Linux-ACPI Archive on lore.kernel.org
 help / color / Atom feed
* [PATCH v3] ACPI / APEI: do memory failure on the physical address reported by ARM processor error section
@ 2020-09-28  2:02 Xiaofei Tan
  2020-10-01 13:44 ` James Morse
  0 siblings, 1 reply; 3+ messages in thread
From: Xiaofei Tan @ 2020-09-28  2:02 UTC (permalink / raw)
  To: james.morse, rafael, rjw, lenb, tony.luck, bp, akpm, jroedel, peterz
  Cc: linux-acpi, linux-kernel, linuxarm, Xiaofei Tan

After the commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea()
synchronise with APEI's irq work") applied, do_sea() return directly
for user-mode if apei_claim_sea() handled any error record. Therefore,
each error record reported by the user-mode SEA must be effectively
processed in APEI GHES driver.

Currently, GHES driver only processes Memory Error Section.(Ignore PCIe
Error Section, as it has nothing to do with SEA). It is not enough.
Because ARM Processor Error could also be used for SEA in some hardware
platforms, such as Kunpeng9xx series. We can't ask them to switch to
use Memory Error Section for two reasons:
1)The server was delivered to customers, and it will introduce
compatibility issue.
2)It make sense to use ARM Processor Error Section. Because either
cache or memory errors could generate SEA when consumed by a processor.

Do memory failure handling for ARM Processor Error Section just like
for Memory Error Section.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
---
Changes since v2:
- Updated commit log
---
 drivers/acpi/apei/ghes.c | 70 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 53 insertions(+), 17 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 99df00f..ca0aa97 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head)
 	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
 }
 
-static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
-				       int sev)
+static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
 	unsigned long pfn;
-	int flags = -1;
-	int sec_sev = ghes_severity(gdata->error_severity);
-	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
 		return false;
 
-	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
-		return false;
-
-	pfn = mem_err->physical_addr >> PAGE_SHIFT;
+	pfn = PHYS_PFN(physical_addr);
 	if (!pfn_valid(pfn)) {
 		pr_warn_ratelimited(FW_WARN GHES_PFX
 		"Invalid address in generic error data: %#llx\n",
-		mem_err->physical_addr);
+		physical_addr);
 		return false;
 	}
 
+	memory_failure_queue(pfn, flags);
+	return true;
+}
+
+static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
+				       int sev)
+{
+	int flags = -1;
+	int sec_sev = ghes_severity(gdata->error_severity);
+	struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata);
+
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
+		return false;
+
 	/* iff following two events can be handled properly by now */
 	if (sec_sev == GHES_SEV_CORRECTED &&
 	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
@@ -470,14 +477,45 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
 		flags = 0;
 
-	if (flags != -1) {
-		memory_failure_queue(pfn, flags);
-		return true;
-	}
+	if (flags != -1)
+		return ghes_do_memory_failure(mem_err->physical_addr, flags);
 
 	return false;
 }
 
+static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
+{
+	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
+	struct cper_arm_err_info *err_info;
+	bool queued = false;
+	int sec_sev, i;
+
+	log_arm_hw_error(err);
+
+	sec_sev = ghes_severity(gdata->error_severity);
+	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
+		return false;
+
+	err_info = (struct cper_arm_err_info *) (err + 1);
+	for (i = 0; i < err->err_info_num; i++, err_info++) {
+		if (!(err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR))
+			continue;
+
+		if (err_info->type != CPER_ARM_CACHE_ERROR) {
+			pr_warn_ratelimited(FW_WARN GHES_PFX
+			"Physical address should be invalid for %s\n",
+			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
+			cper_proc_error_type_strs[err_info->type] : "unknown error type");
+			continue;
+		}
+
+		if (ghes_do_memory_failure(err_info->physical_fault_addr, 0))
+			queued = true;
+	}
+
+	return queued;
+}
+
 /*
  * PCIe AER errors need to be sent to the AER driver for reporting and
  * recovery. The GHES severities map to the following AER severities and
@@ -605,9 +643,7 @@ static bool ghes_do_proc(struct ghes *ghes,
 			ghes_handle_aer(gdata);
 		}
 		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
-			struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
-
-			log_arm_hw_error(err);
+			queued = ghes_handle_arm_hw_error(gdata, sev);
 		} else {
 			void *err = acpi_hest_get_payload(gdata);
 
