[PATCH 0/2] Add other fields to ARM trace event

[PATCH 0/2] Add other fields to ARM trace event

[Mauro Carvalho Chehab]

This series was previously sent at:
https://lore.kernel.org/all/20240321-b4-arm-ras-error-vendor-info-v5-rc3-v5-0-850f9bfb97a8@os.amperecomputing.com/

Those patches that fix UEFI 2.6+ implementation of the ARM trace event,
as the original implementation was incomplete.

In summary:
changeset e9279e83ad1f ("trace, ras: add ARM processor error trace event")
was incomplete: it added a trace event that was reporting only some fields
of the CPER record generated for ARM processor from UEFI 2.6 spec.

Those are not enough there to actually parse such events on userspace,
for it to properly report/record the error nor to take appropriate measures
to prevent future problems, like poisoning problematic CPU cores and taking
them offline.

The patch was validated with the help of an ARM EINJ code for QEMU:

	https://github.com/mchehab/rasdaemon/wiki/error-injection

I tested the ghes and cper reports both with and without this change,
using different versions of rasdaemon, with and without support for
the extended trace event. Those are a summary of the test results:

- adding more fields to the trace events didn't break userspace API:
  both versions of rasdaemon handled it;

- the rasdaemon patches to handle the new trace report was missing
  a backward-compatibility logic. I fixed already. With that, rasdaemon
  can handle both old and new trace events.

Btw, rasdaemon has gained support for the extended trace since its
version 0.5.8 (released in 2021). I didn't saw any issues there
complain about troubles on it, so either distros used on ARM servers
are using an old version of rasdaemon, or they're carrying on the trace
event changes as well.

---

- Changes over the original changeset:
  - First patch was simplified to avoid too many #ifdefs;
  - reordered local vars using reverse xmas tree;
  - removed uneeded typecasts;
  - some coding style fixes.

Daniel Ferguson (1):
  RAS: ACPI: APEI: add conditional compilation to ARM error report
    functions

Shengwei Luo (1):
  RAS: Report all ARM processor CPER information to userspace

 drivers/acpi/apei/ghes.c | 14 +++++-------
 drivers/ras/ras.c        | 47 +++++++++++++++++++++++++++++++++++++--
 include/linux/ras.h      | 16 ++++++++++----
 include/ras/ras_event.h  | 48 +++++++++++++++++++++++++++++++++++-----
 4 files changed, 106 insertions(+), 19 deletions(-)

-- 
2.45.2

[PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions

[Mauro Carvalho Chehab]

From: Daniel Ferguson <danielf@os.amperecomputing.com>

This prevents the unnecessary inclusion of ARM specific RAS error
handling routines in non-ARM platforms.

[mchehab: avoid unneeded ifdefs and fix coding style issues]
Signed-off-by: Daniel Ferguson <danielf@os.amperecomputing.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/acpi/apei/ghes.c | 11 +++++------
 drivers/ras/ras.c        |  2 ++
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 623cc0cb4a65..25f876b8fa4c 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -529,8 +529,9 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata,
 }
 
 static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
-				       int sev, bool sync)
+				     int sev, bool sync)
 {
+#if defined(CONFIG_ARM) || defined (CONFIG_ARM64)
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
 	int flags = sync ? MF_ACTION_REQUIRED : 0;
 	bool queued = false;
@@ -570,7 +571,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 				    error_type);
 		p += err_info->length;
 	}
-
+#endif
 	return queued;
 }
 
@@ -773,11 +774,9 @@ static bool ghes_do_proc(struct ghes *ghes,
 
 			arch_apei_report_mem_error(sev, mem_err);
 			queued = ghes_handle_memory_failure(gdata, sev, sync);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			ghes_handle_aer(gdata);
-		}
-		else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
+		} else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 			queued = ghes_handle_arm_hw_error(gdata, sev, sync);
 		} else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index a6e4792a1b2e..5d94ab79c8c3 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -54,7 +54,9 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id,
 
 void log_arm_hw_error(struct cper_sec_proc_arm *err)
 {
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
 	trace_arm_event(err);
+#endif
 }
 
 static int __init ras_init(void)
-- 
2.45.2

Re: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions

[Borislav Petkov]

On Thu, Jun 27, 2024 at 09:01:08AM +0200, Mauro Carvalho Chehab wrote:
> @@ -570,7 +571,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
>  				    error_type);
>  		p += err_info->length;
>  	}
> -
> +#endif
>  	return queued;

