diff mbox

[V15,07/11] acpi: apei: panic OS with fatal error status block

Message ID 1492556723-9189-8-git-send-email-tbaicar@codeaurora.org (mailing list archive)
State New, archived
Headers show

Commit Message

Tyler Baicar April 18, 2017, 11:05 p.m. UTC
From: "Jonathan (Zhixiong) Zhang" <zjzhang@codeaurora.org>

Even if an error status block's severity is fatal, the kernel does not
honor the severity level and panic.

With the firmware first model, the platform could inform the OS about a
fatal hardware error through the non-NMI GHES notification type. The OS
should panic when a hardware error record is received with this
severity.

Call panic() after CPER data in error status block is printed if
severity is fatal, before each error section is handled.

Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Reviewed-by: James Morse <james.morse@arm.com>
---
 drivers/acpi/apei/ghes.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

Comments

Borislav Petkov April 28, 2017, 1:07 p.m. UTC | #1
On Tue, Apr 18, 2017 at 05:05:19PM -0600, Tyler Baicar wrote:
> From: "Jonathan (Zhixiong) Zhang" <zjzhang@codeaurora.org>
> 
> Even if an error status block's severity is fatal, the kernel does not
> honor the severity level and panic.
> 
> With the firmware first model, the platform could inform the OS about a
> fatal hardware error through the non-NMI GHES notification type. The OS
> should panic when a hardware error record is received with this
> severity.
> 
> Call panic() after CPER data in error status block is printed if
> severity is fatal, before each error section is handled.
> 
> Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
> Reviewed-by: James Morse <james.morse@arm.com>
> ---
>  drivers/acpi/apei/ghes.c | 19 ++++++++++++++-----
>  1 file changed, 14 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 2d387f8..b91123f 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -134,6 +134,8 @@
>  static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
>  static atomic_t ghes_estatus_cache_alloced;
>  
> +static int ghes_panic_timeout __read_mostly = 30;
> +
>  static int ghes_ioremap_init(void)
>  {
>  	ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
> @@ -692,6 +694,13 @@ static int ghes_ack_error(struct acpi_hest_generic_v2 *generic_v2)
>  	return apei_write(val, &generic_v2->read_ack_register);
>  }
>  
> +static void __ghes_call_panic(void)

__ghes_panic()

> +{
> +	if (panic_timeout == 0)

	if (!panic_timeout)

> +		panic_timeout = ghes_panic_timeout;
> +	panic("Fatal hardware error!");
> +}
> +
>  static int ghes_proc(struct ghes *ghes)
>  {
>  	int rc;
> @@ -699,6 +708,10 @@ static int ghes_proc(struct ghes *ghes)
>  	rc = ghes_read_estatus(ghes, 0);
>  	if (rc)
>  		goto out;

<---- newline here.

> +	if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
> +		__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
> +		__ghes_call_panic();
> +	}

ditto.

>  	if (!ghes_estatus_cached(ghes->estatus)) {
>  		if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
>  			ghes_estatus_cache_add(ghes->generic, ghes->estatus);
diff mbox

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 2d387f8..b91123f 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -134,6 +134,8 @@ 
 static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
 static atomic_t ghes_estatus_cache_alloced;
 
+static int ghes_panic_timeout __read_mostly = 30;
+
 static int ghes_ioremap_init(void)
 {
 	ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
@@ -692,6 +694,13 @@  static int ghes_ack_error(struct acpi_hest_generic_v2 *generic_v2)
 	return apei_write(val, &generic_v2->read_ack_register);
 }
 
+static void __ghes_call_panic(void)
+{
+	if (panic_timeout == 0)
+		panic_timeout = ghes_panic_timeout;
+	panic("Fatal hardware error!");
+}
+
 static int ghes_proc(struct ghes *ghes)
 {
 	int rc;
@@ -699,6 +708,10 @@  static int ghes_proc(struct ghes *ghes)
 	rc = ghes_read_estatus(ghes, 0);
 	if (rc)
 		goto out;
+	if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
+		__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
+		__ghes_call_panic();
+	}
 	if (!ghes_estatus_cached(ghes->estatus)) {
 		if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
 			ghes_estatus_cache_add(ghes->generic, ghes->estatus);
@@ -835,8 +848,6 @@  static inline void ghes_sea_remove(struct ghes *ghes)
 
 static LIST_HEAD(ghes_nmi);
 
-static int ghes_panic_timeout	__read_mostly = 30;
-
 static void ghes_proc_in_irq(struct irq_work *irq_work)
 {
 	struct llist_node *llnode, *next;
@@ -929,9 +940,7 @@  static void __ghes_panic(struct ghes *ghes)
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
 
 	/* reboot to log the error! */
-	if (panic_timeout == 0)
-		panic_timeout = ghes_panic_timeout;
-	panic("Fatal hardware error!");
+	__ghes_call_panic();
 }
 
 static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)