Blob Blame History Raw
From d24a67b2d997c860a42516076f3315c2ad2d2884 Mon Sep 17 00:00:00 2001
From: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Date: Fri, 22 Sep 2017 13:58:46 -0400
Git-commit: d24a67b2d997c860a42516076f3315c2ad2d2884
References: bsc#1174206
Patch-mainline: v4.15-rc1
Subject: [PATCH] btrfs: add a flags argument to LOGICAL_INO and call it
 LOGICAL_INO_V2

Now that check_extent_in_eb()'s extent offset filter can be turned off,
we need a way to do it from userspace.

Add a 'flags' field to the btrfs_logical_ino_args structure to disable
extent offset filtering, taking the place of one of the existing
reserved[] fields.

Previous versions of LOGICAL_INO neglected to check whether any of the
reserved fields have non-zero values.  Assigning meaning to those fields
now may change the behavior of existing programs that left these fields
uninitialized.  The lack of a zero check also means that new programs
have no way to know whether the kernel is honoring the flags field.

To avoid these problems, define a new ioctl LOGICAL_INO_V2.  We can
use the same argument layout as LOGICAL_INO, but shorten the reserved[]
array by one element and turn it into the 'flags' field.  The V2 ioctl
explicitly checks that reserved fields and unsupported flag bits are zero
so that userspace can negotiate future feature bits as they are defined.

Since the memory layouts of the two ioctls' arguments are compatible,
there is no need for a separate function for logical_to_ino_v2 (contrast
with tree_search_v2 vs tree_search where the layout and code are quite
different).  A version parameter and an 'if' statement will suffice.

Now that we have a flags field in logical_ino_args, add a flag
BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET to get the behavior we want,
and pass it down the stack to iterate_inodes_from_logical.

Motivation and background, copied from the patchset cover letter:

Suppose we have a file with one extent:

    root@tester:~# zcat /usr/share/doc/cpio/changelog.gz > /test/a
    root@tester:~# sync

Split the extent by overwriting it in the middle:

    root@tester:~# cat /dev/urandom | dd bs=4k seek=2 skip=2 count=1 conv=notrunc of=/test/a

We should now have 3 extent refs to 2 extents, with one block unreachable.
The extent tree looks like:

    root@tester:~# btrfs-debug-tree /dev/vdc -t 2
    [...]
            item 9 key (1103101952 EXTENT_ITEM 73728) itemoff 15942 itemsize 53
                    extent refs 2 gen 29 flags DATA
                    extent data backref root 5 objectid 261 offset 0 count 2
    [...]
            item 11 key (1103175680 EXTENT_ITEM 4096) itemoff 15865 itemsize 53
                    extent refs 1 gen 30 flags DATA
                    extent data backref root 5 objectid 261 offset 8192 count 1
    [...]

and the ref tree looks like:

    root@tester:~# btrfs-debug-tree /dev/vdc -t 5
    [...]
            item 6 key (261 EXTENT_DATA 0) itemoff 15825 itemsize 53
                    extent data disk byte 1103101952 nr 73728
                    extent data offset 0 nr 8192 ram 73728
                    extent compression(none)
            item 7 key (261 EXTENT_DATA 8192) itemoff 15772 itemsize 53
                    extent data disk byte 1103175680 nr 4096
                    extent data offset 0 nr 4096 ram 4096
                    extent compression(none)
            item 8 key (261 EXTENT_DATA 12288) itemoff 15719 itemsize 53
                    extent data disk byte 1103101952 nr 73728
                    extent data offset 12288 nr 61440 ram 73728
                    extent compression(none)
    [...]

There are two references to the same extent with different, non-overlapping
byte offsets:

    [------------------72K extent at 1103101952----------------------]
    [--8K----------------|--4K unreachable----|--60K-----------------]
    ^                                         ^
    |                                         |
    [--8K ref offset 0--][--4K ref offset 0--][--60K ref offset 12K--]
                         |
                         v
                         [-----4K extent-----] at 1103175680

We want to find all of the references to extent bytenr 1103101952.

Without the patch (and without running btrfs-debug-tree), we have to
do it with 18 LOGICAL_INO calls:

    root@tester:~# btrfs ins log 1103101952 -P /test/
    Using LOGICAL_INO
    inode 261 offset 0 root 5

    root@tester:~# for x in $(seq 0 17); do btrfs ins log $((1103101952 + x * 4096)) -P /test/; done 2>&1 | grep inode
    inode 261 offset 0 root 5
    inode 261 offset 4096 root 5   <- same extent ref as offset 0
                                   (offset 8192 returns empty set, not reachable)
    inode 261 offset 12288 root 5
    inode 261 offset 16384 root 5  \
    inode 261 offset 20480 root 5  |
    inode 261 offset 24576 root 5  |
    inode 261 offset 28672 root 5  |
    inode 261 offset 32768 root 5  |
    inode 261 offset 36864 root 5  \
    inode 261 offset 40960 root 5   > all the same extent ref as offset 12288.
    inode 261 offset 45056 root 5  /  More processing required in userspace
    inode 261 offset 49152 root 5  |  to figure out these are all duplicates.
    inode 261 offset 53248 root 5  |
    inode 261 offset 57344 root 5  |
    inode 261 offset 61440 root 5  |
    inode 261 offset 65536 root 5  |
    inode 261 offset 69632 root 5  /

In the worst case the extents are 128MB long, and we have to do 32768
iterations of the loop to find one 4K extent ref.