-- 
2.8.1


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH v3] ACPI / APEI: do memory failure on the physical address reported by ARM processor error section
  2020-09-28  2:02 [PATCH v3] ACPI / APEI: do memory failure on the physical address reported by ARM processor error section Xiaofei Tan
@ 2020-10-01 13:44 ` James Morse
  2020-10-09  8:20   ` Xiaofei Tan
  0 siblings, 1 reply; 3+ messages in thread
From: James Morse @ 2020-10-01 13:44 UTC (permalink / raw)
  To: Xiaofei Tan
  Cc: rafael, rjw, lenb, tony.luck, bp, akpm, jroedel, peterz,
	linux-acpi, linux-kernel, linuxarm

Hi Tanxiaofei,

(sorry for the late reply)

On 28/09/2020 03:02, Xiaofei Tan wrote:
> After the commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea()
> synchronise with APEI's irq work") applied, do_sea() return directly
> for user-mode if apei_claim_sea() handled any error record. Therefore,
> each error record reported by the user-mode SEA must be effectively
> processed in APEI GHES driver.
> 
> Currently, GHES driver only processes Memory Error Section.(Ignore PCIe
> Error Section, as it has nothing to do with SEA). It is not enough.
> Because ARM Processor Error could also be used for SEA in some hardware
> platforms, such as Kunpeng9xx series. We can't ask them to switch to
> use Memory Error Section for two reasons:
> 1)The server was delivered to customers, and it will introduce
> compatibility issue.

> 2)It make sense to use ARM Processor Error Section. Because either
> cache or memory errors could generate SEA when consumed by a processor.
> 
> Do memory failure handling for ARM Processor Error Section just like
> for Memory Error Section.


> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 99df00f..ca0aa97 100644
> --- a/drivers/acpi/apei/ghes.
> +++ b/drivers/acpi/apei/ghes.c
> @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head)

> +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
> +{
> +	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
> +	struct cper_arm_err_info *err_info;
> +	bool queued = false;
> +	int sec_sev, i;
> +
> +	log_arm_hw_error(err);
> +
> +	sec_sev = ghes_severity(gdata->error_severity);
> +	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
> +		return false;
> +
> +	err_info = (struct cper_arm_err_info *) (err + 1);
> +	for (i = 0; i < err->err_info_num; i++, err_info++) {

err_info has its own length, could we use that in case someone comes up with a new table
version? (like this, old versions of the kernel will read mis-aligned structures)


> +		if (!(err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR))
> +			continue;
> +
> +		if (err_info->type != CPER_ARM_CACHE_ERROR) {
> +			pr_warn_ratelimited(FW_WARN GHES_PFX
> +			"Physical address should be invalid for %s\n",

Should? A bus-error could have a valid physical address. I can't see anything in the spec
that forbids this. In general we shouldn't try to validate what firmware is doing.


> +			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
> +			cper_proc_error_type_strs[err_info->type] : "unknown error type");
> +			continue;
> +		}

I think we should warn for the cases this handler doesn't cover, but we should try to
catch all of them. e.g:

|	bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
|	bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR)
|
|	if (!is_cache || !has_pa) {
|		pr_warn_ratelimited(..."Unhandled processor error type %s\n", ...);
|		continue;
|	}


For cache errors, (err_info->error_info & BIT(26)) has its own corrected/uncorrected flag.
You filter out 'overall corrected' section types earlier, could you check this error
record before invoking memory_failure()?

(sections may contain a set of errors. I'm not convinced a 'corrected section' can't
contain latent uncorrected errors, it just means the machine didn't need that data yet)



> +		if (ghes_do_memory_failure(err_info->physical_fault_addr, 0))
> +			queued = true;

May as well:
|		return ghes_do_memory_failure(...);


> +	}
> +
> +	return queued;

(and make this:
|	return false
)

> +}



Thanks,

James

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH v3] ACPI / APEI: do memory failure on the physical address reported by ARM processor error section
  2020-10-01 13:44 ` James Morse
@ 2020-10-09  8:20   ` Xiaofei Tan
  0 siblings, 0 replies; 3+ messages in thread
From: Xiaofei Tan @ 2020-10-09  8:20 UTC (permalink / raw)
  To: James Morse
  Cc: rafael, rjw, lenb, tony.luck, bp, akpm, jroedel, peterz,
	linux-acpi, linux-kernel, linuxarm

Hi James, Thanks for reviewing the patch.