The previous version I saw, had it right. "queued" was outside the ifdeffery:

drivers/acpi/apei/ghes.c: In function ‘ghes_handle_arm_hw_error’:
drivers/acpi/apei/ghes.c:575:16: error: ‘queued’ undeclared (first use in this function)
  575 |         return queued;
      |                ^~~~~~
drivers/acpi/apei/ghes.c:575:16: note: each undeclared identifier is reported only once for each function it appears in
drivers/acpi/apei/ghes.c:576:1: error: control reaches end of non-void function [-Werror=return-type]
  576 | }
      | ^
cc1: some warnings being treated as errors
make[5]: *** [scripts/Makefile.build:244: drivers/acpi/apei/ghes.o] Error 1
make[4]: *** [scripts/Makefile.build:485: drivers/acpi/apei] Error 2
make[4]: *** Waiting for unfinished jobs....
make[3]: *** [scripts/Makefile.build:485: drivers/acpi] Error 2
make[3]: *** Waiting for unfinished jobs....
make[2]: *** [scripts/Makefile.build:485: drivers] Error 2
make[2]: *** Waiting for unfinished jobs....
make[1]: *** [/mnt/kernel/kernel/2nd/linux/Makefile:1934: .] Error 2
make: *** [Makefile:240: __sub-make] Error 2


-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette

Re: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions

[Mauro Carvalho Chehab]

Em Thu, 27 Jun 2024 09:50:34 +0200
Borislav Petkov <bp@alien8.de> escreveu:

> On Thu, Jun 27, 2024 at 09:01:08AM +0200, Mauro Carvalho Chehab wrote:
> > @@ -570,7 +571,7 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
> >  				    error_type);
> >  		p += err_info->length;
> >  	}
> > -
> > +#endif
> >  	return queued;  
> 
> The previous version I saw, had it right. "queued" was outside the ifdeffery:
> 
> drivers/acpi/apei/ghes.c: In function ‘ghes_handle_arm_hw_error’:
> drivers/acpi/apei/ghes.c:575:16: error: ‘queued’ undeclared (first use in this function)
>   575 |         return queued;
>       |                ^~~~~~
> drivers/acpi/apei/ghes.c:575:16: note: each undeclared identifier is reported only once for each function it appears in
> drivers/acpi/apei/ghes.c:576:1: error: control reaches end of non-void function [-Werror=return-type]
>   576 | }
>       | ^
> cc1: some warnings being treated as errors
> make[5]: *** [scripts/Makefile.build:244: drivers/acpi/apei/ghes.o] Error 1
> make[4]: *** [scripts/Makefile.build:485: drivers/acpi/apei] Error 2
> make[4]: *** Waiting for unfinished jobs....
> make[3]: *** [scripts/Makefile.build:485: drivers/acpi] Error 2
> make[3]: *** Waiting for unfinished jobs....
> make[2]: *** [scripts/Makefile.build:485: drivers] Error 2
> make[2]: *** Waiting for unfinished jobs....
> make[1]: *** [/mnt/kernel/kernel/2nd/linux/Makefile:1934: .] Error 2
> make: *** [Makefile:240: __sub-make] Error 2


Sorry, bad conflict resolution during rebase. Will send a v2.


Thanks,
Mauro

Re: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions

[kernel test robot]

Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on rafael-pm/bleeding-edge linus/master v6.10-rc5 next-20240627]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Mauro-Carvalho-Chehab/RAS-ACPI-APEI-add-conditional-compilation-to-ARM-error-report-functions/20240627-225843
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/95baa46a5e1c88f08e328dbbfbbd01602e092234.1719471257.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions
config: x86_64-buildonly-randconfig-003-20240628 (https://download.01.org/0day-ci/archive/20240628/202406281232.xTKmzO76-lkp@intel.com/config)
compiler: gcc-13 (Ubuntu 13.2.0-4ubuntu3) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240628/202406281232.xTKmzO76-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202406281232.xTKmzO76-lkp@intel.com/

