diff mbox

[v1,1/2] ACPI / APEI: Add SEI notification type support for ARMv8

Message ID 1527770506-8076-2-git-send-email-gengdongjiu@huawei.com (mailing list archive)
State Not Applicable, archived
Headers show

Commit Message

Dongjiu Geng May 31, 2018, 12:41 p.m. UTC
ACPI 6.x adds support for NOTIFY_SEI as a GHES notification
mechanism, so add new GHES notification handling functions.
Expose API ghes_notify_sei() to arch code, arch code will call
this API when it gets this NOTIFY_SEI.

Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com>
---
Note:
Firmware will follow the SError mask rule, if the SError is masked,
the firmware will not deliver NOTIFY_SEI notification.
---
 drivers/acpi/apei/Kconfig | 15 ++++++++++++++
 drivers/acpi/apei/ghes.c  | 53 +++++++++++++++++++++++++++++++++++++++++++++++
 include/acpi/ghes.h       |  1 +
 3 files changed, 69 insertions(+)

Comments

Mark Rutland May 31, 2018, 10:52 a.m. UTC | #1
On Thu, May 31, 2018 at 08:41:45PM +0800, Dongjiu Geng wrote:
> +#ifdef CONFIG_ACPI_APEI_SEI
> +static LIST_HEAD(ghes_sei);
> +
> +/*
> + * Return 0 only if one of the SEI error sources successfully reported an error
> + * record sent from the firmware.
> + */
> +int ghes_notify_sei(void)
> +{
> +	struct ghes *ghes;
> +	int ret = -ENOENT;
> +
> +	rcu_read_lock();
> +	list_for_each_entry_rcu(ghes, &ghes_sei, list) {
> +		if (!ghes_proc(ghes))
> +			ret = 0;
> +	}
> +	rcu_read_unlock();
> +	return ret;
> +}
> +
> +static void ghes_sei_add(struct ghes *ghes)
> +{
> +	mutex_lock(&ghes_list_mutex);
> +	list_add_rcu(&ghes->list, &ghes_sei);
> +	mutex_unlock(&ghes_list_mutex);
> +}
> +
> +static void ghes_sei_remove(struct ghes *ghes)
> +{
> +	mutex_lock(&ghes_list_mutex);
> +	list_del_rcu(&ghes->list);
> +	mutex_unlock(&ghes_list_mutex);
> +	synchronize_rcu();
> +}
> +#else /* CONFIG_ACPI_APEI_SEI */
> +static inline void ghes_sei_add(struct ghes *ghes) { }
> +static inline void ghes_sei_remove(struct ghes *ghes) { }
> +#endif /* CONFIG_ACPI_APEI_SEI */
> +
>  #ifdef CONFIG_HAVE_ACPI_APEI_NMI
>  /*

> index 8feb0c8..9ba59e2 100644
> --- a/include/acpi/ghes.h
> +++ b/include/acpi/ghes.h
> @@ -120,5 +120,6 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
>  	     section = acpi_hest_get_next(section))
>  
>  int ghes_notify_sea(void);
> +int ghes_notify_sei(void);

It would be nice to have a stub definition when !CONFIG_ACPI_APEI_SEI,
e.g.

#ifdef CONFIG_ACPI_APEI_SEI
int ghes_notify_sei(void);
#else
static in int ghes_notify_sei(void) { return -ENOENT; }
#endif

... as callers could simply call this without additional checks.

As a cleanup, similar would be nice for ghes_notify_sea() with
CONFIG_ACPI_APEI_SEA.

Thanks,
Mark.
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Dongjiu Geng June 1, 2018, 10:07 a.m. UTC | #2
Hi Mark,
   Thanks for the comments.

On 2018/5/31 18:52, Mark Rutland wrote:
> On Thu, May 31, 2018 at 08:41:45PM +0800, Dongjiu Geng wrote:
>> +#ifdef CONFIG_ACPI_APEI_SEI
>> +static LIST_HEAD(ghes_sei);
>> +
>> +/*
>> + * Return 0 only if one of the SEI error sources successfully reported an error
>> + * record sent from the firmware.
>> + */
>> +int ghes_notify_sei(void)
>> +{
>> +	struct ghes *ghes;
>> +	int ret = -ENOENT;
>> +
>> +	rcu_read_lock();
>> +	list_for_each_entry_rcu(ghes, &ghes_sei, list) {
>> +		if (!ghes_proc(ghes))
>> +			ret = 0;
>> +	}
>> +	rcu_read_unlock();
>> +	return ret;
>> +}
>> +
>> +static void ghes_sei_add(struct ghes *ghes)
>> +{
>> +	mutex_lock(&ghes_list_mutex);
>> +	list_add_rcu(&ghes->list, &ghes_sei);
>> +	mutex_unlock(&ghes_list_mutex);
>> +}
>> +
>> +static void ghes_sei_remove(struct ghes *ghes)
>> +{
>> +	mutex_lock(&ghes_list_mutex);
>> +	list_del_rcu(&ghes->list);
>> +	mutex_unlock(&ghes_list_mutex);
>> +	synchronize_rcu();
>> +}
>> +#else /* CONFIG_ACPI_APEI_SEI */
>> +static inline void ghes_sei_add(struct ghes *ghes) { }
>> +static inline void ghes_sei_remove(struct ghes *ghes) { }
>> +#endif /* CONFIG_ACPI_APEI_SEI */
>> +
>>  #ifdef CONFIG_HAVE_ACPI_APEI_NMI
>>  /*
> 
>> index 8feb0c8..9ba59e2 100644
>> --- a/include/acpi/ghes.h
>> +++ b/include/acpi/ghes.h
>> @@ -120,5 +120,6 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
>>  	     section = acpi_hest_get_next(section))
>>  
>>  int ghes_notify_sea(void);
>> +int ghes_notify_sei(void);
> 
> It would be nice to have a stub definition when !CONFIG_ACPI_APEI_SEI,
> e.g.
> 
> #ifdef CONFIG_ACPI_APEI_SEI
> int ghes_notify_sei(void);
> #else
> static in int ghes_notify_sei(void) { return -ENOENT; }
> #endif
> 
> ... as callers could simply call this without additional checks.
> 
> As a cleanup, similar would be nice for ghes_notify_sea() with
> CONFIG_ACPI_APEI_SEA.

