4.4.263-rc1 review

From: Jan Kara <[email protected]>

commit ce9f24cccdc019229b70a5c15e2b09ad9c0ab5d1 upstream.

Currently, system zones just track ranges of block, that are "important" fs metadata (bitmaps, group descriptors, journal blocks, etc.). This however complicates how extent tree (or indirect blocks) can be checked for inodes that actually track such metadata - currently the journal inode but arguably we should be treating quota files or resize inode similarly. We cannot run __ext4_ext_check() on such metadata inodes when loading their extents as that would immediately trigger the validity checks and so we just hack around that and special-case the journal inode. This however leads to a situation that a journal inode which has extent tree of depth at least one can have invalid extent tree that gets unnoticed until ext4_cache_extents() crashes.

To overcome this limitation, track inode number each system zone belongs to (0 is used for zones not belonging to any inode). We can then verify inode number matches the expected one when verifying extent tree and thus avoid the false errors. With this there's no need to to special-case journal inode during extent tree checking anymore so remove it.

---
 fs/ext4/block_validity.c |   37 +++++++++++++++++++++----------------
 fs/ext4/ext4.h           |    6 +++---
 fs/ext4/extents.c        |   16 ++++++----------
 fs/ext4/indirect.c       |    6 ++----
 fs/ext4/inode.c          |    5 ++---
 fs/ext4/mballoc.c        |    4 ++--
 6 files changed, 36 insertions(+), 38 deletions(-)

@@ -23,6 +23,7 @@ struct ext4_system_zone {
 	struct rb_node	node;
 	ext4_fsblk_t	start_blk;
 	unsigned int	count;
+	u32		ino;
 };
 
 static struct kmem_cache *ext4_system_zone_cachep;

@@ -43,7 +44,8 @@ void ext4_exit_system_zone(void)
 static inline int can_merge(struct ext4_system_zone *entry1,
 		     struct ext4_system_zone *entry2)
 {
-	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
 		return 1;
 	return 0;
 }

@@ -55,7 +57,7 @@ static inline int can_merge(struct ext4_
  */
 static int add_system_zone(struct ext4_sb_info *sbi,
 			   ext4_fsblk_t start_blk,
-			   unsigned int count)
+			   unsigned int count, u32 ino)
 {
 	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &sbi->system_blks.rb_node, *node;

@@ -78,6 +80,7 @@ static int add_system_zone(struct ext4_s
 		return -ENOMEM;
 	new_entry->start_blk = start_blk;
 	new_entry->count = count;
+	new_entry->ino = ino;
 	new_node = &new_entry->node;
 
 	rb_link_node(new_node, parent, n);

@@ -153,16 +156,16 @@ static int ext4_protect_reserved_inode(s
 		if (n == 0) {
 			i++;
 		} else {
-			if (!ext4_data_block_valid(sbi, map.m_pblk, n)) {
-				ext4_error(sb, "blocks %llu-%llu from inode %u "
+			err = add_system_zone(sbi, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					ext4_error(sb,
+					   "blocks %llu-%llu from inode %u "
 					   "overlap system zone", map.m_pblk,
 					   map.m_pblk + map.m_len - 1, ino);
-				err = -EFSCORRUPTED;
+				}
 				break;
 			}
-			err = add_system_zone(sbi, map.m_pblk, n);
-			if (err < 0)
-				break;
 			i += n;
 		}
 	}

@@ -191,16 +194,16 @@ int ext4_setup_system_zone(struct super_
 		if (ext4_bg_has_super(sb, i) &&
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1);
+					ext4_bg_num_gdb(sb, i) + 1, 0);
 		gdp = ext4_get_group_desc(sb, i, NULL);
-		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
+		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			return ret;
-		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1);
+		ret = add_system_zone(sbi, ext4_inode_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			return ret;
 		ret = add_system_zone(sbi, ext4_inode_table(sb, gdp),
-				sbi->s_itb_per_group);
+				sbi->s_itb_per_group, 0);
 		if (ret)
 			return ret;
 	}

@@ -233,10 +236,11 @@ void ext4_release_system_zone(struct sup
  * start_blk+count) is valid; 0 if some part of the block region
  * overlaps with filesystem metadata blocks.
  */
-int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
-			  unsigned int count)
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
+			   unsigned int count)
 {
 	struct ext4_system_zone *entry;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct rb_node *n = sbi->system_blks.rb_node;
 
 	if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||

@@ -252,6 +256,8 @@ int ext4_data_block_valid(struct ext4_sb
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = n->rb_right;
 		else {
+			if (entry->ino == inode->i_ino)
+				return 1;
 			sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
 			return 0;
 		}

@@ -274,8 +280,7 @@ int ext4_check_blockref(const char *func
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
 		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						    blk, 1))) {
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
 			es->s_last_error_block = cpu_to_le64(blk);
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");

@@ -3134,9 +3134,9 @@ extern void ext4_release_system_zone(str
 extern int ext4_setup_system_zone(struct super_block *sb);
 extern int __init ext4_init_system_zone(void);
 extern void ext4_exit_system_zone(void);
-extern int ext4_data_block_valid(struct ext4_sb_info *sbi,
-				 ext4_fsblk_t start_blk,
-				 unsigned int count);
+extern int ext4_inode_block_valid(struct inode *inode,
+				  ext4_fsblk_t start_blk,
+				  unsigned int count);
 extern int ext4_check_blockref(const char *, unsigned int,
 			       struct inode *, __le32 *, unsigned int);
 

@@ -384,7 +384,7 @@ static int ext4_valid_extent(struct inod
 	 */
 	if (lblock + len <= lblock)
 		return 0;
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
+	return ext4_inode_block_valid(inode, block, len);
 }
 
 static int ext4_valid_extent_idx(struct inode *inode,

@@ -392,7 +392,7 @@ static int ext4_valid_extent_idx(struct
 {
 	ext4_fsblk_t block = ext4_idx_pblock(ext_idx);
 
-	return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1);
+	return ext4_inode_block_valid(inode, block, 1);
 }
 
 static int ext4_valid_extent_entries(struct inode *inode,

@@ -549,14 +549,10 @@ __read_extent_tree_block(const char *fun
 	}
 	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
 		return bh;
-	if (!ext4_has_feature_journal(inode->i_sb) ||
-	    (inode->i_ino !=
-	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) {
-		err = __ext4_ext_check(function, line, inode,
-				       ext_block_hdr(bh), depth, pblk);
-		if (err)
-			goto errout;
-	}
+	err = __ext4_ext_check(function, line, inode,
+			       ext_block_hdr(bh), depth, pblk);
+	if (err)
+		goto errout;
 	set_buffer_verified(bh);
 	/*
 	 * If this is a leaf block, cache all of its entries