All error/warnings (new ones prefixed by >>):

   drivers/acpi/apei/ghes.c: In function 'ghes_handle_arm_hw_error':
>> drivers/acpi/apei/ghes.c:575:16: error: 'queued' undeclared (first use in this function)
     575 |         return queued;
         |                ^~~~~~
   drivers/acpi/apei/ghes.c:575:16: note: each undeclared identifier is reported only once for each function it appears in
>> drivers/acpi/apei/ghes.c:576:1: warning: control reaches end of non-void function [-Wreturn-type]
     576 | }
         | ^


vim +/queued +575 drivers/acpi/apei/ghes.c

7f17b4a121d0d5 James Morse     2020-05-01  530  
a70297d2213253 Shuai Xue       2023-12-18  531  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
a70297d2213253 Shuai Xue       2023-12-18  532  				     int sev, bool sync)
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  533  {
4a485d7f807462 Daniel Ferguson 2024-06-27  534  #if defined(CONFIG_ARM) || defined (CONFIG_ARM64)
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  535  	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
a70297d2213253 Shuai Xue       2023-12-18  536  	int flags = sync ? MF_ACTION_REQUIRED : 0;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  537  	bool queued = false;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  538  	int sec_sev, i;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  539  	char *p;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  540  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  541  	log_arm_hw_error(err);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  542  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  543  	sec_sev = ghes_severity(gdata->error_severity);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  544  	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
7f17b4a121d0d5 James Morse     2020-05-01  545  		return false;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  546  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  547  	p = (char *)(err + 1);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  548  	for (i = 0; i < err->err_info_num; i++) {
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  549  		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  550  		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  551  		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  552  		const char *error_type = "unknown error";
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  553  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  554  		/*
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  555  		 * The field (err_info->error_info & BIT(26)) is fixed to set to
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  556  		 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  557  		 * firmware won't mix corrected errors in an uncorrected section,
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  558  		 * and don't filter out 'corrected' error here.
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  559  		 */
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  560  		if (is_cache && has_pa) {
a70297d2213253 Shuai Xue       2023-12-18  561  			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  562  			p += err_info->length;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  563  			continue;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  564  		}
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  565  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  566  		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  567  			error_type = cper_proc_error_type_strs[err_info->type];
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  568  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  569  		pr_warn_ratelimited(FW_WARN GHES_PFX
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  570  				    "Unhandled processor error type: %s\n",
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  571  				    error_type);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  572  		p += err_info->length;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  573  	}
4a485d7f807462 Daniel Ferguson 2024-06-27  574  #endif
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11 @575  	return queued;
cf870c70a19444 Naveen N. Rao   2013-07-10 @576  }
cf870c70a19444 Naveen N. Rao   2013-07-10  577  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions

[kernel test robot]

Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on rafael-pm/bleeding-edge linus/master v6.10-rc5 next-20240627]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Mauro-Carvalho-Chehab/RAS-ACPI-APEI-add-conditional-compilation-to-ARM-error-report-functions/20240627-225843
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/95baa46a5e1c88f08e328dbbfbbd01602e092234.1719471257.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH 1/2] RAS: ACPI: APEI: add conditional compilation to ARM error report functions
config: x86_64-randconfig-161-20240628 (https://download.01.org/0day-ci/archive/20240628/202406281337.j4rbN9nr-lkp@intel.com/config)
compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240628/202406281337.j4rbN9nr-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202406281337.j4rbN9nr-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/acpi/apei/ghes.c:575:9: error: use of undeclared identifier 'queued'
     575 |         return queued;
         |                ^
   1 error generated.


