EDAC: Robustify workqueues destruction

Orabug: 23330596

[ Upstream commit fcd5c4dd8201595d4c598c9cca5e54760277d687 ]

EDAC workqueue destruction is really fragile. We cancel delayed work
but if it is still running and requeues itself, we still go ahead and
destroy the workqueue and the queued work explodes when workqueue core
attempts to run it.

Make the destruction more robust by switching op_state to offline so
that requeuing stops. Cancel any pending work *synchronously* too.

  EDAC i7core: Driver loaded.
  general protection fault: 0000 [#1] SMP
  CPU 12
  Modules linked in:
  Supported: Yes
  Pid: 0, comm: kworker/0:1 Tainted: G          IE   3.0.101-0-default #1 HP ProLiant DL380 G7
  RIP: 0010:[<ffffffff8107dcd7>]  [<ffffffff8107dcd7>] __queue_work+0x17/0x3f0
  < ... regs ...>
  Process kworker/0:1 (pid: 0, threadinfo ffff88019def6000, task ffff88019def4600)
  Stack:
   ...
  Call Trace:
   call_timer_fn
   run_timer_softirq
   __do_softirq
   call_softirq
   do_softirq
   irq_exit
   smp_apic_timer_interrupt
   apic_timer_interrupt
   intel_idle
   cpuidle_idle_call
   cpu_idle
  Code: ...
  RIP  __queue_work
   RSP <...>

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
(cherry picked from commit 94fde0abd09b14f0e50efe87edb36ec0d1e88510)

Signed-off-by: Dan Duval <dan.duval@oracle.com>

diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 592af5f0cf391d292e05fd5c3a94b5589c7cb684..53587377e67268fd90efb4fbfed2358dcbe03717 100644 (file)
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -435,16 +435,13 @@ void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev,
  */
 void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev)
 {
-       int status;
-
        if (!edac_dev->edac_check)
                return;
 
-       status = cancel_delayed_work(&edac_dev->work);
-       if (status == 0) {
-               /* workq instance might be running, wait for it */
-               flush_workqueue(edac_workqueue);
-       }
+       edac_dev->op_state = OP_OFFLINE;
+
+       cancel_delayed_work_sync(&edac_dev->work);
+       flush_workqueue(edac_workqueue);
 }
 
 /*

diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index af3be1914dbb8f85496473c4c3c5977edd0ed17a..63ceb2d985654d1d4e58c66119fd7b74ecc9aa41 100644 (file)
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -581,18 +581,10 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec,
  */
 static void edac_mc_workq_teardown(struct mem_ctl_info *mci)
 {
-       int status;
-
-       if (mci->op_state != OP_RUNNING_POLL)
-               return;
-
-       status = cancel_delayed_work(&mci->work);
-       if (status == 0) {
-               edac_dbg(0, "not canceled, flush the queue\n");
+       mci->op_state = OP_OFFLINE;
 
-               /* workq instance might be running, wait for it */
-               flush_workqueue(edac_workqueue);
-       }
+       cancel_delayed_work_sync(&mci->work);
+       flush_workqueue(edac_workqueue);
 }
 
 /*

diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c
index 2cf44b4db80c8beac0a5575cf00d1ed4cca32c4d..b4b38603b804e839480f75c1ce38281108ef1186 100644 (file)
--- a/drivers/edac/edac_pci.c
+++ b/drivers/edac/edac_pci.c
@@ -274,13 +274,12 @@ static void edac_pci_workq_setup(struct edac_pci_ctl_info *pci,
  */
 static void edac_pci_workq_teardown(struct edac_pci_ctl_info *pci)
 {
-       int status;
-
        edac_dbg(0, "\n");
 
-       status = cancel_delayed_work(&pci->work);
-       if (status == 0)
-               flush_workqueue(edac_workqueue);
+       pci->op_state = OP_OFFLINE;
+
+       cancel_delayed_work_sync(&pci->work);
+       flush_workqueue(edac_workqueue);
 }
 
 /*