pve-qemu/debian/patches/pve/0057-PVE-Backup-ensure-jobs...

74 lines
2.5 KiB
Diff

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Fabian Ebner <f.ebner@proxmox.com>
Date: Wed, 25 May 2022 13:59:38 +0200
Subject: [PATCH] PVE-Backup: ensure jobs in di_list are referenced
Ensures that qmp_backup_cancel doesn't pick a job that's already been
freed. With unlucky timings it seems possible that:
1. job_exit -> job_completed -> job_finalize_single starts
2. pvebackup_co_complete_stream gets spawned in completion callback
3. job finalize_single finishes -> job's refcount hits zero -> job is
freed
4. qmp_backup_cancel comes in and locks backup_state.backup_mutex
before pvebackup_co_complete_stream can remove the job from the
di_list
5. qmp_backup_cancel will pick a job that's already been freed
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
[FE: adapt for new job lock mechanism replacing AioContext locks]
Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
---
pve-backup.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/pve-backup.c b/pve-backup.c
index 79d14d6a0b..67e2b99d74 100644
--- a/pve-backup.c
+++ b/pve-backup.c
@@ -318,6 +318,13 @@ static void coroutine_fn pvebackup_co_complete_stream(void *opaque)
}
}
+ if (di->job) {
+ WITH_JOB_LOCK_GUARD() {
+ job_unref_locked(&di->job->job);
+ di->job = NULL;
+ }
+ }
+
// remove self from job list
backup_state.di_list = g_list_remove(backup_state.di_list, di);
@@ -493,6 +500,11 @@ static void create_backup_jobs_bh(void *opaque) {
aio_context_release(aio_context);
di->job = job;
+ if (job) {
+ WITH_JOB_LOCK_GUARD() {
+ job_ref_locked(&job->job);
+ }
+ }
if (!job || local_err) {
error_setg(errp, "backup_job_create failed: %s",
@@ -520,11 +532,15 @@ static void create_backup_jobs_bh(void *opaque) {
di->target = NULL;
}
- if (!canceled && di->job) {
+ if (di->job) {
WITH_JOB_LOCK_GUARD() {
- job_cancel_sync_locked(&di->job->job, true);
+ if (!canceled) {
+ job_cancel_sync_locked(&di->job->job, true);
+ canceled = true;
+ }
+ job_unref_locked(&di->job->job);
+ di->job = NULL;
}
- canceled = true;
}
}
}