for-6.7-rc3-tag

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAmVmHvEACgkQxWXV+ddt
 WDtczA//UdxSPxQwJY1oOQj3k5Zgb/zOThfyD4x5wrDxFAYwVh1XhuyxV2XT8qyq
 ipp+mi9doVykZKLSY+oRAeqjGlF0nIYm1z2PGSU7JXz4VsEj970rsDs3ePwH5TW6
 V8/6VraOIIvmOnTft7aiuM8CXUjyndalNl7RvHu+v6grgAAgQAaly/3CmRIsm/Ui
 2Wb6/J8ciAOBZ8TkFMr0PiTJd+CjUL+1Y9IaYEywujf0nVNJSgHp+R2CpwLDvM/5
 1x6LdRrUKmnY7mhOvC7QwWfQmgsPnj3OuR+3+L+8jULTvcpwka2KEcpCH8/s6mUK
 +4XhKQ4xXOJr8M+KmAUpy1yZZ30G6cDSwnfCWbWRCfR03396tTb08kb6G21fR+NL
 o2qEUOe4DoMbYX/5zd9xEVqbwyGhAIXB0fJ7KJ0RqbaNBh/roRALBVCseP2CFwJE
 P0DE9phjeIGQf3ybdfP7XqnMfk520bqoeV49Akbn2us2SrV1+O9Yjqmj2pbTnljE
 M30Jh/btaiTFtsGB3MBDRRnGhf7F2l1dsmdmMVhdOK8HMY6obcJUdv6YXVLAjBDn
 ATWtUVVizOpHvSZL0G/+1fXqHhLqOnHLY4A97uMjcElK5WJfuYZv8vZK7GVKC/jW
 y5F4w/FPxU8dmhorMGksya2CLMvUsv5dikyAzGHirjEAdyrK1jg=
 =85Pb
 -----END PGP SIGNATURE-----

Merge tag 'for-6.7-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A few fixes and message updates:

   - for simple quotas, handle the case when a snapshot is created and
     the target qgroup already exists

   - fix a warning when file descriptor given to send ioctl is not
     writable

   - fix off-by-one condition when checking chunk maps

   - free pages when page array allocation fails during compression
     read, other cases were handled

   - fix memory leak on error handling path in ref-verify debugging
     feature

   - copy missing struct member 'version' in 64/32bit compat send ioctl

   - tree-checker verifies inline backref ordering

   - print messages to syslog on first mount and last unmount

   - update error messages when reading chunk maps"

* tag 'for-6.7-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: send: ensure send_fd is writable
  btrfs: free the allocated memory if btrfs_alloc_page_array() fails
  btrfs: fix 64bit compat send ioctl arguments not initializing version member
  btrfs: make error messages more clear when getting a chunk map
  btrfs: fix off-by-one when checking chunk map includes logical address
  btrfs: ref-verify: fix memory leaks in btrfs_ref_tree_mod()
  btrfs: add dmesg output for first mount and last unmount of a filesystem
  btrfs: do not abort transaction if there is already an existing qgroup
  btrfs: tree-checker: add type and sequence check for inline backrefs

fs/btrfs/disk-io.c

@@ -3213,6 +3213,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_alloc;
 	}
 
+	btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid);
 	/*
 	 * Verify the type first, if that or the checksum value are
 	 * corrupted, we'll find out

fs/btrfs/extent_io.c

@@ -674,8 +674,8 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio)
  * 		the array will be skipped
  *
  * Return: 0        if all pages were able to be allocated;
- *         -ENOMEM  otherwise, and the caller is responsible for freeing all
- *                  non-null page pointers in the array.
+ *         -ENOMEM  otherwise, the partially allocated pages would be freed and
+ *                  the array slots zeroed
  */
 int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
 {
@@ -694,8 +694,13 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array)
 		 * though alloc_pages_bulk_array() falls back to alloc_page()
 		 * if  it could not bulk-allocate. So we must be out of memory.
 		 */
-		if (allocated == last)
+		if (allocated == last) {
+			for (int i = 0; i < allocated; i++) {
+				__free_page(page_array[i]);
+				page_array[i] = NULL;
+			}
 			return -ENOMEM;
+		}
 
 		memalloc_retry_wait(GFP_NOFS);
 	}

fs/btrfs/ioctl.c

@@ -4356,6 +4356,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat
 		arg->clone_sources = compat_ptr(args32.clone_sources);
 		arg->parent_root = args32.parent_root;
 		arg->flags = args32.flags;
+		arg->version = args32.version;
 		memcpy(arg->reserved, args32.reserved,
 		       sizeof(args32.reserved));
 #else

fs/btrfs/ref-verify.c

@@ -794,6 +794,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		} else if (be->num_refs == 0) {
 			btrfs_err(fs_info,
@@ -803,6 +804,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
+			kfree(re);
 			goto out_unlock;
 		}
 

fs/btrfs/send.c

@@ -8158,7 +8158,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg)
 	}
 
 	sctx->send_filp = fget(arg->send_fd);
-	if (!sctx->send_filp) {
+	if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) {
 		ret = -EBADF;
 		goto out;
 	}

fs/btrfs/super.c

@@ -80,7 +80,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data);
 
 static void btrfs_put_super(struct super_block *sb)
 {
-	close_ctree(btrfs_sb(sb));
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	btrfs_info(fs_info, "last unmount of filesystem %pU", fs_info->fs_devices->fsid);
+	close_ctree(fs_info);
 }
 
 enum {

fs/btrfs/transaction.c

@@ -1774,7 +1774,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	ret = btrfs_create_qgroup(trans, objectid);
-	if (ret) {
+	if (ret && ret != -EEXIST) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}

fs/btrfs/tree-checker.c

@@ -31,6 +31,7 @@
 #include "inode-item.h"
 #include "dir-item.h"
 #include "raid-stripe-tree.h"
+#include "extent-tree.h"
 
