From: Wang Xiaoguang <wangxg.f...@cn.fujitsu.com>

This issue was revealed by modifying BTRFS_MAX_EXTENT_SIZE(128MB) to 64KB,
When modifying BTRFS_MAX_EXTENT_SIZE(128MB) to 64KB, fsstress test often
gets these warnings from btrfs_destroy_inode():
        WARN_ON(BTRFS_I(inode)->outstanding_extents);
        WARN_ON(BTRFS_I(inode)->reserved_extents);

Simple test program below can reproduce this issue steadily.
Note: you need to modify BTRFS_MAX_EXTENT_SIZE to 64KB to have test,
otherwise there won't be such WARNING.
        #include <string.h>
        #include <unistd.h>
        #include <sys/types.h>
        #include <sys/stat.h>
        #include <fcntl.h>

        int main(void)
        {
                int fd;
                char buf[68 *1024];

                memset(buf, 0, 68 * 1024);
                fd = open("testfile", O_CREAT | O_EXCL | O_RDWR);
                pwrite(fd, buf, 68 * 1024, 64 * 1024);
                return;
        }

When BTRFS_MAX_EXTENT_SIZE is 64KB, and buffered data range is:
64KB                                            128K            132KB
|-----------------------------------------------|---------------|
                         64 + 4KB

1) for above data range, btrfs_delalloc_reserve_metadata() will reserve
metadata and set BTRFS_I(inode)->outstanding_extents to 2.
(68KB + 64KB - 1) / 64KB == 2

Outstanding_extents: 2

2) then btrfs_dirty_page() will be called to dirty pages and set
EXTENT_DELALLOC flag. In this case, btrfs_set_bit_hook() will be called
twice.
The 1st set_bit_hook() call will set DEALLOC flag for the first 64K.
64KB                                            128KB
|-----------------------------------------------|
        64KB DELALLOC
Outstanding_extents: 2

Set_bit_hooks() uses FIRST_DELALLOC flag to avoid re-increase
outstanding_extents counter.
So for 1st set_bit_hooks() call, it won't modify outstanding_extents,
it's still 2.

Then FIRST_DELALLOC flag is *CLEARED*.

3) 2nd btrfs_set_bit_hook() call.
Because FIRST_DELALLOC have been cleared by previous set_bit_hook(),
btrfs_set_bit_hook() will increase BTRFS_I(inode)->outstanding_extents by
one, so now BTRFS_I(inode)->outstanding_extents is 3.
64KB                                            128KB            132KB
|-----------------------------------------------|----------------|
        64K DELALLOC                               4K DELALLOC
Outstanding_extents: 3

But the correct outstanding_extents number should be 2, not 3.
The 2nd btrfs_set_bit_hook() call just screwed up this, and leads to the
WARN_ON().

Normally, we can solve it by only increasing outstanding_extents in
set_bit_hook().
But the problem is for delalloc_reserve/release_metadata(), we only have
a 'length' parameter, and calculate in-accurate outstanding_extents.
If we only rely on set_bit_hook() release_metadata() will crew things up
as it will decrease inaccurate number.

So the fix we use is:
1) Increase *INACCURATE* outstanding_extents at delalloc_reserve_meta
   Just as a place holder.
2) Increase *accurate* outstanding_extents at set_bit_hooks()
   This is the real increaser.
3) Decrease *INACCURATE* outstanding_extents before returning
   This makes outstanding_extents to correct value.

For 128M BTRFS_MAX_EXTENT_SIZE, due to limitation of
__btrfs_buffered_write(), each iteration will only handle about 2MB
data.
So btrfs_dirty_pages() won't need to handle cases cross 2 extents.

Signed-off-by: Wang Xiaoguang <wangxg.f...@cn.fujitsu.com>
Signed-off-by: Lu Fengqi <lufq.f...@cn.fujitsu.com>
---
 fs/btrfs/ctree.h |  2 ++
 fs/btrfs/inode.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++------
 fs/btrfs/ioctl.c |  6 ++----
 3 files changed, 61 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5bdd36664421..1c52d5a3544a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3175,6 +3175,8 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info 
*fs_info, int delay_iput,
                               int nr);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
                              struct extent_state **cached_state, int dedupe);
+int btrfs_set_extent_defrag(struct inode *inode, u64 start, u64 end,
+                           struct extent_state **cached_state);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
                             struct btrfs_root *new_root,
                             struct btrfs_root *parent_root,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5d3c6ac960fd..e644f936449b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1601,6 +1601,9 @@ static void btrfs_split_extent_hook(void *private_data,
        if (!(orig->state & EXTENT_DELALLOC))
                return;
 
