summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMichael Neuling <mikey@neuling.org>2018-03-26 15:17:07 +1100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2018-05-01 15:13:10 -0700
commit80bb480f341dc75ca4cf7f3a1496d6493503c42a (patch)
tree504867d687c4a7bbbdee1f54e62a7e1475737ce0
parentc11a6ed509f086efebc52ad4fd8713e7acfbc076 (diff)
powerpc/eeh: Fix race with driver un/bind
commit f0295e047fcf52ccb42561fb7de6942f5201b676 upstream. The current EEH callbacks can race with a driver unbind. This can result in a backtraces like this: EEH: Frozen PHB#0-PE#1fc detected EEH: PE location: S000009, PHB location: N/A CPU: 2 PID: 2312 Comm: kworker/u258:3 Not tainted 4.15.6-openpower1 #2 Workqueue: nvme-wq nvme_reset_work [nvme] Call Trace: dump_stack+0x9c/0xd0 (unreliable) eeh_dev_check_failure+0x420/0x470 eeh_check_failure+0xa0/0xa4 nvme_reset_work+0x138/0x1414 [nvme] process_one_work+0x1ec/0x328 worker_thread+0x2e4/0x3a8 kthread+0x14c/0x154 ret_from_kernel_thread+0x5c/0xc8 nvme nvme1: Removing after probe failure status: -19 <snip> cpu 0x23: Vector: 300 (Data Access) at [c000000ff50f3800] pc: c0080000089a0eb0: nvme_error_detected+0x4c/0x90 [nvme] lr: c000000000026564: eeh_report_error+0xe0/0x110 sp: c000000ff50f3a80 msr: 9000000000009033 dar: 400 dsisr: 40000000 current = 0xc000000ff507c000 paca = 0xc00000000fdc9d80 softe: 0 irq_happened: 0x01 pid = 782, comm = eehd Linux version 4.15.6-openpower1 (smc@smc-desktop) (gcc version 6.4.0 (Buildroot 2017.11.2-00008-g4b6188e)) #2 SM P Tue Feb 27 12:33:27 PST 2018 enter ? for help eeh_report_error+0xe0/0x110 eeh_pe_dev_traverse+0xc0/0xdc eeh_handle_normal_event+0x184/0x4c4 eeh_handle_event+0x30/0x288 eeh_event_handler+0x124/0x170 kthread+0x14c/0x154 ret_from_kernel_thread+0x5c/0xc8 The first part is an EEH (on boot), the second half is the resulting crash. nvme probe starts the nvme_reset_work() worker thread. This worker thread starts touching the device which see a device error (EEH) and hence queues up an event in the powerpc EEH worker thread. nvme_reset_work() then continues and runs nvme_remove_dead_ctrl_work() which results in unbinding the driver from the device and hence releases all resources. At the same time, the EEH worker thread starts doing the EEH .error_detected() driver callback, which no longer works since the resources have been freed. This fixes the problem in the same way the generic PCIe AER code (in drivers/pci/pcie/aer/aerdrv_core.c) does. It makes the EEH code hold the device_lock() while performing the driver EEH callbacks and associated code. This ensures either the callbacks are no longer register, or if they are registered the driver will not be removed from underneath us. This has been broken forever. The EEH call backs were first introduced in 2005 (in 77bd7415610) but it's not clear if a lock was needed back then. Fixes: 77bd74156101 ("[PATCH] powerpc: PCI Error Recovery: PPC64 core recovery routines") Cc: stable@vger.kernel.org # v2.6.16+ Signed-off-by: Michael Neuling <mikey@neuling.org> Reviewed-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--arch/powerpc/kernel/eeh_driver.c61
1 files changed, 38 insertions, 23 deletions
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6ef8f0bceacd..27843665da9e 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -207,18 +207,18 @@ static void *eeh_report_error(void *data, void *userdata)
if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
+
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_frozen;
