Merge v6.9.5

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

27 files changed, 200 insertions, 142 deletions

diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index f16f73581634..01338d4c2d9e 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry)
 static void v9fs_dentry_release(struct dentry *dentry)
 {
 	struct hlist_node *p, *n;
+	struct hlist_head head;
 
 	p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n",
 		 dentry, dentry);
-	hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata)
+
+	spin_lock(&dentry->d_lock);
+	hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head);
+	spin_unlock(&dentry->d_lock);
+
+	hlist_for_each_safe(p, n, &head)
 		p9_fid_put(hlist_entry(p, struct p9_fid, dlist));
-	dentry->d_fsdata = NULL;
 }
 
 static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 97f50e9fd9eb..297487ee8323 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		put_page(page);
 		if (ret < 0)
 			return ret;
+
+		/* Don't cross a backup volume mountpoint from a backup volume */
+		if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL &&
+		    ctx->type == AFSVL_BACKVOL)
+			return -ENODEV;
 	}
 
 	return 0;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3df5477d48a8..3a47eec87b26 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4544,18 +4544,10 @@ static void btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				       struct btrfs_fs_info *fs_info)
 {
 	struct rb_node *node;
-	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_root *delayed_refs = &trans->delayed_refs;
 	struct btrfs_delayed_ref_node *ref;
 
-	delayed_refs = &trans->delayed_refs;
-
 	spin_lock(&delayed_refs->lock);
-	if (atomic_read(&delayed_refs->num_entries) == 0) {
-		spin_unlock(&delayed_refs->lock);
-		btrfs_debug(fs_info, "delayed_refs has NO entry");
-		return;
-	}
-
 	while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) {
 		struct btrfs_delayed_ref_head *head;
 		struct rb_node *n;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 87f487b11657..41173701f1be 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3662,6 +3662,8 @@ static struct extent_buffer *grab_extent_buffer(
 	struct folio *folio = page_folio(page);
 	struct extent_buffer *exists;
 
+	lockdep_assert_held(&page->mapping->i_private_lock);
+
 	/*
 	 * For subpage case, we completely rely on radix tree to ensure we
 	 * don't try to insert two ebs for the same bytenr.  So here we always
@@ -3729,13 +3731,14 @@ static int check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start)
  * The caller needs to free the existing folios and retry using the same order.
  */
 static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i,
+				      struct btrfs_subpage *prealloc,
 				      struct extent_buffer **found_eb_ret)
 {
 
 	struct btrfs_fs_info *fs_info = eb->fs_info;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	const unsigned long index = eb->start >> PAGE_SHIFT;
-	struct folio *existing_folio;
+	struct folio *existing_folio = NULL;
 	int ret;
 
 	ASSERT(found_eb_ret);
@@ -3747,12 +3750,14 @@ retry:
 	ret = filemap_add_folio(mapping, eb->folios[i], index + i,
 				GFP_NOFS | __GFP_NOFAIL);
 	if (!ret)
-		return 0;
+		goto finish;
 
 	existing_folio = filemap_lock_folio(mapping, index + i);
 	/* The page cache only exists for a very short time, just retry. */
-	if (IS_ERR(existing_folio))
+	if (IS_ERR(existing_folio)) {
+		existing_folio = NULL;
 		goto retry;
+	}
 
 	/* For now, we should only have single-page folios for btree inode. */
 	ASSERT(folio_nr_pages(existing_folio) == 1);
@@ -3763,14 +3768,13 @@ retry:
 		return -EAGAIN;
 	}
 
-	if (fs_info->nodesize < PAGE_SIZE) {
-		/*
-		 * We're going to reuse the existing page, can drop our page
-		 * and subpage structure now.
-		 */
+finish:
+	spin_lock(&mapping->i_private_lock);
+	if (existing_folio && fs_info->nodesize < PAGE_SIZE) {
+		/* We're going to reuse the existing page, can drop our folio now. */
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
-	} else {
+	} else if (existing_folio) {
 		struct extent_buffer *existing_eb;
 