On 2020/10/1 21:44, James Morse wrote:
> Hi Tanxiaofei,
> 
> (sorry for the late reply)
> 
> On 28/09/2020 03:02, Xiaofei Tan wrote:
>> After the commit 8fcc4ae6faf8 ("arm64: acpi: Make apei_claim_sea()
>> synchronise with APEI's irq work") applied, do_sea() return directly
>> for user-mode if apei_claim_sea() handled any error record. Therefore,
>> each error record reported by the user-mode SEA must be effectively
>> processed in APEI GHES driver.
>>
>> Currently, GHES driver only processes Memory Error Section.(Ignore PCIe
>> Error Section, as it has nothing to do with SEA). It is not enough.
>> Because ARM Processor Error could also be used for SEA in some hardware
>> platforms, such as Kunpeng9xx series. We can't ask them to switch to
>> use Memory Error Section for two reasons:
>> 1)The server was delivered to customers, and it will introduce
>> compatibility issue.
> 
>> 2)It make sense to use ARM Processor Error Section. Because either
>> cache or memory errors could generate SEA when consumed by a processor.
>>
>> Do memory failure handling for ARM Processor Error Section just like
>> for Memory Error Section.
> 
> 
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index 99df00f..ca0aa97 100644
>> --- a/drivers/acpi/apei/ghes.
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head)
> 
>> +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev)
>> +{
>> +	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
>> +	struct cper_arm_err_info *err_info;
>> +	bool queued = false;
>> +	int sec_sev, i;
>> +
>> +	log_arm_hw_error(err);
>> +
>> +	sec_sev = ghes_severity(gdata->error_severity);
>> +	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
>> +		return false;
>> +
>> +	err_info = (struct cper_arm_err_info *) (err + 1);
>> +	for (i = 0; i < err->err_info_num; i++, err_info++) {
> 
> err_info has its own length, could we use that in case someone comes up with a new table
> version? (like this, old versions of the kernel will read mis-aligned structures)
> 

The length of err_info is hard written in "ARM Processor Error Section", always 32 bytes.
If someone comes up with a new table version, must also be this length. It seems no much
differences to change to use the fixed 32 bytes here.

> 
>> +		if (!(err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR))
>> +			continue;
>> +
>> +		if (err_info->type != CPER_ARM_CACHE_ERROR) {
>> +			pr_warn_ratelimited(FW_WARN GHES_PFX
>> +			"Physical address should be invalid for %s\n",
> 
> Should? A bus-error could have a valid physical address. I can't see anything in the spec
> that forbids this.

Really? Our platform can't physical address for bus-error.
I remember you asked this in earlier version patch, which is why i skipped non-cache error.


 In general we shouldn't try to validate what firmware is doing.
> 
> 
>> +			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
>> +			cper_proc_error_type_strs[err_info->type] : "unknown error type");
>> +			continue;
>> +		}
> 
> I think we should warn for the cases this handler doesn't cover, but we should try to
> catch all of them. e.g:
> 
> |	bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
> |	bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR)
> |
> |	if (!is_cache || !has_pa) {
> |		pr_warn_ratelimited(..."Unhandled processor error type %s\n", ...);
> |		continue;
> |	}
> 

OK

> 
> For cache errors, (err_info->error_info & BIT(26)) has its own corrected/uncorrected flag.
> You filter out 'overall corrected' section types earlier, could you check this error
> record before invoking memory_failure()?
> 

Do you mean skip corrected error in a recoverable or fatal error section ?
We only use the  severity type of section header, and this corrected/uncorrected flag
may not be filled correctly in firmware.

> (sections may contain a set of errors. I'm not convinced a 'corrected section' can't
> contain latent uncorrected errors, it just means the machine didn't need that data yet)
> 

If contain uncorrected errors, then the error section should be defined as recoverable.

> 
> 
>> +		if (ghes_do_memory_failure(err_info->physical_fault_addr, 0))
>> +			queued = true;
> 
> May as well:
> |		return ghes_do_memory_failure(...);
> 

We can't return directly from here, as other error info may not have been handled.

> 
>> +	}
>> +
>> +	return queued;
> 
> (and make this:
> |	return false
> )
> 
>> +}
> 
> 
> 
> Thanks,
> 
> James
> 
> .
> 

-- 
 thanks
tanxiaofei


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, back to index

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-28  2:02 [PATCH v3] ACPI / APEI: do memory failure on the physical address reported by ARM processor error section Xiaofei Tan
2020-10-01 13:44 ` James Morse
2020-10-09  8:20   ` Xiaofei Tan

Linux-ACPI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-acpi/0 linux-acpi/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-acpi linux-acpi/ https://lore.kernel.org/linux-acpi \
		linux-acpi@vger.kernel.org
	public-inbox-index linux-acpi

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-acpi


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git