diff mbox series

[RESEND,v8,1/2] ACPI: APEI: set memory failure flags as MF_ACTION_REQUIRED on synchronous events

Message ID 20230919022127.69732-2-xueshuai@linux.alibaba.com
State Superseded
Headers show
Series [RESEND,v8,1/2] ACPI: APEI: set memory failure flags as MF_ACTION_REQUIRED on synchronous events | expand

Commit Message

Shuai Xue Sept. 19, 2023, 2:21 a.m. UTC
There are two major types of uncorrected recoverable (UCR) errors :

- Action Required (AR): The error is detected and the processor already
  consumes the memory. OS requires to take action (for example, offline
  failure page/kill failure thread) to recover this uncorrectable error.

- Action Optional (AO): The error is detected out of processor execution
  context. Some data in the memory are corrupted. But the data have not
  been consumed. OS is optional to take action to recover this
  uncorrectable error.

The essential difference between AR and AO errors is that AR is a
synchronous event, while AO is an asynchronous event. The hardware will
signal a synchronous exception (Machine Check Exception on X86 and
Synchronous External Abort on Arm64) when an error is detected and the
memory access has been architecturally executed.

When APEI firmware first is enabled, a platform may describe one error
source for the handling of synchronous errors (e.g. MCE or SEA notification
), or for handling asynchronous errors (e.g. SCI or External Interrupt
notification). In other words, we can distinguish synchronous errors by
APEI notification. For AR errors, kernel will kill current process
accessing the poisoned page by sending SIGBUS with BUS_MCEERR_AR. In
addition, for AO errors, kernel will notify the process who owns the
poisoned page by sending SIGBUS with BUS_MCEERR_AO in early kill mode.
However, the GHES driver always sets mf_flags to 0 so that all UCR errors
are handled as AO errors in memory failure.

To this end, set memory failure flags as MF_ACTION_REQUIRED on synchronous
events.

Fixes: ba61ca4aab47 ("ACPI, APEI, GHES: Add hardware memory error recovery support")'
Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Tested-by: Ma Wupeng <mawupeng1@huawei.com>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
---
 drivers/acpi/apei/ghes.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

Comments

Jarkko Sakkinen Sept. 25, 2023, 2:43 p.m. UTC | #1
On Tue Sep 19, 2023 at 5:21 AM EEST, Shuai Xue wrote:
> There are two major types of uncorrected recoverable (UCR) errors :
>
> - Action Required (AR): The error is detected and the processor already
>   consumes the memory. OS requires to take action (for example, offline
>   failure page/kill failure thread) to recover this uncorrectable error.
>
> - Action Optional (AO): The error is detected out of processor execution
>   context. Some data in the memory are corrupted. But the data have not
>   been consumed. OS is optional to take action to recover this
>   uncorrectable error.
>
> The essential difference between AR and AO errors is that AR is a
> synchronous event, while AO is an asynchronous event. The hardware will
> signal a synchronous exception (Machine Check Exception on X86 and
> Synchronous External Abort on Arm64) when an error is detected and the
> memory access has been architecturally executed.
>
> When APEI firmware first is enabled, a platform may describe one error
> source for the handling of synchronous errors (e.g. MCE or SEA notification
> ), or for handling asynchronous errors (e.g. SCI or External Interrupt
> notification). In other words, we can distinguish synchronous errors by
> APEI notification. For AR errors, kernel will kill current process
> accessing the poisoned page by sending SIGBUS with BUS_MCEERR_AR. In
> addition, for AO errors, kernel will notify the process who owns the
> poisoned page by sending SIGBUS with BUS_MCEERR_AO in early kill mode.
> However, the GHES driver always sets mf_flags to 0 so that all UCR errors
> are handled as AO errors in memory failure.
>
> To this end, set memory failure flags as MF_ACTION_REQUIRED on synchronous
> events.
>
> Fixes: ba61ca4aab47 ("ACPI, APEI, GHES: Add hardware memory error recovery support")'
> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
> Tested-by: Ma Wupeng <mawupeng1@huawei.com>
> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
> Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
>  drivers/acpi/apei/ghes.c | 29 +++++++++++++++++++++++------
>  1 file changed, 23 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index ef59d6ea16da..88178aa6222d 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -101,6 +101,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
>  	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
>  }
>  
> +/*
> + * A platform may describe one error source for the handling of synchronous
> + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
> + * or External Interrupt). On x86, the HEST notifications are always
> + * asynchronous, so only SEA on ARM is delivered as a synchronous
> + * notification.
> + */
> +static inline bool is_hest_sync_notify(struct ghes *ghes)
> +{
> +	u8 notify_type = ghes->generic->notify.type;
> +
> +	return notify_type == ACPI_HEST_NOTIFY_SEA;
> +}
> +
>  /*
>   * This driver isn't really modular, however for the time being,
>   * continuing to use module_param is the easiest way to remain
> @@ -475,7 +489,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
>  }
>  
>  static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
> -				       int sev)
> +				       int sev, bool sync)
>  {
>  	int flags = -1;
>  	int sec_sev = ghes_severity(gdata->error_severity);
> @@ -489,7 +503,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
>  	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
>  		flags = MF_SOFT_OFFLINE;
>  	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
> -		flags = 0;
> +		flags = sync ? MF_ACTION_REQUIRED : 0;