vim +/queued +575 drivers/acpi/apei/ghes.c

7f17b4a121d0d5 James Morse     2020-05-01  530  
a70297d2213253 Shuai Xue       2023-12-18  531  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
a70297d2213253 Shuai Xue       2023-12-18  532  				     int sev, bool sync)
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  533  {
4a485d7f807462 Daniel Ferguson 2024-06-27  534  #if defined(CONFIG_ARM) || defined (CONFIG_ARM64)
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  535  	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
a70297d2213253 Shuai Xue       2023-12-18  536  	int flags = sync ? MF_ACTION_REQUIRED : 0;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  537  	bool queued = false;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  538  	int sec_sev, i;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  539  	char *p;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  540  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  541  	log_arm_hw_error(err);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  542  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  543  	sec_sev = ghes_severity(gdata->error_severity);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  544  	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
7f17b4a121d0d5 James Morse     2020-05-01  545  		return false;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  546  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  547  	p = (char *)(err + 1);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  548  	for (i = 0; i < err->err_info_num; i++) {
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  549  		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  550  		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  551  		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  552  		const char *error_type = "unknown error";
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  553  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  554  		/*
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  555  		 * The field (err_info->error_info & BIT(26)) is fixed to set to
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  556  		 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  557  		 * firmware won't mix corrected errors in an uncorrected section,
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  558  		 * and don't filter out 'corrected' error here.
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  559  		 */
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  560  		if (is_cache && has_pa) {
a70297d2213253 Shuai Xue       2023-12-18  561  			queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  562  			p += err_info->length;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  563  			continue;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  564  		}
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  565  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  566  		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  567  			error_type = cper_proc_error_type_strs[err_info->type];
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  568  
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  569  		pr_warn_ratelimited(FW_WARN GHES_PFX
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  570  				    "Unhandled processor error type: %s\n",
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  571  				    error_type);
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  572  		p += err_info->length;
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11  573  	}
4a485d7f807462 Daniel Ferguson 2024-06-27  574  #endif
ccb5ecdc2ddeaf Xiaofei Tan     2021-06-11 @575  	return queued;
cf870c70a19444 Naveen N. Rao   2013-07-10  576  }
cf870c70a19444 Naveen N. Rao   2013-07-10  577  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

[PATCH 2/2] RAS: Report all ARM processor CPER information to userspace

[Mauro Carvalho Chehab]

From: Shengwei Luo <luoshengwei@huawei.com>

The ARM processor CPER record was added at UEFI 2.6, and hasn't
any changes up to UEFI 2.10 on its struct.

Yet, the original arm_event trace code added on changeset
e9279e83ad1f ("trace, ras: add ARM processor error trace event") is
incomplete, as it only traces some fields of UAPI 2.6 table N.16,
not exporting at all any information from tables N.17 to N.29 of
the record.

This is not enough for user to take appropriate action or to log
what exactly happened.

According to UEFI_2_9 specification chapter N2.4.4, the ARM processor
error section includes:

- several (ERR_INFO_NUM) ARM processor error information structures
  (Tables N.17 to N.20);
- several (CONTEXT_INFO_NUM) ARM processor context information
  structures (Tables N.21 to N.29);
- several vendor specific error information structures. The
  size is given by Section Length minus the size of the other
  fields.

In addition to those data, it also exports two fields that are
parsed by the GHES driver when firmware reports it, e. g.:

- error severity
- cpu logical index

Report all of these information to userspace via trace uAPI, So that
userspace can properly record the error and take decisions related
to cpu core isolation according to error severity and other info.

After this patch, all the data from ARM Processor record from table
N.16 are directly or indirectly visible on userspace:

======================================	=============================
UEFI field on table N.16		ARM Processor trace fields
======================================	=============================
Validation				handled when filling data for
					affinity MPIDR and running
					state.
ERR_INFO_NUM				pei_len
CONTEXT_INFO_NUM			ctx_len
Section Length				indirectly reported by
					pei_len, ctx_len and oem_len
Error affinity level			affinity
MPIDR_EL1				mpidr
MIDR_EL1				midr
Running State				running_state
PSCI State				psci_state
Processor Error Information Structure	pei_err - count at pei_len
Processor Context			ctx_err- count at ctx_len
Vendor Specific Error Info		oem - count at oem_len
======================================	=============================

It should be noticed that decoding of tables N.17 to N.29, if needed,
will be handled on userspace. That gives more flexibility, as there
won't be any need to flood the Kernel with micro-architecture specific
error decoding).
Also, decoding the other fields require a complex logic, and should
be done for each of the several values inside the record field.
So, let userspace daemons like rasdaemon decode them, parsing such
tables and having vendor-specific micro-architecture-specific decoders.

