Merge tag 'asoc-fix-v6.18-rc7' of https://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus

ASoC: Fixes for v6.18

A small pile of driver specific fixes that came in during the past few
weeks, none of them especially major.

36 files changed, 488 insertions, 257 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 755ec6dfd51c..23273d0e6f22 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2228,6 +2228,14 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
 		wbc_account_cgroup_owner(wbc, folio, range_len);
 		folio_unlock(folio);
 	}
+	/*
+	 * If the fs is already in error status, do not submit any writeback
+	 * but immediately finish it.
+	 */
+	if (unlikely(BTRFS_FS_ERROR(fs_info))) {
+		btrfs_bio_end_io(bbio, errno_to_blk_status(BTRFS_FS_ERROR(fs_info)));
+		return;
+	}
 	btrfs_submit_bbio(bbio, 0);
 }
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7efd1f8a1912..fa82def46e39 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2854,12 +2854,22 @@ static int btrfs_fallocate_update_isize(struct inode *inode,
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	u64 range_start;
+	u64 range_end;
 	int ret;
 	int ret2;
 
 	if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode))
 		return 0;
 
+	range_start = round_down(i_size_read(inode), root->fs_info->sectorsize);
+	range_end = round_up(end, root->fs_info->sectorsize);
+
+	ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), range_start,
+						range_end - range_start);
+	if (ret)
+		return ret;
+
 	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3b1b3a0553ee..6282911e536f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -177,8 +177,10 @@ static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
 		return ret;
 	}
 	ret = paths_from_inode(inum, ipath);
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_put_root(local_root);
 		goto err;
+	}
 
 	/*
 	 * We deliberately ignore the bit ipath might have been too small to
@@ -6873,7 +6875,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	BTRFS_I(inode)->dir_index = 0ULL;
 	inode_inc_iversion(inode);
 	inode_set_ctime_current(inode);
-	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     &fname.disk_name, 1, index);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 1175b8192cd7..31ad8580322a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1539,8 +1539,10 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst
 	ASSERT(prealloc);
 
 	/* Check the level of src and dst first */
-	if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
+	if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) {
+		kfree(prealloc);
 		return -EINVAL;
+	}
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 651b11884f82..ba20d9286a34 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2203,6 +2203,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 	ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, full_stripe_start,
 			      &length, &bioc, NULL, NULL);
 	if (ret < 0) {
+		bio_put(bio);
 		btrfs_put_bioc(bioc);
 		btrfs_bio_counter_dec(fs_info);
 		goto out;
@@ -2212,6 +2213,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 	btrfs_put_bioc(bioc);
 	if (!rbio) {
 		ret = -ENOMEM;
+		bio_put(bio);
 		btrfs_bio_counter_dec(fs_info);
 		goto out;
 	}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 621e0df097e3..30f3c3b849c1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -7122,7 +7122,7 @@ log_extents:
 	 *    a power failure unless the log was synced as part of an fsync
 	 *    against any other unrelated inode.
 	 */
-	if (inode_only != LOG_INODE_EXISTS)
+	if (!ctx->logging_new_name && inode_only != LOG_INODE_EXISTS)
 		inode->last_log_commit = inode->last_sub_trans;
 	spin_unlock(&inode->lock);
 
@@ -7910,6 +7910,9 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	bool log_pinned = false;
 	int ret;
 
+	/* The inode has a new name (ref/extref), so make sure we log it. */
+	set_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags);
+
 	btrfs_init_log_ctx(&ctx, inode);
 	ctx.logging_new_name = true;
 
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 0ea0df18a8e4..d1db7fa1fe58 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1317,6 +1317,7 @@ static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
 	if (!btrfs_dev_is_sequential(device, info->physical)) {
 		up_read(&dev_replace->rwsem);
 		info->alloc_offset = WP_CONVENTIONAL;
+		info->capacity = device->zone_info->zone_size;
 		return 0;
 	}
 
@@ -1522,6 +1523,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 					u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
+	u64 stripe_nr = 0, stripe_offset = 0;
+	u32 stripe_index = 0;
 
 	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
 		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
@@ -1529,28 +1532,26 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 		return -EINVAL;
 	}
 
+	if (last_alloc) {
+		u32 factor = map->num_stripes;
+
+		stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT;
+		stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK;
+		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
+	}
+
 	for (int i = 0; i < map->num_stripes; i++) {
 		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
 			continue;
 
 		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
-			u64 stripe_nr, full_stripe_nr;
-			u64 stripe_offset;
-			int stripe_index;
 
-			stripe_nr = div64_u64(last_alloc, map->stripe_size);
-			stripe_offset = stripe_nr * map->stripe_size;
-			full_stripe_nr = div_u64(stripe_nr, map->num_stripes);
-			div_u64_rem(stripe_nr, map->num_stripes, &stripe_index);
-
-			zone_info[i].alloc_offset =
-				full_stripe_nr * map->stripe_size;
+			zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr);
 
 			if (stripe_index > i)
-				zone_info[i].alloc_offset += map->stripe_size;
+				zone_info[i].alloc_offset += BTRFS_STRIPE_LEN;
 			else if (stripe_index == i)
-				zone_info[i].alloc_offset +=
-					(last_alloc - stripe_offset);
+				zone_info[i].alloc_offset += stripe_offset;
 		}
 
 		if (test_bit(0, active) != test_bit(i, active)) {
@@ -1574,6 +1575,8 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 					 u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
+	u64 stripe_nr = 0, stripe_offset = 0;
+	u32 stripe_index = 0;
 
 	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
 		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
@@ -1581,6 +1584,14 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 		return -EINVAL;
 	}
 
+	if (last_alloc) {
+		u32 factor = map->num_stripes / map->sub_stripes;
+
+		stripe_nr = last_alloc >> BTRFS_STRIPE_LEN_SHIFT;
+		stripe_offset = last_alloc & BTRFS_STRIPE_LEN_MASK;
+		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
+	}
+
 	for (int i = 0; i < map->num_stripes; i++) {
 		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
 			continue;
@@ -1594,26 +1605,12 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 		}
 
 		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
-			u64 stripe_nr, full_stripe_nr;
-			u64 stripe_offset;
-			int stripe_index;
-
-			stripe_nr = div64_u64(last_alloc, map->stripe_size);
-			stripe_offset = stripe_nr * map->stripe_size;
-			full_stripe_nr = div_u64(stripe_nr,
-					 map->num_stripes / map->sub_stripes);
-			div_u64_rem(stripe_nr,
-				    (map->num_stripes / map->sub_stripes),
-				    &stripe_index);
-
-			zone_info[i].alloc_offset =
-				full_stripe_nr * map->stripe_size;
+			zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr);
 
 			if (stripe_index > (i / map->sub_stripes))
-				zone_info[i].alloc_offset += map->stripe_size;
+				zone_info[i].alloc_offset += BTRFS_STRIPE_LEN;
 			else if (stripe_index == (i / map->sub_stripes))
-				zone_info[i].alloc_offset +=
-					(last_alloc - stripe_offset);
+				zone_info[i].alloc_offset += stripe_offset;
 		}
 
 		if ((i % map->sub_stripes) == 0) {
@@ -1683,8 +1680,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		set_bit(BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, &cache->runtime_flags);
 
 	if (num_conventional > 0) {
-		/* Zone capacity is always zone size in emulation */
-		cache->zone_capacity = cache->length;
 		ret = calculate_alloc_pointer(cache, &last_alloc, new);
 		if (ret) {
 			btrfs_err(fs_info,
@@ -1693,6 +1688,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			goto out;
 		} else if (map->num_stripes == num_conventional) {
 			cache->alloc_offset = last_alloc;
+			cache->zone_capacity = cache->length;
 			set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags);
 			goto out;
 		}
diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c
index 5dee7c498bc8..ed6e926226b5 100644
--- a/fs/crypto/inline_crypt.c
+++ b/fs/crypto/inline_crypt.c
@@ -333,8 +333,7 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh,
 	inode = mapping->host;
 