@@ -946,8 +946,7 @@ static int ext4_clear_blocks(handle_t *h
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
 
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free,
-				   count)) {
+	if (!ext4_inode_block_valid(inode, block_to_free, count)) {
 		EXT4_ERROR_INODE(inode, "attempt to clear invalid "
 				 "blocks %llu len %lu",
 				 (unsigned long long) block_to_free, count);

@@ -1109,8 +1108,7 @@ static void ext4_free_branches(handle_t
 			if (!nr)
 				continue;		/* A hole */
 
-			if (!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						   nr, 1)) {
+			if (!ext4_inode_block_valid(inode, nr, 1)) {
 				EXT4_ERROR_INODE(inode,
 						 "invalid indirect mapped "
 						 "block %lu (level %d)",

@@ -381,8 +381,7 @@ static int __check_block_validity(struct
 	    (inode->i_ino ==
 	     le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum)))
 		return 0;
-	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
-				   map->m_len)) {
+	if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
 				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,

@@ -4437,7 +4436,7 @@ struct inode *__ext4_iget(struct super_b
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) {
+	    !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) {
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: bad extended attribute block %llu",
 				 ei->i_file_acl);

@@ -2960,7 +2960,7 @@ ext4_mb_mark_diskspace_used(struct ext4_
 	block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
 
 	len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-	if (!ext4_data_block_valid(sbi, block, len)) {
+	if (!ext4_inode_block_valid(ac->ac_inode, block, len)) {
 		ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
 			   "fs metadata", block, block+len);
 		/* File system mounted not to panic on error

@@ -4718,7 +4718,7 @@ void ext4_free_blocks(handle_t *handle,
 
 	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
-	    !ext4_data_block_valid(sbi, block, count)) {
+	    !ext4_inode_block_valid(inode, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
 			   "block = %llu, count = %lu", block, count);
 		goto error_return;

From: Gwendal Grignou <[email protected]>

commit 5d749d0bbe811c10d9048cde6dfebc761713abfd upstream.

Prevent memory scribble by checking that ioctl buffer size parameters are sane.
Without this check, on 32 bits system, if .insize = 0xffffffff - 20 and .outsize the amount to scribble, we would overflow, allocate a small amounts and be able to write outside of the malloc'ed area. Adding a hard limit allows argument checking of the ioctl. With the current EC, it is expected .insize and .outsize to be at around 512 bytes or less.

---
 drivers/platform/chrome/cros_ec_dev.c   |    4 ++++
 drivers/platform/chrome/cros_ec_proto.c |    4 ++--
 include/linux/mfd/cros_ec.h             |    6 ++++--
 3 files changed, 10 insertions(+), 4 deletions(-)

@@ -137,6 +137,10 @@ static long ec_device_ioctl_xcmd(struct
 	if (copy_from_user(&u_cmd, arg, sizeof(u_cmd)))
 		return -EFAULT;
 
+	if ((u_cmd.outsize > EC_MAX_MSG_BYTES) ||
+	    (u_cmd.insize > EC_MAX_MSG_BYTES))
+		return -EINVAL;
+
 	s_cmd = kmalloc(sizeof(*s_cmd) + max(u_cmd.outsize, u_cmd.insize),
 			GFP_KERNEL);
 	if (!s_cmd)

@@ -311,8 +311,8 @@ int cros_ec_query_all(struct cros_ec_dev
 			ec_dev->max_response = EC_PROTO2_MAX_PARAM_SIZE;
 			ec_dev->max_passthru = 0;
 			ec_dev->pkt_xfer = NULL;
-			ec_dev->din_size = EC_MSG_BYTES;
-			ec_dev->dout_size = EC_MSG_BYTES;
+			ec_dev->din_size = EC_PROTO2_MSG_BYTES;
+			ec_dev->dout_size = EC_PROTO2_MSG_BYTES;
 		} else {
 			/*
 			 * It's possible for a test to occur too early when

@@ -50,9 +50,11 @@ enum {
 					EC_MSG_TX_TRAILER_BYTES,
 	EC_MSG_RX_PROTO_BYTES	= 3,
 
-	/* Max length of messages */
-	EC_MSG_BYTES		= EC_PROTO2_MAX_PARAM_SIZE +
+	/* Max length of messages for proto 2*/
+	EC_PROTO2_MSG_BYTES		= EC_PROTO2_MAX_PARAM_SIZE +
 					EC_MSG_TX_PROTO_BYTES,
+
+	EC_MAX_MSG_BYTES		= 64 * 1024,
 };
 
 /*

From: Filipe Manana <[email protected]>

commit dbcc7d57bffc0c8cac9dac11bec548597d59a6a5 upstream.

While resolving backreferences, as part of a logical ino ioctl call or fiemap, we can end up hitting a BUG_ON() when replaying tree mod log operations of a root, triggering a stack trace like the following:

  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/ctree.c:1210!
  invalid opcode: 0000 [#1] SMP KASAN PTI
  CPU: 1 PID: 19054 Comm: crawl_335 Tainted: G        W         5.11.0-2d11c0084b02-misc-next+ #89
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  RIP: 0010:__tree_mod_log_rewind+0x3b1/0x3c0
  Code: 05 48 8d 74 10 (...)
  RSP: 0018:ffffc90001eb70b8 EFLAGS: 00010297
  RAX: 0000000000000000 RBX: ffff88812344e400 RCX: ffffffffb28933b6
  RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff88812344e42c
  RBP: ffffc90001eb7108 R08: 1ffff11020b60a20 R09: ffffed1020b60a20
  R10: ffff888105b050f9 R11: ffffed1020b60a1f R12: 00000000000000ee
  R13: ffff8880195520c0 R14: ffff8881bc958500 R15: ffff88812344e42c
  FS:  00007fd1955e8700(0000) GS:ffff8881f5600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007efdb7928718 CR3: 000000010103a006 CR4: 0000000000170ee0
  Call Trace:
   btrfs_search_old_slot+0x265/0x10d0
   ? lock_acquired+0xbb/0x600
   ? btrfs_search_slot+0x1090/0x1090
   ? free_extent_buffer.part.61+0xd7/0x140
   ? free_extent_buffer+0x13/0x20
   resolve_indirect_refs+0x3e9/0xfc0
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? add_prelim_ref.part.11+0x150/0x150
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? do_raw_spin_unlock+0xa8/0x140
   ? rb_insert_color+0x30/0x360
   ? prelim_ref_insert+0x12d/0x430
   find_parent_nodes+0x5c3/0x1830
   ? resolve_indirect_refs+0xfc0/0xfc0
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x160/0x210
   ? lock_release+0xc8/0x620
   ? fs_reclaim_acquire+0x67/0xf0
   ? lock_acquire+0xc7/0x510
   ? poison_range+0x38/0x40
   ? unpoison_range+0x14/0x40
   ? trace_hardirqs_on+0x55/0x120
   btrfs_find_all_roots_safe+0x142/0x1e0
   ? find_parent_nodes+0x1830/0x1830
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   iterate_extent_inodes+0x20e/0x580
   ? tree_backref_for_extent+0x230/0x230
   ? lock_downgrade+0x3d0/0x3d0
   ? read_extent_buffer+0xdd/0x110
   ? lock_downgrade+0x3d0/0x3d0
   ? __kasan_check_read+0x11/0x20
   ? lock_acquired+0xbb/0x600
   ? __kasan_check_write+0x14/0x20
   ? _raw_spin_unlock+0x22/0x30
   ? __kasan_check_write+0x14/0x20
   iterate_inodes_from_logical+0x129/0x170
   ? iterate_inodes_from_logical+0x129/0x170
   ? btrfs_inode_flags_to_xflags+0x50/0x50
   ? iterate_extent_inodes+0x580/0x580
   ? __vmalloc_node+0x92/0xb0
   ? init_data_container+0x34/0xb0
   ? init_data_container+0x34/0xb0
   ? kvmalloc_node+0x60/0x80
   btrfs_ioctl_logical_to_ino+0x158/0x230
   btrfs_ioctl+0x205e/0x4040
   ? __might_sleep+0x71/0xe0
   ? btrfs_ioctl_get_supported_features+0x30/0x30
   ? getrusage+0x4b6/0x9c0
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __might_fault+0x64/0xd0
   ? lock_acquire+0xc7/0x510
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? do_vfs_ioctl+0xfc/0x9d0
   ? ioctl_file_clone+0xe0/0xe0
   ? lock_downgrade+0x3d0/0x3d0
   ? lockdep_hardirqs_on_prepare+0x210/0x210
   ? __kasan_check_read+0x11/0x20
   ? lock_release+0xc8/0x620
   ? __task_pid_nr_ns+0xd3/0x250
   ? lock_acquire+0xc7/0x510
   ? __fget_files+0x160/0x230
   ? __fget_light+0xf2/0x110
   __x64_sys_ioctl+0xc3/0x100
   do_syscall_64+0x37/0x80
   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  RIP: 0033:0x7fd1976e2427
  Code: 00 00 90 48 8b 05 (...)
  RSP: 002b:00007fd1955e5cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 00007fd1955e5f40 RCX: 00007fd1976e2427
  RDX: 00007fd1955e5f48 RSI: 00000000c038943b RDI: 0000000000000004
  RBP: 0000000001000000 R08: 0000000000000000 R09: 00007fd1955e6120
  R10: 0000557835366b00 R11: 0000000000000246 R12: 0000000000000004
  R13: 00007fd1955e5f48 R14: 00007fd1955e5f40 R15: 00007fd1955e5ef8
  Modules linked in:
  ---[ end trace ec8931a1c36e57be ]---

(gdb) l *(__tree_mod_log_rewind+0x3b1)
0xffffffff81893521 is in __tree_mod_log_rewind (fs/btrfs/ctree.c:1210).

  1205                     * the modification. as we're going backwards, we do the
  1206                     * opposite of each operation here.
  1207                     */

1208 switch (tm->op) {
1209 case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
1210 BUG_ON(tm->slot < n);
1211 fallthrough;
1212 case MOD_LOG_KEY_REMOVE_WHILE_MOVING:
1213 case MOD_LOG_KEY_REMOVE:
1214 btrfs_set_node_key(eb, &tm->key, tm->slot);

Here's what happens to hit that BUG_ON():

1) We have one tree mod log user (through fiemap or the logical ino ioctl), with a sequence number of 1, so we have fs_info->tree_mod_seq == 1;

2) Another task is at ctree.c:balance_level() and we have eb X currently as the root of the tree, and we promote its single child, eb Y, as the new root.

Then, at ctree.c:balance_level(), we call:

      tree_mod_log_insert_root(eb X, eb Y, 1);

3) At tree_mod_log_insert_root() we create tree mod log elements for each slot of eb X, of operation type MOD_LOG_KEY_REMOVE_WHILE_FREEING each with a ->logical pointing to ebX->start. These are placed in an array named tm_list.
Lets assume there are N elements (N pointers in eb X);

4) Then, still at tree_mod_log_insert_root(), we create a tree mod log element of operation type MOD_LOG_ROOT_REPLACE, ->logical set to ebY->start, ->old_root.logical set to ebX->start, ->old_root.level set to the level of eb X and ->generation set to the generation of eb X;

5) Then tree_mod_log_insert_root() calls tree_mod_log_free_eb() with tm_list as argument. After that, tree_mod_log_free_eb() calls __tree_mod_log_insert() for each member of tm_list in reverse order, from highest slot in eb X, slot N - 1, to slot 0 of eb X;

6) __tree_mod_log_insert() sets the sequence number of each given tree mod log operation - it increments fs_info->tree_mod_seq and sets fs_info->tree_mod_seq as the sequence number of the given tree mod log operation.

This means that for the tm_list created at tree_mod_log_insert_root(), the element corresponding to slot 0 of eb X has the highest sequence number (1 + N), and the element corresponding to the last slot has the lowest sequence number (2);

7) Then, after inserting tm_list's elements into the tree mod log rbtree, the MOD_LOG_ROOT_REPLACE element is inserted, which gets the highest sequence number, which is N + 2;

8) Back to ctree.c:balance_level(), we free eb X by calling btrfs_free_tree_block() on it. Because eb X was created in the current transaction, has no other references and writeback did not happen for it, we add it back to the free space cache/tree;

9) Later some other task T allocates the metadata extent from eb X, since it is marked as free space in the space cache/tree, and uses it as a node for some other btree;

10) The tree mod log user task calls btrfs_search_old_slot(), which calls get_old_root(), and finally that calls __tree_mod_log_oldest_root() with time_seq == 1 and eb_root == eb Y;

11) First iteration of the while loop finds the tree mod log element with sequence number N + 2, for the logical address of eb Y and of type MOD_LOG_ROOT_REPLACE;

12) Because the operation type is MOD_LOG_ROOT_REPLACE, we don't break out

    of the loop, and set root_logical to point to tm->old_root.logical
    which corresponds to the logical address of eb X;

13) On the next iteration of the while loop, the call to tree_mod_log_search_oldest() returns the smallest tree mod log element for the logical address of eb X, which has a sequence number of 2, an operation type of MOD_LOG_KEY_REMOVE_WHILE_FREEING and corresponds to the old slot N - 1 of eb X (eb X had N items in it before being freed);

14) We then break out of the while loop and return the tree mod log operation of type MOD_LOG_ROOT_REPLACE (eb Y), and not the one for slot N - 1 of eb X, to get_old_root();

15) At get_old_root(), we process the MOD_LOG_ROOT_REPLACE operation and set "logical" to the logical address of eb X, which was the old root. We then call tree_mod_log_search() passing it the logical address of eb X and time_seq == 1;

16) Then before calling tree_mod_log_search(), task T adds a key to eb X, which results in adding a tree mod log operation of type MOD_LOG_KEY_ADD to the tree mod log - this is done at ctree.c:insert_ptr() - but after adding the tree mod log operation and before updating the number of items in eb X from 0 to 1...