[mchehab: modified patch description and fix coding style]
Fixes: e9279e83ad1f ("trace, ras: add ARM processor error trace event")
Signed-off-by: Shengwei Luo <luoshengwei@huawei.com>
Signed-off-by: Jason Tian <jason@os.amperecomputing.com>
Signed-off-by: Daniel Ferguson <danielf@os.amperecomputing.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Link: https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#arm-processor-error-section
---
 drivers/acpi/apei/ghes.c |  3 +--
 drivers/ras/ras.c        | 45 +++++++++++++++++++++++++++++++++++--
 include/linux/ras.h      | 16 ++++++++++----
 include/ras/ras_event.h  | 48 +++++++++++++++++++++++++++++++++++-----
 4 files changed, 99 insertions(+), 13 deletions(-)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 25f876b8fa4c..59ace17c8fd8 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -538,9 +538,8 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 	int sec_sev, i;
 	char *p;
 
-	log_arm_hw_error(err);
-
 	sec_sev = ghes_severity(gdata->error_severity);
+	log_arm_hw_error(err, sec_sev);
 	if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
 		return false;
 
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 5d94ab79c8c3..b515659cc8cc 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -52,10 +52,51 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id,
 	trace_non_standard_event(sec_type, fru_id, fru_text, sev, err, len);
 }
 
-void log_arm_hw_error(struct cper_sec_proc_arm *err)
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
 {
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-	trace_arm_event(err);
+	struct cper_arm_err_info *err_info;
+	struct cper_arm_ctx_info *ctx_info;
+	u8 *ven_err_data;
+	u32 ctx_len = 0;
+	int n, sz, cpu;
+	s32 vsei_len;
+	u32 pei_len;
+	u8 *pei_err;
+	u8 *ctx_err;
+
+	pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
+	pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
+
+	err_info = (struct cper_arm_err_info *)(err + 1);
+	ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
+	ctx_err = ctx_info;
+	for (n = 0; n < err->context_info_num; n++) {
+		sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
+		ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
+		ctx_len += sz;
+	}
+
+	vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
+					  pei_len + ctx_len);
+	if (vsei_len < 0) {
+		pr_warn(FW_BUG
+			"section length: %d\n", err->section_length);
+		pr_warn(FW_BUG
+			"section length is too small\n");
+		pr_warn(FW_BUG
+			"firmware-generated error record is incorrect\n");
+		vsei_len = 0;
+	}
+	ven_err_data = (u8 *)ctx_info;
+
+	cpu = GET_LOGICAL_INDEX(err->mpidr);
+	/* when return value is invalid, set cpu index to -1 */
+	if (cpu < 0)
+		cpu = -1;
+
+	trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
+			ven_err_data, (u32)vsei_len, sev, cpu);
 #endif
 }
 
diff --git a/include/linux/ras.h b/include/linux/ras.h
index a64182bc72ad..6025afe5736a 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -24,8 +24,7 @@ int __init parse_cec_param(char *str);
 void log_non_standard_event(const guid_t *sec_type,
 			    const guid_t *fru_id, const char *fru_text,
 			    const u8 sev, const u8 *err, const u32 len);
-void log_arm_hw_error(struct cper_sec_proc_arm *err);
-
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev);
 #else
 static inline void
 log_non_standard_event(const guid_t *sec_type,
@@ -33,7 +32,7 @@ log_non_standard_event(const guid_t *sec_type,
 		       const u8 sev, const u8 *err, const u32 len)
 { return; }
 static inline void
-log_arm_hw_error(struct cper_sec_proc_arm *err) { return; }
+log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { return; }
 #endif
 
 struct atl_err {
@@ -52,5 +51,14 @@ static inline void amd_retire_dram_row(struct atl_err *err) { }
 static inline unsigned long
 amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; }
 #endif /* CONFIG_AMD_ATL */
-
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+#include <asm/smp_plat.h>
+/*
+ * Include ARM specific SMP header which provides a function mapping mpidr to
+ * cpu logical index.
+ */
+#define GET_LOGICAL_INDEX(mpidr) get_logical_index(mpidr & MPIDR_HWID_BITMASK)
+#else
+#define GET_LOGICAL_INDEX(mpidr) -EINVAL
+#endif /* CONFIG_ARM || CONFIG_ARM64 */
 #endif /* __RAS_H__ */
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 7c47151d5c72..ce5214f008eb 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -168,11 +168,24 @@ TRACE_EVENT(mc_event,
  * This event is generated when hardware detects an ARM processor error
  * has occurred. UEFI 2.6 spec section N.2.4.4.
  */
+#define APEIL "ARM Processor Err Info data len"
+#define APEID "ARM Processor Err Info raw data"
+#define APECIL "ARM Processor Err Context Info data len"
+#define APECID "ARM Processor Err Context Info raw data"
+#define VSEIL "Vendor Specific Err Info data len"
+#define VSEID "Vendor Specific Err Info raw data"
 TRACE_EVENT(arm_event,
 
