|
 |
357786 |
From 08e7b4d1dc3f71818fec2ebd5f189142011969a9 Mon Sep 17 00:00:00 2001
|
|
|
357786 |
From: Kevin Wolf <kwolf@redhat.com>
|
|
|
357786 |
Date: Thu, 12 Jul 2018 16:06:19 +0200
|
|
|
357786 |
Subject: [PATCH 41/89] block: fix QEMU crash with scsi-hd and drive_del
|
|
|
357786 |
|
|
|
357786 |
RH-Author: Kevin Wolf <kwolf@redhat.com>
|
|
|
357786 |
Message-id: <20180712160619.30712-2-kwolf@redhat.com>
|
|
|
357786 |
Patchwork-id: 81334
|
|
|
357786 |
O-Subject: [RHV-7.6 qemu-kvm-rhev PATCH 1/1] block: fix QEMU crash with scsi-hd and drive_del
|
|
|
357786 |
Bugzilla: 1599515
|
|
|
357786 |
RH-Acked-by: Fam Zheng <famz@redhat.com>
|
|
|
357786 |
RH-Acked-by: Max Reitz <mreitz@redhat.com>
|
|
|
357786 |
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
|
357786 |
|
|
|
357786 |
From: Greg Kurz <groug@kaod.org>
|
|
|
357786 |
|
|
|
357786 |
Removing a drive with drive_del while it is being used to run an I/O
|
|
|
357786 |
intensive workload can cause QEMU to crash.
|
|
|
357786 |
|
|
|
357786 |
An AIO flush can yield at some point:
|
|
|
357786 |
|
|
|
357786 |
blk_aio_flush_entry()
|
|
|
357786 |
blk_co_flush(blk)
|
|
|
357786 |
bdrv_co_flush(blk->root->bs)
|
|
|
357786 |
...
|
|
|
357786 |
qemu_coroutine_yield()
|
|
|
357786 |
|
|
|
357786 |
and let the HMP command to run, free blk->root and give control
|
|
|
357786 |
back to the AIO flush:
|
|
|
357786 |
|
|
|
357786 |
hmp_drive_del()
|
|
|
357786 |
blk_remove_bs()
|
|
|
357786 |
bdrv_root_unref_child(blk->root)
|
|
|
357786 |
child_bs = blk->root->bs
|
|
|
357786 |
bdrv_detach_child(blk->root)
|
|
|
357786 |
bdrv_replace_child(blk->root, NULL)
|
|
|
357786 |
blk->root->bs = NULL
|
|
|
357786 |
g_free(blk->root) <============== blk->root becomes stale
|
|
|
357786 |
bdrv_unref(child_bs)
|
|
|
357786 |
bdrv_delete(child_bs)
|
|
|
357786 |
bdrv_close()
|
|
|
357786 |
bdrv_drained_begin()
|
|
|
357786 |
bdrv_do_drained_begin()
|
|
|
357786 |
bdrv_drain_recurse()
|
|
|
357786 |
aio_poll()
|
|
|
357786 |
...
|
|
|
357786 |
qemu_coroutine_switch()
|
|
|
357786 |
|
|
|
357786 |
and the AIO flush completion ends up dereferencing blk->root:
|
|
|
357786 |
|
|
|
357786 |
blk_aio_complete()
|
|
|
357786 |
scsi_aio_complete()
|
|
|
357786 |
blk_get_aio_context(blk)
|
|
|
357786 |
bs = blk_bs(blk)
|
|
|
357786 |
ie, bs = blk->root ? blk->root->bs : NULL
|
|
|
357786 |
^^^^^
|
|
|
357786 |
stale
|
|
|
357786 |
|
|
|
357786 |
The problem is that we should avoid making block driver graph
|
|
|
357786 |
changes while we have in-flight requests. Let's drain all I/O
|
|
|
357786 |
for this BB before calling bdrv_root_unref_child().
|
|
|
357786 |
|
|
|
357786 |
Signed-off-by: Greg Kurz <groug@kaod.org>
|
|
|
357786 |
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
|
|
|
357786 |
(cherry picked from commit f45280cbf66d8e58224f6a253d0ae2aa72cc6280)
|
|
|
357786 |
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
|
|
|
357786 |
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
|
|
|
357786 |
---
|
|
|
357786 |
block/block-backend.c | 5 +++++
|
|
|
357786 |
1 file changed, 5 insertions(+)
|
|
|
357786 |
|
|
|
357786 |
diff --git a/block/block-backend.c b/block/block-backend.c
|
|
|
357786 |
index 56ae535..a469fc6 100644
|
|
|
357786 |
--- a/block/block-backend.c
|
|
|
357786 |
+++ b/block/block-backend.c
|
|
|
357786 |
@@ -768,6 +768,11 @@ void blk_remove_bs(BlockBackend *blk)
|
|
|
357786 |
|
|
|
357786 |
blk_update_root_state(blk);
|
|
|
357786 |
|
|
|
357786 |
+ /* bdrv_root_unref_child() will cause blk->root to become stale and may
|
|
|
357786 |
+ * switch to a completion coroutine later on. Let's drain all I/O here
|
|
|
357786 |
+ * to avoid that and a potential QEMU crash.
|
|
|
357786 |
+ */
|
|
|
357786 |
+ blk_drain(blk);
|
|
|
357786 |
bdrv_root_unref_child(blk->root);
|
|
|
357786 |
blk->root = NULL;
|
|
|
357786 |
}
|
|
|
357786 |
--
|
|
|
357786 |
1.8.3.1
|
|
|
357786 |
|