17) The task at get_old_root() calls tree_mod_log_search() and gets the tree mod log operation of type MOD_LOG_KEY_ADD just added by task T. Then it enters the following if branch:

if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
(...)
} (...)

Calls read_tree_block() for eb X, which gets a reference on eb X but does not lock it - task T has it locked.
Then it clones eb X while it has nritems set to 0 in its header, before task T sets nritems to 1 in eb X's header. From hereupon we use the clone of eb X which no other task has access to;

18) Then we call __tree_mod_log_rewind(), passing it the MOD_LOG_KEY_ADD mod log operation we just got from tree_mod_log_search() in the previous step and the cloned version of eb X;

19) At __tree_mod_log_rewind(), we set the local variable "n" to the number of items set in eb X's clone, which is 0. Then we enter the while loop, and in its first iteration we process the MOD_LOG_KEY_ADD operation, which just decrements "n" from 0 to (u32)-1, since "n" is declared with a type of u32. At the end of this iteration we call rb_next() to find the next tree mod log operation for eb X, that gives us the mod log operation of type MOD_LOG_KEY_REMOVE_WHILE_FREEING, for slot 0, with a sequence number of N + 1 (steps 3 to 6);

20) Then we go back to the top of the while loop and trigger the following

    BUG_ON():

        (...)
        switch (tm->op) {
        case MOD_LOG_KEY_REMOVE_WHILE_FREEING:
                 BUG_ON(tm->slot < n);
                 fallthrough;
        (...)

    Because "n" has a value of (u32)-1 (4294967295) and tm->slot is 0.

Fix this by taking a read lock on the extent buffer before cloning it at ctree.c:get_old_root(). This should be done regardless of the extent buffer having been freed and reused, as a concurrent task might be modifying it (while holding a write lock on it).

---
 fs/btrfs/ctree.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1431,7 +1431,9 @@ get_old_root(struct btrfs_root *root, u6
 			btrfs_warn(root->fs_info,
 				"failed to read tree block %llu from get_old_root", logical);
 		} else {
+			btrfs_tree_read_lock(old);
 			eb = btrfs_clone_extent_buffer(old);
+			btrfs_tree_read_unlock(old);
 			free_extent_buffer(old);
 		}
 	} else if (old_root) {

From: Joe Korty <[email protected]>

commit c7de87ff9dac5f396f62d584f3908f80ddc0e07b upstream.

[ This problem is in mainline, but only rt has the chops to be able to detect it. ]

Lockdep reports a circular lock dependency between serv->sv_lock and softirq_ctl.lock on system shutdown, when using a kernel built with CONFIG_PREEMPT_RT=y, and a nfs mount exists.

This is due to the definition of spin_lock_bh on rt:

	local_bh_disable();
	rt_spin_lock(lock);

which forces a softirq_ctl.lock -> serv->sv_lock dependency. This is not a problem as long as _every_ lock of serv->sv_lock is a:

	spin_lock_bh(&serv->sv_lock);

but there is one of the form:

	spin_lock(&serv->sv_lock);

This is what is causing the circular dependency splat. The spin_lock() grabs the lock without first grabbing softirq_ctl.lock via local_bh_disable. If later on in the critical region, someone does a local_bh_disable, we get a serv->sv_lock -> softirq_ctrl.lock dependency established. Deadlock.

Fix is to make serv->sv_lock be locked with spin_lock_bh everywhere, no exceptions.

[ OK ] Stopped target NFS client services.
Stopping Logout off all iSCSI sessions on shutdown... Stopping NFS server and services...

[  109.442380]
[  109.442385] ======================================================
[  109.442386] WARNING: possible circular locking dependency detected
[  109.442387] 5.10.16-rt30 #1 Not tainted
[  109.442389] ------------------------------------------------------
[  109.442390] nfsd/1032 is trying to acquire lock:
[  109.442392] ffff994237617f60 ((softirq_ctrl.lock).lock){+.+.}-{2:2}, at: __local_bh_disable_ip+0xd9/0x270
[  109.442405]
[  109.442405] but task is already holding lock:
[  109.442406] ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442415]
[  109.442415] which lock already depends on the new lock.
[  109.442415]
[  109.442416]
[  109.442416] the existing dependency chain (in reverse order) is:
[  109.442417]
[  109.442417] -> #1 (&serv->sv_lock){+.+.}-{0:0}:
[  109.442421]        rt_spin_lock+0x2b/0xc0
[  109.442428]        svc_add_new_perm_xprt+0x42/0xa0
[  109.442430]        svc_addsock+0x135/0x220
[  109.442434]        write_ports+0x4b3/0x620
[  109.442438]        nfsctl_transaction_write+0x45/0x80
[  109.442440]        vfs_write+0xff/0x420
[  109.442444]        ksys_write+0x4f/0xc0
[  109.442446]        do_syscall_64+0x33/0x40
[  109.442450]        entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  109.442454]
[  109.442454] -> #0 ((softirq_ctrl.lock).lock){+.+.}-{2:2}:
[  109.442457]        __lock_acquire+0x1264/0x20b0
[  109.442463]        lock_acquire+0xc2/0x400
[  109.442466]        rt_spin_lock+0x2b/0xc0
[  109.442469]        __local_bh_disable_ip+0xd9/0x270
[  109.442471]        svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442474]        svc_close_list+0x60/0x90
[  109.442476]        svc_close_net+0x49/0x1a0
[  109.442478]        svc_shutdown_net+0x12/0x40
[  109.442480]        nfsd_destroy+0xc5/0x180
[  109.442482]        nfsd+0x1bc/0x270
[  109.442483]        kthread+0x194/0x1b0
[  109.442487]        ret_from_fork+0x22/0x30
[  109.442492]
[  109.442492] other info that might help us debug this:
[  109.442492]
[  109.442493]  Possible unsafe locking scenario:
[  109.442493]
[  109.442493]        CPU0                    CPU1
[  109.442494]        ----                    ----
[  109.442495]   lock(&serv->sv_lock);
[  109.442496]                                lock((softirq_ctrl.lock).lock);
[  109.442498]                                lock(&serv->sv_lock);
[  109.442499]   lock((softirq_ctrl.lock).lock);
[  109.442501]
[  109.442501]  *** DEADLOCK ***
[  109.442501]
[  109.442501] 3 locks held by nfsd/1032:
[  109.442503]  #0: ffffffff93b49258 (nfsd_mutex){+.+.}-{3:3}, at: nfsd+0x19a/0x270
[  109.442508]  #1: ffff994245cb00b0 (&serv->sv_lock){+.+.}-{0:0}, at: svc_close_list+0x1f/0x90
[  109.442512]  #2: ffffffff93a81b20 (rcu_read_lock){....}-{1:2}, at: rt_spin_lock+0x5/0xc0
[  109.442518]
[  109.442518] stack backtrace:
[  109.442519] CPU: 0 PID: 1032 Comm: nfsd Not tainted 5.10.16-rt30 #1
[  109.442522] Hardware name: Supermicro X9DRL-3F/iF/X9DRL-3F/iF, BIOS 3.2 09/22/2015
[  109.442524] Call Trace:
[  109.442527]  dump_stack+0x77/0x97
[  109.442533]  check_noncircular+0xdc/0xf0
[  109.442546]  __lock_acquire+0x1264/0x20b0
[  109.442553]  lock_acquire+0xc2/0x400
[  109.442564]  rt_spin_lock+0x2b/0xc0
[  109.442570]  __local_bh_disable_ip+0xd9/0x270
[  109.442573]  svc_xprt_do_enqueue+0xc0/0x4d0
[  109.442577]  svc_close_list+0x60/0x90
[  109.442581]  svc_close_net+0x49/0x1a0
[  109.442585]  svc_shutdown_net+0x12/0x40
[  109.442588]  nfsd_destroy+0xc5/0x180
[  109.442590]  nfsd+0x1bc/0x270
[  109.442595]  kthread+0x194/0x1b0
[  109.442600]  ret_from_fork+0x22/0x30
[  109.518225] nfsd: last server has exited, flushing export cache
[  OK  ] Stopped NFSv4 ID-name mapping service.
[  OK  ] Stopped GSSAPI Proxy Daemon.
[  OK  ] Stopped NFS Mount Daemon.
[  OK  ] Stopped NFS status monitor for NFSv2/3 locking..