 	*inode_ret = inode;
-	*lblk_num_ret = ((u64)folio->index << (PAGE_SHIFT - inode->i_blkbits)) +
-			(bh_offset(bh) >> inode->i_blkbits);
+	*lblk_num_ret = (folio_pos(folio) + bh_offset(bh)) >> inode->i_blkbits;
 	return true;
 }
 
diff --git a/fs/erofs/decompressor_zstd.c b/fs/erofs/decompressor_zstd.c
index b4bfe14229f9..e38d93bb2104 100644
--- a/fs/erofs/decompressor_zstd.c
+++ b/fs/erofs/decompressor_zstd.c
@@ -172,7 +172,6 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 	dctx.bounce = strm->bounce;
 
 	do {
-		dctx.avail_out = out_buf.size - out_buf.pos;
 		dctx.inbuf_sz = in_buf.size;
 		dctx.inbuf_pos = in_buf.pos;
 		err = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst,
@@ -188,14 +187,18 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq,
 		in_buf.pos = dctx.inbuf_pos;
 
 		zerr = zstd_decompress_stream(stream, &out_buf, &in_buf);
-		if (zstd_is_error(zerr) || (!zerr && rq->outputsize)) {
+		dctx.avail_out = out_buf.size - out_buf.pos;
+		if (zstd_is_error(zerr) ||
+		    ((rq->outputsize + dctx.avail_out) && (!zerr || (zerr > 0 &&
+				!(rq->inputsize + in_buf.size - in_buf.pos))))) {
 			erofs_err(sb, "failed to decompress in[%u] out[%u]: %s",
 				  rq->inputsize, rq->outputsize,
-				  zerr ? zstd_get_error_name(zerr) : "unexpected end of stream");
+				  zstd_is_error(zerr) ? zstd_get_error_name(zerr) :
+					"unexpected end of stream");
 			err = -EFSCORRUPTED;
 			break;
 		}
-	} while (rq->outputsize || out_buf.pos < out_buf.size);
+	} while (rq->outputsize + dctx.avail_out);
 
 	if (dctx.kout)
 		kunmap_local(dctx.kout);
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 4e3dcc157a83..54699299d5b1 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -338,6 +338,14 @@ again:
 		/* Match the xprt security policy */
 		if (clp->cl_xprtsec.policy != data->xprtsec.policy)
 			continue;
+		if (clp->cl_xprtsec.policy == RPC_XPRTSEC_TLS_X509) {
+			if (clp->cl_xprtsec.cert_serial !=
+			    data->xprtsec.cert_serial)
+				continue;
+			if (clp->cl_xprtsec.privkey_serial !=
+			    data->xprtsec.privkey_serial)
+				continue;
+		}
 
 		refcount_inc(&clp->cl_count);
 		return clp;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 46d9c65d50f8..ea9f6ca8f30f 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2268,11 +2268,12 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
 		return -ENAMETOOLONG;
 
 	if (open_flags & O_CREAT) {
-		file->f_mode |= FMODE_CREATED;
 		error = nfs_do_create(dir, dentry, mode, open_flags);
-		if (error)
+		if (!error) {
+			file->f_mode |= FMODE_CREATED;
+			return finish_open(file, dentry, NULL);
+		} else if (error != -EEXIST || open_flags & O_EXCL)
 			return error;
-		return finish_open(file, dentry, NULL);
 	}
 	if (d_in_lookup(dentry)) {
 		/* The only flags nfs_lookup considers are
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 18b57c7c2f97..13ad70fc00d8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -718,6 +718,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	struct nfs_fattr *fattr;
 	loff_t oldsize = i_size_read(inode);
 	int error = 0;
+	kuid_t task_uid = current_fsuid();
+	kuid_t owner_uid = inode->i_uid;
 
 	nfs_inc_stats(inode, NFSIOS_VFSSETATTR);
 
@@ -739,9 +741,11 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) {
 		spin_lock(&inode->i_lock);
 		if (attr->ia_valid & ATTR_MTIME_SET) {
-			nfs_set_timestamps_to_ts(inode, attr);
-			attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
+			if (uid_eq(task_uid, owner_uid)) {
+				nfs_set_timestamps_to_ts(inode, attr);
+				attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET|
 						ATTR_ATIME|ATTR_ATIME_SET);
+			}
 		} else {
 			nfs_update_timestamps(inode, attr->ia_valid);
 			attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME);
@@ -751,10 +755,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		   attr->ia_valid & ATTR_ATIME &&
 		   !(attr->ia_valid & ATTR_MTIME)) {
 		if (attr->ia_valid & ATTR_ATIME_SET) {
-			spin_lock(&inode->i_lock);
-			nfs_set_timestamps_to_ts(inode, attr);
-			spin_unlock(&inode->i_lock);
-			attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+			if (uid_eq(task_uid, owner_uid)) {
+				spin_lock(&inode->i_lock);
+				nfs_set_timestamps_to_ts(inode, attr);
+				spin_unlock(&inode->i_lock);
+				attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET);
+			}
 		} else {
 			nfs_update_delegated_atime(inode);
 			attr->ia_valid &= ~ATTR_ATIME;
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index 2c0455e91571..656976b4f42c 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -42,10 +42,9 @@ struct nfs_local_kiocb {
 	/* Begin mostly DIO-specific members */
 	size_t                  end_len;
 	short int		end_iter_index;
-	short int		n_iters;
+	atomic_t		n_iters;
 	bool			iter_is_dio_aligned[NFSLOCAL_MAX_IOS];
-	loff_t                  offset[NFSLOCAL_MAX_IOS] ____cacheline_aligned;
-	struct iov_iter		iters[NFSLOCAL_MAX_IOS];
+	struct iov_iter		iters[NFSLOCAL_MAX_IOS] ____cacheline_aligned;
 	/* End mostly DIO-specific members */
 };
 
@@ -314,7 +313,9 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr,
 	init_sync_kiocb(&iocb->kiocb, file);
 
 	iocb->hdr = hdr;
+	iocb->kiocb.ki_pos = hdr->args.offset;
 	iocb->kiocb.ki_flags &= ~IOCB_APPEND;
+	iocb->kiocb.ki_complete = NULL;
 	iocb->aio_complete_work = NULL;
 
 	iocb->end_iter_index = -1;
@@ -388,13 +389,24 @@ static bool nfs_iov_iter_aligned_bvec(const struct iov_iter *i,
 	return true;
 }
 
