| Message ID | 20200720100141.129739-1-stefanha@redhat.com |
|---|---|
| State | New |
| Headers | show |
| Series | [for-5.1] block: fix bdrv_aio_cancel() for ENOMEDIUM requests | expand |
On 20.07.20 12:01, Stefan Hajnoczi wrote: > bdrv_aio_cancel() calls aio_poll() on the AioContext for the given I/O > request until it has completed. ENOMEDIUM requests are special because > there is no BlockDriverState when the drive has no medium! > > Define a .get_aio_context() function for BlkAioEmAIOCB requests so that > bdrv_aio_cancel() can find the AioContext where the completion BH is > pending. Without this function bdrv_aio_cancel() aborts on ENOMEDIUM > requests! > > libFuzzer triggered the following assertion: > > cat << EOF | qemu-system-i386 -M pc-q35-5.0 \ > -nographic -monitor none -serial none \ > -qtest stdio -trace ide\* > outl 0xcf8 0x8000fa24 > outl 0xcfc 0xe106c000 > outl 0xcf8 0x8000fa04 > outw 0xcfc 0x7 > outl 0xcf8 0x8000fb20 > write 0x0 0x3 0x2780e7 > write 0xe106c22c 0xd 0x1130c218021130c218021130c2 > write 0xe106c218 0x15 0x110010110010110010110010110010110010110010 > EOF > ide_exec_cmd IDE exec cmd: bus 0x56170a77a2b8; state 0x56170a77a340; cmd 0xe7 > ide_reset IDEstate 0x56170a77a340 > Aborted (core dumped) > > (gdb) bt > #1 0x00007ffff4f93895 in abort () at /lib64/libc.so.6 > #2 0x0000555555dc6c00 in bdrv_aio_cancel (acb=0x555556765550) at block/io.c:2745 > #3 0x0000555555dac202 in blk_aio_cancel (acb=0x555556765550) at block/block-backend.c:1546 > #4 0x0000555555b1bd74 in ide_reset (s=0x555557213340) at hw/ide/core.c:1318 > #5 0x0000555555b1e3a1 in ide_bus_reset (bus=0x5555572132b8) at hw/ide/core.c:2422 > #6 0x0000555555b2aa27 in ahci_reset_port (s=0x55555720eb50, port=2) at hw/ide/ahci.c:650 > #7 0x0000555555b29fd7 in ahci_port_write (s=0x55555720eb50, port=2, offset=44, val=16) at hw/ide/ahci.c:360 > #8 0x0000555555b2a564 in ahci_mem_write (opaque=0x55555720eb50, addr=556, val=16, size=1) at hw/ide/ahci.c:513 > #9 0x000055555598415b in memory_region_write_accessor (mr=0x55555720eb80, addr=556, value=0x7fffffffb838, size=1, shift=0, mask=255, attrs=...) at softmmu/memory.c:483 > > Looking at bdrv_aio_cancel: > > 2728 /* async I/Os */ > 2729 > 2730 void bdrv_aio_cancel(BlockAIOCB *acb) > 2731 { > 2732 qemu_aio_ref(acb); > 2733 bdrv_aio_cancel_async(acb); > 2734 while (acb->refcnt > 1) { > 2735 if (acb->aiocb_info->get_aio_context) { > 2736 aio_poll(acb->aiocb_info->get_aio_context(acb), true); > 2737 } else if (acb->bs) { > 2738 /* qemu_aio_ref and qemu_aio_unref are not thread-safe, so > 2739 * assert that we're not using an I/O thread. Thread-safe > 2740 * code should use bdrv_aio_cancel_async exclusively. > 2741 */ > 2742 assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context()); > 2743 aio_poll(bdrv_get_aio_context(acb->bs), true); > 2744 } else { > 2745 abort(); <=============== > 2746 } > 2747 } > 2748 qemu_aio_unref(acb); > 2749 } > > Fixes: 02c50efe08736116048d5fc355043080f4d5859c ("block: Add bdrv_aio_cancel_async") > Reported-by: Alexander Bulekov <alxndr@bu.edu> > Buglink: https://bugs.launchpad.net/qemu/+bug/1878255 > Originally-by: Philippe Mathieu-Daudé <f4bug@amsat.org> > Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> > --- > block/block-backend.c | 8 ++++++++ > 1 file changed, 8 insertions(+) Thanks, applied to my block branch: https://git.xanclic.moe/XanClic/qemu/commits/branch/block
