Merge tag 'v5.12' into next

Sync up with mainline to get the latest device tree bindings and kernel
APIs.

40 files changed, 384 insertions, 191 deletions

diff --git a/fs/afs/write.c b/fs/afs/write.c
index c9195fc67fd8..eb737ed63afb 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -851,8 +851,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	fscache_wait_on_page_write(vnode->cache, vmf->page);
 #endif
 
-	if (PageWriteback(vmf->page) &&
-	    wait_on_page_bit_killable(vmf->page, PG_writeback) < 0)
+	if (wait_on_page_writeback_killable(vmf->page))
 		return VM_FAULT_RETRY;
 
 	if (lock_page_killable(vmf->page) < 0)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 92ed7d5df677..09d6f7229db9 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -275,6 +275,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		bio.bi_opf = dio_bio_write_op(iocb);
 		task_io_account_write(ret);
 	}
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio.bi_opf |= REQ_NOWAIT;
 	if (iocb->ki_flags & IOCB_HIPRI)
 		bio_set_polled(&bio, iocb);
 
@@ -428,6 +430,8 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			bio->bi_opf = dio_bio_write_op(iocb);
 			task_io_account_write(bio->bi_iter.bi_size);
 		}
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			bio->bi_opf |= REQ_NOWAIT;
 
 		dio->size += bio->bi_iter.bi_size;
 		pos += bio->bi_iter.bi_size;
@@ -1240,13 +1244,13 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
-	clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
-
 rescan:
 	ret = blk_drop_partitions(bdev);
 	if (ret)
 		return ret;
 
+	clear_bit(GD_NEED_PART_SCAN, &disk->state);
+
 	/*
 	 * Historically we only set the capacity to zero for devices that
 	 * support partitions (independ of actually having partitions created).
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index b634c42115ea..b4fb997eda16 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute
 subdir-ccflags-y += -Wmissing-prototypes
 subdir-ccflags-y += -Wold-style-definition
 subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+	$(call cc-option, -Wunused-but-set-variable)		\
+	$(call cc-option, -Wunused-const-variable)		\
+	$(call cc-option, -Wpacked-not-aligned)			\
+	$(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
 # The following turn off the warnings enabled by -Wextra
 subdir-ccflags-y += -Wno-missing-field-initializers
 subdir-ccflags-y += -Wno-sign-compare
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 3a9c1e046ebe..d05f73530af7 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 	struct btrfs_dev_replace_item *ptr;
 	u64 src_devid;
 
+	if (!dev_root)
+		return 0;
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 41b718cfea40..289f1f09481d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	} else {
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 		fs_info->dev_root = root;
-		btrfs_init_devices_late(fs_info);
 	}
+	/* Initialize fs_info for all devices in any case */
+	btrfs_init_devices_late(fs_info);
 
 	/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
 	if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
@@ -3009,6 +3010,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	/*
+	 * btrfs_find_orphan_roots() is responsible for finding all the dead
+	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+	 * them into the fs_info->fs_roots_radix tree. This must be done before
+	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+	 * item before the root's tree is deleted - this means that if we unmount
+	 * or crash before the deletion completes, on the next mount we will not
+	 * delete what remains of the tree because the orphan item does not
+	 * exists anymore, which is what tells us we have a pending deletion.
+	 */
+	ret = btrfs_find_orphan_roots(fs_info);
+	if (ret)
+		goto out;
+
 	ret = btrfs_cleanup_fs_roots(fs_info);
 	if (ret)
 		goto out;
@@ -3068,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7cdf65be3707..a520775949a0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3099,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
  * @bio_offset:	offset to the beginning of the bio (in bytes)
  * @page:	page where is the data to be verified
  * @pgoff:	offset inside the page
+ * @start:	logical offset in the file
  *
  * The length of such check is always one sector size.
  */
 static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
-			   u32 bio_offset, struct page *page, u32 pgoff)
+			   u32 bio_offset, struct page *page, u32 pgoff,
+			   u64 start)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3130,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
 	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
-	btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
-				    csum, csum_expected, io_bio->mirror_num);
+	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+				    io_bio->mirror_num);
 	if (io_bio->device)
 		btrfs_dev_stat_inc_and_print(io_bio->device,
 					     BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3184,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
 	     pg_off += sectorsize, bio_offset += sectorsize) {
 		int ret;
 
-		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+		ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+				      page_offset(page) + pg_off);
 		if (ret < 0)
 			return -EIO;
 	}
@@ -7910,7 +7913,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
 			ASSERT(pgoff < PAGE_SIZE);
 			if (uptodate &&
 			    (!csum || !check_data_csum(inode, io_bio,
-					bio_offset, bvec.bv_page, pgoff))) {
+						       bio_offset, bvec.bv_page,
+						       pgoff, start))) {
 				clean_io_failure(fs_info, failure_tree, io_tree,
 						 start, bvec.bv_page,
 						 btrfs_ino(BTRFS_I(inode)),
@@ -8169,10 +8173,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
 		bio->bi_end_io = btrfs_end_dio_bio;
 		btrfs_io_bio(bio)->logical = file_offset;
 
-		WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
-			     fs_info->max_zone_append_size &&
-			     bio_op(bio) != REQ_OP_ZONE_APPEND);
-
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
 			status = extract_ordered_extent(BTRFS_I(inode), bio,
 							file_offset);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 14ff388fd3bd..f0b9ef13153a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup_list *list;
 
-	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
 	list_del(&qgroup->dirty);
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
@@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
 		list_del(&list->next_member);
 		kfree(list);
 	}
-	kfree(qgroup);
 }
 