+static void
+nfs_local_iter_setup(struct iov_iter *iter, int rw, struct bio_vec *bvec,
+		     unsigned int nvecs, unsigned long total,
+		     size_t start, size_t len)
+{
+	iov_iter_bvec(iter, rw, bvec, nvecs, total);
+	if (start)
+		iov_iter_advance(iter, start);
+	iov_iter_truncate(iter, len);
+}
+
 /*
  * Setup as many as 3 iov_iter based on extents described by @local_dio.
  * Returns the number of iov_iter that were setup.
  */
 static int
 nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
-			  unsigned int nvecs, size_t len,
+			  unsigned int nvecs, unsigned long total,
 			  struct nfs_local_dio *local_dio)
 {
 	int n_iters = 0;
@@ -402,39 +414,17 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
 
 	/* Setup misaligned start? */
 	if (local_dio->start_len) {
-		iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
-		iters[n_iters].count = local_dio->start_len;
-		iocb->offset[n_iters] = iocb->hdr->args.offset;
-		iocb->iter_is_dio_aligned[n_iters] = false;
+		nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec,
+				     nvecs, total, 0, local_dio->start_len);
 		++n_iters;
 	}
 
-	/* Setup misaligned end?
-	 * If so, the end is purposely setup to be issued using buffered IO
-	 * before the middle (which will use DIO, if DIO-aligned, with AIO).
-	 * This creates problems if/when the end results in a partial write.
-	 * So must save index and length of end to handle this corner case.
-	 */
-	if (local_dio->end_len) {
-		iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
-		iocb->offset[n_iters] = local_dio->end_offset;
-		iov_iter_advance(&iters[n_iters],
-			local_dio->start_len + local_dio->middle_len);
-		iocb->iter_is_dio_aligned[n_iters] = false;
-		/* Save index and length of end */
-		iocb->end_iter_index = n_iters;
-		iocb->end_len = local_dio->end_len;
-		++n_iters;
-	}
-
-	/* Setup DIO-aligned middle to be issued last, to allow for
-	 * DIO with AIO completion (see nfs_local_call_{read,write}).
+	/*
+	 * Setup DIO-aligned middle, if there is no misaligned end (below)
+	 * then AIO completion is used, see nfs_local_call_{read,write}
 	 */
-	iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len);
-	if (local_dio->start_len)
-		iov_iter_advance(&iters[n_iters], local_dio->start_len);
-	iters[n_iters].count -= local_dio->end_len;
-	iocb->offset[n_iters] = local_dio->middle_offset;
+	nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, nvecs,
+			     total, local_dio->start_len, local_dio->middle_len);
 
 	iocb->iter_is_dio_aligned[n_iters] =
 		nfs_iov_iter_aligned_bvec(&iters[n_iters],
@@ -442,12 +432,22 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw,
 
 	if (unlikely(!iocb->iter_is_dio_aligned[n_iters])) {
 		trace_nfs_local_dio_misaligned(iocb->hdr->inode,
-			iocb->hdr->args.offset, len, local_dio);
+			local_dio->start_len, local_dio->middle_len, local_dio);
 		return 0; /* no DIO-aligned IO possible */
 	}
+	iocb->end_iter_index = n_iters;
 	++n_iters;
 
-	iocb->n_iters = n_iters;
+	/* Setup misaligned end? */
+	if (local_dio->end_len) {
+		nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec,
+				     nvecs, total, local_dio->start_len +
+				     local_dio->middle_len, local_dio->end_len);
+		iocb->end_iter_index = n_iters;
+		++n_iters;
+	}
+
+	atomic_set(&iocb->n_iters, n_iters);
 	return n_iters;
 }
 
@@ -473,18 +473,26 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw)
 	}
 	len = hdr->args.count - total;
 
+	/*
+	 * For each iocb, iocb->n_iters is always at least 1 and we always
+	 * end io after first nfs_local_pgio_done call unless misaligned DIO.
+	 */
+	atomic_set(&iocb->n_iters, 1);
+
 	if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) {
 		struct nfs_local_dio local_dio;
 
 		if (nfs_is_local_dio_possible(iocb, rw, len, &local_dio) &&
-		    nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0)
+		    nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) {
+			/* Ensure DIO WRITE's IO on stable storage upon completion */
+			if (rw == ITER_SOURCE)
+				iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC;
 			return; /* is DIO-aligned */
+		}
 	}
 
 	/* Use buffered IO */
-	iocb->offset[0] = hdr->args.offset;
 	iov_iter_bvec(&iocb->iters[0], rw, iocb->bvec, v, len);
-	iocb->n_iters = 1;
 }
 
 static void
@@ -504,9 +512,11 @@ nfs_local_pgio_init(struct nfs_pgio_header *hdr,
 		hdr->task.tk_start = ktime_get();
 }
 
-static void
-nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
+static bool
+nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force)
 {
+	struct nfs_pgio_header *hdr = iocb->hdr;
+
 	/* Must handle partial completions */
 	if (status >= 0) {
 		hdr->res.count += status;
@@ -517,6 +527,12 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
 		hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status);
 		hdr->task.tk_status = status;
 	}
+
+	if (force)
+		return true;
+
+	BUG_ON(atomic_read(&iocb->n_iters) <= 0);
+	return atomic_dec_and_test(&iocb->n_iters);
 }
 
 static void
@@ -547,11 +563,11 @@ static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb)
 	queue_work(nfsiod_workqueue, &iocb->work);
 }
 
-static void
-nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
+static void nfs_local_read_done(struct nfs_local_kiocb *iocb)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 	struct file *filp = iocb->kiocb.ki_filp;
+	long status = hdr->task.tk_status;
 
 	if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) {
 		/* Underlying FS will return -EINVAL if misaligned DIO is attempted. */
@@ -564,20 +580,27 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status)
 	 */
 	hdr->res.replen = 0;
 
-	if (hdr->res.count != hdr->args.count ||
-	    hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
+	/* nfs_readpage_result() handles short read */
+
+	if (hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp)))
 		hdr->res.eof = true;
 
 	dprintk("%s: read %ld bytes eof %d.\n", __func__,
 			status > 0 ? status : 0, hdr->res.eof);
 }
 
+static inline void nfs_local_read_iocb_done(struct nfs_local_kiocb *iocb)
+{
+	nfs_local_read_done(iocb);
+	nfs_local_pgio_release(iocb);
+}
+
 static void nfs_local_read_aio_complete_work(struct work_struct *work)
 {
 	struct nfs_local_kiocb *iocb =
 		container_of(work, struct nfs_local_kiocb, work);
 
-	nfs_local_pgio_release(iocb);
+	nfs_local_read_iocb_done(iocb);
 }
 
 static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
@@ -585,8 +608,10 @@ static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret)
 	struct nfs_local_kiocb *iocb =
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
-	nfs_local_pgio_done(iocb->hdr, ret);
-	nfs_local_read_done(iocb, ret);
+	/* AIO completion of DIO read should always be last to complete */
+	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+		return;
+
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */
 }
 
@@ -596,32 +621,36 @@ static void nfs_local_call_read(struct work_struct *work)
 		container_of(work, struct nfs_local_kiocb, work);
 	struct file *filp = iocb->kiocb.ki_filp;
 	const struct cred *save_cred;
+	bool force_done = false;
 	ssize_t status;
+	int n_iters;
 
 	save_cred = override_creds(filp->f_cred);
 
-	for (int i = 0; i < iocb->n_iters ; i++) {
+	n_iters = atomic_read(&iocb->n_iters);
+	for (int i = 0; i < n_iters ; i++) {
 		if (iocb->iter_is_dio_aligned[i]) {
 			iocb->kiocb.ki_flags |= IOCB_DIRECT;
-			iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
-			iocb->aio_complete_work = nfs_local_read_aio_complete_work;
-		}
+			/* Only use AIO completion if DIO-aligned segment is last */
+			if (i == iocb->end_iter_index) {
+				iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
+				iocb->aio_complete_work = nfs_local_read_aio_complete_work;
+			}
+		} else
+			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
 