 		existing_eb = grab_extent_buffer(fs_info,
@@ -3778,6 +3782,7 @@ retry:
 		if (existing_eb) {
 			/* The extent buffer still exists, we can use it directly. */
 			*found_eb_ret = existing_eb;
+			spin_unlock(&mapping->i_private_lock);
 			folio_unlock(existing_folio);
 			folio_put(existing_folio);
 			return 1;
@@ -3786,6 +3791,22 @@ retry:
 		__free_page(folio_page(eb->folios[i], 0));
 		eb->folios[i] = existing_folio;
 	}
+	eb->folio_size = folio_size(eb->folios[i]);
+	eb->folio_shift = folio_shift(eb->folios[i]);
+	/* Should not fail, as we have preallocated the memory. */
+	ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc);
+	ASSERT(!ret);
+	/*
+	 * To inform we have an extra eb under allocation, so that
+	 * detach_extent_buffer_page() won't release the folio private when the
+	 * eb hasn't been inserted into radix tree yet.
+	 *
+	 * The ref will be decreased when the eb releases the page, in
+	 * detach_extent_buffer_page().  Thus needs no special handling in the
+	 * error path.
+	 */
+	btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]);
+	spin_unlock(&mapping->i_private_lock);
 	return 0;
 }
 
@@ -3797,7 +3818,6 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int attached = 0;
 	struct extent_buffer *eb;
 	struct extent_buffer *existing_eb = NULL;
-	struct address_space *mapping = fs_info->btree_inode->i_mapping;
 	struct btrfs_subpage *prealloc = NULL;
 	u64 lockdep_owner = owner_root;
 	bool page_contig = true;
@@ -3863,7 +3883,7 @@ reallocate:
 	for (int i = 0; i < num_folios; i++) {
 		struct folio *folio;
 
-		ret = attach_eb_folio_to_filemap(eb, i, &existing_eb);
+		ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb);
 		if (ret > 0) {
 			ASSERT(existing_eb);
 			goto out;
@@ -3900,24 +3920,6 @@ reallocate:
 		 * and free the allocated page.
 		 */
 		folio = eb->folios[i];
-		eb->folio_size = folio_size(folio);
-		eb->folio_shift = folio_shift(folio);
-		spin_lock(&mapping->i_private_lock);
-		/* Should not fail, as we have preallocated the memory */
-		ret = attach_extent_buffer_folio(eb, folio, prealloc);
-		ASSERT(!ret);
-		/*
-		 * To inform we have extra eb under allocation, so that
-		 * detach_extent_buffer_page() won't release the folio private
-		 * when the eb hasn't yet been inserted into radix tree.
-		 *
-		 * The ref will be decreased when the eb released the page, in
-		 * detach_extent_buffer_page().
-		 * Thus needs no special handling in error path.
-		 */
-		btrfs_folio_inc_eb_refs(fs_info, folio);
-		spin_unlock(&mapping->i_private_lock);
-
 		WARN_ON(btrfs_folio_test_dirty(fs_info, folio, eb->start, eb->len));
 
 		/*
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 40e5f7f2fcb7..1167899a16d0 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -468,6 +468,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 		}
 		if (!qgroup) {
 			struct btrfs_qgroup *prealloc;
+			struct btrfs_root *tree_root = fs_info->tree_root;
 
 			prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 			if (!prealloc) {
@@ -475,6 +476,25 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 				goto out;
 			}
 			qgroup = add_qgroup_rb(fs_info, prealloc, found_key.offset);
+			/*
+			 * If a qgroup exists for a subvolume ID, it is possible
+			 * that subvolume has been deleted, in which case
+			 * re-using that ID would lead to incorrect accounting.
+			 *
+			 * Ensure that we skip any such subvol ids.
+			 *
+			 * We don't need to lock because this is only called
+			 * during mount before we start doing things like creating
+			 * subvolumes.
+			 */
+			if (is_fstree(qgroup->qgroupid) &&
+			    qgroup->qgroupid > tree_root->free_objectid)
+				/*
+				 * Don't need to check against BTRFS_LAST_FREE_OBJECTID,
+				 * as it will get checked on the next call to
+				 * btrfs_get_free_objectid.
+				 */
+				tree_root->free_objectid = qgroup->qgroupid + 1;
 		}
 		ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
 		if (ret < 0)
@@ -3129,7 +3149,7 @@ static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
 	qgids = res->qgroups;
 