 /* must be called with qgroup_lock held */
@@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 		qgroup = rb_entry(n, struct btrfs_qgroup, node);
 		rb_erase(n, &fs_info->qgroup_tree);
 		__del_qgroup_rb(fs_info, qgroup);
+		btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+		kfree(qgroup);
 	}
 	/*
 	 * We call btrfs_free_qgroup_config() when unmounting
@@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	spin_lock(&fs_info->qgroup_lock);
 	del_qgroup_rb(fs_info, qgroupid);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	/*
+	 * Remove the qgroup from sysfs now without holding the qgroup_lock
+	 * spinlock, since the sysfs_remove_group() function needs to take
+	 * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+	 */
+	btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+	kfree(qgroup);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bc3b33efddc5..1c6810bbaf8b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device,
 	int item_size;
 	int i, ret, slot;
 
+	if (!device->fs_info->dev_root)
+		return 0;
+
 	key.objectid = BTRFS_DEV_STATS_OBJECTID;
 	key.type = BTRFS_PERSISTENT_ITEM_KEY;
 	key.offset = device->devid;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 1f972b75a9ab..eeb3ebe11d7a 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -21,9 +21,30 @@
 /* Pseudo write pointer value for conventional zone */
 #define WP_CONVENTIONAL ((u64)-2)
 
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock:    0B (zone 0)
+ * - first copy:          512G (zone starting at that offset)
+ * - second copy:           4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET	(0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET	(512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET	(4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT	const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT	const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
 /* Number of superblock log zones */
 #define BTRFS_NR_SB_LOG_ZONES 2
 
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE		SZ_8G
+
 static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
 {
 	struct blk_zone *zones = data;
@@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
 }
 
 /*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- *  - The primary superblock: zones 0 and 1
- *  - The first copy: zones 16 and 17
- *  - The second copy: zones 1024 or zone at 256GB which is minimum, and
- *                     the following one
+ * Get the first zone number of the superblock mirror
  */
 static inline u32 sb_zone_number(int shift, int mirror)
 {
-	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+	u64 zone;
 
+	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
 	switch (mirror) {
-	case 0: return 0;
-	case 1: return 16;
-	case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+	case 0: zone = 0; break;
+	case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+	case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
 	}
 
-	return 0;
+	ASSERT(zone <= U32_MAX);
+
+	return (u32)zone;
 }
 
 /*
@@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
 		zone_sectors = bdev_zone_sectors(bdev);
 	}
 
-	nr_sectors = bdev_nr_sectors(bdev);
 	/* Check if it's power of 2 (see is_power_of_2) */
 	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
 	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+	/* We reject devices with a zone size larger than 8GB */
+	if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+		btrfs_err_in_rcu(fs_info,
+		"zoned: %s: zone size %llu larger than supported maximum %llu",
+				 rcu_str_deref(device->name),
+				 zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	nr_sectors = bdev_nr_sectors(bdev);
 	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
 	zone_info->max_zone_append_size =
 		(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index dfb14dbddf51..38bb7764b454 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -118,6 +118,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 	cache->mnt = path.mnt;
 	root = path.dentry;
 
+	ret = -EINVAL;
+	if (mnt_user_ns(path.mnt) != &init_user_ns) {
+		pr_warn("File cache on idmapped mounts not supported");
+		goto error_unsupported;
+	}
+
 	/* check parameters */
 	ret = -EOPNOTSUPP;
 	if (d_is_negative(root) ||
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index e027c718ca01..8ffc40e84a59 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -24,17 +24,16 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 		container_of(wait, struct cachefiles_one_read, monitor);
 	struct cachefiles_object *object;
 	struct fscache_retrieval *op = monitor->op;
-	struct wait_bit_key *key = _key;
+	struct wait_page_key *key = _key;
 	struct page *page = wait->private;
 
 	ASSERT(key);
 
 	_enter("{%lu},%u,%d,{%p,%u}",
 	       monitor->netfs_page->index, mode, sync,
-	       key->flags, key->bit_nr);
+	       key->page, key->bit_nr);
 
-	if (key->flags != &page->flags ||
-	    key->bit_nr != PG_locked)
+	if (key->page != page || key->bit_nr != PG_locked)
 		return 0;
 
 	_debug("--- monitor %p %lx ---", page, page->flags);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index fe03cbdae959..bf52e9326ebe 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -18,6 +18,7 @@ config CIFS
 	select CRYPTO_AES
 	select CRYPTO_LIB_DES
 	select KEYS
+	select DNS_RESOLVER
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
 	  (including support for the most recent, most secure dialect SMB3.1.1)
@@ -112,7 +113,6 @@ config CIFS_WEAK_PW_HASH
 config CIFS_UPCALL
 	bool "Kerberos/SPNEGO advanced session setup"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Enables an upcall mechanism for CIFS which accesses userspace helper
 	  utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
@@ -179,7 +179,6 @@ config CIFS_DEBUG_DUMP_KEYS
 config CIFS_DFS_UPCALL
 	bool "DFS feature support"
 	depends on CIFS
-	select DNS_RESOLVER
 	help
 	  Distributed File System (DFS) support is used to access shares
 	  transparently in an enterprise name space, even if the share
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 5213b20843b5..3ee3b7de4ded 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -10,13 +10,14 @@ cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \
 	  cifs_unicode.o nterr.o cifsencrypt.o \
 	  readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \
 	  smb2ops.o smb2maperror.o smb2transport.o \
-	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o
+	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \
+	  dns_resolve.o
 
 cifs-$(CONFIG_CIFS_XATTR) += xattr.o
 
 cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
 
-cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o
+cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o
 
 cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o
 
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 2be22a5c690f..d178cf85e926 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1130,8 +1130,7 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
 		}
 