Not my territory but this branching looks a bit weird to my
eyes so just in case putting a comment.

What *if* the previous condition sets MF_SOFT_OFFLINE and
this condition overwrites the value?

I know that earlier it could have been overwritten by zero.

Neither the function comment has any explanation why it is
ok overwrite like this.

Or if these cannot happen simultaenously why there is not
immediate return after settting MF_SOFT_OFFLINE?

For someone like me the functions logic is tediously hard
to understand tbh.

BR, Jarkko
Shuai Xue Sept. 26, 2023, 6:23 a.m. UTC | #2
On 2023/9/25 22:43, Jarkko Sakkinen wrote:
> On Tue Sep 19, 2023 at 5:21 AM EEST, Shuai Xue wrote:
>> There are two major types of uncorrected recoverable (UCR) errors :
>>
>> - Action Required (AR): The error is detected and the processor already
>>   consumes the memory. OS requires to take action (for example, offline
>>   failure page/kill failure thread) to recover this uncorrectable error.
>>
>> - Action Optional (AO): The error is detected out of processor execution
>>   context. Some data in the memory are corrupted. But the data have not
>>   been consumed. OS is optional to take action to recover this
>>   uncorrectable error.
>>
>> The essential difference between AR and AO errors is that AR is a
>> synchronous event, while AO is an asynchronous event. The hardware will
>> signal a synchronous exception (Machine Check Exception on X86 and
>> Synchronous External Abort on Arm64) when an error is detected and the
>> memory access has been architecturally executed.
>>
>> When APEI firmware first is enabled, a platform may describe one error
>> source for the handling of synchronous errors (e.g. MCE or SEA notification
>> ), or for handling asynchronous errors (e.g. SCI or External Interrupt
>> notification). In other words, we can distinguish synchronous errors by
>> APEI notification. For AR errors, kernel will kill current process
>> accessing the poisoned page by sending SIGBUS with BUS_MCEERR_AR. In
>> addition, for AO errors, kernel will notify the process who owns the
>> poisoned page by sending SIGBUS with BUS_MCEERR_AO in early kill mode.
>> However, the GHES driver always sets mf_flags to 0 so that all UCR errors
>> are handled as AO errors in memory failure.
>>
>> To this end, set memory failure flags as MF_ACTION_REQUIRED on synchronous
>> events.
>>
>> Fixes: ba61ca4aab47 ("ACPI, APEI, GHES: Add hardware memory error recovery support")'
>> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
>> Tested-by: Ma Wupeng <mawupeng1@huawei.com>
>> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
>> Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
>> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
>> ---
>>  drivers/acpi/apei/ghes.c | 29 +++++++++++++++++++++++------
>>  1 file changed, 23 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index ef59d6ea16da..88178aa6222d 100644
>> --- a/drivers/acpi/apei/ghes.c
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -101,6 +101,20 @@ static inline bool is_hest_type_generic_v2(struct ghes *ghes)
>>  	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
>>  }
>>  
>> +/*
>> + * A platform may describe one error source for the handling of synchronous
>> + * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
>> + * or External Interrupt). On x86, the HEST notifications are always
>> + * asynchronous, so only SEA on ARM is delivered as a synchronous
>> + * notification.
>> + */
>> +static inline bool is_hest_sync_notify(struct ghes *ghes)
>> +{
>> +	u8 notify_type = ghes->generic->notify.type;
>> +
>> +	return notify_type == ACPI_HEST_NOTIFY_SEA;
>> +}
>> +
>>  /*
>>   * This driver isn't really modular, however for the time being,
>>   * continuing to use module_param is the easiest way to remain
>> @@ -475,7 +489,7 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
>>  }
>>  
>>  static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
>> -				       int sev)
>> +				       int sev, bool sync)
>>  {
>>  	int flags = -1;
>>  	int sec_sev = ghes_severity(gdata->error_severity);
>> @@ -489,7 +503,7 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
>>  	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
>>  		flags = MF_SOFT_OFFLINE;
>>  	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
>> -		flags = 0;
>> +		flags = sync ? MF_ACTION_REQUIRED : 0;
> 
> Not my territory but this branching looks a bit weird to my
> eyes so just in case putting a comment.
> 
> What *if* the previous condition sets MF_SOFT_OFFLINE and
> this condition overwrites the value?
> 
> I know that earlier it could have been overwritten by zero.
> 
> Neither the function comment has any explanation why it is
> ok overwrite like this.
> 
> Or if these cannot happen simultaenously why there is not
> immediate return after settting MF_SOFT_OFFLINE?
> 
> For someone like me the functions logic is tediously hard
> to understand tbh.
> 
> BR, Jarkko

