Merge tag 'kvm-s390-master-6.0-2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

More pci fixes
Fix for a code analyser warning

31 files changed, 276 insertions, 216 deletions

diff --git a/fs/afs/flock.c b/fs/afs/flock.c
index c4210a3964d8..bbcc5afd1576 100644
--- a/fs/afs/flock.c
+++ b/fs/afs/flock.c
@@ -76,7 +76,7 @@ void afs_lock_op_done(struct afs_call *call)
 	if (call->error == 0) {
 		spin_lock(&vnode->lock);
 		trace_afs_flock_ev(vnode, NULL, afs_flock_timestamp, 0);
-		vnode->locked_at = call->reply_time;
+		vnode->locked_at = call->issue_time;
 		afs_schedule_lock_extension(vnode);
 		spin_unlock(&vnode->lock);
 	}
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 4943413d9c5f..7d37f63ef0f0 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -131,7 +131,7 @@ bad:
 
 static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry)
 {
-	return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry;
+	return ktime_divns(call->issue_time, NSEC_PER_SEC) + expiry;
 }
 
 static void xdr_decode_AFSCallBack(const __be32 **_bp,
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 64ad55494349..723d162078a3 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -137,7 +137,6 @@ struct afs_call {
 	bool			need_attention;	/* T if RxRPC poked us */
 	bool			async;		/* T if asynchronous */
 	bool			upgrade;	/* T to request service upgrade */
-	bool			have_reply_time; /* T if have got reply_time */
 	bool			intr;		/* T if interruptible */
 	bool			unmarshalling_error; /* T if an unmarshalling error occurred */
 	u16			service_id;	/* Actual service ID (after upgrade) */
@@ -151,7 +150,7 @@ struct afs_call {
 		} __attribute__((packed));
 		__be64		tmp64;
 	};
-	ktime_t			reply_time;	/* Time of first reply packet */
+	ktime_t			issue_time;	/* Time of issue of operation */
 };
 
 struct afs_call_type {
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 933e67fcdab1..805328ca5428 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -69,6 +69,7 @@ int afs_abort_to_error(u32 abort_code)
 		/* Unified AFS error table */
 	case UAEPERM:			return -EPERM;
 	case UAENOENT:			return -ENOENT;
+	case UAEAGAIN:			return -EAGAIN;
 	case UAEACCES:			return -EACCES;
 	case UAEBUSY:			return -EBUSY;
 	case UAEEXIST:			return -EEXIST;
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index d5c4785c862d..eccc3cd0cb70 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -351,6 +351,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp)
 	if (call->max_lifespan)
 		rxrpc_kernel_set_max_life(call->net->socket, rxcall,
 					  call->max_lifespan);
+	call->issue_time = ktime_get_real();
 
 	/* send the request */
 	iov[0].iov_base	= call->request;
@@ -501,12 +502,6 @@ static void afs_deliver_to_call(struct afs_call *call)
 			return;
 		}
 
-		if (!call->have_reply_time &&
-		    rxrpc_kernel_get_reply_time(call->net->socket,
-						call->rxcall,
-						&call->reply_time))
-			call->have_reply_time = true;
-
 		ret = call->type->deliver(call);
 		state = READ_ONCE(call->state);
 		if (ret == 0 && call->unmarshalling_error)
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index fdc7d675b4b0..11571cca86c1 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -232,8 +232,7 @@ static void xdr_decode_YFSCallBack(const __be32 **_bp,
 	struct afs_callback *cb = &scb->callback;
 	ktime_t cb_expiry;
 
-	cb_expiry = call->reply_time;
-	cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100);
+	cb_expiry = ktime_add(call->issue_time, xdr_to_u64(x->expiration_time) * 100);
 	cb->expires_at	= ktime_divns(cb_expiry, NSEC_PER_SEC);
 	scb->have_cb	= true;
 	*_bp += xdr_size(x);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9ef162dbd4bc..df8c99c99df9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1088,8 +1088,6 @@ struct btrfs_fs_info {
 
 	spinlock_t zone_active_bgs_lock;
 	struct list_head zone_active_bgs;
-	/* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */
-	wait_queue_head_t zone_finish_wait;
 
 	/* Updates are not protected by any lock */
 	struct btrfs_commit_stats commit_stats;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 820b1f1e6b67..1af28b066b42 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3068,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	init_waitqueue_head(&fs_info->transaction_blocked_wait);
 	init_waitqueue_head(&fs_info->async_submit_wait);
 	init_waitqueue_head(&fs_info->delayed_iputs_wait);
-	init_waitqueue_head(&fs_info->zone_finish_wait);
 