With the patch, we just use one call to map all refs to the extent at once:
    root@tester:~# btrfs ins log 1103101952 -P /test/
    Using LOGICAL_INO_V2
    inode 261 offset 0 root 5
    inode 261 offset 12288 root 5

The TREE_SEARCH ioctl allows userspace to retrieve the offset and
extent bytenr fields easily once the root, inode and offset are known.
This is sufficient information to build a complete map of the extent
and all of its references.  Userspace can use this information to make
better choices to dedup or defrag.

Signed-off-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Reviewed-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
Tested-by: Hans van Kranenburg <hans.van.kranenburg@mendix.com>
[ copy background and motivation from cover letter ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c           | 26 +++++++++++++++++++++++---
 include/uapi/linux/btrfs.h |  8 +++++++-
 2 files changed, 30 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2497a5d45d9c..fa9996ab3da6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4530,13 +4530,14 @@ static int build_ino_list(u64 inum, u64 offset, u64 root, void *ctx)
 }
 
 static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
-					void __user *arg)
+					void __user *arg, int version)
 {
 	int ret = 0;
 	int size;
 	struct btrfs_ioctl_logical_ino_args *loi;
 	struct btrfs_data_container *inodes = NULL;
 	struct btrfs_path *path = NULL;
+	bool ignore_offset;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -4545,6 +4546,22 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(loi))
 		return PTR_ERR(loi);
 
+	if (version == 1) {
+		ignore_offset = false;
+	} else {
+		/* All reserved bits must be 0 for now */
+		if (memchr_inv(loi->reserved, 0, sizeof(loi->reserved))) {
+			ret = -EINVAL;
+			goto out_loi;
+		}
+		/* Only accept flags we have defined so far */
+		if (loi->flags & ~(BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET)) {
+			ret = -EINVAL;
+			goto out_loi;
+		}
+		ignore_offset = loi->flags & BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
@@ -4560,7 +4577,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 	}
 
 	ret = iterate_inodes_from_logical(loi->logical, fs_info, path,
-					  build_ino_list, inodes, false);
+					  build_ino_list, inodes, ignore_offset);
 	if (ret == -EINVAL)
 		ret = -ENOENT;
 	if (ret < 0)
@@ -4574,6 +4591,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 out:
 	btrfs_free_path(path);
 	kvfree(inodes);
+out_loi:
 	kfree(loi);
 
 	return ret;
@@ -5575,7 +5593,9 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_INO_PATHS:
 		return btrfs_ioctl_ino_to_path(root, argp);
 	case BTRFS_IOC_LOGICAL_INO:
-		return btrfs_ioctl_logical_to_ino(fs_info, argp);
+		return btrfs_ioctl_logical_to_ino(fs_info, argp, 1);
+	case BTRFS_IOC_LOGICAL_INO_V2:
+		return btrfs_ioctl_logical_to_ino(fs_info, argp, 2);
 	case BTRFS_IOC_SPACE_INFO:
 		return btrfs_ioctl_space_info(fs_info, argp);
 	case BTRFS_IOC_SYNC: {
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index 378230c163d5..99bb7988e6fe 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -608,10 +608,14 @@ struct btrfs_ioctl_ino_path_args {
 struct btrfs_ioctl_logical_ino_args {
 	__u64				logical;	/* in */
 	__u64				size;		/* in */
-	__u64				reserved[4];
+	__u64				reserved[3];	/* must be 0 for now */
+	__u64				flags;		/* in, v2 only */
 	/* struct btrfs_data_container	*inodes;	out   */
 	__u64				inodes;
 };
+/* Return every ref to the extent, not just those containing logical block.
+ * Requires logical == extent bytenr. */
+#define BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET	(1ULL << 0)
 
 enum btrfs_dev_stat_values {
 	/* disk I/O failure stats */
@@ -835,5 +839,7 @@ enum btrfs_err_code {
 				   struct btrfs_ioctl_feature_flags[3])
 #define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \
 				   struct btrfs_ioctl_vol_args_v2)
+#define BTRFS_IOC_LOGICAL_INO_V2 _IOWR(BTRFS_IOCTL_MAGIC, 59, \
+					struct btrfs_ioctl_logical_ino_args)
 
 #endif /* _UAPI_LINUX_BTRFS_H */
-- 
2.26.2