 		/* If it's any one of the ACE we're replacing, skip! */
-		if (!mode_from_sid &&
-				((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+		if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
 				(compare_sids(&pntace->sid, pownersid) == 0) ||
 				(compare_sids(&pntace->sid, pgrpsid) == 0) ||
 				(compare_sids(&pntace->sid, &sid_everyone) == 0) ||
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 099ad9f3660b..5ddd20b62484 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -476,7 +476,8 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root)
 		seq_puts(m, "none");
 	else {
 		convert_delimiter(devname, '/');
-		seq_puts(m, devname);
+		/* escape all spaces in share names */
+		seq_escape(m, devname, " \t");
 		kfree(devname);
 	}
 	return 0;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 31fc8695abd6..ec824ab8c5ca 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -919,8 +919,8 @@ struct cifs_ses {
 	bool binding:1; /* are we binding the session? */
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
-	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+	__u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
+	__u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE];
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 
 	__u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
@@ -1283,8 +1283,6 @@ struct cifs_aio_ctx {
 	bool			direct_io;
 };
 
-struct cifs_readdata;
-
 /* asynchronous read support */
 struct cifs_readdata {
 	struct kref			refcount;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 64fe5a47b5e8..9adc74bd9f8f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -147,6 +147,11 @@
  */
 #define SMB3_SIGN_KEY_SIZE (16)
 
+/*
+ * Size of the smb3 encryption/decryption keys
+ */
+#define SMB3_ENC_DEC_KEY_SIZE (32)
+
 #define CIFS_CLIENT_CHALLENGE_SIZE (8)
 #define CIFS_SERVER_CHALLENGE_SIZE (8)
 #define CIFS_HMAC_MD5_HASH_SIZE (16)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index eec8a2052da2..24668eb006c6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -87,7 +87,6 @@ static void cifs_prune_tlinks(struct work_struct *work);
  *
  * This should be called with server->srv_mutex held.
  */
-#ifdef CONFIG_CIFS_DFS_UPCALL
 static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 {
 	int rc;
@@ -124,6 +123,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	return !rc ? -1 : 0;
 }
 
+#ifdef CONFIG_CIFS_DFS_UPCALL
 /* These functions must be called with server->srv_mutex held */
 static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
 				       struct cifs_sb_info *cifs_sb,
@@ -321,14 +321,29 @@ cifs_reconnect(struct TCP_Server_Info *server)
 #endif
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
+		if (cifs_sb && cifs_sb->origin_fullpath)
 			/*
 			 * Set up next DFS target server (if any) for reconnect. If DFS
 			 * feature is disabled, then we will retry last server we
 			 * connected to before.
 			 */
 			reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+		else {
+#endif
+			/*
+			 * Resolve the hostname again to make sure that IP address is up-to-date.
+			 */
+			rc = reconn_set_ipaddr_from_hostname(server);
+			if (rc) {
+				cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+						__func__, rc);
+			}
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+		}
 #endif
 
+
 #ifdef CONFIG_CIFS_SWN_UPCALL
 		}
 #endif
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 26de4329d161..042e24aad410 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -165,6 +165,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
 			goto posix_open_ret;
 		}
 	} else {
+		cifs_revalidate_mapping(*pinode);
 		cifs_fattr_to_inode(*pinode, &fattr);
 	}
 
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 99a1951a01ec..d9a990c99121 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -58,6 +58,7 @@
 #define SMB2_HMACSHA256_SIZE (32)
 #define SMB2_CMACAES_SIZE (16)
 #define SMB3_SIGNKEY_SIZE (16)
+#define SMB3_GCM128_CRYPTKEY_SIZE (16)
 #define SMB3_GCM256_CRYPTKEY_SIZE (32)
 
 /* Maximum buffer size value we can send with 1 credit */
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index b50164e2c88d..aac384f69f74 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -754,8 +754,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 		}
 	}
 	spin_unlock(&cifs_tcp_ses_lock);
-	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
-	return false;
+	cifs_dbg(FYI, "No file id matched, oplock break ignored\n");
+	return true;
 }
 
 void
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 9bae7e8deb09..f703204fb185 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2038,6 +2038,7 @@ smb2_duplicate_extents(const unsigned int xid,
 {
 	int rc;
 	unsigned int ret_data_len;
+	struct inode *inode;
 	struct duplicate_extents_to_file dup_ext_buf;
 	struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
 
@@ -2054,10 +2055,21 @@ smb2_duplicate_extents(const unsigned int xid,
 	cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
 		src_off, dest_off, len);
 
-	rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
-	if (rc)
-		goto duplicate_extents_out;
+	inode = d_inode(trgtfile->dentry);
+	if (inode->i_size < dest_off + len) {
+		rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
+		if (rc)
+			goto duplicate_extents_out;
 
+		/*
+		 * Although also could set plausible allocation size (i_blocks)
+		 * here in addition to setting the file size, in reflink
+		 * it is likely that the target file is sparse. Its allocation
+		 * size will be queried on next revalidate, but it is important
+		 * to make sure that file's cached size is updated immediately
+		 */
+		cifs_setsize(inode, dest_off + len);
+	}
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
@@ -4158,7 +4170,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
 			if (ses->Suid == ses_id) {
 				ses_enc_key = enc ? ses->smb3encryptionkey :
 					ses->smb3decryptionkey;
-				memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+				memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
 				spin_unlock(&cifs_tcp_ses_lock);
 				return 0;
 			}
@@ -4185,7 +4197,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	int rc = 0;
 	struct scatterlist *sg;
 	u8 sign[SMB2_SIGNATURE_SIZE] = {};
-	u8 key[SMB3_SIGN_KEY_SIZE];
+	u8 key[SMB3_ENC_DEC_KEY_SIZE];
 	struct aead_request *req;
 	char *iv;
 	unsigned int iv_len;
@@ -4209,10 +4221,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst,
 	tfm = enc ? server->secmech.ccmaesencrypt :
 						server->secmech.ccmaesdecrypt;
 