-		iocb->kiocb.ki_pos = iocb->offset[i];
 		status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]);
 		if (status != -EIOCBQUEUED) {
-			nfs_local_pgio_done(iocb->hdr, status);
-			if (iocb->hdr->task.tk_status)
+			if (unlikely(status >= 0 && status < iocb->iters[i].count))
+				force_done = true; /* Partial read */
+			if (nfs_local_pgio_done(iocb, status, force_done)) {
+				nfs_local_read_iocb_done(iocb);
 				break;
+			}
 		}
 	}
 
 	revert_creds(save_cred);
-
-	if (status != -EIOCBQUEUED) {
-		nfs_local_read_done(iocb, status);
-		nfs_local_pgio_release(iocb);
-	}
 }
 
 static int
@@ -736,11 +765,10 @@ static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb)
 	fattr->du.nfs3.used = stat.blocks << 9;
 }
 
-static void
-nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
+static void nfs_local_write_done(struct nfs_local_kiocb *iocb)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
-	struct inode *inode = hdr->inode;
+	long status = hdr->task.tk_status;
 
 	dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0);
 
@@ -759,10 +787,17 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status)
 		nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset);
 		status = -ENOSPC;
 		/* record -ENOSPC in terms of nfs_local_pgio_done */
-		nfs_local_pgio_done(hdr, status);
+		(void) nfs_local_pgio_done(iocb, status, true);
 	}
 	if (hdr->task.tk_status < 0)
-		nfs_reset_boot_verifier(inode);
+		nfs_reset_boot_verifier(hdr->inode);
+}
+
+static inline void nfs_local_write_iocb_done(struct nfs_local_kiocb *iocb)
+{
+	nfs_local_write_done(iocb);
+	nfs_local_vfs_getattr(iocb);
+	nfs_local_pgio_release(iocb);
 }
 
 static void nfs_local_write_aio_complete_work(struct work_struct *work)
@@ -770,8 +805,7 @@ static void nfs_local_write_aio_complete_work(struct work_struct *work)
 	struct nfs_local_kiocb *iocb =
 		container_of(work, struct nfs_local_kiocb, work);
 
-	nfs_local_vfs_getattr(iocb);
-	nfs_local_pgio_release(iocb);
+	nfs_local_write_iocb_done(iocb);
 }
 
 static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
@@ -779,8 +813,10 @@ static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret)
 	struct nfs_local_kiocb *iocb =
 		container_of(kiocb, struct nfs_local_kiocb, kiocb);
 
-	nfs_local_pgio_done(iocb->hdr, ret);
-	nfs_local_write_done(iocb, ret);
+	/* AIO completion of DIO write should always be last to complete */
+	if (unlikely(!nfs_local_pgio_done(iocb, ret, false)))
+		return;
+
 	nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */
 }
 
@@ -791,63 +827,40 @@ static void nfs_local_call_write(struct work_struct *work)
 	struct file *filp = iocb->kiocb.ki_filp;
 	unsigned long old_flags = current->flags;
 	const struct cred *save_cred;
+	bool force_done = false;
 	ssize_t status;
+	int n_iters;
 
 	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
 	save_cred = override_creds(filp->f_cred);
 
 	file_start_write(filp);
-	for (int i = 0; i < iocb->n_iters ; i++) {
+	n_iters = atomic_read(&iocb->n_iters);
+	for (int i = 0; i < n_iters ; i++) {
 		if (iocb->iter_is_dio_aligned[i]) {
 			iocb->kiocb.ki_flags |= IOCB_DIRECT;
-			iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
-			iocb->aio_complete_work = nfs_local_write_aio_complete_work;
-		}
-retry:
-		iocb->kiocb.ki_pos = iocb->offset[i];
+			/* Only use AIO completion if DIO-aligned segment is last */
+			if (i == iocb->end_iter_index) {
+				iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
+				iocb->aio_complete_work = nfs_local_write_aio_complete_work;
+			}
+		} else
+			iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
+
 		status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]);
 		if (status != -EIOCBQUEUED) {
-			if (unlikely(status >= 0 && status < iocb->iters[i].count)) {
-				/* partial write */
-				if (i == iocb->end_iter_index) {
-					/* Must not account partial end, otherwise, due
-					 * to end being issued before middle: the partial
-					 * write accounting in nfs_local_write_done()
-					 * would incorrectly advance hdr->args.offset
-					 */
-					status = 0;
-				} else {
-					/* Partial write at start or buffered middle,
-					 * exit early.
-					 */
-					nfs_local_pgio_done(iocb->hdr, status);
-					break;
-				}
-			} else if (unlikely(status == -ENOTBLK &&
-					    (iocb->kiocb.ki_flags & IOCB_DIRECT))) {
-				/* VFS will return -ENOTBLK if DIO WRITE fails to
-				 * invalidate the page cache. Retry using buffered IO.
-				 */
-				iocb->kiocb.ki_flags &= ~IOCB_DIRECT;
-				iocb->kiocb.ki_complete = NULL;
-				iocb->aio_complete_work = NULL;
-				goto retry;
-			}
-			nfs_local_pgio_done(iocb->hdr, status);
-			if (iocb->hdr->task.tk_status)
+			if (unlikely(status >= 0 && status < iocb->iters[i].count))
+				force_done = true; /* Partial write */
+			if (nfs_local_pgio_done(iocb, status, force_done)) {
+				nfs_local_write_iocb_done(iocb);
 				break;
+			}
 		}
 	}
 	file_end_write(filp);
 
 	revert_creds(save_cred);
 	current->flags = old_flags;
-
-	if (status != -EIOCBQUEUED) {
-		nfs_local_write_done(iocb, status);
-		nfs_local_vfs_getattr(iocb);
-		nfs_local_pgio_release(iocb);
-	}
 }
 
 static int
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index 0d7310c1ee0c..5d97c1d38bb6 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -2,6 +2,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/sunrpc/addr.h>
+#include <net/handshake.h>
 #include "internal.h"
 #include "nfs3_fs.h"
 #include "netns.h"
@@ -98,7 +99,11 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 		.net = mds_clp->cl_net,
 		.timeparms = &ds_timeout,
 		.cred = mds_srv->cred,
-		.xprtsec = mds_clp->cl_xprtsec,
+		.xprtsec = {
+			.policy = RPC_XPRTSEC_NONE,
+			.cert_serial = TLS_NO_CERT,
+			.privkey_serial = TLS_NO_PRIVKEY,
+		},
 		.connect_timeout = connect_timeout,
 		.reconnect_timeout = connect_timeout,
 	};
@@ -111,9 +116,14 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_TCP_TLS:
+		if (mds_clp->cl_xprtsec.policy != RPC_XPRTSEC_NONE)
+			cl_init.xprtsec = mds_clp->cl_xprtsec;
+		else
+			ds_proto = XPRT_TRANSPORT_TCP;
+		fallthrough;
 	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
-	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1)
 			cl_init.nconnect = mds_clp->cl_nconnect;
 	}
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 5998d6bd8a4f..3a4baed993c9 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -11,6 +11,7 @@
 #include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <net/handshake.h>
 #include "internal.h"
 #include "callback.h"
 #include "delegation.h"
@@ -983,7 +984,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		.net = mds_clp->cl_net,
 		.timeparms = &ds_timeout,
 		.cred = mds_srv->cred,
-		.xprtsec = mds_srv->nfs_client->cl_xprtsec,
+		.xprtsec = {
+			.policy = RPC_XPRTSEC_NONE,
+			.cert_serial = TLS_NO_CERT,
+			.privkey_serial = TLS_NO_PRIVKEY,
+		},
 	};
 	char buf[INET6_ADDRSTRLEN + 1];
 
