The patch titled
Subject: ocfs2: don't put and assigning null to bh allocated outside
has been added to the -mm tree. Its filename is
ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Changwei Ge <ge.changwei@xxxxxxx>
Subject: ocfs2: don't put and assigning null to bh allocated outside
ocfs2_read_blocks() and ocfs2_read_blocks_sync() are both used to read
several blocks from disk. Currently, the input argument *bhs* can be NULL
or NOT. It depends on the caller's behavior. If the function fails in
reading blocks from disk, the corresponding bh will be assigned to NULL
and put.
Obviously, above process for non-NULL input bh is not appropriate.
Because the caller doesn't even know its bhs are put and re-assigned.
If buffer head is managed by caller, ocfs2_read_blocks and
ocfs2_read_blocks_sync() should not evaluate it to NULL. It will cause
caller accessing illegal memory, thus crash.
Link: http://lkml.kernel.org/r/HK2PR06MB045285E0F4FBB561F9F2F9B3D5680@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Changwei Ge <ge.changwei@xxxxxxx>
Reviewed-by: Guozhonghua <guozhonghua@xxxxxxx>
Cc: Mark Fasheh <mark@xxxxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Junxiao Bi <junxiao.bi@xxxxxxxxxx>
Cc: Joseph Qi <jiangqi903@xxxxxxxxx>
Cc: Changwei Ge <ge.changwei@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/ocfs2/buffer_head_io.c | 77 +++++++++++++++++++++++++++---------
1 file changed, 59 insertions(+), 18 deletions(-)
diff -puN fs/ocfs2/buffer_head_io.c~ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside fs/ocfs2/buffer_head_io.c
--- a/fs/ocfs2/buffer_head_io.c~ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside
+++ a/fs/ocfs2/buffer_head_io.c
@@ -99,25 +99,34 @@ out:
return ret;
}
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
unsigned int nr, struct buffer_head *bhs[])
{
int status = 0;
unsigned int i;
struct buffer_head *bh;
+ int new_bh = 0;
trace_ocfs2_read_blocks_sync((unsigned long long)block, nr);
if (!nr)
goto bail;
+ /* Don't put buffer head and re-assign it to NULL if it is allocated
+ * outside since the caller can't be aware of this alternation!
+ */
+ new_bh = (bhs[0] == NULL);
+
for (i = 0 ; i < nr ; i++) {
if (bhs[i] == NULL) {
bhs[i] = sb_getblk(osb->sb, block++);
if (bhs[i] == NULL) {
status = -ENOMEM;
mlog_errno(status);
- goto bail;
+ break;
}
}
bh = bhs[i];
@@ -158,9 +167,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_
submit_bh(REQ_OP_READ, 0, bh);
}
+read_failure:
for (i = nr; i > 0; i--) {
bh = bhs[i - 1];
+ if (unlikely(status)) {
+ if (new_bh && bh) {
+ /* If middle bh fails, let previous bh
+ * finish its read and then put it to
+ * aovoid bh leak
+ */
+ if (!buffer_jbd(bh))
+ wait_on_buffer(bh);
+ put_bh(bh);
+ bhs[i - 1] = NULL;
+ } else if (bh && buffer_uptodate(bh)) {
+ clear_buffer_uptodate(bh);
+ }
+ continue;
+ }
+
/* No need to wait on the buffer if it's managed by JBD. */
if (!buffer_jbd(bh))
wait_on_buffer(bh);
@@ -170,8 +196,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_
* so we can safely record this and loop back
* to cleanup the other buffers. */
status = -EIO;
- put_bh(bh);
- bhs[i - 1] = NULL;
+ goto read_failure;
}
}
@@ -179,6 +204,9 @@ bail:
return status;
}
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
struct buffer_head *bhs[], int flags,
int (*validate)(struct super_block *sb,
@@ -188,6 +216,7 @@ int ocfs2_read_blocks(struct ocfs2_cachi
int i, ignore_cache = 0;
struct buffer_head *bh;
struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+ int new_bh = 0;
trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags);
@@ -213,6 +242,11 @@ int ocfs2_read_blocks(struct ocfs2_cachi
goto bail;
}
+ /* Don't put buffer head and re-assign it to NULL if it is allocated
+ * outside since the caller can't be aware of this alternation!
+ */
+ new_bh = (bhs[0] == NULL);
+
ocfs2_metadata_cache_io_lock(ci);
for (i = 0 ; i < nr ; i++) {
if (bhs[i] == NULL) {
@@ -221,7 +255,8 @@ int ocfs2_read_blocks(struct ocfs2_cachi
ocfs2_metadata_cache_io_unlock(ci);
status = -ENOMEM;
mlog_errno(status);
- goto bail;
+ /* Don't forget to put previous bh! */
+ break;
}
}
bh = bhs[i];
@@ -316,16 +351,27 @@ int ocfs2_read_blocks(struct ocfs2_cachi
}
}
- status = 0;
-
+read_failure:
for (i = (nr - 1); i >= 0; i--) {
bh = bhs[i];
if (!(flags & OCFS2_BH_READAHEAD)) {
- if (status) {
- /* Clear the rest of the buffers on error */
- put_bh(bh);
- bhs[i] = NULL;
+ if (unlikely(status)) {
+ /* Clear the buffers on error including those
+ * ever succeeded in reading
+ */
+ if (new_bh && bh) {
+ /* If middle bh fails, let previous bh
+ * finish its read and then put it to
+ * aovoid bh leak
+ */
+ if (!buffer_jbd(bh))
+ wait_on_buffer(bh);
+ put_bh(bh);
+ bhs[i] = NULL;
+ } else if (bh && buffer_uptodate(bh)) {
+ clear_buffer_uptodate(bh);
+ }
continue;
}
/* We know this can't have changed as we hold the
@@ -342,9 +388,7 @@ int ocfs2_read_blocks(struct ocfs2_cachi
* for this bh as it's not marked locally
* uptodate. */
status = -EIO;
- put_bh(bh);
- bhs[i] = NULL;
- continue;
+ goto read_failure;
}
if (buffer_needs_validate(bh)) {
@@ -354,11 +398,8 @@ int ocfs2_read_blocks(struct ocfs2_cachi
BUG_ON(buffer_jbd(bh));
clear_buffer_needs_validate(bh);
status = validate(sb, bh);
- if (status) {
- put_bh(bh);
- bhs[i] = NULL;
- continue;
- }
+ if (status)
+ goto read_failure;
}
}
_
Patches currently in -mm which might be from ge.changwei@xxxxxxx are
ocfs2-dont-use-iocb-when-eiocbqueued-returns.patch
ocfs2-fix-a-misuse-a-of-brelse-after-failing-ocfs2_check_dir_entry.patch
ocfs2-dont-put-and-assigning-null-to-bh-allocated-outside.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