 	/* Usable values until the real ones are cached from the superblock */
 	fs_info->nodesize = 4096;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ad250892028d..1372210869b1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
 			done_offset = end;
 
 		if (done_offset == start) {
-			struct btrfs_fs_info *info = inode->root->fs_info;
-
-			wait_var_event(&info->zone_finish_wait,
-				       !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags));
+			wait_on_bit_io(&inode->root->fs_info->flags,
+				       BTRFS_FS_NEED_ZONE_FINISH,
+				       TASK_UNINTERRUPTIBLE);
 			continue;
 		}
 
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d0cbeb7ae81c..435559ba94fa 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags)
 	ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
-		return SZ_1G;
+		return BTRFS_MAX_DATA_CHUNK_SIZE;
 	else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		return SZ_32M;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 064ab2a79c80..f63ff91e2883 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5267,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl,
 				       ctl->stripe_size);
 	}
 
+	/* Stripe size should not go beyond 1G. */
+	ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G);
+
 	/* Align to BTRFS_STRIPE_LEN */
 	ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN);
 	ctl->chunk_size = ctl->stripe_size * data_stripes;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b150b07ba1a7..62e7007a7e46 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
 	 * increase the metadata reservation even if it increases the number of
 	 * extents, it is safe to stick with the limit.
+	 *
+	 * With the zoned emulation, we can have non-zoned device on the zoned
+	 * mode. In this case, we don't have a valid max zone append size. So,
+	 * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size.
 	 */
-	zone_info->max_zone_append_size =
-		min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
-		      (u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	if (bdev_is_zoned(bdev)) {
+		zone_info->max_zone_append_size = min_t(u64,
+			(u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	} else {
+		zone_info->max_zone_append_size =
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT;
+	}
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
  * offset.
  */
 static int calculate_alloc_pointer(struct btrfs_block_group *cache,
-				   u64 *offset_ret)
+				   u64 *offset_ret, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_root *root;
@@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache,
 	int ret;
 	u64 length;
 
+	/*
+	 * Avoid  tree lookups for a new block group, there's no use for it.
+	 * It must always be 0.
+	 *
+	 * Also, we have a lock chain of extent buffer lock -> chunk mutex.
+	 * For new a block group, this function is called from
+	 * btrfs_make_block_group() which is already taking the chunk mutex.
+	 * Thus, we cannot call calculate_alloc_pointer() which takes extent
+	 * buffer locks to avoid deadlock.
+	 */
+	if (new) {
+		*offset_ret = 0;
+		return 0;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		else
 			num_conventional++;
 
+		/*
+		 * Consider a zone as active if we can allow any number of
+		 * active zones.
+		 */
+		if (!device->zone_info->max_active_zones)
+			__set_bit(i, active);
+
 		if (!is_sequential) {
 			alloc_offsets[i] = WP_CONVENTIONAL;
 			continue;
@@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			__set_bit(i, active);
 			break;
 		}
-
-		/*
-		 * Consider a zone as active if we can allow any number of
-		 * active zones.
-		 */
-		if (!device->zone_info->max_active_zones)
-			__set_bit(i, active);
 	}
 
 	if (num_sequential > 0)
 		cache->seq_zone = true;
 
 	if (num_conventional > 0) {
-		/*
-		 * Avoid calling calculate_alloc_pointer() for new BG. It
-		 * is no use for new BG. It must be always 0.
-		 *
-		 * Also, we have a lock chain of extent buffer lock ->
-		 * chunk mutex.  For new BG, this function is called from
-		 * btrfs_make_block_group() which is already taking the
-		 * chunk mutex. Thus, we cannot call
-		 * calculate_alloc_pointer() which takes extent buffer
-		 * locks to avoid deadlock.
-		 */
-
 		/* Zone capacity is always zone size in emulation */
 		cache->zone_capacity = cache->length;
-		if (new) {
-			cache->alloc_offset = 0;
-			goto out;
-		}
-		ret = calculate_alloc_pointer(cache, &last_alloc);
-		if (ret || map->num_stripes == num_conventional) {
-			if (!ret)
-				cache->alloc_offset = last_alloc;
-			else
-				btrfs_err(fs_info,
+		ret = calculate_alloc_pointer(cache, &last_alloc, new);
+		if (ret) {
+			btrfs_err(fs_info,
 			"zoned: failed to determine allocation offset of bg %llu",
-					  cache->start);
+				  cache->start);
+			goto out;
+		} else if (map->num_stripes == num_conventional) {
+			cache->alloc_offset = last_alloc;
+			cache->zone_is_active = 1;
 			goto out;
 		}
 	}
@@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		goto out;
 	}
 