Hi, Jarkko,

I hope the original source code can help to understand:

	/* iff following two events can be handled properly by now */
	if (sec_sev == GHES_SEV_CORRECTED &&
	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
		flags = MF_SOFT_OFFLINE;
	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
		flags = 0;

	if (flags != -1)
		return ghes_do_memory_failure(mem_err->physical_addr, flags);

The sec_sev of gdata is either GHES_SEV_CORRECTED or GHES_SEV_RECOVERABLE.
So the two if-conditions are independent of each other and these cannot
happen simultaneously. ghes_do_memory_failure() then handle the two events
with a proper seted flags.

Thanks.

Best Regards,
Shuai
diff mbox series

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ef59d6ea16da..88178aa6222d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -101,6 +101,20 @@  static inline bool is_hest_type_generic_v2(struct ghes *ghes)
 	return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2;
 }
 
+/*
+ * A platform may describe one error source for the handling of synchronous
+ * errors (e.g. MCE or SEA), or for handling asynchronous errors (e.g. SCI
+ * or External Interrupt). On x86, the HEST notifications are always
+ * asynchronous, so only SEA on ARM is delivered as a synchronous
+ * notification.
+ */
+static inline bool is_hest_sync_notify(struct ghes *ghes)
+{
+	u8 notify_type = ghes->generic->notify.type;
+
+	return notify_type == ACPI_HEST_NOTIFY_SEA;
+}
+
 /*
  * This driver isn't really modular, however for the time being,
  * continuing to use module_param is the easiest way to remain
@@ -475,7 +489,7 @@  static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 }
 
 static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+				       int sev, bool sync)
 {
 	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
@@ -489,7 +503,7 @@  static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
 		flags = MF_SOFT_OFFLINE;
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
-		flags = 0;
+		flags = sync ? MF_ACTION_REQUIRED : 0;
 
 	if (flags != -1)
 		return ghes_do_memory_failure(mem_err->physical_addr, flags);
@@ -497,9 +511,11 @@  static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	return false;
 }
 
-static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
+				       int sev, bool sync)
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	int flags = sync ? MF_ACTION_REQUIRED : 0;
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -524,7 +540,7 @@  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int s
 		 * and don't filter out 'corrected' error here.
 		 */
 		if (is_cache && has_pa) {
-			queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0);
+			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
 			p += err_info->length;
 			continue;
 		}
@@ -645,6 +661,7 @@  static bool ghes_do_proc(struct ghes *ghes,
 	const guid_t *fru_id = &guid_null;
 	char *fru_text = "";
 	bool queued = false;
+	bool sync = is_hest_sync_notify(ghes);
 
 	sev = ghes_severity(estatus->error_severity);
 	apei_estatus_for_each_section(estatus, gdata) {
@@ -662,13 +679,13 @@  static bool ghes_do_proc(struct ghes *ghes,
 			atomic_notifier_call_chain(&ghes_report_chain, sev, mem_err);
 
 			arch_apei_report_mem_error(sev, mem_err);
-			queued = ghes_handle_memory_failure(gdata, sev);
+			queued = ghes_handle_memory_failure(gdata, sev, sync);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			queued = ghes_handle_arm_hw_error(gdata, sev);
+			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);