---
 net/sunrpc/svc_xprt.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1011,7 +1011,7 @@ static int svc_close_list(struct svc_ser
 	struct svc_xprt *xprt;
 	int ret = 0;
 
-	spin_lock(&serv->sv_lock);
+	spin_lock_bh(&serv->sv_lock);
 	list_for_each_entry(xprt, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;

@@ -1019,7 +1019,7 @@ static int svc_close_list(struct svc_ser
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
 		svc_xprt_enqueue(xprt);
 	}
-	spin_unlock(&serv->sv_lock);
+	spin_unlock_bh(&serv->sv_lock);
 	return ret;
 }
 

From: Dan Carpenter <[email protected]>

commit 19f1bc7edf0f97186810e13a88f5b62069d89097 upstream.

If copy_from_user() or kstrtoull() fail then the correct behavior is to return a negative error code.

---
 drivers/scsi/lpfc/lpfc_debugfs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1061,7 +1061,7 @@ lpfc_debugfs_dif_err_write(struct file *
 	memset(dstbuf, 0, 32);
 	size = (nbytes < 32) ? nbytes : 32;
 	if (copy_from_user(dstbuf, buf, size))
-		return 0;
+		return -EFAULT;
 
 	if (dent == phba->debug_InjErrLBA) {
 		if ((buf[0] == 'o') && (buf[1] == 'f') && (buf[2] == 'f'))

@@ -1069,7 +1069,7 @@ lpfc_debugfs_dif_err_write(struct file *
 	}
 
 	if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp)))
-		return 0;
+		return -EINVAL;
 
 	if (dent == phba->debug_writeGuard)
 		phba->lpfc_injerr_wgrd_cnt = (uint32_t)tmp;

This is the start of the stable review cycle for the 4.4.263 release. There are 14 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 24 Mar 2021 12:19:09 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.263-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.4.263-rc1

Thomas Gleixner <[email protected]>
genirq: Disable interrupts for force threaded handlers

Shijie Luo <[email protected]>
ext4: fix potential error in ext4_do_update_inode

zhangyi (F) <[email protected]>
ext4: find old entry again if failed to rename whiteout

Thomas Gleixner <[email protected]>
x86/ioapic: Ignore IRQ2 again

Tyrel Datwyler <[email protected]>
PCI: rpadlpar: Fix potential drc_name corruption in store functions

Jim Lin <[email protected]>
usb: gadget: configfs: Fix KASAN use-after-free

Macpaul Lin <[email protected]>
USB: replace hardcode maximum usb string length by definition

Dan Carpenter <[email protected]>
scsi: lpfc: Fix some error codes in debugfs

Joe Korty <[email protected]>

    NFSD: Repair misuse of sv_lock in 5.10.16-rt30.

Filipe Manana <[email protected]>
btrfs: fix race when cloning extent buffer during rewind of an old root

Gwendal Grignou <[email protected]>
platform/chrome: cros_ec_dev - Fix security issue

Jan Kara <[email protected]>
ext4: check journal inode extents more carefully

Jan Kara <[email protected]>
ext4: don't allow overlapping system zones

Jan Kara <[email protected]>
ext4: handle error of ext4_setup_system_zone() on remount

-------------

Diffstat:

 Makefile                                |  4 +-
 arch/x86/kernel/apic/io_apic.c          | 10 +++++
 drivers/pci/hotplug/rpadlpar_sysfs.c    | 14 +++----
 drivers/platform/chrome/cros_ec_dev.c   |  4 ++
 drivers/platform/chrome/cros_ec_proto.c |  4 +-
 drivers/scsi/lpfc/lpfc_debugfs.c        |  4 +-
 drivers/usb/gadget/composite.c          |  4 +-
 drivers/usb/gadget/configfs.c           | 16 +++++---
 drivers/usb/gadget/usbstring.c          |  4 +-
 fs/btrfs/ctree.c                        |  2 +
 fs/ext4/block_validity.c                | 71 +++++++++++++++------------------
 fs/ext4/ext4.h                          |  6 +--
 fs/ext4/extents.c                       | 16 +++-----
 fs/ext4/indirect.c                      |  6 +--
 fs/ext4/inode.c                         | 13 +++---
 fs/ext4/mballoc.c                       |  4 +-
 fs/ext4/namei.c                         | 29 +++++++++++++-
 fs/ext4/super.c                         |  5 ++-
 include/linux/mfd/cros_ec.h             |  6 ++-
 include/uapi/linux/usb/ch9.h            |  3 ++
 kernel/irq/manage.c                     |  4 ++
 net/sunrpc/svc_xprt.c                   |  4 +-
 22 files changed, 139 insertions(+), 94 deletions(-)

From: Macpaul Lin <[email protected]>

commit 81c7462883b0cc0a4eeef0687f80ad5b5baee5f6 upstream.