-	if (cache->zone_is_active) {
-		btrfs_get_block_group(cache);
-		spin_lock(&fs_info->zone_active_bgs_lock);
-		list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs);
-		spin_unlock(&fs_info->zone_active_bgs_lock);
-	}
-
 out:
 	if (cache->alloc_offset > fs_info->zone_size) {
 		btrfs_err(fs_info,
@@ -1526,10 +1528,16 @@ out:
 		ret = -EIO;
 	}
 
-	if (!ret)
+	if (!ret) {
 		cache->meta_write_pointer = cache->alloc_offset + cache->start;
-
-	if (ret) {
+		if (cache->zone_is_active) {
+			btrfs_get_block_group(cache);
+			spin_lock(&fs_info->zone_active_bgs_lock);
+			list_add_tail(&cache->active_bg_list,
+				      &fs_info->zone_active_bgs);
+			spin_unlock(&fs_info->zone_active_bgs_lock);
+		}
+	} else {
 		kfree(cache->physical_map);
 		cache->physical_map = NULL;
 	}
@@ -2007,8 +2015,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	/* For active_bg_list */
 	btrfs_put_block_group(block_group);
 
-	clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
-	wake_up_all(&fs_info->zone_finish_wait);
+	clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
 
 	return 0;
 }
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 6cba2c6de2f9..2ad58c465208 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -111,6 +111,7 @@ struct cachefiles_cache {
 	char				*tag;		/* cache binding tag */
 	refcount_t			unbind_pincount;/* refcount to do daemon unbind */
 	struct xarray			reqs;		/* xarray of pending on-demand requests */
+	unsigned long			req_id_next;
 	struct xarray			ondemand_ids;	/* xarray for ondemand_id allocation */
 	u32				ondemand_id_next;
 };
diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c
index 1fee702d5529..0254ed39f68c 100644
--- a/fs/cachefiles/ondemand.c
+++ b/fs/cachefiles/ondemand.c
@@ -158,9 +158,13 @@ int cachefiles_ondemand_copen(struct cachefiles_cache *cache, char *args)
 
 	/* fail OPEN request if daemon reports an error */
 	if (size < 0) {
-		if (!IS_ERR_VALUE(size))
-			size = -EINVAL;
-		req->error = size;
+		if (!IS_ERR_VALUE(size)) {
+			req->error = -EINVAL;
+			ret = -EINVAL;
+		} else {
+			req->error = size;
+			ret = 0;
+		}
 		goto out;
 	}
 
@@ -238,14 +242,19 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	unsigned long id = 0;
 	size_t n;
 	int ret = 0;
-	XA_STATE(xas, &cache->reqs, 0);
+	XA_STATE(xas, &cache->reqs, cache->req_id_next);
 
 	/*
-	 * Search for a request that has not ever been processed, to prevent
-	 * requests from being processed repeatedly.
+	 * Cyclically search for a request that has not ever been processed,
+	 * to prevent requests from being processed repeatedly, and make
+	 * request distribution fair.
 	 */
 	xa_lock(&cache->reqs);
 	req = xas_find_marked(&xas, UINT_MAX, CACHEFILES_REQ_NEW);
+	if (!req && cache->req_id_next > 0) {
+		xas_set(&xas, 0);
+		req = xas_find_marked(&xas, cache->req_id_next - 1, CACHEFILES_REQ_NEW);
+	}
 	if (!req) {
 		xa_unlock(&cache->reqs);
 		return 0;
@@ -260,6 +269,7 @@ ssize_t cachefiles_ondemand_daemon_read(struct cachefiles_cache *cache,
 	}
 
 	xas_clear_mark(&xas, CACHEFILES_REQ_NEW);
+	cache->req_id_next = xas.xa_index + 1;
 	xa_unlock(&cache->reqs);
 
 	id = xas.xa_index;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f54d8bf2732a..8042d7280dec 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1248,6 +1248,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
 	lock_two_nondirectories(target_inode, src_inode);
 
 	cifs_dbg(FYI, "about to flush pages\n");
+
+	rc = filemap_write_and_wait_range(src_inode->i_mapping, off,
+					  off + len - 1);
+	if (rc)
+		goto out;
+
 	/* should we flush first and last page first */
 	truncate_inode_pages(&target_inode->i_data, 0);
 
