From 6b7faadd985c990324b5b5bd18cc4ba5c395eb65 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 23 Oct 2019 21:57:27 +0800
Patch-mainline: v5.5-rc1
Git-commit: 6b7faadd985c990324b5b5bd18cc4ba5c395eb65
References: bsc#1151910
Subject: [PATCH 2/2] btrfs: Ensure we trim ranges across block group boundary
[BUG]
When deleting large files (which cross block group boundary) with
discard mount option, we find some btrfs_discard_extent() calls only
trimmed part of its space, not the whole range:
btrfs_discard_extent: type=0x1 start=19626196992 len=2144530432 trimmed=1073741824 ratio=50%
type: bbio->map_type, in above case, it's SINGLE DATA.
start: Logical address of this trim
len: Logical length of this trim
trimmed: Physically trimmed bytes
ratio: trimmed / len
Thus leaving some unused space not discarded.
[CAUSE]
When discard mount option is specified, after a transaction is fully
committed (super block written to disk), we begin to cleanup pinned
extents in the following call chain:
btrfs_commit_transaction()
|- btrfs_finish_extent_commit()
|- find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY);
|- btrfs_discard_extent()
However, pinned extents are recorded in an extent_io_tree, which can
merge adjacent extent states.
When a large file gets deleted and it has adjacent file extents across
block group boundary, we will get a large merged range like this:
|<--- BG1 --->|<--- BG2 --->|
|//////|<-- Range to discard --->|/////|
To discard that range, we have the following calls:
btrfs_discard_extent()
|- btrfs_map_block()
| Returned bbio will end at BG1's end. As btrfs_map_block()
| never returns result across block group boundary.
|- btrfs_issuse_discard()
Issue discard for each stripe.
So we will only discard the range in BG1, not the remaining part in BG2.
Furthermore, this bug is not that reliably observed, for above case, if
there is no other extent in BG2, BG2 will be empty and btrfs will trim
all space of BG2, covering up the bug.
[FIX]
- Allow __btrfs_map_block_for_discard() to modify @length parameter
btrfs_map_block() uses its @length paramter to notify the caller how
many bytes are mapped in current call.
With __btrfs_map_block_for_discard() also modifing the @length,
btrfs_discard_extent() now understands when to do extra trim.
- Call btrfs_map_block() in a loop until we hit the range end Since we
now know how many bytes are mapped each time, we can iterate through
each block group boundary and issue correct trim for each range.
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/extent-tree.c | 41 +++++++++++++++++++++++++++++++----------
fs/btrfs/volumes.c | 6 ++++--
2 files changed, 35 insertions(+), 12 deletions(-)
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2137,8 +2137,10 @@ static int btrfs_issue_discard(struct bl
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 num_bytes, u64 *actual_bytes)
{
- int ret;
+ int ret = 0;
u64 discarded_bytes = 0;
+ u64 end = bytenr + num_bytes;
+ u64 cur = bytenr;
struct btrfs_bio *bbio = NULL;
@@ -2147,15 +2149,23 @@ int btrfs_discard_extent(struct btrfs_fs
* associated to its stripes that don't go away while we are discarding.
*/
btrfs_bio_counter_inc_blocked(fs_info);
- /* Tell the block device(s) that the sectors can be discarded */
- ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
- &bbio, 0);
- /* Error condition is -ENOMEM */
- if (!ret) {
- struct btrfs_bio_stripe *stripe = bbio->stripes;
+ while (cur < end) {
+ struct btrfs_bio_stripe *stripe;
int i;
+ num_bytes = end - cur;
+ /* Tell the block device(s) that the sectors can be discarded */
+ ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, cur,
+ &num_bytes, &bbio, 0);
+ /*
+ * Error can be -ENOMEM, -ENOENT (no such chunk mapping) or
+ * -EOPNOTSUPP. For any such error, @num_bytes is not updated,
+ * thus we can't continue anyway.
+ */
+ if (ret < 0)
+ goto out;
+ stripe = bbio->stripes;
for (i = 0; i < bbio->num_stripes; i++, stripe++) {
u64 bytes;
if (!stripe->dev->can_discard)
@@ -2165,10 +2175,19 @@ int btrfs_discard_extent(struct btrfs_fs
stripe->physical,
stripe->length,
&bytes);
- if (!ret)
+ if (!ret) {
discarded_bytes += bytes;
- else if (ret != -EOPNOTSUPP)
- break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */
+ } else if (ret != -EOPNOTSUPP) {
+ /*
+ * Logic errors or -ENOMEM, or -EIO, but
+ * unlikely to happen.
+ *
+ * And since there are two loops, explicitly
+ * go to out to avoid confusion.
+ */
+ btrfs_put_bbio(bbio);
+ goto out;
+ }
/*
* Just in case we get back EOPNOTSUPP for some reason,
@@ -2178,7 +2197,9 @@ int btrfs_discard_extent(struct btrfs_fs
ret = 0;
}
btrfs_put_bbio(bbio);
+ cur += num_bytes;
}
+out:
btrfs_bio_counter_dec(fs_info);
if (actual_bytes)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5412,12 +5412,13 @@ void btrfs_put_bbio(struct btrfs_bio *bb
* replace.
*/
static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
- u64 logical, u64 length,
+ u64 logical, u64 *length_ret,
struct btrfs_bio **bbio_ret)
{
struct extent_map *em;
struct map_lookup *map;
struct btrfs_bio *bbio;
+ u64 length = *length_ret;
u64 offset;
u64 stripe_nr;
u64 stripe_nr_end;
@@ -5451,6 +5452,7 @@ static int __btrfs_map_block_for_discard
offset = logical - em->start;
length = min_t(u64, em->start + em->len - logical, length);
+ *length_ret = length;
stripe_len = map->stripe_len;
/*
@@ -5762,7 +5764,7 @@ static int __btrfs_map_block(struct btrf
if (op == BTRFS_MAP_DISCARD)
return __btrfs_map_block_for_discard(fs_info, logical,
- *length, bbio_ret);
+ length, bbio_ret);
em = get_chunk_map(fs_info, logical, *length);
if (IS_ERR(em))