Replace hardcoded maximum USB string length (126 bytes) by definition "USB_MAX_STRING_LEN".

---
 drivers/usb/gadget/composite.c |    4 ++--
 drivers/usb/gadget/configfs.c  |    2 +-
 drivers/usb/gadget/usbstring.c |    4 ++--
 include/uapi/linux/usb/ch9.h   |    3 +++
 4 files changed, 8 insertions(+), 5 deletions(-)

@@ -933,7 +933,7 @@ static void collect_langs(struct usb_gad
 	while (*sp) {
 		s = *sp;
 		language = cpu_to_le16(s->language);
-		for (tmp = buf; *tmp && tmp < &buf[126]; tmp++) {
+		for (tmp = buf; *tmp && tmp < &buf[USB_MAX_STRING_LEN]; tmp++) {
 			if (*tmp == language)
 				goto repeat;
 		}

@@ -1008,7 +1008,7 @@ static int get_string(struct usb_composi
 			collect_langs(sp, s->wData);
 		}
 
-		for (len = 0; len <= 126 && s->wData[len]; len++)
+		for (len = 0; len <= USB_MAX_STRING_LEN && s->wData[len]; len++)
 			continue;
 		if (!len)
 			return -EINVAL;

@@ -117,7 +117,7 @@ static int usb_string_copy(const char *s
 	char *str;
 	char *copy = *s_copy;
 	ret = strlen(s);
-	if (ret > 126)
+	if (ret > USB_MAX_STRING_LEN)
 		return -EOVERFLOW;
 
 	str = kstrdup(s, GFP_KERNEL);

@@ -59,9 +59,9 @@ usb_gadget_get_string (struct usb_gadget
 		return -EINVAL;
 
 	/* string descriptors have length, tag, then UTF16-LE text */
-	len = min ((size_t) 126, strlen (s->s));
+	len = min((size_t)USB_MAX_STRING_LEN, strlen(s->s));
 	len = utf8s_to_utf16s(s->s, len, UTF16_LITTLE_ENDIAN,
-			(wchar_t *) &buf[2], 126);
+			(wchar_t *) &buf[2], USB_MAX_STRING_LEN);
 	if (len < 0)
 		return -EINVAL;
 	buf [0] = (len + 1) * 2;

@@ -333,6 +333,9 @@ struct usb_config_descriptor {
 
 /*-------------------------------------------------------------------------*/
 
+/* USB String descriptors can contain at most 126 characters. */
+#define USB_MAX_STRING_LEN	126
+
 /* USB_DT_STRING: String descriptor */
 struct usb_string_descriptor {
 	__u8  bLength;

From: Tyrel Datwyler <[email protected]>

commit cc7a0bb058b85ea03db87169c60c7cfdd5d34678 upstream.

Both add_slot_store() and remove_slot_store() try to fix up the drc_name copied from the store buffer by placing a NUL terminator at nbyte + 1 or in place of a '\n' if present. However, the static buffer that we copy the drc_name data into is not zeroed and can contain anything past the n-th byte.

This is problematic if a '\n' byte appears in that buffer after nbytes and the string copied into the store buffer was not NUL terminated to start with as the strchr() search for a '\n' byte will mark this incorrectly as the end of the drc_name string resulting in a drc_name string that contains garbage data after the n-th byte.

Additionally it will cause us to overwrite that '\n' byte on the stack with NUL, potentially corrupting data on the stack.

The following debugging shows an example of the drmgr utility writing "PHB 4543" to the add_slot sysfs attribute, but add_slot_store() logging a corrupted string value.

drmgr: drmgr: -c phb -a -s PHB 4543 -d 1
add_slot_store: drc_name = PHB 4543°|<82>!, rc = -19

Fix this by using strscpy() instead of memcpy() to ensure the string is NUL terminated when copied into the static drc_name buffer. Further, since the string is now NUL terminated the code only needs to change '\n' to '\0' when present.

---
 drivers/pci/hotplug/rpadlpar_sysfs.c |   14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

@@ -39,12 +39,11 @@ static ssize_t add_slot_store(struct kob
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_add_slot(drc_name);
 	if (rc)

@@ -70,12 +69,11 @@ static ssize_t remove_slot_store(struct
 	if (nbytes >= MAX_DRC_NAME_LEN)
 		return 0;
 
-	memcpy(drc_name, buf, nbytes);
+	strscpy(drc_name, buf, nbytes + 1);
 
 	end = strchr(drc_name, '\n');
-	if (!end)
-		end = &drc_name[nbytes];
-	*end = '\0';
+	if (end)
+		*end = '\0';
 
 	rc = dlpar_remove_slot(drc_name);
 	if (rc)

From: Thomas Gleixner <[email protected]>

commit a501b048a95b79e1e34f03cac3c87ff1e9f229ad upstream.

Vitaly ran into an issue with hotplugging CPU0 on an Amazon instance where the matrix allocator claimed to be out of vectors. He analyzed it down to the point that IRQ2, the PIC cascade interrupt, which is supposed to be not ever routed to the IO/APIC ended up having an interrupt vector assigned which got moved during unplug of CPU0.

The underlying issue is that IRQ2 for various reasons (see commit af174783b925 ("x86: I/O APIC: Never configure IRQ2" for details) is treated as a reserved system vector by the vector core code and is not accounted as a regular vector. The Amazon BIOS has an routing entry of pin2 to IRQ2 which causes the IO/APIC setup to claim that interrupt which is granted by the vector domain because there is no sanity check. As a consequence the allocation counter of CPU0 underflows which causes a subsequent unplug to fail with:

[ ... ] CPU 0 has 4294967295 vectors, 589 available. Cannot disable CPU

There is another sanity check missing in the matrix allocator, but the underlying root cause is that the IO/APIC code lost the IRQ2 ignore logic during the conversion to irqdomains.

For almost 6 years nobody complained about this wreckage, which might indicate that this requirement could be lifted, but for any system which actually has a PIC IRQ2 is unusable by design so any routing entry has no effect and the interrupt cannot be connected to a device anyway.

Due to that and due to history biased paranoia reasons restore the IRQ2 ignore logic and treat it as non existent despite a routing entry claiming otherwise.