diff --git a/block/block-backend.c b/block/block-backend.c index 0bf0188133..3a13cb5f0b 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -1394,8 +1394,16 @@ typedef struct BlkAioEmAIOCB { bool has_returned; } BlkAioEmAIOCB; +static AioContext *blk_aio_em_aiocb_get_aio_context(BlockAIOCB *acb_) +{ + BlkAioEmAIOCB *acb = container_of(acb_, BlkAioEmAIOCB, common); + + return blk_get_aio_context(acb->rwco.blk); +} + static const AIOCBInfo blk_aio_em_aiocb_info = { .aiocb_size = sizeof(BlkAioEmAIOCB), + .get_aio_context = blk_aio_em_aiocb_get_aio_context, }; static void blk_aio_complete(BlkAioEmAIOCB *acb)
bdrv_aio_cancel() calls aio_poll() on the AioContext for the given I/O request until it has completed. ENOMEDIUM requests are special because there is no BlockDriverState when the drive has no medium! Define a .get_aio_context() function for BlkAioEmAIOCB requests so that bdrv_aio_cancel() can find the AioContext where the completion BH is pending. Without this function bdrv_aio_cancel() aborts on ENOMEDIUM requests! libFuzzer triggered the following assertion: cat << EOF | qemu-system-i386 -M pc-q35-5.0 \ -nographic -monitor none -serial none \ -qtest stdio -trace ide\* outl 0xcf8 0x8000fa24 outl 0xcfc 0xe106c000 outl 0xcf8 0x8000fa04 outw 0xcfc 0x7 outl 0xcf8 0x8000fb20 write 0x0 0x3 0x2780e7 write 0xe106c22c 0xd 0x1130c218021130c218021130c2 write 0xe106c218 0x15 0x110010110010110010110010110010110010110010 EOF ide_exec_cmd IDE exec cmd: bus 0x56170a77a2b8; state 0x56170a77a340; cmd 0xe7 ide_reset IDEstate 0x56170a77a340 Aborted (core dumped) (gdb) bt #1 0x00007ffff4f93895 in abort () at /lib64/libc.so.6 #2 0x0000555555dc6c00 in bdrv_aio_cancel (acb=0x555556765550) at block/io.c:2745 #3 0x0000555555dac202 in blk_aio_cancel (acb=0x555556765550) at block/block-backend.c:1546 #4 0x0000555555b1bd74 in ide_reset (s=0x555557213340) at hw/ide/core.c:1318 #5 0x0000555555b1e3a1 in ide_bus_reset (bus=0x5555572132b8) at hw/ide/core.c:2422 #6 0x0000555555b2aa27 in ahci_reset_port (s=0x55555720eb50, port=2) at hw/ide/ahci.c:650 #7 0x0000555555b29fd7 in ahci_port_write (s=0x55555720eb50, port=2, offset=44, val=16) at hw/ide/ahci.c:360 #8 0x0000555555b2a564 in ahci_mem_write (opaque=0x55555720eb50, addr=556, val=16, size=1) at hw/ide/ahci.c:513 #9 0x000055555598415b in memory_region_write_accessor (mr=0x55555720eb80, addr=556, value=0x7fffffffb838, size=1, shift=0, mask=255, attrs=...) at softmmu/memory.c:483 Looking at bdrv_aio_cancel: 2728 /* async I/Os */ 2729 2730 void bdrv_aio_cancel(BlockAIOCB *acb) 2731 { 2732 qemu_aio_ref(acb); 2733 bdrv_aio_cancel_async(acb); 2734 while (acb->refcnt > 1) { 2735 if (acb->aiocb_info->get_aio_context) { 2736 aio_poll(acb->aiocb_info->get_aio_context(acb), true); 2737 } else if (acb->bs) { 2738 /* qemu_aio_ref and qemu_aio_unref are not thread-safe, so 2739 * assert that we're not using an I/O thread. Thread-safe 2740 * code should use bdrv_aio_cancel_async exclusively. 2741 */ 2742 assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context()); 2743 aio_poll(bdrv_get_aio_context(acb->bs), true); 2744 } else { 2745 abort(); <=============== 2746 } 2747 } 2748 qemu_aio_unref(acb); 2749 } Fixes: 02c50efe08736116048d5fc355043080f4d5859c ("block: Add bdrv_aio_cancel_async") Reported-by: Alexander Bulekov <alxndr@bu.edu> Buglink: https://bugs.launchpad.net/qemu/+bug/1878255 Originally-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block/block-backend.c | 8 ++++++++ 1 file changed, 8 insertions(+)