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 81f4c15936d0..5b4a7a32bdc5 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -153,6 +153,6 @@ extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
 /* when changing internal version - update following two lines at same time */
-#define SMB3_PRODUCT_BUILD 38
-#define CIFS_VERSION   "2.38"
+#define SMB3_PRODUCT_BUILD 39
+#define CIFS_VERSION   "2.39"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a0a06b6f252b..7ae6f2c08153 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -702,9 +702,6 @@ cifs_readv_from_socket(struct TCP_Server_Info *server, struct msghdr *smb_msg)
 	int length = 0;
 	int total_read;
 
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
-
 	for (total_read = 0; msg_data_left(smb_msg); total_read += length) {
 		try_to_freeze();
 
@@ -760,7 +757,7 @@ int
 cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 		      unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct kvec iov = {.iov_base = buf, .iov_len = to_read};
 	iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read);
 
@@ -770,15 +767,13 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf,
 ssize_t
 cifs_discard_from_socket(struct TCP_Server_Info *server, size_t to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 
 	/*
 	 *  iov_iter_discard already sets smb_msg.type and count and iov_offset
 	 *  and cifs_readv_from_socket sets msg_control and msg_controllen
 	 *  so little to initialize in struct msghdr
 	 */
-	smb_msg.msg_name = NULL;
-	smb_msg.msg_namelen = 0;
 	iov_iter_discard(&smb_msg.msg_iter, READ, to_read);
 
 	return cifs_readv_from_socket(server, &smb_msg);
@@ -788,7 +783,7 @@ int
 cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page,
 	unsigned int page_offset, unsigned int to_read)
 {
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	struct bio_vec bv = {
 		.bv_page = page, .bv_len = to_read, .bv_offset = page_offset};
 	iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read);
@@ -2350,7 +2345,9 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	ses = tcon->ses;
 	cifs_dbg(FYI, "%s: tc_count=%d\n", __func__, tcon->tc_count);
 	spin_lock(&cifs_tcp_ses_lock);
+	spin_lock(&tcon->tc_lock);
 	if (--tcon->tc_count > 0) {
+		spin_unlock(&tcon->tc_lock);
 		spin_unlock(&cifs_tcp_ses_lock);
 		return;
 	}
@@ -2359,6 +2356,7 @@ cifs_put_tcon(struct cifs_tcon *tcon)
 	WARN_ON(tcon->tc_count < 0);
 
 	list_del_init(&tcon->tcon_list);
+	spin_unlock(&tcon->tc_lock);
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	/* cancel polling of interfaces */
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index fa738adc031f..6f38b134a346 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3575,6 +3575,9 @@ static ssize_t __cifs_writev(
 
 ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from)
 {
+	struct file *file = iocb->ki_filp;
+
+	cifs_revalidate_mapping(file->f_inode);
 	return __cifs_writev(iocb, from, true);
 }
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4810bd62266a..421be43af425 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1600,17 +1600,8 @@ smb2_copychunk_range(const unsigned int xid,
 	int chunks_copied = 0;
 	bool chunk_sizes_updated = false;
 	ssize_t bytes_written, total_bytes_written = 0;
-	struct inode *inode;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
-
-	/*
-	 * We need to flush all unwritten data before we can send the
-	 * copychunk ioctl to the server.
-	 */
-	inode = d_inode(trgtfile->dentry);
-	filemap_write_and_wait(inode->i_mapping);
-
 	if (pcchunk == NULL)
 		return -ENOMEM;
 
@@ -3678,39 +3669,50 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
 {
 	int rc;
 	unsigned int xid;
-	struct inode *inode;
+	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
-	struct cifsInodeInfo *cifsi;
+	struct cifsInodeInfo *cifsi = CIFS_I(inode);
 	__le64 eof;
+	loff_t old_eof;
 
 	xid = get_xid();
 
-	inode = d_inode(cfile->dentry);
-	cifsi = CIFS_I(inode);
+	inode_lock(inode);
 
-	if (off >= i_size_read(inode) ||
-	    off + len >= i_size_read(inode)) {
+	old_eof = i_size_read(inode);
+	if ((off >= old_eof) ||
+	    off + len >= old_eof) {
 		rc = -EINVAL;
 		goto out;
 	}
 