I think your suggestion is better, I will do the cleanup include the ghes_notify_sea().
thanks again.

> 
> Thanks,
> Mark.
> 
> .
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index 52ae543..ff4afc3 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -55,6 +55,21 @@  config ACPI_APEI_SEA
 	  option allows the OS to look for such hardware error record, and
 	  take appropriate action.
 
+config ACPI_APEI_SEI
+	bool "APEI SError(System Error) Interrupt logging/recovering support"
+	depends on ARM64 && ACPI_APEI_GHES
+	default y
+	help
+	  This option should be enabled if the system supports
+	  firmware first handling of SEI (SError interrupt).
+
+	  SEI happens with asynchronous external abort for errors on device
+	  memory reads on ARMv8 systems. If a system supports firmware first
+	  handling of SEI, the platform analyzes and handles hardware error
+	  notifications from SEI, and it may then form a hardware error record for
+	  the OS to parse and handle. This option allows the OS to look for
+	  such hardware error record, and take appropriate action.
+
 config ACPI_APEI_MEMORY_FAILURE
 	bool "APEI memory error recovering support"
 	depends on ACPI_APEI && MEMORY_FAILURE
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 1efefe9..33f77ae 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -827,6 +827,46 @@  static inline void ghes_sea_add(struct ghes *ghes) { }
 static inline void ghes_sea_remove(struct ghes *ghes) { }
 #endif /* CONFIG_ACPI_APEI_SEA */
 
+#ifdef CONFIG_ACPI_APEI_SEI
+static LIST_HEAD(ghes_sei);
+
+/*
+ * Return 0 only if one of the SEI error sources successfully reported an error
+ * record sent from the firmware.
+ */
+int ghes_notify_sei(void)
+{
+	struct ghes *ghes;
+	int ret = -ENOENT;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ghes, &ghes_sei, list) {
+		if (!ghes_proc(ghes))
+			ret = 0;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+static void ghes_sei_add(struct ghes *ghes)
+{
+	mutex_lock(&ghes_list_mutex);
+	list_add_rcu(&ghes->list, &ghes_sei);
+	mutex_unlock(&ghes_list_mutex);
+}
+
+static void ghes_sei_remove(struct ghes *ghes)
+{
+	mutex_lock(&ghes_list_mutex);
+	list_del_rcu(&ghes->list);
+	mutex_unlock(&ghes_list_mutex);
+	synchronize_rcu();
+}
+#else /* CONFIG_ACPI_APEI_SEI */
+static inline void ghes_sei_add(struct ghes *ghes) { }
+static inline void ghes_sei_remove(struct ghes *ghes) { }
+#endif /* CONFIG_ACPI_APEI_SEI */
+
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
 /*
  * printk is not safe in NMI context.  So in NMI handler, we allocate
@@ -1055,6 +1095,13 @@  static int ghes_probe(struct platform_device *ghes_dev)
 			goto err;
 		}
 		break;
+	case ACPI_HEST_NOTIFY_SEI:
+		if (!IS_ENABLED(CONFIG_ACPI_APEI_SEI)) {
+			pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEI is not supported!\n",
+				generic->header.source_id);
+		goto err;
+	}
+	break;
 	case ACPI_HEST_NOTIFY_NMI:
 		if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
 			pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
@@ -1126,6 +1173,9 @@  static int ghes_probe(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_SEA:
 		ghes_sea_add(ghes);
 		break;
+	case ACPI_HEST_NOTIFY_SEI:
+		ghes_sei_add(ghes);
+		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_add(ghes);
 		break;
@@ -1179,6 +1229,9 @@  static int ghes_remove(struct platform_device *ghes_dev)
 	case ACPI_HEST_NOTIFY_SEA:
 		ghes_sea_remove(ghes);
 		break;
+	case ACPI_HEST_NOTIFY_SEI:
+		ghes_sei_remove(ghes);
+		break;
 	case ACPI_HEST_NOTIFY_NMI:
 		ghes_nmi_remove(ghes);
 		break;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 8feb0c8..9ba59e2 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -120,5 +120,6 @@  static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
 	     section = acpi_hest_get_next(section))
 
 int ghes_notify_sea(void);
+int ghes_notify_sei(void);
 
 #endif /* GHES_H */