 	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
-		qgids[i] = qg_list->group->qgroupid;
+		qgids[i++] = qg_list->group->qgroupid;
 
 	*inherit = res;
 	return 0;
@@ -3826,14 +3846,14 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		/* we're resuming qgroup rescan at mount time */
 		if (!(fs_info->qgroup_flags &
 		      BTRFS_QGROUP_STATUS_FLAG_RESCAN)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup rescan is not queued");
 			ret = -EINVAL;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		}
 
 		if (ret)
@@ -3844,14 +3864,12 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 
 	if (init_flags) {
 		if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
-			btrfs_warn(fs_info,
-				   "qgroup rescan is already in progress");
 			ret = -EINPROGRESS;
 		} else if (!(fs_info->qgroup_flags &
 			     BTRFS_QGROUP_STATUS_FLAG_ON)) {
-			btrfs_warn(fs_info,
+			btrfs_debug(fs_info,
 			"qgroup rescan init failed, qgroup is not enabled");
-			ret = -EINVAL;
+			ret = -ENOTCONN;
 		} else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
 			/* Quota disable is in progress */
 			ret = -EBUSY;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 7e44ccaf348f..fa6964de3437 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -119,6 +119,7 @@ enum {
 	Opt_thread_pool,
 	Opt_treelog,
 	Opt_user_subvol_rm_allowed,
+	Opt_norecovery,
 
 	/* Rescue options */
 	Opt_rescue,
@@ -245,6 +246,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = {
 	__fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL),
 	/* Deprecated, with alias rescue=usebackuproot */
 	__fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL),
+	/* For compatibility only, alias for "rescue=nologreplay". */
+	fsparam_flag("norecovery", Opt_norecovery),
 
 	/* Debugging options. */
 	fsparam_flag_no("enospc_debug", Opt_enospc_debug),
@@ -438,6 +441,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		"'nologreplay' is deprecated, use 'rescue=nologreplay' instead");
 		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
 		break;
+	case Opt_norecovery:
+		btrfs_info(NULL,
+"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'");
+		btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY);
+		break;
 	case Opt_flushoncommit:
 		if (result.negated)
 			btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 472918a5bc73..d4fc5fedd8ee 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4856,18 +4856,23 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			path->slots[0]++;
 			continue;
 		}
-		if (!dropped_extents) {
-			/*
-			 * Avoid logging extent items logged in past fsync calls
-			 * and leading to duplicate keys in the log tree.
-			 */
+		/*
+		 * Avoid overlapping items in the log tree. The first time we
+		 * get here, get rid of everything from a past fsync. After
+		 * that, if the current extent starts before the end of the last
+		 * extent we copied, truncate the last one. This can happen if
+		 * an ordered extent completion modifies the subvolume tree
+		 * while btrfs_next_leaf() has the tree unlocked.
+		 */
+		if (!dropped_extents || key.offset < truncate_offset) {
 			ret = truncate_inode_items(trans, root->log_root, inode,
-						   truncate_offset,
+						   min(key.offset, truncate_offset),
 						   BTRFS_EXTENT_DATA_KEY);
 			if (ret)
 				goto out;
 			dropped_extents = true;
 		}
+		truncate_offset = btrfs_file_extent_end(path);
 		if (ins_nr == 0)
 			start_slot = slot;
 		ins_nr++;
diff --git a/fs/erofs/decompressor_deflate.c b/fs/erofs/decompressor_deflate.c
index 81e65c453ef0..3a3461561a3c 100644
--- a/fs/erofs/decompressor_deflate.c
+++ b/fs/erofs/decompressor_deflate.c
@@ -46,39 +46,15 @@ int __init z_erofs_deflate_init(void)
 	/* by default, use # of possible CPUs instead */
 	if (!z_erofs_deflate_nstrms)
 		z_erofs_deflate_nstrms = num_possible_cpus();
-
-	for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms;
-	     ++z_erofs_deflate_avail_strms) {
-		struct z_erofs_deflate *strm;
-
-		strm = kzalloc(sizeof(*strm), GFP_KERNEL);
-		if (!strm)
-			goto out_failed;
-
-		/* XXX: in-kernel zlib cannot shrink windowbits currently */
-		strm->z.workspace = vmalloc(zlib_inflate_workspacesize());
-		if (!strm->z.workspace) {
-			kfree(strm);
-			goto out_failed;
-		}
-
-		spin_lock(&z_erofs_deflate_lock);
-		strm->next = z_erofs_deflate_head;
-		z_erofs_deflate_head = strm;
-		spin_unlock(&z_erofs_deflate_lock);
-	}
 	return 0;
-
-out_failed:
-	erofs_err(NULL, "failed to allocate zlib workspace");
-	z_erofs_deflate_exit();
-	return -ENOMEM;
 }
 
