 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		stack[ctr].layer = lower.layer;
 		ctr++;
 
-		if (d.stop)
-			break;
-
 		/*
 		 * Following redirects can have security consequences: it's like
 		 * a symlink into the lower layer without the permission checks.
@@ -933,6 +930,9 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			goto out_put;
 		}
 
+		if (d.stop)
+			break;
+
 		if (d.redirect && d.redirect[0] == '/' && poe != roe) {
 			poe = roe;
 			/* Find the current layer on the root dentry */
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 0df25a9c94bd..225ff1171147 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -40,6 +40,7 @@ enum ovl_inode_flag {
 enum ovl_entry_flag {
 	OVL_E_UPPER_ALIAS,
 	OVL_E_OPAQUE,
+	OVL_E_CONNECTED,
 };
 
 /*
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 9ee37c76091d..7c24619ae7fc 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1359,6 +1359,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	/* Root is always merge -> can have whiteouts */
 	ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry));
+	ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry);
 	ovl_inode_init(d_inode(root_dentry), upperpath.dentry,
 		       ovl_dentry_lower(root_dentry));
 
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 8664db25a9a6..215c225b2ca1 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -106,6 +106,7 @@ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
 {
 	return sysfs_do_create_link(kobj, target, name, 0);
 }
+EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn);
 
 /**
  *	sysfs_delete_link - remove symlink in object's directory.
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 66e1edbfb2b2..046469fcc1b8 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -955,15 +955,29 @@ static inline bool imap_needs_alloc(struct inode *inode,
 		(IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
 }
 
+static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps)
+{
+	return nimaps &&
+		imap->br_startblock != HOLESTARTBLOCK &&
+		imap->br_state != XFS_EXT_UNWRITTEN;
+}
+
 static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
 {
 	/*
-	 * COW writes will allocate delalloc space, so we need to make sure
-	 * to take the lock exclusively here.
+	 * COW writes may allocate delalloc space or convert unwritten COW
+	 * extents, so we need to make sure to take the lock exclusively here.
 	 */
 	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
 		return true;
-	if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE))
+
+	/*
+	 * Extents not yet cached requires exclusive access, don't block.
+	 * This is an opencoded xfs_ilock_data_map_shared() to cater for the
+	 * non-blocking behaviour.
+	 */
+	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+	    !(ip->i_df.if_flags & XFS_IFEXTENTS))
 		return true;
 	return false;
 }
@@ -993,16 +1007,18 @@ xfs_file_iomap_begin(
 		return xfs_file_iomap_begin_delay(inode, offset, length, iomap);
 	}
 
-	if (need_excl_ilock(ip, flags)) {
+	if (need_excl_ilock(ip, flags))
 		lockmode = XFS_ILOCK_EXCL;
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-	} else {
-		lockmode = xfs_ilock_data_map_shared(ip);
-	}
+	else
+		lockmode = XFS_ILOCK_SHARED;
 
-	if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) {
-		error = -EAGAIN;
-		goto out_unlock;
+	if (flags & IOMAP_NOWAIT) {
+		if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
+			return -EAGAIN;
+		if (!xfs_ilock_nowait(ip, lockmode))
+			return -EAGAIN;
+	} else {
+		xfs_ilock(ip, lockmode);
 	}
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
@@ -1024,7 +1040,9 @@ xfs_file_iomap_begin(
 			goto out_unlock;
 	}
 
-	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+	if (xfs_is_reflink_inode(ip) &&
+	    ((flags & IOMAP_WRITE) ||
+	     ((flags & IOMAP_ZERO) && needs_cow_for_zeroing(&imap, nimaps)))) {
 		if (flags & IOMAP_DIRECT) {
 			/*
 			 * A reflinked inode will result in CoW alloc.