Home Home > GIT Browse > SLE12-SP4-AZURE
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMichal Suchanek <msuchanek@suse.de>2019-06-10 19:03:59 +0200
committerMichal Suchanek <msuchanek@suse.de>2019-06-10 19:04:03 +0200
commit4862a16157004184c11c294a64e4c8c977a06ca0 (patch)
tree51698797ea97048247d216af2e2ba2f4c8dcf2a6
parenta33e8021f8423b3d072c161beb266162043c7d2f (diff)
powerpc/eeh: Fix race with driver un/bind (bsc#1065729).
-rw-r--r--patches.arch/powerpc-eeh-Fix-race-with-driver-un-bind.patch262
-rw-r--r--series.conf1
2 files changed, 263 insertions, 0 deletions
diff --git a/patches.arch/powerpc-eeh-Fix-race-with-driver-un-bind.patch b/patches.arch/powerpc-eeh-Fix-race-with-driver-un-bind.patch
new file mode 100644
index 0000000000..f270f3a932
--- /dev/null
+++ b/patches.arch/powerpc-eeh-Fix-race-with-driver-un-bind.patch
@@ -0,0 +1,262 @@
+From f0295e047fcf52ccb42561fb7de6942f5201b676 Mon Sep 17 00:00:00 2001
+From: Michael Neuling <mikey@neuling.org>
+Date: Mon, 26 Mar 2018 15:17:07 +1100
+Subject: [PATCH] powerpc/eeh: Fix race with driver un/bind
+
+References: bsc#1065729
+Patch-mainline: v4.17-rc1
+Git-commit: f0295e047fcf52ccb42561fb7de6942f5201b676
+
+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>
+Acked-by: Michal Suchanek <msuchanek@suse.de>
+---
+ arch/powerpc/kernel/eeh_driver.c | 68 ++++++++++++++++++++------------
+ 1 file changed, 42 insertions(+), 26 deletions(-)
+
+diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
+index 43ceb6263cd8..b8a329f04814 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);
+
+@@ -227,8 +227,12 @@ static void *eeh_report_error(void *data, void *userdata)
+ if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+ edev->in_error = true;
+- eeh_pcid_put(dev);
+ pci_uevent_ers(dev, PCI_ERS_RESULT_NONE);
++
++out:
++ eeh_pcid_put(dev);
++out_no_dev:
++ device_unlock(&dev->dev);
+ return NULL;
+ }
+
+@@ -251,15 +255,14 @@ 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);
+
+@@ -267,7 +270,10 @@ 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;
+ }
+
+@@ -290,20 +296,20 @@ 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) ||
+@@ -311,7 +317,10 @@ 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;
+ }
+
+@@ -362,10 +371,12 @@ 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;
+@@ -375,18 +386,20 @@ 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);
+
+- eeh_pcid_put(dev);
+ pci_uevent_ers(dev, PCI_ERS_RESULT_RECOVERED);
++out:
++ eeh_pcid_put(dev);
+ #ifdef CONFIG_PCI_IOV
+ if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev))
+ eeh_ops->notify_resume(eeh_dev_to_pdn(edev));
+ #endif
++out_no_dev:
++ device_unlock(&dev->dev);
+ return NULL;
+ }
+
+@@ -406,23 +419,26 @@ 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);
+
+- eeh_pcid_put(dev);
+ pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
++out:
++ eeh_pcid_put(dev);
++out_no_dev:
++ device_unlock(&dev->dev);
+ return NULL;
+ }
+
+--
+2.20.1
+
diff --git a/series.conf b/series.conf
index e7032d44bf..5fbae3ec46 100644
--- a/series.conf
+++ b/series.conf
@@ -15420,6 +15420,7 @@
patches.arch/powerpc-setup-Add-cpu_to_phys_id-array.patch
patches.arch/powerpc-kvm-Fix-guest-boot-failure-on-Power9-since-D.patch
patches.arch/powerpc-kexec_file-Fix-error-code-when-trying-to-loa.patch
+ patches.arch/powerpc-eeh-Fix-race-with-driver-un-bind.patch
patches.arch/powerpc-64s-idle-avoid-sync-for-KVM-state-when-wakin.patch
patches.arch/powerpc-64s-Add-all-POWER9-features-to-CPU_FTRS_ALWA.patch
patches.arch/powerpc-64s-Explicitly-add-vector-features-to-CPU_FT.patch