 int z_erofs_load_deflate_config(struct super_block *sb,
 			struct erofs_super_block *dsb, void *data, int size)
 {
 	struct z_erofs_deflate_cfgs *dfl = data;
+	static DEFINE_MUTEX(deflate_resize_mutex);
+	static bool inited;
 
 	if (!dfl || size < sizeof(struct z_erofs_deflate_cfgs)) {
 		erofs_err(sb, "invalid deflate cfgs, size=%u", size);
@@ -89,9 +65,36 @@ int z_erofs_load_deflate_config(struct super_block *sb,
 		erofs_err(sb, "unsupported windowbits %u", dfl->windowbits);
 		return -EOPNOTSUPP;
 	}
+	mutex_lock(&deflate_resize_mutex);
+	if (!inited) {
+		for (; z_erofs_deflate_avail_strms < z_erofs_deflate_nstrms;
+		     ++z_erofs_deflate_avail_strms) {
+			struct z_erofs_deflate *strm;
+
+			strm = kzalloc(sizeof(*strm), GFP_KERNEL);
+			if (!strm)
+				goto failed;
+			/* XXX: in-kernel zlib cannot customize windowbits */
+			strm->z.workspace = vmalloc(zlib_inflate_workspacesize());
+			if (!strm->z.workspace) {
+				kfree(strm);
+				goto failed;
+			}
 
+			spin_lock(&z_erofs_deflate_lock);
+			strm->next = z_erofs_deflate_head;
+			z_erofs_deflate_head = strm;
+			spin_unlock(&z_erofs_deflate_lock);
+		}
+		inited = true;
+	}
+	mutex_unlock(&deflate_resize_mutex);
 	erofs_info(sb, "EXPERIMENTAL DEFLATE feature in use. Use at your own risk!");
 	return 0;
+failed:
+	mutex_unlock(&deflate_resize_mutex);
+	z_erofs_deflate_exit();
+	return -ENOMEM;
 }
 
 int z_erofs_deflate_decompress(struct z_erofs_decompress_req *rq,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 6de6bf57699b..30e824866274 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2334,7 +2334,7 @@ static int mpage_journal_page_buffers(handle_t *handle,
 
 	if (folio_pos(folio) + len > size &&
 	    !ext4_verity_in_progress(inode))
-		len = size - folio_pos(folio);
+		len = size & (len - 1);
 
 	return ext4_journal_folio_buffers(handle, folio, len);
 }
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 56938532b4ce..7bfc5fb5a128 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -193,8 +193,8 @@ struct ext4_allocation_context {
 	ext4_grpblk_t	ac_orig_goal_len;
 
 	__u32 ac_flags;		/* allocation hints */
+	__u32 ac_groups_linear_remaining;
 	__u16 ac_groups_scanned;
-	__u16 ac_groups_linear_remaining;
 	__u16 ac_found;
 	__u16 ac_cX_found[EXT4_MB_NUM_CRS];
 	__u16 ac_tail;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index b67a176bfcf9..9fdd13422073 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -3113,8 +3113,10 @@ ext4_xattr_block_cache_find(struct inode *inode,
 
 		bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO);
 		if (IS_ERR(bh)) {
-			if (PTR_ERR(bh) == -ENOMEM)
+			if (PTR_ERR(bh) == -ENOMEM) {
+				mb_cache_entry_put(ea_block_cache, ce);
 				return NULL;
+			}
 			bh = NULL;
 			EXT4_ERROR_INODE(inode, "block %lu read error",
 					 (unsigned long)ce->e_value);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index c26effdce9aa..2af50bc34fcd 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -361,6 +361,12 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
+	if (fi->i_xattr_nid && f2fs_check_nid_range(sbi, fi->i_xattr_nid)) {
+		f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_xattr_nid: %u, run fsck to fix.",
+			  __func__, inode->i_ino, fi->i_xattr_nid);
+		return false;
+	}
+
 	return true;
 }
 