-	TP_PROTO(const struct cper_sec_proc_arm *proc),
+	TP_PROTO(const struct cper_sec_proc_arm *proc, const u8 *pei_err,
+			const u32 pei_len,
+			const u8 *ctx_err,
+			const u32 ctx_len,
+			const u8 *oem,
+			const u32 oem_len,
+			u8 sev,
+			int cpu),
 
-	TP_ARGS(proc),
+	TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu),
 
 	TP_STRUCT__entry(
 		__field(u64, mpidr)
@@ -180,6 +193,14 @@ TRACE_EVENT(arm_event,
 		__field(u32, running_state)
 		__field(u32, psci_state)
 		__field(u8, affinity)
+		__field(u32, pei_len)
+		__dynamic_array(u8, buf, pei_len)
+		__field(u32, ctx_len)
+		__dynamic_array(u8, buf1, ctx_len)
+		__field(u32, oem_len)
+		__dynamic_array(u8, buf2, oem_len)
+		__field(u8, sev)
+		__field(int, cpu)
 	),
 
 	TP_fast_assign(
@@ -199,12 +220,29 @@ TRACE_EVENT(arm_event,
 			__entry->running_state = ~0;
 			__entry->psci_state = ~0;
 		}
+		__entry->pei_len = pei_len;
+		memcpy(__get_dynamic_array(buf), pei_err, pei_len);
+		__entry->ctx_len = ctx_len;
+		memcpy(__get_dynamic_array(buf1), ctx_err, ctx_len);
+		__entry->oem_len = oem_len;
+		memcpy(__get_dynamic_array(buf2), oem, oem_len);
+		__entry->sev = sev;
+		__entry->cpu = cpu;
 	),
 
-	TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
-		  "running state: %d; PSCI state: %d",
+	TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
+		  "running state: %d; PSCI state: %d; "
+		  "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s",
+		  __entry->cpu,
+		  __entry->sev,
 		  __entry->affinity, __entry->mpidr, __entry->midr,
-		  __entry->running_state, __entry->psci_state)
+		  __entry->running_state, __entry->psci_state,
+		  APEIL, __entry->pei_len, APEID,
+		  __print_hex(__get_dynamic_array(buf), __entry->pei_len),
+		  APECIL, __entry->ctx_len, APECID,
+		  __print_hex(__get_dynamic_array(buf1), __entry->ctx_len),
+		  VSEIL, __entry->oem_len, VSEID,
+		  __print_hex(__get_dynamic_array(buf2), __entry->oem_len))
 );
 
 /*
-- 
2.45.2

Re: [PATCH 2/2] RAS: Report all ARM processor CPER information to userspace

[kernel test robot]

Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on rafael-pm/bleeding-edge linus/master v6.10-rc5 next-20240627]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Mauro-Carvalho-Chehab/RAS-ACPI-APEI-add-conditional-compilation-to-ARM-error-report-functions/20240627-225843
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/eed2c4a4fbbb71226ca1944bc7e319bfa9f8aec0.1719471257.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH 2/2] RAS: Report all ARM processor CPER information to userspace
config: arm64-randconfig-002-20240628 (https://download.01.org/0day-ci/archive/20240628/202406281339.b9yJADtu-lkp@intel.com/config)
compiler: aarch64-linux-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240628/202406281339.b9yJADtu-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202406281339.b9yJADtu-lkp@intel.com/

All errors (new ones prefixed by >>):

   drivers/ras/ras.c: In function 'log_arm_hw_error':
>> drivers/ras/ras.c:73:17: error: assignment to 'u8 *' {aka 'unsigned char *'} from incompatible pointer type 'struct cper_arm_ctx_info *' [-Werror=incompatible-pointer-types]
      73 |         ctx_err = ctx_info;
         |                 ^
   cc1: some warnings being treated as errors


