[PATCH 1/3] powerpc/powernv: Rework EEH reset

Subsystems: linux for powerpc (32-bit and 64-bit), pci enhanced error handling (eeh) for powerpc, the rest

DORMANTno replies

3 messages, 1 author, 2014-02-12 · open the first message on its own page

[PATCH 1/3] powerpc/powernv: Rework EEH reset

From: Gavin Shan <hidden>
Date: 2014-02-12 07:25:43

When doing reset in order to recover the affected PE, we issue
hot reset on PE primary bus if it's not root bus. Otherwise, we
issue hot or fundamental reset on root port or PHB accordingly.
For the later case, we didn't cover the situation where PE only
includes root port and it potentially causes kernel crash upon
EEH error to the PE.

The patch reworks the logic of EEH reset to improve the code
readability and also avoid the kernel crash.

Cc: stable@vger.kernel.org
Reported-by: Thadeu Lima de Souza Cascardo <redacted>
Signed-off-by: Gavin Shan <redacted>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c |   29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e1e7161..fcb79cf 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -489,8 +489,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose,
 static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
-	struct eeh_dev *edev;
-	struct pci_dev *dev;
+	struct pci_bus *bus;
 	int ret;
 
 	/*
@@ -519,31 +518,11 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
-		if (pe->type & EEH_PE_DEVICE) {
-			/*
-			 * If it's device PE, we didn't refer to the parent
-			 * PCI bus yet. So we have to figure it out indirectly.
-			 */
-			edev = list_first_entry(&pe->edevs,
-					struct eeh_dev, list);
-			dev = eeh_dev_to_pci_dev(edev);
-			dev = dev->bus->self;
-		} else {
-			/*
-			 * If it's bus PE, the parent PCI bus is already there
-			 * and just pick it up.
-			 */
-			dev = pe->bus->self;
-		}
-
-		/*
-		 * Do reset based on the fact that the direct upstream bridge
-		 * is root bridge (port) or not.
-		 */
-		if (dev->bus->number == 0)
+		bus = eeh_pe_bus_get(pe);
+		if (pci_is_root_bus(bus))
 			ret = ioda_eeh_root_reset(hose, option);
 		else
-			ret = ioda_eeh_bridge_reset(hose, dev, option);
+			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
 	}
 
 	return ret;
-- 
1.7.10.4

[PATCH 2/3] powerpc/eeh: Cleanup on eeh_subsystem_enabled

From: Gavin Shan <hidden>
Date: 2014-02-12 07:25:33

The patch cleans up variable eeh_subsystem_enabled so that we needn't
refer the variable directly from external. Instead, we will use
function eeh_enabled() and eeh_set_enable() to operate the variable.

Signed-off-by: Gavin Shan <redacted>
---
 arch/powerpc/include/asm/eeh.h               |   21 +++++++++++++++++++--
 arch/powerpc/kernel/eeh.c                    |   12 ++++++------
 arch/powerpc/platforms/powernv/eeh-powernv.c |    2 +-
 arch/powerpc/platforms/pseries/eeh_pseries.c |    2 +-
 4 files changed, 27 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 9e39ceb..d4dd41f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -172,10 +172,20 @@ struct eeh_ops {
 };
 
 extern struct eeh_ops *eeh_ops;
-extern int eeh_subsystem_enabled;
+extern bool eeh_subsystem_enabled;
 extern raw_spinlock_t confirm_error_lock;
 extern int eeh_probe_mode;
 
+static inline bool eeh_enabled(void)
+{
+	return eeh_subsystem_enabled;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+	eeh_subsystem_enabled = mode;
+}
+
 #define EEH_PROBE_MODE_DEV	(1<<0)	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	(1<<1)	/* From device tree	*/
 
@@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *);
  * If this macro yields TRUE, the caller relays to eeh_check_failure()
  * which does further tests out of line.
  */
-#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_enabled())
 
 /*
  * Reads from a device which has been isolated by EEH will return
@@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *);
 
 #else /* !CONFIG_EEH */
 
+static inline bool eeh_enabled(void)
+{
+        return false;
+}
+
+static inline void eeh_set_enable(bool mode) { }
+
 static inline int eeh_init(void)
 {
 	return 0;
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 148db72..f22f7b6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -89,7 +89,7 @@
 /* Platform dependent EEH operations */
 struct eeh_ops *eeh_ops = NULL;
 