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 4e8e41c8b3c0..4ac6c8c403c2 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -909,11 +909,11 @@ static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
 	loff_t length = iomap_length(iter);
-	size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
 	loff_t pos = iter->pos;
 	ssize_t written = 0;
 	long status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
+	size_t chunk = mapping_max_folio_size(mapping);
 	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
 
 	do {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 06253695fe53..2ff0c35d80e0 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -710,9 +710,9 @@ unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
 	if ((bsize & (bsize - 1)) || nrbitsp) {
 		unsigned char	nrbits;
 
-		for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
+		for (nrbits = 31; nrbits && !(bsize & (1UL << nrbits)); nrbits--)
 			;
-		bsize = 1 << nrbits;
+		bsize = 1UL << nrbits;
 		if (nrbitsp)
 			*nrbitsp = nrbits;
 	}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ea390db94b62..c93c12063b3a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5456,7 +5456,7 @@ static bool nfs4_read_plus_not_supported(struct rpc_task *task,
 	struct rpc_message *msg = &task->tk_msg;
 
 	if (msg->rpc_proc == &nfs4_procedures[NFSPROC4_CLNT_READ_PLUS] &&
-	    server->caps & NFS_CAP_READ_PLUS && task->tk_status == -ENOTSUPP) {
+	    task->tk_status == -ENOTSUPP) {
 		server->caps &= ~NFS_CAP_READ_PLUS;
 		msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_READ];
 		rpc_restart_call_prepare(task);
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index aee40db7a036..35e6c55a0d23 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -608,7 +608,7 @@ int nilfs_empty_dir(struct inode *inode)
 
 		kaddr = nilfs_get_folio(inode, i, &folio);
 		if (IS_ERR(kaddr))
-			continue;
+			return 0;
 
 		de = (struct nilfs_dir_entry *)kaddr;
 		kaddr += nilfs_last_byte(inode, i) - NILFS_DIR_REC_LEN(1);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 3c1e4e9eafa3..a1b011cb4b47 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1652,6 +1652,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 			if (bh->b_folio != bd_folio) {
 				if (bd_folio) {
 					folio_lock(bd_folio);
+					folio_wait_writeback(bd_folio);
 					folio_clear_dirty_for_io(bd_folio);
 					folio_start_writeback(bd_folio);
 					folio_unlock(bd_folio);
@@ -1665,6 +1666,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 			if (bh == segbuf->sb_super_root) {
 				if (bh->b_folio != bd_folio) {
 					folio_lock(bd_folio);
+					folio_wait_writeback(bd_folio);
 					folio_clear_dirty_for_io(bd_folio);
 					folio_start_writeback(bd_folio);
 					folio_unlock(bd_folio);
@@ -1681,6 +1683,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
 	}
 	if (bd_folio) {
 		folio_lock(bd_folio);
+		folio_wait_writeback(bd_folio);
 		folio_clear_dirty_for_io(bd_folio);
 		folio_start_writeback(bd_folio);
 		folio_unlock(bd_folio);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 18550c071d71..72a1acd03675 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3214,7 +3214,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 	mm = get_task_mm(task);
 	if (mm) {
 		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
-		seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages);
+		seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm));
 		seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
 		seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
 		mmput(mm);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 6e72e5ad42bc..f4b1c8b42a51 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -74,7 +74,18 @@ out:
 	return 0;
 }
 