@@ -992,9 +997,14 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	cl_init.hostname = buf;
 
 	switch (ds_proto) {
+	case XPRT_TRANSPORT_TCP_TLS:
+		if (mds_srv->nfs_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE)
+			cl_init.xprtsec = mds_srv->nfs_client->cl_xprtsec;
+		else
+			ds_proto = XPRT_TRANSPORT_TCP;
+		fallthrough;
 	case XPRT_TRANSPORT_RDMA:
 	case XPRT_TRANSPORT_TCP:
-	case XPRT_TRANSPORT_TCP_TLS:
 		if (mds_clp->cl_nconnect > 1) {
 			cl_init.nconnect = mds_clp->cl_nconnect;
 			cl_init.max_connect = NFS_MAX_TRANSPORTS;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 411776718494..93c6ce04332b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4715,16 +4715,19 @@ static int _nfs4_proc_lookupp(struct inode *inode,
 	};
 	unsigned short task_flags = 0;
 
-	if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)
+	if (server->flags & NFS_MOUNT_SOFTREVAL)
 		task_flags |= RPC_TASK_TIMEOUT;
+	if (server->caps & NFS_CAP_MOVEABLE)
+		task_flags |= RPC_TASK_MOVEABLE;
 
 	args.bitmask = nfs4_bitmask(server, fattr->label);
 
 	nfs_fattr_init(fattr);
+	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
 
 	dprintk("NFS call  lookupp ino=0x%lx\n", inode->i_ino);
-	status = nfs4_call_sync(clnt, server, &msg, &args.seq_args,
-				&res.seq_res, task_flags);
+	status = nfs4_do_call_sync(clnt, server, &msg, &args.seq_args,
+				   &res.seq_res, task_flags);
 	dprintk("NFS reply lookupp: %d\n", status);
 	return status;
 }
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 7b32afb29782..9976cc16b689 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -809,8 +809,11 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				 unsigned int retrans)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
+	enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy;
 	struct nfs4_pnfs_ds_addr *da;
 	unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10;
+	int ds_proto;
 	int status = 0;
 
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
@@ -834,27 +837,28 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				.xprtsec = clp->cl_xprtsec,
 			};
 
-			if (da->da_transport != clp->cl_proto &&
-			    clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
-				continue;
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
-			    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
+			if (xprt_args.ident == XPRT_TRANSPORT_TCP &&
+			    clp->cl_proto == XPRT_TRANSPORT_TCP_TLS)
 				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
 
-			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
+			if (xprt_args.ident != clp->cl_proto)
+				continue;
+			if (xprt_args.dstaddr->sa_family !=
+			    clp->cl_addr.ss_family)
 				continue;
 			/* Add this address as an alias */
 			rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
-					rpc_clnt_test_and_add_xprt, NULL);
+					  rpc_clnt_test_and_add_xprt, NULL);
 			continue;
 		}
-		if (da->da_transport == XPRT_TRANSPORT_TCP &&
-		    mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS)
-			da->da_transport = XPRT_TRANSPORT_TCP_TLS;
-		clp = get_v3_ds_connect(mds_srv,
-				&da->da_addr,
-				da->da_addrlen, da->da_transport,
-				timeo, retrans);
+
+		ds_proto = da->da_transport;
+		if (ds_proto == XPRT_TRANSPORT_TCP &&
+		    xprtsec_policy != RPC_XPRTSEC_NONE)
+			ds_proto = XPRT_TRANSPORT_TCP_TLS;
+
+		clp = get_v3_ds_connect(mds_srv, &da->da_addr, da->da_addrlen,
+					ds_proto, timeo, retrans);
 		if (IS_ERR(clp))
 			continue;
 		clp->cl_rpcclient->cl_softerr = 0;
@@ -880,7 +884,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				 u32 minor_version)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs_client *mds_clp = mds_srv->nfs_client;
+	enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy;
 	struct nfs4_pnfs_ds_addr *da;
+	int ds_proto;
 	int status = 0;
 
 	dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
@@ -908,12 +915,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				.data = &xprtdata,
 			};
 
-			if (da->da_transport != clp->cl_proto &&
-					clp->cl_proto != XPRT_TRANSPORT_TCP_TLS)
-				continue;
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
-				mds_srv->nfs_client->cl_proto ==
-					XPRT_TRANSPORT_TCP_TLS) {
+			if (xprt_args.ident == XPRT_TRANSPORT_TCP &&
+			    clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) {
 				struct sockaddr *addr =
 					(struct sockaddr *)&da->da_addr;
 				struct sockaddr_in *sin =
@@ -944,7 +947,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;
 				xprt_args.servername = servername;
 			}
-			if (da->da_addr.ss_family != clp->cl_addr.ss_family)
+			if (xprt_args.ident != clp->cl_proto)
+				continue;
+			if (xprt_args.dstaddr->sa_family !=
+			    clp->cl_addr.ss_family)
 				continue;
 
 			/**
@@ -958,15 +964,14 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 			if (xprtdata.cred)
 				put_cred(xprtdata.cred);
 		} else {
-			if (da->da_transport == XPRT_TRANSPORT_TCP &&
-				mds_srv->nfs_client->cl_proto ==
-					XPRT_TRANSPORT_TCP_TLS)
-				da->da_transport = XPRT_TRANSPORT_TCP_TLS;
-			clp = nfs4_set_ds_client(mds_srv,
-						&da->da_addr,
-						da->da_addrlen,
-						da->da_transport, timeo,
-						retrans, minor_version);
+			ds_proto = da->da_transport;
+			if (ds_proto == XPRT_TRANSPORT_TCP &&
+			    xprtsec_policy != RPC_XPRTSEC_NONE)
+				ds_proto = XPRT_TRANSPORT_TCP_TLS;
+
+			clp = nfs4_set_ds_client(mds_srv, &da->da_addr,
+						 da->da_addrlen, ds_proto,
+						 timeo, retrans, minor_version);
 			if (IS_ERR(clp))
 				continue;
 
@@ -977,7 +982,6 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
 				clp = ERR_PTR(-EIO);
 				continue;
 			}
-
 		}
 	}
 
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 545148d42dcc..ea6e6168092b 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -189,6 +189,7 @@ static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent,
 			return p;
 
 		kobject_put(&p->kobject);
+		kobject_put(&p->nfs_net_kobj);
 	}
 	return NULL;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c1b54322c412..8a6960500217 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1542,7 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid)
 	release_all_access(stp);
 	if (stp->st_stateowner)
 		nfs4_put_stateowner(stp->st_stateowner);
-	WARN_ON(!list_empty(&stid->sc_cp_list));
+	if (!list_empty(&stid->sc_cp_list))
+		nfs4_free_cpntf_statelist(stid->sc_client->net, stid);
 	kmem_cache_free(stateid_slab, stid);
 }
 
