From f45280cbf66d8e58224f6a253d0ae2aa72cc6280 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Mon, 28 May 2018 14:03:59 +0200 Subject: block: fix QEMU crash with scsi-hd and drive_del Removing a drive with drive_del while it is being used to run an I/O intensive workload can cause QEMU to crash. An AIO flush can yield at some point: blk_aio_flush_entry() blk_co_flush(blk) bdrv_co_flush(blk->root->bs) ... qemu_coroutine_yield() and let the HMP command to run, free blk->root and give control back to the AIO flush: hmp_drive_del() blk_remove_bs() bdrv_root_unref_child(blk->root) child_bs = blk->root->bs bdrv_detach_child(blk->root) bdrv_replace_child(blk->root, NULL) blk->root->bs = NULL g_free(blk->root) <============== blk->root becomes stale bdrv_unref(child_bs) bdrv_delete(child_bs) bdrv_close() bdrv_drained_begin() bdrv_do_drained_begin() bdrv_drain_recurse() aio_poll() ... qemu_coroutine_switch() and the AIO flush completion ends up dereferencing blk->root: blk_aio_complete() scsi_aio_complete() blk_get_aio_context(blk) bs = blk_bs(blk) ie, bs = blk->root ? blk->root->bs : NULL ^^^^^ stale The problem is that we should avoid making block driver graph changes while we have in-flight requests. Let's drain all I/O for this BB before calling bdrv_root_unref_child(). Signed-off-by: Greg Kurz Signed-off-by: Kevin Wolf --- block/block-backend.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'block/block-backend.c') diff --git a/block/block-backend.c b/block/block-backend.c index 2d1a3463e8..6b75bca317 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -767,6 +767,11 @@ void blk_remove_bs(BlockBackend *blk) blk_update_root_state(blk); + /* bdrv_root_unref_child() will cause blk->root to become stale and may + * switch to a completion coroutine later on. Let's drain all I/O here + * to avoid that and a potential QEMU crash. + */ + blk_drain(blk); bdrv_root_unref_child(blk->root); blk->root = NULL; } -- cgit v1.2.3