-	if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM))
 		rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE);
 	else
-		rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+		rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE);
 
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index ebccd71cc60a..e6fa76ab70be 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 {
 	unsigned char zero = 0x0;
 	__u8 i[4] = {0, 0, 0, 1};
-	__u8 L[4] = {0, 0, 0, 128};
+	__u8 L128[4] = {0, 0, 0, 128};
+	__u8 L256[4] = {0, 0, 1, 0};
 	int rc = 0;
 	unsigned char prfhash[SMB2_HMACSHA256_SIZE];
 	unsigned char *hashptr = prfhash;
@@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label,
 		goto smb3signkey_ret;
 	}
 
-	rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
-				L, 4);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L256, 4);
+	} else {
+		rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+				L128, 4);
+	}
 	if (rc) {
 		cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__);
 		goto smb3signkey_ret;
@@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses,
 			const struct derivation_triplet *ptriplet)
 {
 	int rc;
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+	struct TCP_Server_Info *server = ses->server;
+#endif
 
 	/*
 	 * All channels use the same encryption/decryption keys but
@@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses,
 		rc = generate_key(ses, ptriplet->encryption.label,
 				  ptriplet->encryption.context,
 				  ses->smb3encryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		rc = generate_key(ses, ptriplet->decryption.label,
 				  ptriplet->decryption.context,
 				  ses->smb3decryptionkey,
-				  SMB3_SIGN_KEY_SIZE);
+				  SMB3_ENC_DEC_KEY_SIZE);
 		if (rc)
 			return rc;
 	}
@@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses,
 	 */
 	cifs_dbg(VFS, "Session Id    %*ph\n", (int)sizeof(ses->Suid),
 			&ses->Suid);
+	cifs_dbg(VFS, "Cipher type   %d\n", server->cipher_type);
 	cifs_dbg(VFS, "Session Key   %*ph\n",
 		 SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
 	cifs_dbg(VFS, "Signing Key   %*ph\n",
 		 SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
-	cifs_dbg(VFS, "ServerIn Key  %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
-	cifs_dbg(VFS, "ServerOut Key %*ph\n",
-		 SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+	if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+		(server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	} else {
+		cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+		cifs_dbg(VFS, "ServerOut Key %*ph\n",
+				SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+	}
 #endif
 	return rc;
 }
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 128d63df5bfb..ef5ca22bfb3e 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -175,10 +175,10 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	ret = call_mmap(vma->vm_file, vma);
 
 	if (ret) {
-		/* if call_mmap fails, our caller will put coda_file so we
-		 * should drop the reference to the host_file that we got.
+		/* if call_mmap fails, our caller will put host_file so we
+		 * should drop the reference to the coda_file that we got.
 		 */
-		fput(host_file);
+		fput(coda_file);
 		kfree(cvm_ops);
 	} else {
 		/* here we add redirects for the open/close vm_operations */
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b61491bf3166..b2e86e739d7a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 		    struct buffer_head *map_bh)
 {
 	int ret = 0;
+	int boundary = sdio->boundary;	/* dio_send_cur_page may clear it */
 
 	if (dio->op == REQ_OP_WRITE) {
 		/*
@@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
 	sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
 out:
 	/*
-	 * If sdio->boundary then we want to schedule the IO now to
+	 * If boundary then we want to schedule the IO now to
 	 * avoid metadata seeks.
 	 */
-	if (sdio->boundary) {
+	if (boundary) {
 		ret = dio_send_cur_page(dio, sdio, map_bh);
 		if (sdio->bio)
 			dio_bio_submit(dio, sdio);
diff --git a/fs/file.c b/fs/file.c
index f3a4bac2cbe9..f633348029a5 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -629,17 +629,30 @@ int close_fd(unsigned fd)
 }
 EXPORT_SYMBOL(close_fd); /* for ksys_close() */
 
+/**
+ * last_fd - return last valid index into fd table
+ * @cur_fds: files struct
+ *
+ * Context: Either rcu read lock or files_lock must be held.
+ *
+ * Returns: Last valid index into fdtable.
+ */
+static inline unsigned last_fd(struct fdtable *fdt)
+{
+	return fdt->max_fds - 1;
+}
+
 static inline void __range_cloexec(struct files_struct *cur_fds,
 				   unsigned int fd, unsigned int max_fd)
 {
 	struct fdtable *fdt;
 
-	if (fd > max_fd)
-		return;
-
+	/* make sure we're using the correct maximum value */
 	spin_lock(&cur_fds->file_lock);
 	fdt = files_fdtable(cur_fds);
-	bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+	max_fd = min(last_fd(fdt), max_fd);
+	if (fd <= max_fd)
+		bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
 	spin_unlock(&cur_fds->file_lock);
 }
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 97076d3f562f..8fb9602d79b4 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -162,8 +162,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	int error;
 
 	error = init_threads(sdp);
-	if (error)
+	if (error) {
+		gfs2_withdraw_delayed(sdp);
 		return error;
+	}
 
 	j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
 	if (gfs2_withdrawn(sdp)) {
@@ -750,11 +752,13 @@ void gfs2_freeze_func(struct work_struct *work)
 static int gfs2_freeze(struct super_block *sb)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
-	int error = 0;
+	int error;
 
 	mutex_lock(&sdp->sd_freeze_mutex);
-	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
+	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) {
+		error = -EBUSY;
 		goto out;
+	}
 
 	for (;;) {
 		if (gfs2_withdrawn(sdp)) {
@@ -795,10 +799,10 @@ static int gfs2_unfreeze(struct super_block *sb)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 
 	mutex_lock(&sdp->sd_freeze_mutex);
-        if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
+	if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
 	    !gfs2_holder_initialized(&sdp->sd_freeze_gh)) {
 		mutex_unlock(&sdp->sd_freeze_mutex);
-                return 0;
+		return -EINVAL;
 	}
 
 	gfs2_freeze_unlock(&sdp->sd_freeze_gh);
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 29e407762626..743a005a5c64 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -144,7 +144,7 @@ static char *follow_link(char *link)
 	char *name, *resolved, *end;
 	int n;
 