+	filemap_invalidate_lock(inode->i_mapping);
+	rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof - 1);
+	if (rc < 0)
+		goto out_2;
+
+	truncate_pagecache_range(inode, off, old_eof);
+
 	rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
-				  i_size_read(inode) - off - len, off);
+				  old_eof - off - len, off);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
-	eof = cpu_to_le64(i_size_read(inode) - len);
+	eof = cpu_to_le64(old_eof - len);
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 			  cfile->fid.volatile_fid, cfile->pid, &eof);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = 0;
 
 	cifsi->server_eof = i_size_read(inode) - len;
 	truncate_setsize(inode, cifsi->server_eof);
 	fscache_resize_cookie(cifs_inode_cookie(inode), cifsi->server_eof);
+out_2:
+	filemap_invalidate_unlock(inode->i_mapping);
  out:
+	inode_unlock(inode);
 	free_xid(xid);
 	return rc;
 }
@@ -3721,34 +3723,47 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
 	int rc;
 	unsigned int xid;
 	struct cifsFileInfo *cfile = file->private_data;
+	struct inode *inode = file_inode(file);
 	__le64 eof;
-	__u64  count;
+	__u64  count, old_eof;
 
 	xid = get_xid();
 
-	if (off >= i_size_read(file->f_inode)) {
+	inode_lock(inode);
+
+	old_eof = i_size_read(inode);
+	if (off >= old_eof) {
 		rc = -EINVAL;
 		goto out;
 	}
 
-	count = i_size_read(file->f_inode) - off;
-	eof = cpu_to_le64(i_size_read(file->f_inode) + len);
+	count = old_eof - off;
+	eof = cpu_to_le64(old_eof + len);
+
+	filemap_invalidate_lock(inode->i_mapping);
+	rc = filemap_write_and_wait_range(inode->i_mapping, off, old_eof + len - 1);
+	if (rc < 0)
+		goto out_2;
+	truncate_pagecache_range(inode, off, old_eof);
 
 	rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
 			  cfile->fid.volatile_fid, cfile->pid, &eof);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
-	rc = smb3_zero_range(file, tcon, off, len, 1);
+	rc = smb3_zero_data(file, tcon, off, len, xid);
 	if (rc < 0)
-		goto out;
+		goto out_2;
 
 	rc = 0;
+out_2:
+	filemap_invalidate_unlock(inode->i_mapping);
  out:
+	inode_unlock(inode);
 	free_xid(xid);
 	return rc;
 }
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 128e44e57528..6352ab32c7e7 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -965,16 +965,17 @@ SMB2_negotiate(const unsigned int xid,
 	} else if (rc != 0)
 		goto neg_exit;
 
+	rc = -EIO;
 	if (strcmp(server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2.1 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb311_operations;
@@ -985,7 +986,7 @@ SMB2_negotiate(const unsigned int xid,
 		if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
 			cifs_server_dbg(VFS,
 				"SMB2 dialect returned but not requested\n");
-			return -EIO;
+			goto neg_exit;
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			server->ops = &smb21_operations;
@@ -999,7 +1000,7 @@ SMB2_negotiate(const unsigned int xid,
 		/* if requested single dialect ensure returned dialect matched */
 		cifs_server_dbg(VFS, "Invalid 0x%x dialect returned: not requested\n",
 				le16_to_cpu(rsp->DialectRevision));
-		return -EIO;
+		goto neg_exit;
 	}
 
 	cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode);
@@ -1017,9 +1018,10 @@ SMB2_negotiate(const unsigned int xid,
 	else {
 		cifs_server_dbg(VFS, "Invalid dialect returned by server 0x%x\n",
 				le16_to_cpu(rsp->DialectRevision));
-		rc = -EIO;
 		goto neg_exit;
 	}
+
+	rc = 0;
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
 	/*
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c2fe035e573b..9a2753e21170 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -194,10 +194,6 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
 
 	*sent = 0;
 
-	smb_msg->msg_name = (struct sockaddr *) &server->dstaddr;
-	smb_msg->msg_namelen = sizeof(struct sockaddr);
-	smb_msg->msg_control = NULL;
-	smb_msg->msg_controllen = 0;
 	if (server->noblocksnd)
 		smb_msg->msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
 	else
@@ -309,7 +305,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	sigset_t mask, oldmask;
 	size_t total_len = 0, sent, size;
 	struct socket *ssocket = server->ssocket;
-	struct msghdr smb_msg;
+	struct msghdr smb_msg = {};
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server)) {
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 3dcf0b8b4e93..232cfdf095ae 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -745,6 +745,28 @@ void debugfs_remove(struct dentry *dentry)
 EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
+ * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it
+ * @name: a pointer to a string containing the name of the item to look up.
+ * @parent: a pointer to the parent dentry of the item.
+ *
+ * This is the equlivant of doing something like
+ * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting
+ * handled for the directory being looked up.
+ */
+void debugfs_lookup_and_remove(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	dentry = debugfs_lookup(name, parent);
+	if (!dentry)
+		return;
+
+	debugfs_remove(dentry);
+	dput(dentry);
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove);
+
+/**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
  * @old_dir: a pointer to the parent dentry for the renamed object. This
  *          should be a directory dentry.
diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c
index 8e01d89c3319..b5fd9d71e67f 100644
--- a/fs/erofs/fscache.c
+++ b/fs/erofs/fscache.c
@@ -222,8 +222,10 @@ static int erofs_fscache_meta_read_folio(struct file *data, struct folio *folio)
 