@@ -3486,7 +3487,20 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
 	struct nfsd4_slot *slot = resp->cstate.slot;
 	unsigned int base;
 
-	dprintk("--> %s slot %p\n", __func__, slot);
+	/*
+	 * RFC 5661 Section 2.10.6.1.2:
+	 *
+	 * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT
+	 * modify the reply cache entry for the slot whenever an error is
+	 * returned from SEQUENCE ...
+	 *
+	 * Because nfsd4_store_cache_entry is called only by
+	 * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only
+	 * when a SEQUENCE operation was part of the COMPOUND.
+	 * nfs41_check_op_ordering() ensures SEQUENCE is the first op.
+	 */
+	if (resp->opcnt == 1 && resp->cstate.status != nfs_ok)
+		return;
 
 	slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
 	slot->sl_opcnt = resp->opcnt;
@@ -4349,6 +4363,36 @@ static bool replay_matches_cache(struct svc_rqst *rqstp,
 	return true;
 }
 
+/*
+ * Note that the response is constructed here both for the case
+ * of a new SEQUENCE request and for a replayed SEQUENCE request.
+ * We do not cache SEQUENCE responses as SEQUENCE is idempotent.
+ */
+static void nfsd4_construct_sequence_response(struct nfsd4_session *session,
+					      struct nfsd4_sequence *seq)
+{
+	struct nfs4_client *clp = session->se_client;
+
+	seq->maxslots_response = max(session->se_target_maxslots,
+				     seq->maxslots);
+	seq->target_maxslots = session->se_target_maxslots;
+
+	switch (clp->cl_cb_state) {
+	case NFSD4_CB_DOWN:
+		seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN;
+		break;
+	case NFSD4_CB_FAULT:
+		seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT;
+		break;
+	default:
+		seq->status_flags = 0;
+	}
+	if (!list_empty(&clp->cl_revoked))
+		seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED;
+	if (atomic_read(&clp->cl_admin_revoked))
+		seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED;
+}
+
 __be32
 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		union nfsd4_op_u *u)
@@ -4398,6 +4442,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	dprintk("%s: slotid %d\n", __func__, seq->slotid);
 
 	trace_nfsd_slot_seqid_sequence(clp, seq, slot);
+
+	nfsd4_construct_sequence_response(session, seq);
+
 	status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags);
 	if (status == nfserr_replay_cache) {
 		status = nfserr_seq_misordered;
@@ -4495,23 +4542,6 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	}
 
 out:
-	seq->maxslots = max(session->se_target_maxslots, seq->maxslots);
-	seq->target_maxslots = session->se_target_maxslots;
-
-	switch (clp->cl_cb_state) {
-	case NFSD4_CB_DOWN:
-		seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN;
-		break;
-	case NFSD4_CB_FAULT:
-		seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT;
-		break;
-	default:
-		seq->status_flags = 0;
-	}
-	if (!list_empty(&clp->cl_revoked))
-		seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED;
-	if (atomic_read(&clp->cl_admin_revoked))
-		seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED;
 	trace_nfsd_seq4_status(rqstp, seq);
 out_no_session:
 	if (conn)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 6040a6145dad..67bb9c0b9fcb 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -5073,7 +5073,7 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
 		return nfserr;
 	/* Note slotid's are numbered from zero: */
 	/* sr_highest_slotid */
-	nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots - 1);
+	nfserr = nfsd4_encode_slotid4(xdr, seq->maxslots_response - 1);
 	if (nfserr != nfs_ok)
 		return nfserr;
 	/* sr_target_highest_slotid */
@@ -5925,8 +5925,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
 		 */
 		warn_on_nonidempotent_op(op);
 		xdr_truncate_encode(xdr, op_status_offset + XDR_UNIT);
-	}
-	if (so) {
+	} else if (so) {
 		int len = xdr->buf->len - (op_status_offset + XDR_UNIT);
 
 		so->so_replay.rp_status = op->status;
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index f19320018639..b752433c3c2c 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -458,6 +458,7 @@ enum {
 #define NFSD4_2_SUPPORTED_ATTRS_WORD2 \
 	(NFSD4_1_SUPPORTED_ATTRS_WORD2 | \
 	FATTR4_WORD2_MODE_UMASK | \
+	FATTR4_WORD2_CLONE_BLKSIZE | \
 	NFSD4_2_SECURITY_ATTRS | \
 	FATTR4_WORD2_XATTR_SUPPORT | \
 	FATTR4_WORD2_TIME_DELEG_ACCESS | \
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 3eb724ec9566..ed85dd43da18 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -269,9 +269,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net,
 				dentry);
 	}
 
-	fhp->fh_dentry = dentry;
-	fhp->fh_export = exp;
-
 	switch (fhp->fh_maxsize) {
 	case NFS4_FHSIZE:
 		if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOATOMIC_ATTR)
@@ -293,6 +290,9 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net,
 			goto out;
 	}
 
+	fhp->fh_dentry = dentry;
+	fhp->fh_export = exp;
+
 	return 0;
 out:
 	exp_put(exp);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index ee0570cbdd9e..1ce8e12ae335 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -574,8 +574,9 @@ struct nfsd4_sequence {
 	struct nfs4_sessionid	sessionid;		/* request/response */
 	u32			seqid;			/* request/response */
 	u32			slotid;			/* request/response */
-	u32			maxslots;		/* request/response */
+	u32			maxslots;		/* request */
 	u32			cachethis;		/* request */
+	u32			maxslots_response;	/* response */
 	u32			target_maxslots;	/* response */
 	u32			status_flags;		/* response */
 };
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index f15ca6fc400d..deee16bc9d4e 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2768,7 +2768,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
 
 	if (sci->sc_task) {
 		wake_up(&sci->sc_wait_daemon);
-		kthread_stop(sci->sc_task);
+		if (kthread_stop(sci->sc_task)) {
+			spin_lock(&sci->sc_state_lock);
+			sci->sc_task = NULL;
+			timer_shutdown_sync(&sci->sc_timer);
+			spin_unlock(&sci->sc_state_lock);
+		}
 	}
 
 	spin_lock(&sci->sc_state_lock);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 176281112273..501889856461 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde)
 	}
 }
 
+static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent)
+{
+	rb_erase(&pde->subdir_node, &parent->subdir);
+	RB_CLEAR_NODE(&pde->subdir_node);
+}
+
 /*
  * Remove a /proc entry and free it if it's not currently in use.
  */
@@ -720,7 +726,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 			WARN(1, "removing permanent /proc entry '%s'", de->name);
 			de = NULL;
 		} else {
-			rb_erase(&de->subdir_node, &parent->subdir);
+			pde_erase(de, parent);
 			if (S_ISDIR(de->mode))
 				parent->nlink--;
 		}
@@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 			root->parent->name, root->name);
 		return -EINVAL;
 	}
-	rb_erase(&root->subdir_node, &parent->subdir);
+	pde_erase(root, parent);
 
 	de = root;
 	while (1) {
@@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 					next->parent->name, next->name);
 				return -EINVAL;
 			}
-			rb_erase(&next->subdir_node, &de->subdir);
+			pde_erase(next, de);
 			de = next;
 			continue;
 		}
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index b8ac7b7faf61..018055fd2cdb 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -388,11 +388,11 @@ out:
 			 * lease. Release one here, and the second below.
 			 */
 			cfid->has_lease = false;
-			kref_put(&cfid->refcount, smb2_close_cached_fid);
+			close_cached_dir(cfid);
 		}
 		spin_unlock(&cfids->cfid_list_lock);
 