-	name = __getname();
+	name = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!name) {
 		n = -ENOMEM;
 		goto out_free;
@@ -173,12 +173,11 @@ static char *follow_link(char *link)
 		goto out_free;
 	}
 
-	__putname(name);
-	kfree(link);
+	kfree(name);
 	return resolved;
 
  out_free:
-	__putname(name);
+	kfree(name);
 	return ERR_PTR(n);
 }
 
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 3dc10bfd8c3b..4eba531bea5a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -16,7 +16,6 @@
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
 #include <linux/tracehook.h>
-#include <linux/freezer.h>
 
 #include "../kernel/sched/sched.h"
 #include "io-wq.h"
@@ -388,11 +387,9 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe)
 
 static bool io_flush_signals(void)
 {
-	if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
+	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
 		__set_current_state(TASK_RUNNING);
-		if (current->task_works)
-			task_work_run();
-		clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+		tracehook_notify_signal();
 		return true;
 	}
 	return false;
@@ -418,6 +415,7 @@ static void io_worker_handle_work(struct io_worker *worker)
 {
 	struct io_wqe *wqe = worker->wqe;
 	struct io_wq *wq = wqe->wq;
+	bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
 
 	do {
 		struct io_wq_work *work;
@@ -447,6 +445,9 @@ get_next:
 			unsigned int hash = io_get_work_hash(work);
 
 			next_hashed = wq_next_work(work);
+
+			if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
+				work->flags |= IO_WQ_WORK_CANCEL;
 			wq->do_work(work);
 			io_assign_current_work(worker, NULL);
 
@@ -487,7 +488,7 @@ static int io_wqe_worker(void *data)
 	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
 	io_wqe_inc_running(worker);
 
-	sprintf(buf, "iou-wrk-%d", wq->task_pid);
+	snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task_pid);
 	set_task_comm(current, buf);
 
 	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
@@ -505,10 +506,15 @@ loop:
 		if (io_flush_signals())
 			continue;
 		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
-		if (try_to_freeze() || ret)
-			continue;
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			break;
+		}
+		if (ret)
+			continue;
 		/* timed out, exit unless we're the fixed worker */
 		if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
 		    !(worker->flags & IO_WORKER_F_FIXED))
@@ -709,16 +715,20 @@ static int io_wq_manager(void *data)
 	char buf[TASK_COMM_LEN];
 	int node;
 
-	sprintf(buf, "iou-mgr-%d", wq->task_pid);
+	snprintf(buf, sizeof(buf), "iou-mgr-%d", wq->task_pid);
 	set_task_comm(current, buf);
 
 	do {
 		set_current_state(TASK_INTERRUPTIBLE);
 		io_wq_check_workers(wq);
 		schedule_timeout(HZ);
-		try_to_freeze();
-		if (fatal_signal_pending(current))
+		if (signal_pending(current)) {
+			struct ksignal ksig;
+
+			if (!get_signal(&ksig))
+				continue;
 			set_bit(IO_WQ_BIT_EXIT, &wq->state);
+		}
 	} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
 
 	io_wq_check_workers(wq);
@@ -1065,7 +1075,11 @@ static void io_wq_destroy(struct io_wq *wq)
 
 	for_each_node(node) {
 		struct io_wqe *wqe = wq->wqes[node];
-		WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+		struct io_cb_cancel_data match = {
+			.fn		= io_wq_work_match_all,
+			.cancel_all	= true,
+		};
+		io_wqe_cancel_pending_work(wqe, &match);
 		kfree(wqe);
 	}
 	io_wq_put_hash(wq->hash);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 543551d70327..dff34975d86b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -78,7 +78,6 @@
 #include <linux/task_work.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring.h>
-#include <linux/freezer.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -698,6 +697,7 @@ enum {
 	REQ_F_NO_FILE_TABLE_BIT,
 	REQ_F_LTIMEOUT_ACTIVE_BIT,
 	REQ_F_COMPLETE_INLINE_BIT,
+	REQ_F_REISSUE_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -741,6 +741,8 @@ enum {
 	REQ_F_LTIMEOUT_ACTIVE	= BIT(REQ_F_LTIMEOUT_ACTIVE_BIT),
 	/* completion is deferred through io_comp_state */
 	REQ_F_COMPLETE_INLINE	= BIT(REQ_F_COMPLETE_INLINE_BIT),
+	/* caller should reissue async */
+	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
 };
 
 struct async_poll {
@@ -1095,8 +1097,6 @@ static bool io_match_task(struct io_kiocb *head,
 	io_for_each_link(req, head) {
 		if (req->flags & REQ_F_INFLIGHT)
 			return true;
-		if (req->task->files == files)
-			return true;
 	}
 	return false;
 }
@@ -1216,7 +1216,7 @@ static void io_prep_async_work(struct io_kiocb *req)
 	if (req->flags & REQ_F_ISREG) {
 		if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
 			io_wq_hash_work(&req->work, file_inode(req->file));
-	} else {
+	} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
 		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
 	}
@@ -1239,16 +1239,16 @@ static void io_queue_async_work(struct io_kiocb *req)
 	BUG_ON(!tctx);
 	BUG_ON(!tctx->io_wq);
 