 	rreq = erofs_fscache_alloc_request(folio_mapping(folio),
 				folio_pos(folio), folio_size(folio));
-	if (IS_ERR(rreq))
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
 		goto out;
+	}
 
 	return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
 				rreq, mdev.m_pa);
@@ -301,8 +303,10 @@ static int erofs_fscache_read_folio(struct file *file, struct folio *folio)
 
 	rreq = erofs_fscache_alloc_request(folio_mapping(folio),
 				folio_pos(folio), folio_size(folio));
-	if (IS_ERR(rreq))
+	if (IS_ERR(rreq)) {
+		ret = PTR_ERR(rreq);
 		goto out_unlock;
+	}
 
 	pstart = mdev.m_pa + (pos - map.m_la);
 	return erofs_fscache_read_folios_async(mdev.m_fscache->cookie,
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index cfee49d33b95..a01cc82795a2 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -195,7 +195,6 @@ struct erofs_workgroup {
 	atomic_t refcount;
 };
 
-#if defined(CONFIG_SMP)
 static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
 						 int val)
 {
@@ -224,34 +223,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
 	return atomic_cond_read_relaxed(&grp->refcount,
 					VAL != EROFS_LOCKED_MAGIC);
 }
-#else
-static inline bool erofs_workgroup_try_to_freeze(struct erofs_workgroup *grp,
-						 int val)
-{
-	preempt_disable();
-	/* no need to spin on UP platforms, let's just disable preemption. */
-	if (val != atomic_read(&grp->refcount)) {
-		preempt_enable();
-		return false;
-	}
-	return true;
-}
-
-static inline void erofs_workgroup_unfreeze(struct erofs_workgroup *grp,
-					    int orig_val)
-{
-	preempt_enable();
-}
-
-static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
-{
-	int v = atomic_read(&grp->refcount);
-
-	/* workgroup is never freezed on uniprocessor systems */
-	DBG_BUGON(v == EROFS_LOCKED_MAGIC);
-	return v;
-}
-#endif	/* !CONFIG_SMP */
 #endif	/* !CONFIG_EROFS_FS_ZIP */
 
 /* we strictly follow PAGE_SIZE and no buffer head yet */
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 572f0b8151ba..d58549ca1df9 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -141,7 +141,7 @@ struct z_erofs_maprecorder {
 	u8  type, headtype;
 	u16 clusterofs;
 	u16 delta[2];
-	erofs_blk_t pblk, compressedlcs;
+	erofs_blk_t pblk, compressedblks;
 	erofs_off_t nextpackoff;
 };
 
@@ -192,7 +192,7 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
-			m->compressedlcs = m->delta[0] &
+			m->compressedblks = m->delta[0] &
 				~Z_EROFS_VLE_DI_D0_CBLKCNT;
 			m->delta[0] = 1;
 		}
@@ -293,7 +293,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
 				DBG_BUGON(1);
 				return -EFSCORRUPTED;
 			}
-			m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+			m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
 			m->delta[0] = 1;
 			return 0;
 		} else if (i + 1 != (int)vcnt) {
@@ -497,7 +497,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return 0;
 	}
 	lcn = m->lcn + 1;
-	if (m->compressedlcs)
+	if (m->compressedblks)
 		goto out;
 
 	err = z_erofs_load_cluster_from_disk(m, lcn, false);
@@ -506,7 +506,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 
 	/*
 	 * If the 1st NONHEAD lcluster has already been handled initially w/o
-	 * valid compressedlcs, which means at least it mustn't be CBLKCNT, or
+	 * valid compressedblks, which means at least it mustn't be CBLKCNT, or
 	 * an internal implemenatation error is detected.
 	 *
 	 * The following code can also handle it properly anyway, but let's
@@ -523,12 +523,12 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		 * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type
 		 * rather than CBLKCNT, it's a 1 lcluster-sized pcluster.
 		 */
-		m->compressedlcs = 1;
+		m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE);
 		break;
 	case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
 		if (m->delta[0] != 1)
 			goto err_bonus_cblkcnt;
-		if (m->compressedlcs)
+		if (m->compressedblks)
 			break;
 		fallthrough;
 	default:
@@ -539,7 +539,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
 		return -EFSCORRUPTED;
 	}
 out:
-	map->m_plen = (u64)m->compressedlcs << lclusterbits;
+	map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE;
 	return 0;
 err_bonus_cblkcnt:
 	erofs_err(m->inode->i_sb,
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 27c720d71b4e..898dd95bc7a7 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -606,6 +606,31 @@ static inline gfp_t nfs_io_gfp_mask(void)
 	return GFP_KERNEL;
 }
 