-		kref_put(&cfid->refcount, smb2_close_cached_fid);
+		close_cached_dir(cfid);
 	} else {
 		*ret_cfid = cfid;
 		atomic_inc(&tcon->num_remote_opens);
@@ -438,12 +438,14 @@ int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
 
 static void
 smb2_close_cached_fid(struct kref *ref)
+__releases(&cfid->cfids->cfid_list_lock)
 {
 	struct cached_fid *cfid = container_of(ref, struct cached_fid,
 					       refcount);
 	int rc;
 
-	spin_lock(&cfid->cfids->cfid_list_lock);
+	lockdep_assert_held(&cfid->cfids->cfid_list_lock);
+
 	if (cfid->on_list) {
 		list_del(&cfid->entry);
 		cfid->on_list = false;
@@ -478,7 +480,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon,
 	spin_lock(&cfid->cfids->cfid_list_lock);
 	if (cfid->has_lease) {
 		cfid->has_lease = false;
-		kref_put(&cfid->refcount, smb2_close_cached_fid);
+		close_cached_dir(cfid);
 	}
 	spin_unlock(&cfid->cfids->cfid_list_lock);
 	close_cached_dir(cfid);
@@ -487,7 +489,7 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon,
 
 void close_cached_dir(struct cached_fid *cfid)
 {
-	kref_put(&cfid->refcount, smb2_close_cached_fid);
+	kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock);
 }
 
 /*
@@ -596,7 +598,7 @@ cached_dir_offload_close(struct work_struct *work)
 
 	WARN_ON(cfid->on_list);
 
-	kref_put(&cfid->refcount, smb2_close_cached_fid);
+	close_cached_dir(cfid);
 	cifs_put_tcon(tcon, netfs_trace_tcon_ref_put_cached_close);
 }
 
@@ -762,7 +764,7 @@ static void cfids_laundromat_worker(struct work_struct *work)
 			 * Drop the ref-count from above, either the lease-ref (if there
 			 * was one) or the extra one acquired.
 			 */
-			kref_put(&cfid->refcount, smb2_close_cached_fid);
+			close_cached_dir(cfid);
 	}
 	queue_delayed_work(cfid_put_wq, &cfids->laundromat_work,
 			   dir_cache_timeout * HZ);
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index e60927b2a7c8..0f894d09157b 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1435,12 +1435,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 			cifs_errorf(fc, "Unknown error parsing devname\n");
 			goto cifs_parse_mount_err;
 		}
+		kfree(ctx->source);
 		ctx->source = smb3_fs_context_fullpath(ctx, '/');
 		if (IS_ERR(ctx->source)) {
 			ctx->source = NULL;
 			cifs_errorf(fc, "OOM when copying UNC string\n");
 			goto cifs_parse_mount_err;
 		}
+		kfree(fc->source);
 		fc->source = kstrdup(ctx->source, GFP_KERNEL);
 		if (fc->source == NULL) {
 			cifs_errorf(fc, "OOM when copying UNC string\n");
@@ -1468,7 +1470,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 			break;
 		}
 
-		if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) >
+		if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) ==
 		    CIFS_MAX_USERNAME_LEN) {
 			pr_warn("username too long\n");
 			goto cifs_parse_mount_err;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 09e3fc81d7cb..69cb81fa0d3a 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -1294,6 +1294,8 @@ static int smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	smb2_to_name = cifs_convert_path_to_utf16(to_name, cifs_sb);
 	if (smb2_to_name == NULL) {
 		rc = -ENOMEM;
+		if (cfile)
+			cifsFileInfo_put(cfile);
 		goto smb2_rename_path;
 	}
 	in_iov.iov_base = smb2_to_name;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index b0739a2661bf..8b4a4573e9c3 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4054,9 +4054,12 @@ replay_again:
 
 		smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base;
 
-		smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset),
-				le32_to_cpu(smb_rsp->OutputBufferLength), &rsp_iov,
+		rc = smb2_validate_iov(le16_to_cpu(smb_rsp->OutputBufferOffset),
+				le32_to_cpu(smb_rsp->OutputBufferLength),
+				&rsp_iov,
 				sizeof(struct file_notify_information));
+		if (rc)
+			goto cnotify_exit;
 
 		*out_data = kmemdup((char *)smb_rsp + le16_to_cpu(smb_rsp->OutputBufferOffset),
 				le32_to_cpu(smb_rsp->OutputBufferLength), GFP_KERNEL);
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 85a4c55b61b8..c6c428c2e08d 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -290,6 +290,9 @@ static void smbd_disconnect_rdma_connection(struct smbdirect_socket *sc)
 		break;
 
 	case SMBDIRECT_SOCKET_CREATED:
+		sc->status = SMBDIRECT_SOCKET_DISCONNECTED;
+		break;
+
 	case SMBDIRECT_SOCKET_CONNECTED:
 		sc->status = SMBDIRECT_SOCKET_ERROR;
 		break;
diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
index 051cd9dbba13..915cedde5d66 100644
--- a/fs/smb/client/transport.c
+++ b/fs/smb/client/transport.c
@@ -830,7 +830,7 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 		if (!server || server->terminate)
 			continue;
 
-		if (CIFS_CHAN_NEEDS_RECONNECT(ses, i))
+		if (CIFS_CHAN_NEEDS_RECONNECT(ses, cur))
 			continue;
 
 		/*
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 7d86553fcc7c..e2be9a496154 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -334,6 +334,9 @@ smb_direct_disconnect_rdma_connection(struct smbdirect_socket *sc)
 		break;
 
 	case SMBDIRECT_SOCKET_CREATED:
+		sc->status = SMBDIRECT_SOCKET_DISCONNECTED;
+		break;
+
 	case SMBDIRECT_SOCKET_CONNECTED:
 		sc->status = SMBDIRECT_SOCKET_ERROR;
 		break;
@@ -1883,6 +1886,7 @@ static int smb_direct_accept_client(struct smbdirect_socket *sc)
 static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc)
 {
 	struct smbdirect_recv_io *recvmsg;
+	bool recv_posted = false;
 	int ret;
 
 	WARN_ON_ONCE(sc->status != SMBDIRECT_SOCKET_CREATED);
@@ -1899,6 +1903,7 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc)
 		pr_err("Can't post recv: %d\n", ret);
 		goto out_err;
 	}
+	recv_posted = true;
 
 	ret = smb_direct_accept_client(sc);
 	if (ret) {
@@ -1908,7 +1913,14 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc)
 
 	return 0;
 out_err:
-	put_recvmsg(sc, recvmsg);
+	/*
+	 * If the recv was never posted, return it to the free list.
+	 * If it was posted, leave it alone so disconnect teardown can
+	 * drain the QP and complete it (flush) and the completion path
+	 * will unmap it exactly once.
+	 */
+	if (!recv_posted)
+		put_recvmsg(sc, recvmsg);
 	return ret;
 }
 
@@ -2606,7 +2618,7 @@ void ksmbd_rdma_destroy(void)
 	}
 }
 
-bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
+static bool ksmbd_find_rdma_capable_netdev(struct net_device *netdev)
 {
 	struct smb_direct_device *smb_dev;
 	int i;
@@ -2648,6 +2660,28 @@ out:
 	return rdma_capable;
 }
 
