[RFC PATCH v4 12/12] powerpc/powernv: Machine check exception handling.

Mahesh J Salgaonkar mahesh at linux.vnet.ibm.com
Mon Sep 16 22:42:25 EST 2013


From: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>

Add basic error handling in machine check exception handler.

- If MSR_RI isn't set, we can not recover.
- Check if disposition set to OpalMCE_DISPOSITION_RECOVERED.
- Check if address at fault is inside kernel address space, if not then send
  SIGBUS to process if we hit exception when in userspace.
- If address at fault is not provided then and if we get a synchronous machine
  check while in userspace then kill the task.

Signed-off-by: Mahesh Salgaonkar <mahesh at linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mce.h        |    1 +
 arch/powerpc/kernel/mce.c             |   27 +++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal.c |   43 ++++++++++++++++++++++++++++++++-
 3 files changed, 70 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 3276b40..a2b8c7b 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -193,5 +193,6 @@ extern void release_mce_event(void);
 extern void machine_check_queue_event(void);
 extern void machine_check_process_queued_event(void);
 extern void machine_check_print_event_info(struct machine_check_event *evt);
+extern uint64_t get_mce_fault_addr(struct machine_check_event *evt);
 
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 1cca4b6..3100509 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -316,3 +316,30 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 		break;
 	}
 }
+
+uint64_t get_mce_fault_addr(struct machine_check_event *evt)
+{
+	switch (evt->error_type) {
+	case MCE_ERROR_TYPE_UE:
+		if (evt->u.ue_error.effective_address_provided)
+			return evt->u.ue_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_SLB:
+		if (evt->u.slb_error.effective_address_provided)
+			return evt->u.slb_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_ERAT:
+		if (evt->u.erat_error.effective_address_provided)
+			return evt->u.erat_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_TLB:
+		if (evt->u.tlb_error.effective_address_provided)
+			return evt->u.tlb_error.effective_address;
+		break;
+	default:
+	case MCE_ERROR_TYPE_UNKNOWN:
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(get_mce_fault_addr);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 0170d19..2070970 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
@@ -240,6 +241,44 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	return written;
 }
 
+static int opal_recover_mce(struct pt_regs *regs,
+					struct machine_check_event *evt)
+{
+	int recovered = 0;
+	uint64_t ea = get_mce_fault_addr(evt);
+
+	if (!(regs->msr & MSR_RI)) {
+		/* If MSR_RI isn't set, we cannot recover */
+		recovered = 0;
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
+		/* Platform corrected itself */
+		recovered = 1;
+	} else if (ea && !is_kernel_addr(ea)) {
+		/*
+		 * Faulting address is not in kernel text. We should be fine.
+		 * We need to find which process uses this address.
+		 * For now, kill the task if we have received exception when
+		 * in userspace.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 */
+		if (user_mode(regs) && !is_global_init(current)) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else
+			recovered = 0;
+	} else if (user_mode(regs) && !is_global_init(current) &&
+		evt->severity == MCE_SEV_ERROR_SYNC) {
+		/*
+		 * If we have received a synchronous error when in userspace
+		 * kill the task.
+		 */
+		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+		recovered = 1;
+	}
+	return recovered;
+}
+
 int opal_machine_check(struct pt_regs *regs)
 {
 	struct machine_check_event evt;
@@ -255,7 +294,9 @@ int opal_machine_check(struct pt_regs *regs)
 	}
 	machine_check_print_event_info(&evt);
 
-	return evt.severity == MCE_SEV_FATAL ? 0 : 1;
+	if (opal_recover_mce(regs, &evt))
+		return 1;
+	return 0;
 }
 
 static irqreturn_t opal_interrupt(int irq, void *data)



More information about the Linuxppc-dev mailing list