-	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
-					&req->work, req->flags);
 	/* init ->work of the whole link before punting */
 	io_prep_async_link(req);
+	trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+					&req->work, req->flags);
 	io_wq_enqueue(tctx->io_wq, &req->work);
 	if (link)
 		io_queue_linked_timeout(link);
 }
 
-static void io_kill_timeout(struct io_kiocb *req)
+static void io_kill_timeout(struct io_kiocb *req, int status)
 {
 	struct io_timeout_data *io = req->async_data;
 	int ret;
@@ -1258,31 +1258,11 @@ static void io_kill_timeout(struct io_kiocb *req)
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
-		io_cqring_fill_event(req, 0);
+		io_cqring_fill_event(req, status);
 		io_put_req_deferred(req, 1);
 	}
 }
 
-/*
- * Returns true if we found and killed one or more timeouts
- */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
-			     struct files_struct *files)
-{
-	struct io_kiocb *req, *tmp;
-	int canceled = 0;
-
-	spin_lock_irq(&ctx->completion_lock);
-	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
-		if (io_match_task(req, tsk, files)) {
-			io_kill_timeout(req);
-			canceled++;
-		}
-	}
-	spin_unlock_irq(&ctx->completion_lock);
-	return canceled != 0;
-}
-
 static void __io_queue_deferred(struct io_ring_ctx *ctx)
 {
 	do {
@@ -1327,7 +1307,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 			break;
 
 		list_del_init(&req->timeout.list);
-		io_kill_timeout(req);
+		io_kill_timeout(req, 0);
 	} while (!list_empty(&ctx->timeout_list));
 
 	ctx->cq_last_tm_flush = seq;
@@ -2499,6 +2479,11 @@ static bool io_rw_should_reissue(struct io_kiocb *req)
 		return false;
 	return true;
 }
+#else
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+	return false;
+}
 #endif
 
 static bool io_rw_reissue(struct io_kiocb *req)
@@ -2524,13 +2509,14 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2,
 {
 	int cflags = 0;
 
-	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
+	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
+	if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) {
+		req->flags |= REQ_F_REISSUE;
 		return;
+	}
 	if (res != req->result)
 		req_set_fail_links(req);
-
-	if (req->rw.kiocb.ki_flags & IOCB_WRITE)
-		kiocb_end_write(req);
 	if (req->flags & REQ_F_BUFFER_SELECTED)
 		cflags = io_put_rw_kbuf(req);
 	__io_req_complete(req, issue_flags, res, cflags);
@@ -2776,6 +2762,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
 	struct io_async_rw *io = req->async_data;
+	bool check_reissue = kiocb->ki_complete == io_complete_rw;
 
 	/* add previously done IO, if any */
 	if (io && io->bytes_done > 0) {
@@ -2791,6 +2778,18 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
 		__io_complete_rw(req, ret, 0, issue_flags);
 	else
 		io_rw_done(kiocb, ret);
+
+	if (check_reissue && req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
+		if (!io_rw_reissue(req)) {
+			int cflags = 0;
+
+			req_set_fail_links(req);
+			if (req->flags & REQ_F_BUFFER_SELECTED)
+				cflags = io_put_rw_kbuf(req);
+			__io_req_complete(req, issue_flags, ret, cflags);
+		}
+	}
 }
 
 static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
@@ -3307,11 +3306,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = io_iter_do_read(req, iter);
 
-	if (ret == -EIOCBQUEUED) {
-		if (req->async_data)
-			iov_iter_revert(iter, io_size - iov_iter_count(iter));
-		goto out_free;
-	} else if (ret == -EAGAIN) {
+	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+		req->flags &= ~REQ_F_REISSUE;
 		/* IOPOLL retry should happen for io-wq threads */
 		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
 			goto done;
@@ -3321,6 +3317,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 		/* some cases will consume bytes even on error returns */
 		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 		ret = 0;
+	} else if (ret == -EIOCBQUEUED) {
+		goto out_free;
 	} else if (ret <= 0 || ret == io_size || !force_nonblock ||
 		   (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
 		/* read all, failed, already did sync or don't want to retry */
@@ -3433,6 +3431,11 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	else
 		ret2 = -EINVAL;
 
+	if (req->flags & REQ_F_REISSUE) {
+		req->flags &= ~REQ_F_REISSUE;
+		ret2 = -EAGAIN;
+	}
+
 	/*
 	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
 	 * retry them without IOCB_NOWAIT.
@@ -3442,8 +3445,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	/* no retry on NONBLOCK nor RWF_NOWAIT */
 	if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
 		goto done;
-	if (ret2 == -EIOCBQUEUED && req->async_data)
-		iov_iter_revert(iter, io_size - iov_iter_count(iter));
 	if (!force_nonblock || ret2 != -EAGAIN) {
 		/* IOPOLL retry should happen for io-wq threads */
 		if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
@@ -3978,6 +3979,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
 static int io_provide_buffers_prep(struct io_kiocb *req,
 				   const struct io_uring_sqe *sqe)
 {
+	unsigned long size;
 	struct io_provide_buf *p = &req->pbuf;
 	u64 tmp;
 
@@ -3991,7 +3993,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req,
 	p->addr = READ_ONCE(sqe->addr);
 	p->len = READ_ONCE(sqe->len);
 
