8a8ad1c2f6
This patch tries to fix this crash: #5 [ffff88003c1cd690] do_invalid_op at ffffffff810166d5 #6 [ffff88003c1cd730] invalid_op at ffffffff8159b2de [exception RIP: ocfs2_direct_IO_get_blocks+359] RIP: ffffffffa05dfa27 RSP: ffff88003c1cd7e8 RFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff88003c1cdaa8 RCX: 0000000000000000 RDX: 000000000000000c RSI: ffff880027a95000 RDI: ffff88003c79b540 RBP: ffff88003c1cd858 R8: 0000000000000000 R9: ffffffff815f6ba0 R10: 00000000000001c9 R11: 00000000000001c9 R12: ffff88002d271500 R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000001000 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffff88003c1cd860] do_direct_IO at ffffffff811cd31b #8 [ffff88003c1cd950] direct_IO_iovec at ffffffff811cde9c #9 [ffff88003c1cd9b0] do_blockdev_direct_IO at ffffffff811ce764 #10 [ffff88003c1cdb80] __blockdev_direct_IO at ffffffff811ce7cc #11 [ffff88003c1cdbb0] ocfs2_direct_IO at ffffffffa05df756 [ocfs2] #12 [ffff88003c1cdbe0] generic_file_direct_write_iter at ffffffff8112f935 #13 [ffff88003c1cdc40] ocfs2_file_write_iter at ffffffffa0600ccc [ocfs2] #14 [ffff88003c1cdd50] do_aio_write at ffffffff8119126c #15 [ffff88003c1cddc0] aio_rw_vect_retry at ffffffff811d9bb4 #16 [ffff88003c1cddf0] aio_run_iocb at ffffffff811db880 #17 [ffff88003c1cde30] io_submit_one at ffffffff811dc238 #18 [ffff88003c1cde80] do_io_submit at ffffffff811dc437 #19 [ffff88003c1cdf70] sys_io_submit at ffffffff811dc530 #20 [ffff88003c1cdf80] system_call_fastpath at ffffffff8159a159 It crashes at BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED)); in ocfs2_direct_IO_get_blocks. ocfs2_direct_IO_get_blocks is expecting the OCFS2_EXT_REFCOUNTED be removed in ocfs2_prepare_inode_for_write() if it was there. But no cluster lock is taken during the time before (or inside) ocfs2_prepare_inode_for_write() and after ocfs2_direct_IO_get_blocks(). It can happen in this case: Node A(which crashes) Node B ------------------------ --------------------------- ocfs2_file_aio_write ocfs2_prepare_inode_for_write ocfs2_inode_lock ... ocfs2_inode_unlock #no refcount found .... ocfs2_reflink ocfs2_inode_lock ... ocfs2_inode_unlock #now, refcount flag set on extent ... flush change to disk ocfs2_direct_IO_get_blocks ocfs2_get_clusters #extent map miss #buffer_head miss read extents from disk found refcount flag on extent crash.. Fix: Take rw_lock in ocfs2_reflink path Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com> Reviewed-by: Mark Fasheh <mfasheh@suse.de> Cc: Joel Becker <jlbec@evilplan.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
|---|---|---|
| .. | ||
| cluster | ||
| dlm | ||
| dlmfs | ||
| Kconfig | ||
| Makefile | ||
| acl.c | ||
| acl.h | ||
| alloc.c | ||
| alloc.h | ||
| aops.c | ||
| aops.h | ||
| blockcheck.c | ||
| blockcheck.h | ||
| buffer_head_io.c | ||
| buffer_head_io.h | ||
| dcache.c | ||
| dcache.h | ||
| dir.c | ||
| dir.h | ||
| dlmglue.c | ||
| dlmglue.h | ||
| export.c | ||
| export.h | ||
| extent_map.c | ||
| extent_map.h | ||
| file.c | ||
| file.h | ||
| heartbeat.c | ||
| heartbeat.h | ||
| inode.c | ||
| inode.h | ||
| ioctl.c | ||
| ioctl.h | ||
| journal.c | ||
| journal.h | ||
| localalloc.c | ||
| localalloc.h | ||
| locks.c | ||
| locks.h | ||
| mmap.c | ||
| mmap.h | ||
| move_extents.c | ||
| move_extents.h | ||
| namei.c | ||
| namei.h | ||
| ocfs1_fs_compat.h | ||
| ocfs2.h | ||
| ocfs2_fs.h | ||
| ocfs2_ioctl.h | ||
| ocfs2_lockid.h | ||
| ocfs2_lockingver.h | ||
| ocfs2_trace.h | ||
| quota.h | ||
| quota_global.c | ||
| quota_local.c | ||
| refcounttree.c | ||
| refcounttree.h | ||
| reservations.c | ||
| reservations.h | ||
| resize.c | ||
| resize.h | ||
| slot_map.c | ||
| slot_map.h | ||
| stack_o2cb.c | ||
| stack_user.c | ||
| stackglue.c | ||
| stackglue.h | ||
| suballoc.c | ||
| suballoc.h | ||
| super.c | ||
| super.h | ||
| symlink.c | ||
| symlink.h | ||
| sysfile.c | ||
| sysfile.h | ||
| uptodate.c | ||
| uptodate.h | ||
| xattr.c | ||
| xattr.h | ||