+/*
+ * Special version of should_remove_suid() that ignores capabilities.
+ */
+static inline int nfs_should_remove_suid(const struct inode *inode)
+{
+	umode_t mode = inode->i_mode;
+	int kill = 0;
+
+	/* suid always must be killed */
+	if (unlikely(mode & S_ISUID))
+		kill = ATTR_KILL_SUID;
+
+	/*
+	 * sgid without any exec bits is just a mandatory locking mark; leave
+	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
+	 */
+	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
+		kill |= ATTR_KILL_SGID;
+
+	if (unlikely(kill && S_ISREG(mode)))
+		return kill;
+
+	return 0;
+}
+
 /* unlink.c */
 extern struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 068c45b3bc1a..6dab9e408372 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -78,10 +78,15 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
 
 	status = nfs4_call_sync(server->client, server, msg,
 				&args.seq_args, &res.seq_res, 0);
-	if (status == 0)
+	if (status == 0) {
+		if (nfs_should_remove_suid(inode)) {
+			spin_lock(&inode->i_lock);
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+			spin_unlock(&inode->i_lock);
+		}
 		status = nfs_post_op_update_inode_force_wcc(inode,
 							    res.falloc_fattr);
-
+	}
 	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE])
 		trace_nfs4_fallocate(inode, &args, status);
 	else
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 82944e14fcea..ee66ffdb985e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1051,22 +1051,31 @@ static void nfs_fill_super(struct super_block *sb, struct nfs_fs_context *ctx)
 	if (ctx->bsize)
 		sb->s_blocksize = nfs_block_size(ctx->bsize, &sb->s_blocksize_bits);
 
-	if (server->nfs_client->rpc_ops->version != 2) {
-		/* The VFS shouldn't apply the umask to mode bits. We will do
-		 * so ourselves when necessary.
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		sb->s_time_gran = 1000;
+		sb->s_time_min = 0;
+		sb->s_time_max = U32_MAX;
+		break;
+	case 3:
+		/*
+		 * The VFS shouldn't apply the umask to mode bits.
+		 * We will do so ourselves when necessary.
 		 */
 		sb->s_flags |= SB_POSIXACL;
 		sb->s_time_gran = 1;
-		sb->s_export_op = &nfs_export_ops;
-	} else
-		sb->s_time_gran = 1000;
-
-	if (server->nfs_client->rpc_ops->version != 4) {
 		sb->s_time_min = 0;
 		sb->s_time_max = U32_MAX;
-	} else {
+		sb->s_export_op = &nfs_export_ops;
+		break;
+	case 4:
+		sb->s_flags |= SB_POSIXACL;
+		sb->s_time_gran = 1;
 		sb->s_time_min = S64_MIN;
 		sb->s_time_max = S64_MAX;
+		if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
+			sb->s_export_op = &nfs_export_ops;
+		break;
 	}
 
 	sb->s_magic = NFS_SUPER_MAGIC;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 1843fa235d9b..f41d24b54fd1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1496,31 +1496,6 @@ void nfs_commit_prepare(struct rpc_task *task, void *calldata)
 	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
 }
 
-/*
- * Special version of should_remove_suid() that ignores capabilities.
- */
-static int nfs_should_remove_suid(const struct inode *inode)
-{
-	umode_t mode = inode->i_mode;
-	int kill = 0;
-
-	/* suid always must be killed */
-	if (unlikely(mode & S_ISUID))
-		kill = ATTR_KILL_SUID;
-
-	/*
-	 * sgid without any exec bits is just a mandatory locking mark; leave
-	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
-	 */
-	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
-		kill |= ATTR_KILL_SGID;
-
-	if (unlikely(kill && S_ISREG(mode)))
-		return kill;
-
-	return 0;
-}
-
 static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
 		struct nfs_fattr *fattr)
 {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 9f486b788ed0..fc17b0ac8729 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -300,6 +300,10 @@ commit_metadata(struct svc_fh *fhp)
 static void
 nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 {
+	/* Ignore mode updates on symlinks */
+	if (S_ISLNK(inode->i_mode))
+		iap->ia_valid &= ~ATTR_MODE;
+
 	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
 		iap->ia_mode &= S_IALLUGO;
@@ -353,7 +357,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int		accmode = NFSD_MAY_SATTR;
 	umode_t		ftype = 0;
 	__be32		err;
-	int		host_err;
+	int		host_err = 0;
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
@@ -391,13 +395,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	dentry = fhp->fh_dentry;
 	inode = d_inode(dentry);
 