-static int proc_fdinfo_access_allowed(struct inode *inode)
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, seq_show, inode);
+}
+
+/**
+ * Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
+ * that the current task has PTRACE_MODE_READ in addition to the normal
+ * POSIX-like checks.
+ */
+static int proc_fdinfo_permission(struct mnt_idmap *idmap, struct inode *inode,
+				  int mask)
 {
 	bool allowed = false;
 	struct task_struct *task = get_proc_task(inode);
@@ -88,18 +99,13 @@ static int proc_fdinfo_access_allowed(struct inode *inode)
 	if (!allowed)
 		return -EACCES;
 
-	return 0;
+	return generic_permission(idmap, inode, mask);
 }
 
-static int seq_fdinfo_open(struct inode *inode, struct file *file)
-{
-	int ret = proc_fdinfo_access_allowed(inode);
-
-	if (ret)
-		return ret;
-
-	return single_open(file, seq_show, inode);
-}
+static const struct inode_operations proc_fdinfo_file_inode_operations = {
+	.permission	= proc_fdinfo_permission,
+	.setattr	= proc_setattr,
+};
 
 static const struct file_operations proc_fdinfo_file_operations = {
 	.open		= seq_fdinfo_open,
@@ -388,6 +394,8 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
 	ei = PROC_I(inode);
 	ei->fd = data->fd;
 
+	inode->i_op = &proc_fdinfo_file_inode_operations;
+
 	inode->i_fop = &proc_fdinfo_file_operations;
 	tid_fd_update_inode(task, inode, 0);
 
@@ -407,23 +415,13 @@ static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
 				  proc_fdinfo_instantiate);
 }
 
-static int proc_open_fdinfo(struct inode *inode, struct file *file)
-{
-	int ret = proc_fdinfo_access_allowed(inode);
-
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 const struct inode_operations proc_fdinfo_inode_operations = {
 	.lookup		= proc_lookupfdinfo,
+	.permission	= proc_fdinfo_permission,
 	.setattr	= proc_setattr,
 };
 
 const struct file_operations proc_fdinfo_operations = {
-	.open		= proc_open_fdinfo,
 	.read		= generic_read_dir,
 	.iterate_shared	= proc_readfdinfo,
 	.llseek		= generic_file_llseek,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 102f48668c35..a097c9a65234 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -965,12 +965,17 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
 				break;
 
 			/* Case 1 and 2 above */
-			if (vma->vm_start >= last_vma_end)
+			if (vma->vm_start >= last_vma_end) {
+				smap_gather_stats(vma, &mss, 0);
+				last_vma_end = vma->vm_end;
 				continue;
+			}
 
 			/* Case 4 above */
-			if (vma->vm_end > last_vma_end)
+			if (vma->vm_end > last_vma_end) {
 				smap_gather_stats(vma, &mss, last_vma_end);
+				last_vma_end = vma->vm_end;
+			}
 		}
 	} for_each_vma(vmi, vma);
 
diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h
index c46d418c1c0c..a2072ab9e586 100644
--- a/fs/smb/client/cifspdu.h
+++ b/fs/smb/client/cifspdu.h
@@ -2574,7 +2574,7 @@ typedef struct {
 
 
 struct win_dev {
-	unsigned char type[8]; /* IntxCHR or IntxBLK or LnxFIFO*/
+	unsigned char type[8]; /* IntxCHR or IntxBLK or LnxFIFO or LnxSOCK */
 	__le64 major;
 	__le64 minor;
 } __attribute__((packed));
diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
index 60afab5c83d4..d0e69591332d 100644
--- a/fs/smb/client/inode.c
+++ b/fs/smb/client/inode.c
@@ -591,6 +591,10 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
 				mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
 				fattr->cf_rdev = MKDEV(mjr, mnr);
 			}
+		} else if (memcmp("LnxSOCK", pbuf, 8) == 0) {
+			cifs_dbg(FYI, "Socket\n");
+			fattr->cf_mode |= S_IFSOCK;
+			fattr->cf_dtype = DT_SOCK;
 		} else if (memcmp("IntxLNK", pbuf, 7) == 0) {
 			cifs_dbg(FYI, "Symlink\n");
 			fattr->cf_mode |= S_IFLNK;
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 6fea0aed4346..d35c45f3a25a 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4996,6 +4996,9 @@ static int __cifs_sfu_make_node(unsigned int xid, struct inode *inode,
 		pdev.major = cpu_to_le64(MAJOR(dev));
 		pdev.minor = cpu_to_le64(MINOR(dev));
 		break;
+	case S_IFSOCK:
+		strscpy(pdev.type, "LnxSOCK");
+		break;
 	case S_IFIFO:
 		strscpy(pdev.type, "LnxFIFO");
 		break;
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 02135a605305..1476c445cadc 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -216,8 +216,8 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32  tid)
 	}
 	tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
 	if (!tcon) {
-		cifs_put_smb_ses(ses);
 		spin_unlock(&cifs_tcp_ses_lock);
+		cifs_put_smb_ses(ses);
 		return NULL;
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index a878cea70f4c..55a40a730b10 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -50,8 +50,12 @@ static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei)
 /* Just try to make something consistent and unique */
 static int eventfs_dir_ino(struct eventfs_inode *ei)
 {
-	if (!ei->ino)
+	if (!ei->ino) {
 		ei->ino = get_next_ino();
+		/* Must not have the file inode number */
+		if (ei->ino == EVENTFS_FILE_INODE_INO)
+			ei->ino = get_next_ino();
+	}
 