---
 arch/x86/kernel/apic/io_apic.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -1040,6 +1040,16 @@ static int mp_map_pin_to_irq(u32 gsi, in
 	if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].srcbusirq;
 		legacy = mp_is_legacy_irq(irq);
+		/*
+		 * IRQ2 is unusable for historical reasons on systems which
+		 * have a legacy PIC. See the comment vs. IRQ2 further down.
+		 *
+		 * If this gets removed at some point then the related code
+		 * in lapic_assign_system_vectors() needs to be adjusted as
+		 * well.
+		 */
+		if (legacy && irq == PIC_CASCADE_IR)
+			return -EINVAL;
 	}
 
 	mutex_lock(&ioapic_mutex);

From: zhangyi (F) <[email protected]>

commit b7ff91fd030dc9d72ed91b1aab36e445a003af4f upstream.

If we failed to add new entry on rename whiteout, we cannot reset the old->de entry directly, because the old->de could have moved from under us during make indexed dir. So find the old entry again before reset is needed, otherwise it may corrupt the filesystem as below.

/dev/sda: Entry '00000001' in ??? (12) has deleted/unused inode 15. CLEARED. /dev/sda: Unattached inode 75
/dev/sda: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.

---
 fs/ext4/namei.c |   29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

@@ -3375,6 +3375,31 @@ static int ext4_setent(handle_t *handle,
 	return 0;
 }
 
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+			  unsigned ino, unsigned file_type)
+{
+	struct ext4_renament old = *ent;
+	int retval = 0;
+
+	/*
+	 * old->de could have moved from under us during make indexed dir,
+	 * so the old->de may no longer valid and need to find it again
+	 * before reset old inode info.
+	 */
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	if (IS_ERR(old.bh))
+		retval = PTR_ERR(old.bh);
+	if (!old.bh)
+		retval = -ENOENT;
+	if (retval) {
+		ext4_std_error(old.dir->i_sb, retval);
+		return;
+	}
+
+	ext4_setent(handle, &old, ino, file_type);
+	brelse(old.bh);
+}
+
 static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 				  const struct qstr *d_name)
 {

@@ -3674,8 +3699,8 @@ static int ext4_rename(struct inode *old
 end_rename:
 	if (whiteout) {
 		if (retval) {
-			ext4_setent(handle, &old,
-				old.inode->i_ino, old_file_type);
+			ext4_resetent(handle, &old,
+				      old.inode->i_ino, old_file_type);
 			drop_nlink(whiteout);
 		}
 		unlock_new_inode(whiteout);

From: Shijie Luo <[email protected]>

commit 7d8bd3c76da1d94b85e6c9b7007e20e980bfcfe6 upstream.

If set_large_file = 1 and errors occur in ext4_handle_dirty_metadata(), the error code will be overridden, go to out_brelse to avoid this situation.

---
 fs/ext4/inode.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -4626,7 +4626,7 @@ static int ext4_do_update_inode(handle_t
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct buffer_head *bh = iloc->bh;
 	struct super_block *sb = inode->i_sb;
-	int err = 0, rc, block;
+	int err = 0, block;
 	int need_datasync = 0, set_large_file = 0;
 	uid_t i_uid;
 	gid_t i_gid;

@@ -4726,9 +4726,9 @@ static int ext4_do_update_inode(handle_t
 					      bh->b_data);
 
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
-	rc = ext4_handle_dirty_metadata(handle, NULL, bh);
-	if (!err)
-		err = rc;
+	err = ext4_handle_dirty_metadata(handle, NULL, bh);
+	if (err)
+		goto out_brelse;
 	ext4_clear_inode_state(inode, EXT4_STATE_NEW);
 	if (set_large_file) {
 		BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");

From: Jim Lin <[email protected]>

commit 98f153a10da403ddd5e9d98a3c8c2bb54bb5a0b6 upstream.

When gadget is disconnected, running sequence is like this. . composite_disconnect
. Call trace:

  usb_string_copy+0xd0/0x128
  gadget_config_name_configuration_store+0x4
  gadget_config_name_attr_store+0x40/0x50
  configfs_write_file+0x198/0x1f4
  vfs_write+0x100/0x220
  SyS_write+0x58/0xa8

. configfs_composite_unbind
. configfs_composite_bind

In configfs_composite_bind, it has
"cn->strings.s = cn->configuration;"

When usb_string_copy is invoked. it would
allocate memory, copy input string, release previous pointed memory space, and use new allocated memory.

When gadget is connected, host sends down request to get information.

Call trace:
  usb_gadget_get_string+0xec/0x168
  lookup_string+0x64/0x98
  composite_setup+0xa34/0x1ee8

If gadget is disconnected and connected quickly, in the failed case, cn->configuration memory has been released by usb_string_copy kfree but configfs_composite_bind hasn't been run in time to assign new allocated "cn->configuration" pointer to "cn->strings.s".

When "strlen(s->s) of usb_gadget_get_string is being executed, the dangling memory is accessed, "BUG: KASAN: use-after-free" error occurs.

---
 drivers/usb/gadget/configfs.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

@@ -111,6 +111,8 @@ struct gadget_config_name {
 	struct list_head list;
 };
 
+#define USB_MAX_STRING_WITH_NULL_LEN	(USB_MAX_STRING_LEN+1)
+
 static int usb_string_copy(const char *s, char **s_copy)
 {
 	int ret;

@@ -120,12 +122,16 @@ static int usb_string_copy(const char *s
 	if (ret > USB_MAX_STRING_LEN)
 		return -EOVERFLOW;
 
-	str = kstrdup(s, GFP_KERNEL);
-	if (!str)
-		return -ENOMEM;
+	if (copy) {
+		str = copy;
+	} else {
+		str = kmalloc(USB_MAX_STRING_WITH_NULL_LEN, GFP_KERNEL);
+		if (!str)
+			return -ENOMEM;
+	}
+	strcpy(str, s);
 	if (str[ret - 1] == '\n')
 		str[ret - 1] = '\0';
-	kfree(copy);
 	*s_copy = str;
 	return 0;
 }

From: Thomas Gleixner <[email protected]>

commit 81e2073c175b887398e5bca6c004efa89983f58d upstream.

With interrupt force threading all device interrupt handlers are invoked from kernel threads. Contrary to hard interrupt context the invocation only disables bottom halfs, but not interrupts. This was an oversight back then because any code like this will have an issue:

thread(irq_A)
irq_handler(A)

    spin_lock(&foo->lock);

interrupt(irq_B)
irq_handler(B)

    spin_lock(&foo->lock);

This has been triggered with networking (NAPI vs. hrtimers) and console drivers where printk() happens from an interrupt which interrupted the force threaded handler.

Now people noticed and started to change the spin_lock() in the handler to spin_lock_irqsave() which affects performance or add IRQF_NOTHREAD to the interrupt request which in turn breaks RT.

Fix the root cause and not the symptom and disable interrupts before invoking the force threaded handler which preserves the regular semantics and the usefulness of the interrupt force threading as a general debugging tool.

For not RT this is not changing much, except that during the execution of the threaded handler interrupts are delayed until the handler returns. Vs. scheduling and softirq processing there is no difference.