-	if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
+	size = (unsigned long)p->len * p->nbufs;
+	if (!access_ok(u64_to_user_ptr(p->addr), size))
 		return -EFAULT;
 
 	p->bgid = READ_ONCE(sqe->buf_group);
@@ -4820,7 +4823,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
 			ret = -ENOMEM;
 			goto out;
 		}
-		io = req->async_data;
 		memcpy(req->async_data, &__io, sizeof(__io));
 		return -EAGAIN;
 	}
@@ -5583,7 +5585,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 
 	data->mode = io_translate_timeout_mode(flags);
 	hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
-	io_req_track_inflight(req);
+	if (is_timeout_link)
+		io_req_track_inflight(req);
 	return 0;
 }
 
@@ -6479,8 +6482,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	ret = io_init_req(ctx, req, sqe);
 	if (unlikely(ret)) {
 fail_req:
-		io_put_req(req);
-		io_req_complete(req, ret);
 		if (link->head) {
 			/* fail even hard links since we don't submit */
 			link->head->flags |= REQ_F_FAIL_LINK;
@@ -6488,6 +6489,8 @@ fail_req:
 			io_req_complete(link->head, -ECANCELED);
 			link->head = NULL;
 		}
+		io_put_req(req);
+		io_req_complete(req, ret);
 		return ret;
 	}
 	ret = io_req_prep(req, sqe);
@@ -6740,7 +6743,7 @@ static int io_sq_thread(void *data)
 	char buf[TASK_COMM_LEN];
 	DEFINE_WAIT(wait);
 
-	sprintf(buf, "iou-sqp-%d", sqd->task_pid);
+	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
 	set_task_comm(current, buf);
 	current->pf_io_worker = NULL;
 
@@ -6751,21 +6754,32 @@ static int io_sq_thread(void *data)
 	current->flags |= PF_NO_SETAFFINITY;
 
 	mutex_lock(&sqd->lock);
+	/* a user may had exited before the thread started */
+	io_run_task_work_head(&sqd->park_task_work);
+
 	while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
 		int ret;
 		bool cap_entries, sqt_spin, needs_sched;
 
-		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
+		if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
+		    signal_pending(current)) {
+			bool did_sig = false;
+
 			mutex_unlock(&sqd->lock);
+			if (signal_pending(current)) {
+				struct ksignal ksig;
+
+				did_sig = get_signal(&ksig);
+			}
 			cond_resched();
 			mutex_lock(&sqd->lock);
 			io_run_task_work();
 			io_run_task_work_head(&sqd->park_task_work);
+			if (did_sig)
+				break;
 			timeout = jiffies + sqd->sq_thread_idle;
 			continue;
 		}
-		if (fatal_signal_pending(current))
-			break;
 		sqt_spin = false;
 		cap_entries = !list_is_singular(&sqd->ctx_list);
 		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
@@ -6808,7 +6822,6 @@ static int io_sq_thread(void *data)
 
 			mutex_unlock(&sqd->lock);
 			schedule();
-			try_to_freeze();
 			mutex_lock(&sqd->lock);
 			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 				io_ring_clear_wakeup_flag(ctx);
@@ -6873,7 +6886,7 @@ static int io_run_task_work_sig(void)
 		return 1;
 	if (!signal_pending(current))
 		return 0;
-	if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
 		return -ERESTARTSYS;
 	return -EINTR;
 }
@@ -8563,6 +8576,14 @@ static void io_ring_exit_work(struct work_struct *work)
 	struct io_tctx_node *node;
 	int ret;
 
+	/* prevent SQPOLL from submitting new requests */
+	if (ctx->sq_data) {
+		io_sq_thread_park(ctx->sq_data);
+		list_del_init(&ctx->sqd_list);
+		io_sqd_update_thread_idle(ctx->sq_data);
+		io_sq_thread_unpark(ctx->sq_data);
+	}
+
 	/*
 	 * If we're doing polled IO and end up having requests being
 	 * submitted async (out-of-line), then completions can come in while
@@ -8599,6 +8620,28 @@ static void io_ring_exit_work(struct work_struct *work)
 	io_ring_ctx_free(ctx);
 }
 
+/* Returns true if we found and killed one or more timeouts */
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+			     struct files_struct *files)
+{
+	struct io_kiocb *req, *tmp;
+	int canceled = 0;
+
+	spin_lock_irq(&ctx->completion_lock);
+	list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
+		if (io_match_task(req, tsk, files)) {
+			io_kill_timeout(req, -ECANCELED);
+			canceled++;
+		}
+	}
+	if (canceled != 0)
+		io_commit_cqring(ctx);
+	spin_unlock_irq(&ctx->completion_lock);
+	if (canceled != 0)
+		io_cqring_ev_posted(ctx);
+	return canceled != 0;
+}
+
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
 	unsigned long index;
@@ -8614,14 +8657,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		io_unregister_personality(ctx, index);
 	mutex_unlock(&ctx->uring_lock);
 
-	/* prevent SQPOLL from submitting new requests */
-	if (ctx->sq_data) {
-		io_sq_thread_park(ctx->sq_data);
-		list_del_init(&ctx->sqd_list);
-		io_sqd_update_thread_idle(ctx->sq_data);
-		io_sq_thread_unpark(ctx->sq_data);
-	}
-
 	io_kill_timeouts(ctx, NULL, NULL);
 	io_poll_remove_all(ctx, NULL, NULL);
 
@@ -8998,6 +9033,8 @@ void __io_uring_task_cancel(void)
 