 	return ei->ino;
 }
@@ -345,10 +349,9 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 		 * If the ei is being freed, the ownership of the children
 		 * doesn't matter.
 		 */
-		if (ei->is_freed) {
-			ei = NULL;
-			break;
-		}
+		if (ei->is_freed)
+			return NULL;
+
 		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
 
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 417c840e6403..d8c60c2b76e2 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -439,10 +439,26 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static int tracefs_drop_inode(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	/*
+	 * This inode is being freed and cannot be used for
+	 * eventfs. Clear the flag so that it doesn't call into
+	 * eventfs during the remount flag updates. The eventfs_inode
+	 * gets freed after an RCU cycle, so the content will still
+	 * be safe if the iteration is going on now.
+	 */
+	ti->flags &= ~TRACEFS_EVENT_INODE;
+
+	return 1;
+}
+
 static const struct super_operations tracefs_super_operations = {
 	.alloc_inode    = tracefs_alloc_inode,
 	.free_inode     = tracefs_free_inode,
-	.drop_inode     = generic_delete_inode,
+	.drop_inode     = tracefs_drop_inode,
 	.statfs		= simple_statfs,
 	.remount_fs	= tracefs_remount,
 	.show_options	= tracefs_show_options,
@@ -469,22 +485,7 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return !(ei && ei->is_freed);
 }
 
-static void tracefs_d_iput(struct dentry *dentry, struct inode *inode)
-{
-	struct tracefs_inode *ti = get_tracefs(inode);
-
-	/*
-	 * This inode is being freed and cannot be used for
-	 * eventfs. Clear the flag so that it doesn't call into
-	 * eventfs during the remount flag updates. The eventfs_inode
-	 * gets freed after an RCU cycle, so the content will still
-	 * be safe if the iteration is going on now.
-	 */
-	ti->flags &= ~TRACEFS_EVENT_INODE;
-}
-
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_d_iput,
 	.d_revalidate = tracefs_d_revalidate,
 	.d_release = tracefs_d_release,
 };
diff --git a/fs/verity/init.c b/fs/verity/init.c
index cb2c9aac61ed..f440f0e61e3e 100644
--- a/fs/verity/init.c
+++ b/fs/verity/init.c
@@ -10,8 +10,6 @@
 #include <linux/ratelimit.h>
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table_header *fsverity_sysctl_header;
-
 static struct ctl_table fsverity_sysctl_table[] = {
 #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES
 	{
@@ -28,10 +26,7 @@ static struct ctl_table fsverity_sysctl_table[] = {
 
 static void __init fsverity_init_sysctl(void)
 {
-	fsverity_sysctl_header = register_sysctl("fs/verity",
-						 fsverity_sysctl_table);
-	if (!fsverity_sysctl_header)
-		panic("fsverity sysctl registration failed");
+	register_sysctl_init("fs/verity", fsverity_sysctl_table);
 }
 #else /* CONFIG_SYSCTL */
 static inline void fsverity_init_sysctl(void)