+bool ksmbd_rdma_capable_netdev(struct net_device *netdev)
+{
+	struct net_device *lower_dev;
+	struct list_head *iter;
+
+	if (ksmbd_find_rdma_capable_netdev(netdev))
+		return true;
+
+	/* check if netdev is bridge or VLAN */
+	if (netif_is_bridge_master(netdev) ||
+	    netdev->priv_flags & IFF_802_1Q_VLAN)
+		netdev_for_each_lower_dev(netdev, lower_dev, iter)
+			if (ksmbd_find_rdma_capable_netdev(lower_dev))
+				return true;
+
+	/* check if netdev is IPoIB safely without layer violation */
+	if (netdev->type == ARPHRD_INFINIBAND)
+		return true;
+
+	return false;
+}
+
 static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = {
 	.prepare	= smb_direct_prepare,
 	.disconnect	= smb_direct_disconnect,
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index 7a1e3dcc2cde..d2e391c29464 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -290,8 +290,11 @@ static int ksmbd_kthread_fn(void *p)
 			}
 		}
 		up_read(&conn_list_lock);
-		if (ret == -EAGAIN)
+		if (ret == -EAGAIN) {
+			/* Per-IP limit hit: release the just-accepted socket. */
+			sock_release(client_sk);
 			continue;
+		}
 
 skip_max_ip_conns_limit:
 		if (server_conf.max_connections &&
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index ee49f20875af..6917de832191 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -726,8 +726,10 @@ xfs_trim_rtgroup_extents(
 			break;
 		}
 
-		if (!tr.queued)
+		if (!tr.queued) {
+			kfree(tr.extents);
 			break;
+		}
 
 		/*
 		 * We hand the extent list to the discard function here so the
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d3f6e3e42a11..490e12cb99be 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1091,6 +1091,29 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
 };
 #endif /* CONFIG_XFS_RT */
 
+#ifdef DEBUG
+static void
+xfs_check_atomic_cow_conversion(
+	struct xfs_inode		*ip,
+	xfs_fileoff_t			offset_fsb,
+	xfs_filblks_t			count_fsb,
+	const struct xfs_bmbt_irec	*cmap)
+{
+	struct xfs_iext_cursor		icur;
+	struct xfs_bmbt_irec		cmap2 = { };
+
+	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap2))
+		xfs_trim_extent(&cmap2, offset_fsb, count_fsb);
+
+	ASSERT(cmap2.br_startoff == cmap->br_startoff);
+	ASSERT(cmap2.br_blockcount == cmap->br_blockcount);
+	ASSERT(cmap2.br_startblock == cmap->br_startblock);
+	ASSERT(cmap2.br_state == cmap->br_state);
+}
+#else
+# define xfs_check_atomic_cow_conversion(...)	((void)0)
+#endif
+
 static int
 xfs_atomic_write_cow_iomap_begin(
 	struct inode		*inode,
@@ -1102,9 +1125,10 @@ xfs_atomic_write_cow_iomap_begin(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	const xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
-	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
+	const xfs_fileoff_t	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	const xfs_fileoff_t	end_fsb = XFS_B_TO_FSB(mp, offset + length);
+	const xfs_filblks_t	count_fsb = end_fsb - offset_fsb;
+	xfs_filblks_t		hole_count_fsb;
 	int			nmaps = 1;
 	xfs_filblks_t		resaligned;
 	struct xfs_bmbt_irec	cmap;
@@ -1130,7 +1154,7 @@ xfs_atomic_write_cow_iomap_begin(
 		return -EAGAIN;
 
 	trace_xfs_iomap_atomic_write_cow(ip, offset, length);
-
+retry:
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
 	if (!ip->i_cowfp) {
@@ -1141,14 +1165,22 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+
+		/*
+		 * cmap could extend outside the write range due to previous
+		 * speculative preallocations.  We must trim cmap to the write
+		 * range because the cow fork treats written mappings to mean
+		 * "write in progress".
+		 */
 		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
-	end_fsb = cmap.br_startoff;
-	count_fsb = end_fsb - offset_fsb;
+	hole_count_fsb = cmap.br_startoff - offset_fsb;
 
-	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
+	resaligned = xfs_aligned_fsb_count(offset_fsb, hole_count_fsb,
 			xfs_get_cowextsz_hint(ip));
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
@@ -1169,8 +1201,10 @@ xfs_atomic_write_cow_iomap_begin(
 	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
 		cmap.br_startoff = end_fsb;
 	if (cmap.br_startoff <= offset_fsb) {
-		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		xfs_trans_cancel(tp);
+		if (isnullstartblock(cmap.br_startblock))
+			goto convert_delay;
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
 		goto found;
 	}
 
@@ -1182,7 +1216,7 @@ xfs_atomic_write_cow_iomap_begin(
 	 * atomic writes to that same range will be aligned (and don't require
 	 * this COW-based method).
 	 */
-	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+	error = xfs_bmapi_write(tp, ip, offset_fsb, hole_count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC |
 			XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps);
 	if (error) {
@@ -1195,21 +1229,43 @@ xfs_atomic_write_cow_iomap_begin(
 	if (error)
 		goto out_unlock;
 
+	/*
+	 * cmap could map more blocks than the range we passed into bmapi_write
+	 * because of EXTSZALIGN or adjacent pre-existing unwritten mappings
+	 * that were merged.  Trim cmap to the original write range so that we
+	 * don't convert more than we were asked to do for this write.
+	 */
+	xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+
 found:
 	if (cmap.br_state != XFS_EXT_NORM) {
-		error = xfs_reflink_convert_cow_locked(ip, offset_fsb,
-				count_fsb);
+		error = xfs_reflink_convert_cow_locked(ip, cmap.br_startoff,
+				cmap.br_blockcount);
 		if (error)
 			goto out_unlock;
 		cmap.br_state = XFS_EXT_NORM;
+		xfs_check_atomic_cow_conversion(ip, offset_fsb, count_fsb,
+				&cmap);
 	}
 
-	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
-	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
+	trace_xfs_iomap_found(ip, offset, length, XFS_COW_FORK, &cmap);
 	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);
 
+convert_delay:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_convert_delalloc(ip, XFS_COW_FORK, offset, iomap,
+			NULL);
+	if (error)
+		return error;
+
+	/*
+	 * Try the lookup again, because the delalloc conversion might have
+	 * turned the COW mapping into unwritten, but we need it to be in
+	 * written state.
+	 */
+	goto retry;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 040402240807..ef7a931ebde5 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -615,7 +615,7 @@ xfs_select_open_zone_mru(
 	lockdep_assert_held(&zi->zi_open_zones_lock);
 
 	list_for_each_entry_reverse(oz, &zi->zi_open_zones, oz_entry)
-		if (xfs_try_use_zone(zi, file_hint, oz, false))
+		if (xfs_try_use_zone(zi, file_hint, oz, XFS_ZONE_ALLOC_OK))
 			return oz;
 
 	cond_resched_lock(&zi->zi_open_zones_lock);
@@ -1249,8 +1249,10 @@ xfs_mount_zones(
 
 		while ((rtg = xfs_rtgroup_next(mp, rtg))) {
 			error = xfs_init_zone(&iz, rtg, NULL);
-			if (error)
+			if (error) {
+				xfs_rtgroup_rele(rtg);
 				goto out_free_zone_info;
+			}
 		}
 	}