driver = eeh_pcid_get(dev);
- if (!driver) return NULL;
+ if (!driver) goto out_no_dev;
eeh_disable_irq(dev);
if (!driver->err_handler ||
- !driver->err_handler->error_detected) {
- eeh_pcid_put(dev);
- return NULL;
- }
+ !driver->err_handler->error_detected)
+ goto out;
rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
@@ -227,7 +227,10 @@ static void *eeh_report_error(void *data, void *userdata)
if (*res == PCI_ERS_RESULT_NONE) *res = rc;
edev->in_error = true;
+out:
eeh_pcid_put(dev);
+out_no_dev:
+ device_unlock(&dev->dev);
return NULL;
}
@@ -250,15 +253,14 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata)
if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
+ device_lock(&dev->dev);
driver = eeh_pcid_get(dev);
- if (!driver) return NULL;
+ if (!driver) goto out_no_dev;
if (!driver->err_handler ||
!driver->err_handler->mmio_enabled ||
- (edev->mode & EEH_DEV_NO_HANDLER)) {
- eeh_pcid_put(dev);
- return NULL;
- }
+ (edev->mode & EEH_DEV_NO_HANDLER))
+ goto out;
rc = driver->err_handler->mmio_enabled(dev);
@@ -266,7 +268,10 @@ static void *eeh_report_mmio_enabled(void *data, void *userdata)
if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+out:
eeh_pcid_put(dev);
+out_no_dev:
+ device_unlock(&dev->dev);
return NULL;
}
@@ -289,20 +294,20 @@ static void *eeh_report_reset(void *data, void *userdata)
if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
+
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_normal;
driver = eeh_pcid_get(dev);
- if (!driver) return NULL;
+ if (!driver) goto out_no_dev;
eeh_enable_irq(dev);
if (!driver->err_handler ||
!driver->err_handler->slot_reset ||
(edev->mode & EEH_DEV_NO_HANDLER) ||
- (!edev->in_error)) {
- eeh_pcid_put(dev);
- return NULL;
- }
+ (!edev->in_error))
+ goto out;
rc = driver->err_handler->slot_reset(dev);
if ((*res == PCI_ERS_RESULT_NONE) ||
@@ -310,7 +315,10 @@ static void *eeh_report_reset(void *data, void *userdata)
if (*res == PCI_ERS_RESULT_DISCONNECT &&
rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+out:
eeh_pcid_put(dev);
+out_no_dev:
+ device_unlock(&dev->dev);
return NULL;
}
@@ -361,10 +369,12 @@ static void *eeh_report_resume(void *data, void *userdata)
if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
+
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_normal;
driver = eeh_pcid_get(dev);
- if (!driver) return NULL;
+ if (!driver) goto out_no_dev;
was_in_error = edev->in_error;
edev->in_error = false;
@@ -374,13 +384,15 @@ static void *eeh_report_resume(void *data, void *userdata)
!driver->err_handler->resume ||
(edev->mode & EEH_DEV_NO_HANDLER) || !was_in_error) {
edev->mode &= ~EEH_DEV_NO_HANDLER;
- eeh_pcid_put(dev);
- return NULL;
+ goto out;
}
driver->err_handler->resume(dev);
+out:
eeh_pcid_put(dev);
+out_no_dev:
+ device_unlock(&dev->dev);
return NULL;
}
@@ -400,22 +412,25 @@ static void *eeh_report_failure(void *data, void *userdata)
if (!dev || eeh_dev_removed(edev) || eeh_pe_passed(edev->pe))
return NULL;
+
+ device_lock(&dev->dev);
dev->error_state = pci_channel_io_perm_failure;
driver = eeh_pcid_get(dev);
- if (!driver) return NULL;
+ if (!driver) goto out_no_dev;
eeh_disable_irq(dev);
if (!driver->err_handler ||
- !driver->err_handler->error_detected) {
- eeh_pcid_put(dev);
- return NULL;
- }
+ !driver->err_handler->error_detected)
+ goto out;
driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
+out:
eeh_pcid_put(dev);
+out_no_dev:
+ device_unlock(&dev->dev);
return NULL;
}