For RT kernels there is no issue.

---
 kernel/irq/manage.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -872,11 +872,15 @@ irq_forced_thread_fn(struct irq_desc *de
 	irqreturn_t ret;
 
 	local_bh_disable();
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE))
+		local_irq_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	if (ret == IRQ_HANDLED)
 		atomic_inc(&desc->threads_handled);
 
 	irq_finalize_oneshot(desc, action);
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_BASE))
+		local_irq_enable();
 	local_bh_enable();
 	return ret;
 }

From: Jan Kara <[email protected]>

commit d176b1f62f242ab259ff665a26fbac69db1aecba upstream.

ext4_setup_system_zone() can fail. Handle the failure in ext4_remount().

---
 fs/ext4/super.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -4968,7 +4968,10 @@ static int ext4_remount(struct super_blo
 		ext4_register_li_request(sb, first_not_zeroed);
 	}
 
-	ext4_setup_system_zone(sb);
+	err = ext4_setup_system_zone(sb);
+	if (err)
+		goto restore_opts;
+
 	if (sbi->s_journal == NULL && !(old_sb_flags & MS_RDONLY))
 		ext4_commit_super(sb, 1);
 

From: Jan Kara <[email protected]>

commit bf9a379d0980e7413d94cb18dac73db2bfc5f470 upstream.

Currently, add_system_zone() just silently merges two added system zones that overlap. However the overlap should not happen and it generally suggests that some unrelated metadata overlap which indicates the fs is corrupted. We should have caught such problems earlier (e.g. in ext4_check_descriptors()) but add this check as another line of defense. In later patch we also use this for stricter checking of journal inode extent tree.

---
 fs/ext4/block_validity.c |   34 ++++++++++++----------------------
 1 file changed, 12 insertions(+), 22 deletions(-)

@@ -57,7 +57,7 @@ static int add_system_zone(struct ext4_s
 			   ext4_fsblk_t start_blk,
 			   unsigned int count)
 {
-	struct ext4_system_zone *new_entry = NULL, *entry;
+	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &sbi->system_blks.rb_node, *node;
 	struct rb_node *parent = NULL, *new_node = NULL;
 

@@ -68,30 +68,20 @@ static int add_system_zone(struct ext4_s
 			n = &(*n)->rb_left;
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
-		else {
-			if (start_blk + count > (entry->start_blk +
-						 entry->count))
-				entry->count = (start_blk + count -
-						entry->start_blk);
-			new_node = *n;
-			new_entry = rb_entry(new_node, struct ext4_system_zone,
-					     node);
-			break;
-		}
+		else	/* Unexpected overlap of system zones. */
+			return -EFSCORRUPTED;
 	}
 
-	if (!new_entry) {
-		new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
-					     GFP_KERNEL);
-		if (!new_entry)
-			return -ENOMEM;
-		new_entry->start_blk = start_blk;
-		new_entry->count = count;
-		new_node = &new_entry->node;
+	new_entry = kmem_cache_alloc(ext4_system_zone_cachep,
+				     GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+	new_entry->start_blk = start_blk;
+	new_entry->count = count;
+	new_node = &new_entry->node;
 
-		rb_link_node(new_node, parent, n);
-		rb_insert_color(new_node, &sbi->system_blks);
-	}
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &sbi->system_blks);
 
 	/* Can we merge to the left? */
 	node = rb_prev(new_node);

All tests passing for Tegra ...

Test results for stable-v4.4:

    6 builds:	6 pass, 0 fail
    12 boots:	12 pass, 0 fail
    27 tests:	27 pass, 0 fail

Linux version: 4.4.263-rc1-g769f344ebed2
Boards tested: tegra124-jetson-tk1, tegra20-ventana,

                tegra30-cardhu-a04

Jon

Hi!

CIP testing did not find any problems here:

https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-4.4.y

Best regards,
Pavel

DENX Software Engineering GmbH,      Managing Director: Wolfgang Denk
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany

Build results:

	total: 163 pass: 163 fail: 0
Qemu test results:
	total: 329 pass: 329 fail: 0

Guenter

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

Summary
------------------------------------------------------------------------

kernel: 4.4.263-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-4.4.y
git commit: 769f344ebed2d7d9adc324015195b8c3fda886da
git describe: v4.4.262-15-g769f344ebed2
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-4.4.y/build/v4.4.262-15-g769f344ebed2

No regressions (compared to build v4.4.262)

No fixes (compared to build v4.4.262)

Ran 36066 total tests in the following environments and test suites.

Environments
--------------
- arm
- arm64
- i386
- juno-64k_page_size
- juno-r2 - arm64
- juno-r2-compat
- juno-r2-kasan
- mips
- qemu-arm64-kasan
- qemu-x86_64-kasan
- qemu_arm
- qemu_arm64
- qemu_arm64-compat
- qemu_i386
- qemu_x86_64
- qemu_x86_64-compat
- sparc
- x15 - arm
- x86_64
- x86-kasan
- x86_64

Test Suites
-----------
* build
* linux-log-parser
* libhugetlbfs
* ltp-commands-tests
* ltp-containers-tests
* ltp-math-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-securebits-tests
* ltp-tracing-tests
* network-basic-tests
* ltp-cap_bounds-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-mm-tests
* ltp-sched-tests
* ltp-syscalls-tests
* kselftest-android
* kselftest-bpf
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-livepatch
* kselftest-lkdtm
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-zram
* kvm-unit-tests
* ltp-open-posix-tests
* perf
* v4l2-compliance
* install-android-platform-tools-r2600
* kselftest-kvm
* kselftest-vm
* fwts

Summary
------------------------------------------------------------------------

kernel: 4.4.263-rc1
git repo: https://git.linaro.org/lkft/arm64-stable-rc.git
git branch: 4.4.263-rc1-hikey-20210322-970
git commit: cdbe5973893696eb29efb23b75953efd2f7edf4d
git describe: 4.4.263-rc1-hikey-20210322-970
Test details: https://qa-reports.linaro.org/lkft/linaro-hikey-stable-rc-4.4-oe/build/4.4.263-rc1-hikey-20210322-970

No regressions (compared to 4.4.263-rc1-hikey-20210319-968)

No fixes (compared to 4.4.263-rc1-hikey-20210319-968)

Ran 1863 total tests in the following environments and test suites.

Environments
--------------
- hi6220-hikey - arm64

Test Suites
-----------
* build
* install-android-platform-tools-r2600
* kselftest-android
* kselftest-bpf
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-lib
* kselftest-livepatch
* kselftest-lkdtm
* kselftest-membarrier
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-zram
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-cpuhotplug-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* perf
* spectre-meltdown-checker-test
* v4l2-compliance

Linaro LKFT
https://lkft.linaro.org