+       if (btrfs_is_free_space_inode(BTRFS_I(inode)))
+               return;
+
        size = orig->end - orig->start + 1;
        if (size > BTRFS_MAX_EXTENT_SIZE) {
                u32 num_extents;
@@ -1641,6 +1644,9 @@ static void btrfs_merge_extent_hook(void *private_data,
        if (!(other->state & EXTENT_DELALLOC))
                return;
 
+       if (btrfs_is_free_space_inode(BTRFS_I(inode)))
+               return;
+
        if (new->start > other->start)
                new_size = new->end - other->start + 1;
        else
@@ -1737,7 +1743,6 @@ static void btrfs_set_bit_hook(void *private_data,
                               struct extent_state *state, unsigned *bits)
 {
        struct inode *inode = private_data;
-
        struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 
        if ((*bits & EXTENT_DEFRAG) && !(*bits & EXTENT_DELALLOC))
@@ -1750,13 +1755,16 @@ static void btrfs_set_bit_hook(void *private_data,
        if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
                struct btrfs_root *root = BTRFS_I(inode)->root;
                u64 len = state->end + 1 - state->start;
+               u64 num_extents = div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1,
+                                           BTRFS_MAX_EXTENT_SIZE);
                bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
-               if (*bits & EXTENT_FIRST_DELALLOC) {
+               if (*bits & EXTENT_FIRST_DELALLOC)
                        *bits &= ~EXTENT_FIRST_DELALLOC;
-               } else {
+
+               if (do_list) {
                        spin_lock(&BTRFS_I(inode)->lock);
-                       BTRFS_I(inode)->outstanding_extents++;
+                       BTRFS_I(inode)->outstanding_extents += num_extents;
                        spin_unlock(&BTRFS_I(inode)->lock);
                }
 
@@ -2021,9 +2029,52 @@ static noinline int add_pending_csums(struct 
btrfs_trans_handle *trans,
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
                              struct extent_state **cached_state, int dedupe)
 {
+       int ret;
+       u64 num_extents = div64_u64(end - start + BTRFS_MAX_EXTENT_SIZE,
+                                   BTRFS_MAX_EXTENT_SIZE);
+
+       WARN_ON((end & (PAGE_SIZE - 1)) == 0);
+       ret = set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
+                                 cached_state);
+
+       /*
+        * btrfs_delalloc_reserve_metadata() will first add number of
+        * outstanding extents according to data length, which is inaccurate
+        * for case like dirtying already dirty pages.
+        * so here we will decrease such inaccurate numbers, to make
+        * outstanding_extents only rely on the correct values added by
+        * set_bit_hook()
+        *
+        * Also, we skipped the metadata space reserve for space cache inodes,
+        * so don't modify the outstanding_extents value.
+        */
+       if (ret == 0 && !btrfs_is_free_space_inode(BTRFS_I(inode))) {
+               spin_lock(&BTRFS_I(inode)->lock);
+               BTRFS_I(inode)->outstanding_extents -= num_extents;
+               spin_unlock(&BTRFS_I(inode)->lock);
+       }
+
+       return ret;
+}
+
+int btrfs_set_extent_defrag(struct inode *inode, u64 start, u64 end,
+                           struct extent_state **cached_state)
+{
+       int ret;
+       u64 num_extents = div64_u64(end - start + BTRFS_MAX_EXTENT_SIZE,
+                                   BTRFS_MAX_EXTENT_SIZE);
+
        WARN_ON((end & (PAGE_SIZE - 1)) == 0);
-       return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
-                                  cached_state);
+       ret = set_extent_defrag(&BTRFS_I(inode)->io_tree, start, end,
+                               cached_state);
+
+       if (ret == 0 && !btrfs_is_free_space_inode(BTRFS_I(inode))) {
+               spin_lock(&BTRFS_I(inode)->lock);
+               BTRFS_I(inode)->outstanding_extents -= num_extents;
+               spin_unlock(&BTRFS_I(inode)->lock);
+       }
+
+       return ret;
 }
 
 /* see btrfs_writepage_start_hook for details on why this is required */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fa1b78cf25f6..faa0e7cc0e2c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1232,10 +1232,8 @@ static int cluster_pages_for_defrag(struct inode *inode,
                                (page_cnt - i_done) << PAGE_SHIFT);
        }
 
-
-       set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
-                         &cached_state);
-
+       btrfs_set_extent_defrag(inode, page_start,
+                               page_end - 1, &cached_state);
        unlock_extent_cached(&BTRFS_I(inode)->io_tree,
                             page_start, page_end - 1, &cached_state,
                             GFP_NOFS);
-- 
2.13.2



--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to