 /*
  * Error message should follow the following format:
@@ -1276,6 +1277,8 @@ static int check_extent_item(struct extent_buffer *leaf,
 	unsigned long ptr;	/* Current pointer inside inline refs */
 	unsigned long end;	/* Extent item end */
 	const u32 item_size = btrfs_item_size(leaf, slot);
+	u8 last_type = 0;
+	u64 last_seq = U64_MAX;
 	u64 flags;
 	u64 generation;
 	u64 total_refs;		/* Total refs in btrfs_extent_item */
@@ -1322,6 +1325,18 @@ static int check_extent_item(struct extent_buffer *leaf,
 	 *    2.2) Ref type specific data
 	 *         Either using btrfs_extent_inline_ref::offset, or specific
 	 *         data structure.
+	 *
+	 *    All above inline items should follow the order:
+	 *
+	 *    - All btrfs_extent_inline_ref::type should be in an ascending
+	 *      order
+	 *
+	 *    - Within the same type, the items should follow a descending
+	 *      order by their sequence number. The sequence number is
+	 *      determined by:
+	 *      * btrfs_extent_inline_ref::offset for all types  other than
+	 *        EXTENT_DATA_REF
+	 *      * hash_extent_data_ref() for EXTENT_DATA_REF
 	 */
 	if (unlikely(item_size < sizeof(*ei))) {
 		extent_err(leaf, slot,
@@ -1403,6 +1418,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		struct btrfs_extent_inline_ref *iref;
 		struct btrfs_extent_data_ref *dref;
 		struct btrfs_shared_data_ref *sref;
+		u64 seq;
 		u64 dref_offset;
 		u64 inline_offset;
 		u8 inline_type;
@@ -1416,6 +1432,7 @@ static int check_extent_item(struct extent_buffer *leaf,
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		inline_type = btrfs_extent_inline_ref_type(leaf, iref);
 		inline_offset = btrfs_extent_inline_ref_offset(leaf, iref);
+		seq = inline_offset;
 		if (unlikely(ptr + btrfs_extent_inline_ref_size(inline_type) > end)) {
 			extent_err(leaf, slot,
 "inline ref item overflows extent item, ptr %lu iref size %u end %lu",
@@ -1446,6 +1463,10 @@ static int check_extent_item(struct extent_buffer *leaf,
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
 			dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
+			seq = hash_extent_data_ref(
+					btrfs_extent_data_ref_root(leaf, dref),
+					btrfs_extent_data_ref_objectid(leaf, dref),
+					btrfs_extent_data_ref_offset(leaf, dref));
 			if (unlikely(!IS_ALIGNED(dref_offset,
 						 fs_info->sectorsize))) {
 				extent_err(leaf, slot,
@@ -1475,6 +1496,24 @@ static int check_extent_item(struct extent_buffer *leaf,
 				   inline_type);
 			return -EUCLEAN;
 		}
+		if (inline_type < last_type) {
+			extent_err(leaf, slot,
+				   "inline ref out-of-order: has type %u, prev type %u",
+				   inline_type, last_type);
+			return -EUCLEAN;
+		}
+		/* Type changed, allow the sequence starts from U64_MAX again. */
+		if (inline_type > last_type)
+			last_seq = U64_MAX;
+		if (seq > last_seq) {
+			extent_err(leaf, slot,
+"inline ref out-of-order: has type %u offset %llu seq 0x%llx, prev type %u seq 0x%llx",
+				   inline_type, inline_offset, seq,
+				   last_type, last_seq);
+			return -EUCLEAN;
+		}
+		last_type = inline_type;
+		last_seq = seq;
 		ptr += btrfs_extent_inline_ref_size(inline_type);
 	}
 	/* No padding is allowed */

fs/btrfs/volumes.c

@@ -3006,15 +3006,16 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 	read_unlock(&em_tree->lock);
 
 	if (!em) {
-		btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+		btrfs_crit(fs_info,
+			   "unable to find chunk map for logical %llu length %llu",
 			   logical, length);
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (em->start > logical || em->start + em->len < logical) {
+	if (em->start > logical || em->start + em->len <= logical) {
 		btrfs_crit(fs_info,
-			   "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
-			   logical, length, em->start, em->start + em->len);
+			   "found a bad chunk map, wanted %llu-%llu, found %llu-%llu",
+			   logical, logical + length, em->start, em->start + em->len);
 		free_extent_map(em);
 		return ERR_PTR(-EINVAL);
 	}