-	/* Ignore any mode updates on symlinks */
-	if (S_ISLNK(inode->i_mode))
-		iap->ia_valid &= ~ATTR_MODE;
-
-	if (!iap->ia_valid)
-		return 0;
-
 	nfsd_sanitize_attrs(inode, iap);
 
 	if (check_guard && guardtime != inode->i_ctime.tv_sec)
@@ -448,8 +445,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			goto out_unlock;
 	}
 
-	iap->ia_valid |= ATTR_CTIME;
-	host_err = notify_change(&init_user_ns, dentry, iap, NULL);
+	if (iap->ia_valid) {
+		iap->ia_valid |= ATTR_CTIME;
+		host_err = notify_change(&init_user_ns, dentry, iap, NULL);
+	}
 
 out_unlock:
 	if (attr->na_seclabel && attr->na_seclabel->len)
@@ -846,10 +845,14 @@ nfsd_splice_actor(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		  struct splice_desc *sd)
 {
 	struct svc_rqst *rqstp = sd->u.data;
-
-	svc_rqst_replace_page(rqstp, buf->page);
-	if (rqstp->rq_res.page_len == 0)
-		rqstp->rq_res.page_base = buf->offset;
+	struct page *page = buf->page;	// may be a compound one
+	unsigned offset = buf->offset;
+
+	page += offset / PAGE_SIZE;
+	for (int i = sd->len; i > 0; i -= PAGE_SIZE)
+		svc_rqst_replace_page(rqstp, page++);
+	if (rqstp->rq_res.page_len == 0)	// first call
+		rqstp->rq_res.page_base = offset % PAGE_SIZE;
 	rqstp->rq_res.page_len += sd->len;
 	return sd->len;
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 81d26abf486f..da85b3979195 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -141,6 +141,8 @@ struct tracefs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
 	umode_t mode;
+	/* Opt_* bitfield. */
+	unsigned int opts;
 };
 
 enum {
@@ -241,6 +243,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 	kgid_t gid;
 	char *p;
 
+	opts->opts = 0;
 	opts->mode = TRACEFS_DEFAULT_MODE;
 
 	while ((p = strsep(&data, ",")) != NULL) {
@@ -275,24 +278,36 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
 		 * but traditionally tracefs has ignored all mount options
 		 */
 		}
+
+		opts->opts |= BIT(token);
 	}
 
 	return 0;
 }
 
-static int tracefs_apply_options(struct super_block *sb)
+static int tracefs_apply_options(struct super_block *sb, bool remount)
 {
 	struct tracefs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = d_inode(sb->s_root);
 	struct tracefs_mount_opts *opts = &fsi->mount_opts;
 
-	inode->i_mode &= ~S_IALLUGO;
-	inode->i_mode |= opts->mode;
+	/*
+	 * On remount, only reset mode/uid/gid if they were provided as mount
+	 * options.
+	 */
+
+	if (!remount || opts->opts & BIT(Opt_mode)) {
+		inode->i_mode &= ~S_IALLUGO;
+		inode->i_mode |= opts->mode;
+	}
 
-	inode->i_uid = opts->uid;
+	if (!remount || opts->opts & BIT(Opt_uid))
+		inode->i_uid = opts->uid;
 
-	/* Set all the group ids to the mount option */
-	set_gid(sb->s_root, opts->gid);
+	if (!remount || opts->opts & BIT(Opt_gid)) {
+		/* Set all the group ids to the mount option */
+		set_gid(sb->s_root, opts->gid);
+	}
 
 	return 0;
 }
@@ -307,7 +322,7 @@ static int tracefs_remount(struct super_block *sb, int *flags, char *data)
 	if (err)
 		goto fail;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, true);
 
 fail:
 	return err;
@@ -359,7 +374,7 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_op = &tracefs_super_operations;
 
-	tracefs_apply_options(sb);
+	tracefs_apply_options(sb, false);
 
 	return 0;