vim +73 drivers/ras/ras.c

    54	
    55	void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
    56	{
    57	#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
    58		struct cper_arm_err_info *err_info;
    59		struct cper_arm_ctx_info *ctx_info;
    60		u8 *ven_err_data;
    61		u32 ctx_len = 0;
    62		int n, sz, cpu;
    63		s32 vsei_len;
    64		u32 pei_len;
    65		u8 *pei_err;
    66		u8 *ctx_err;
    67	
    68		pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
    69		pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
    70	
    71		err_info = (struct cper_arm_err_info *)(err + 1);
    72		ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
  > 73		ctx_err = ctx_info;
    74		for (n = 0; n < err->context_info_num; n++) {
    75			sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
    76			ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
    77			ctx_len += sz;
    78		}
    79	
    80		vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
    81						  pei_len + ctx_len);
    82		if (vsei_len < 0) {
    83			pr_warn(FW_BUG
    84				"section length: %d\n", err->section_length);
    85			pr_warn(FW_BUG
    86				"section length is too small\n");
    87			pr_warn(FW_BUG
    88				"firmware-generated error record is incorrect\n");
    89			vsei_len = 0;
    90		}
    91		ven_err_data = (u8 *)ctx_info;
    92	
    93		cpu = GET_LOGICAL_INDEX(err->mpidr);
    94		/* when return value is invalid, set cpu index to -1 */
    95		if (cpu < 0)
    96			cpu = -1;
    97	
    98		trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
    99				ven_err_data, (u32)vsei_len, sev, cpu);
   100	#endif
   101	}
   102	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH 2/2] RAS: Report all ARM processor CPER information to userspace

[kernel test robot]

Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on rafael-pm/linux-next]
[also build test ERROR on rafael-pm/bleeding-edge linus/master v6.10-rc5 next-20240627]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Mauro-Carvalho-Chehab/RAS-ACPI-APEI-add-conditional-compilation-to-ARM-error-report-functions/20240627-225843
base:   https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git linux-next
patch link:    https://lore.kernel.org/r/eed2c4a4fbbb71226ca1944bc7e319bfa9f8aec0.1719471257.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH 2/2] RAS: Report all ARM processor CPER information to userspace
config: arm64-randconfig-003-20240628 (https://download.01.org/0day-ci/archive/20240628/202406281751.Wuf4JcIZ-lkp@intel.com/config)
compiler: clang version 19.0.0git (https://github.com/llvm/llvm-project 326ba38a991250a8587a399a260b0f7af2c9166a)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240628/202406281751.Wuf4JcIZ-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202406281751.Wuf4JcIZ-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from drivers/ras/ras.c:46:
   In file included from include/ras/ras_event.h:12:
   In file included from include/linux/pci.h:1650:
   In file included from include/linux/dmapool.h:14:
   In file included from include/linux/scatterlist.h:8:
   In file included from include/linux/mm.h:2253:
   include/linux/vmstat.h:514:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     514 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
>> drivers/ras/ras.c:73:10: error: incompatible pointer types assigning to 'u8 *' (aka 'unsigned char *') from 'struct cper_arm_ctx_info *' [-Werror,-Wincompatible-pointer-types]
      73 |         ctx_err = ctx_info;
         |                 ^ ~~~~~~~~
   1 warning and 1 error generated.


vim +73 drivers/ras/ras.c

    54	
    55	void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
    56	{
    57	#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
    58		struct cper_arm_err_info *err_info;
    59		struct cper_arm_ctx_info *ctx_info;
    60		u8 *ven_err_data;
    61		u32 ctx_len = 0;
    62		int n, sz, cpu;
    63		s32 vsei_len;
    64		u32 pei_len;
    65		u8 *pei_err;
    66		u8 *ctx_err;
    67	
    68		pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
    69		pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
    70	
    71		err_info = (struct cper_arm_err_info *)(err + 1);
    72		ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
  > 73		ctx_err = ctx_info;
    74		for (n = 0; n < err->context_info_num; n++) {
    75			sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
    76			ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
    77			ctx_len += sz;
    78		}
    79	
    80		vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
    81						  pei_len + ctx_len);
    82		if (vsei_len < 0) {
    83			pr_warn(FW_BUG
    84				"section length: %d\n", err->section_length);
    85			pr_warn(FW_BUG
    86				"section length is too small\n");
    87			pr_warn(FW_BUG
    88				"firmware-generated error record is incorrect\n");
    89			vsei_len = 0;
    90		}
    91		ven_err_data = (u8 *)ctx_info;
    92	
    93		cpu = GET_LOGICAL_INDEX(err->mpidr);
    94		/* when return value is invalid, set cpu index to -1 */
    95		if (cpu < 0)
    96			cpu = -1;
    97	
    98		trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
    99				ven_err_data, (u32)vsei_len, sev, cpu);
   100	#endif
   101	}
   102	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki