If the bio_add_page() call fails, we proceed to write out a
partially constructed log buffer. This corrupts the physical log
such that log recovery is not possible. Worse, persistent
occurrences of this error eventually lead to a BUG_ON() failure in
bio_split() as iclogs wrap the end of the physical log, which
triggers log recovery on subsequent mount.
Rather than warn about writing out a corrupted log buffer, shutdown
the fs as is done for any log I/O related error. This preserves the
consistency of the physical log such that log recovery succeeds on a
subsequent mount. Note that this was observed on a 64k page debug
kernel without upstream commit 59bb47985c1d ("mm, sl[aou]b:
guarantee natural alignment for kmalloc(power-of-two)"), which
demonstrated frequent iclog bio overflows due to unaligned (slab
allocated) iclog data buffers.
Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx>
---
fs/xfs/xfs_log.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 2a90a483c2d6..ebb6a5c95332 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1705,16 +1705,22 @@ xlog_bio_end_io(
static void
xlog_map_iclog_data(
- struct bio *bio,
- void *data,
+ struct xlog_in_core *iclog,
size_t count)
{
+ struct xfs_mount *mp = iclog->ic_log->l_mp;
+ struct bio *bio = &iclog->ic_bio;
+ void *data = iclog->ic_data;
+
do {
struct page *page = kmem_to_page(data);
unsigned int off = offset_in_page(data);
size_t len = min_t(size_t, count, PAGE_SIZE - off);
- WARN_ON_ONCE(bio_add_page(bio, page, len, off) != len);
+ if (bio_add_page(bio, page, len, off) != len) {
+ xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
+ break;
+ }
data += len;
count -= len;
@@ -1762,7 +1768,7 @@ xlog_write_iclog(
if (need_flush)
iclog->ic_bio.bi_opf |= REQ_PREFLUSH;
- xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count);
+ xlog_map_iclog_data(iclog, count);
if (is_vmalloc_addr(iclog->ic_data))
flush_kernel_vmap_range(iclog->ic_data, count);
--
2.21.1