 	/* make sure overflow events are dropped */
 	atomic_inc(&tctx->in_idle);
+	__io_uring_files_cancel(NULL);
+
 	do {
 		/* read completions before cancelations */
 		inflight = tctx_inflight(tctx);
diff --git a/fs/namei.c b/fs/namei.c
index 216f16e74351..48a2f288e802 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -579,6 +579,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 	p->stack = p->internal;
 	p->dfd = dfd;
 	p->name = name;
+	p->path.mnt = NULL;
+	p->path.dentry = NULL;
 	p->total_link_count = old ? old->total_link_count : 0;
 	p->saved = old;
 	current->nameidata = p;
@@ -652,6 +654,8 @@ static void terminate_walk(struct nameidata *nd)
 		rcu_read_unlock();
 	}
 	nd->depth = 0;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 }
 
 /* path_put is needed afterwards regardless of success or failure */
@@ -2322,8 +2326,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
-	nd->path.mnt = NULL;
-	nd->path.dentry = NULL;
 
 	/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
 	if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
@@ -2419,16 +2421,16 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	while (!(err = link_path_walk(s, nd)) &&
 	       (s = lookup_last(nd)) != NULL)
 		;
+	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
+		err = handle_lookup_down(nd);
+		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+	}
 	if (!err)
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY)
 		if (!d_can_lookup(nd->path.dentry))
 			err = -ENOTDIR;
-	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
-		err = handle_lookup_down(nd);
-		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
-	}
 	if (!err) {
 		*path = nd->path;
 		nd->path.mnt = NULL;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3bfb4147895a..ad20403b383f 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	struct ocfs2_alloc_context *meta_ac = NULL;
 	handle_t *handle = NULL;
 	loff_t end = offset + bytes;
-	int ret = 0, credits = 0, locked = 0;
+	int ret = 0, credits = 0;
 
 	ocfs2_init_dealloc_ctxt(&dealloc);
 
@@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
 	    !dwc->dw_orphaned)
 		goto out;
 
-	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
-	 * are in that context. */
-	if (dwc->dw_writer_pid != task_pid_nr(current)) {
-		inode_lock(inode);
-		locked = 1;
-	}
-
 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
 	if (ret < 0) {
 		mlog_errno(ret);
@@ -2393,8 +2386,6 @@ out:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 	ocfs2_run_deallocs(osb, &dealloc);
-	if (locked)
-		inode_unlock(inode);
 	ocfs2_dio_free_write_ctx(inode, dwc);
 
 	return ret;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6611c64ca0be..5edc1d0cf115 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 				goto bail_unlock;
 			}
 		}
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
 					   2 * ocfs2_quota_trans_credits(sb));
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 		status = __dquot_transfer(inode, transfer_to);
 		if (status < 0)
 			goto bail_commit;
 	} else {
+		down_write(&OCFS2_I(inode)->ip_alloc_sem);
 		handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
-			goto bail_unlock;
+			goto bail_unlock_alloc;
 		}
 	}
 
@@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 bail_unlock:
 	if (status && inode_locked) {
 		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index dbfb35fb0ff7..3847cdc069b5 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -430,20 +430,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 	if (WARN_ON(file != vma->vm_file))
 		return -EIO;
 
-	vma->vm_file = get_file(realfile);
+	vma_set_file(vma, realfile);
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
 	ret = call_mmap(vma->vm_file, vma);
 	revert_creds(old_cred);
-
-	if (ret) {
-		/* Drop reference count from new vm_file value */
-		fput(realfile);
-	} else {
-		/* Drop reference count from previous vm_file value */
-		fput(file);
-	}
-
 	ovl_file_accessed(file);
 
 	return ret;
diff --git a/fs/readdir.c b/fs/readdir.c
index 19434b3c982c..09e8ed7d4161 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -150,6 +150,9 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
 
 	if (buf->result)
 		return -EINVAL;
+	buf->result = verify_dirent_name(name, namlen);
+	if (buf->result < 0)
+		return buf->result;
 	d_ino = ino;
 	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
 		buf->result = -EOVERFLOW;
@@ -405,6 +408,9 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name,
 
 	if (buf->result)
 		return -EINVAL;
+	buf->result = verify_dirent_name(name, namlen);
+	if (buf->result < 0)
+		return buf->result;
 	d_ino = ino;
 	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
 		buf->result = -EOVERFLOW;
diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h
index 9b3b06da568c..e47fde1182de 100644
--- a/fs/reiserfs/xattr.h
+++ b/fs/reiserfs/xattr.h
@@ -44,7 +44,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec);
 
 static inline int reiserfs_xattrs_initialized(struct super_block *sb)
 {
-	return REISERFS_SB(sb)->priv_root != NULL;
+	return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root;
 }
 
 #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header))
diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
index eb02072d28dd..723763746238 100644
--- a/fs/squashfs/export.c
+++ b/fs/squashfs/export.c
@@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end
+		    || (end - start) >
+		    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= lookup_table_start ||
+	    (lookup_table_start - start) >
+	    (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index 11581bf31af4..ea5387679723 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= id_table_start || (id_table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 8d64edb80ebf..b3fdc8212c5f 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -17,6 +17,7 @@
 
 /* size of metadata (inode and directory) blocks */
 #define SQUASHFS_METADATA_SIZE		8192
+#define SQUASHFS_BLOCK_OFFSET		2
 
 /* default size of block device I/O */
 #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE
diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c
index ead66670b41a..087cab8c78f4 100644
--- a/fs/squashfs/xattr_id.c
+++ b/fs/squashfs/xattr_id.c
@@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start,
 		start = le64_to_cpu(table[n]);
 		end = le64_to_cpu(table[n + 1]);
 
-		if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+		if (start >= end || (end - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 			kfree(table);
 			return ERR_PTR(-EINVAL);
 		}
 	}
 
 	start = le64_to_cpu(table[indexes - 1]);
-	if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+	if (start >= table_start || (table_start - start) >
+				(SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
 		kfree(table);
 		return ERR_PTR(-EINVAL);
 	}