-int eeh_subsystem_enabled;
+bool eeh_subsystem_enabled = false;
 EXPORT_SYMBOL(eeh_subsystem_enabled);
 
 /*
@@ -364,7 +364,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 
 	eeh_stats.total_mmio_ffs++;
 
-	if (!eeh_subsystem_enabled)
+	if (!eeh_enabled())
 		return 0;
 
 	if (!edev) {
@@ -822,7 +822,7 @@ int eeh_init(void)
 			return ret;
 	}
 
-	if (eeh_subsystem_enabled)
+	if (eeh_enabled())
 		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
 	else
 		pr_warning("EEH: No capable adapters found\n");
@@ -897,7 +897,7 @@ void eeh_add_device_late(struct pci_dev *dev)
 	struct device_node *dn;
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 
 	pr_debug("EEH: Adding device %s\n", pci_name(dev));
@@ -1005,7 +1005,7 @@ void eeh_remove_device(struct pci_dev *dev)
 {
 	struct eeh_dev *edev;
 
-	if (!dev || !eeh_subsystem_enabled)
+	if (!dev || !eeh_enabled())
 		return;
 	edev = pci_dev_to_eeh_dev(dev);
 
@@ -1045,7 +1045,7 @@ void eeh_remove_device(struct pci_dev *dev)
 
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
-	if (0 == eeh_subsystem_enabled) {
+	if (!eeh_enabled()) {
 		seq_printf(m, "EEH Subsystem is globally disabled\n");
 		seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
 	} else {
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a79fddc..a59788e 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * Enable EEH explicitly so that we will do EEH check
 	 * while accessing I/O stuff
 	 */
-	eeh_subsystem_enabled = 1;
+	eeh_set_enable(true);
 
 	/* Save memory bars */
 	eeh_save_bars(edev);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9ef3cc8..8a8f047 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 			enable = 1;
 
 		if (enable) {
-			eeh_subsystem_enabled = 1;
+			eeh_set_enable(true);
 			eeh_add_to_parent_pe(edev);
 
 			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
-- 
1.7.10.4

[PATCH 3/3] powerpc/eeh: Disable EEH on reboot

From: Gavin Shan <hidden>
Date: 2014-02-12 07:25:43

We possiblly detect EEH errors during reboot, particularly in kexec
path, but it's impossible for device drivers and EEH core to handle
or recover them properly.

The patch registers one reboot notifier for EEH and disable EEH
subsystem during reboot. That means the EEH errors is going to be
cleared by hardware reset or second kernel during early stage of
PCI probe.

Signed-off-by: Gavin Shan <redacted>
---
 arch/powerpc/kernel/eeh.c                 |   20 ++++++++++++++++++++
 arch/powerpc/platforms/powernv/eeh-ioda.c |    3 ++-
 2 files changed, 22 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f22f7b6..e7b76a6 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/rbtree.h>
+#include <linux/reboot.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
@@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name)
 	return -EEXIST;
 }
 
+static int eeh_reboot_notifier(struct notifier_block *nb,
+			       unsigned long action, void *unused)
+{
+	eeh_set_enable(false);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+	.notifier_call = eeh_reboot_notifier,
+};
+
 /**
  * eeh_init - EEH initialization
  *
@@ -778,6 +790,14 @@ int eeh_init(void)
 	if (machine_is(powernv) && cnt++ <= 0)
 		return ret;
 
+	/* Register reboot notifier */
+	ret = register_reboot_notifier(&eeh_reboot_nb);
+	if (ret) {
+		pr_warn("%s: Failed to register notifier (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
 	/* call platform initialization function */
 	if (!eeh_ops) {
 		pr_warning("%s: Platform EEH operation not found\n",
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index fcb79cf..f514743 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb,
 
 	/* We simply send special EEH event */
 	if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
-	    (events & OPAL_EVENT_PCI_ERROR))
+	    (events & OPAL_EVENT_PCI_ERROR) &&
+	    eeh_enabled())
 		eeh_send_failure_event(NULL);
 
 	return 0;
-- 
1.7.10.4
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help