diff mbox series

[v5,3/4] efi/cper: align ARM CPER type with UEFI 2.9A/2.10 specs

Message ID b9354882f45a0c600e65df4bacee2f1080c4ba89.1719219886.git.mchehab+huawei@kernel.org (mailing list archive)
State New
Headers show
Series fix CPER issues related to UEFI 2.9A Errata | expand

Commit Message

Mauro Carvalho Chehab June 24, 2024, 9:19 a.m. UTC 
Up to UEFI spec, the type byte of CPER struct for ARM processor was
defined simply as:

Type at byte offset 4:

	- Cache error
	- TLB Error
	- Bus Error
	- Micro-architectural Error
	All other values are reserved

Yet, there was no information about how this would be encoded.

Spec 2.9A errata corrected it by defining:

	- Bit 1 - Cache Error
	- Bit 2 - TLB Error
	- Bit 3 - Bus Error
	- Bit 4 - Micro-architectural Error
	All other values are reserved

That actually aligns with the values already defined on older
versions at N.2.4.1. Generic Processor Error Section.

Spec 2.10 also preserve the same encoding as 2.9A

Adjust CPER and GHES handling code for both generic and ARM
processors to properly handle UEFI 2.9A and 2.10 encoding.

Link: https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#arm-processor-error-information
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
---
 drivers/acpi/apei/ghes.c        | 15 ++++++----
 drivers/firmware/efi/cper-arm.c | 50 ++++++++++++++++-----------------
 include/linux/cper.h            | 10 +++----
 3 files changed, 38 insertions(+), 37 deletions(-)

Comments

kernel test robot June 27, 2024, 8:59 a.m. UTC | #1 
Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on efi/next]
[also build test ERROR on rafael-pm/linux-next rafael-pm/bleeding-edge linus/master v6.10-rc5 next-20240626]
[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/efi-cper-Adjust-infopfx-size-to-accept-an-extra-space/20240625-203952
base:   https://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git next
patch link:    https://lore.kernel.org/r/b9354882f45a0c600e65df4bacee2f1080c4ba89.1719219886.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH v5 3/4] efi/cper: align ARM CPER type with UEFI 2.9A/2.10 specs
config: i386-randconfig-004-20240627 (https://download.01.org/0day-ci/archive/20240627/202406271626.72sHSPJJ-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/20240627/202406271626.72sHSPJJ-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/202406271626.72sHSPJJ-lkp@intel.com/

All errors (new ones prefixed by >>):

>> drivers/acpi/apei/ghes.c:566:6: error: call to undeclared function 'FIELD_GET'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration]
     566 |                                  FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
         |                                  ^
   1 error generated.


vim +/FIELD_GET +566 drivers/acpi/apei/ghes.c

   530	
   531	static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
   532					       int sev, bool sync)
   533	{
   534		struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
   535		int flags = sync ? MF_ACTION_REQUIRED : 0;
   536		char error_type[120];
   537		bool queued = false;
   538		int sec_sev, i;
   539		char *p;
   540	
   541		log_arm_hw_error(err);
   542	
   543		sec_sev = ghes_severity(gdata->error_severity);
   544		if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
   545			return false;
   546	
   547		p = (char *)(err + 1);
   548		for (i = 0; i < err->err_info_num; i++) {
   549			struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
   550			bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
   551			bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
   552	
   553			/*
   554			 * The field (err_info->error_info & BIT(26)) is fixed to set to
   555			 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
   556			 * firmware won't mix corrected errors in an uncorrected section,
   557			 * and don't filter out 'corrected' error here.
   558			 */
   559			if (is_cache && has_pa) {
   560				queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
   561				p += err_info->length;
   562				continue;
   563			}
   564	
   565			cper_bits_to_str(error_type, sizeof(error_type),
 > 566					 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
   567					 cper_proc_error_type_strs,
   568					 ARRAY_SIZE(cper_proc_error_type_strs));
   569	
   570			pr_warn_ratelimited(FW_WARN GHES_PFX
   571					    "Unhandled processor error type 0x%02x: %s%s\n",
   572					    err_info->type, error_type,
   573					    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
   574			p += err_info->length;
   575		}
   576	
   577		return queued;
   578	}
   579
kernel test robot June 28, 2024, 8:28 p.m. UTC | #2 
Hi Mauro,

kernel test robot noticed the following build errors:

[auto build test ERROR on efi/next]
[also build test ERROR on rafael-pm/linux-next 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/efi-cper-Adjust-infopfx-size-to-accept-an-extra-space/20240625-203952
base:   https://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git next
patch link:    https://lore.kernel.org/r/b9354882f45a0c600e65df4bacee2f1080c4ba89.1719219886.git.mchehab%2Bhuawei%40kernel.org
patch subject: [PATCH v5 3/4] efi/cper: align ARM CPER type with UEFI 2.9A/2.10 specs
config: x86_64-buildonly-randconfig-003-20240628 (https://download.01.org/0day-ci/archive/20240629/202406290457.3HKFUkuV-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/20240629/202406290457.3HKFUkuV-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/202406290457.3HKFUkuV-lkp@intel.com/

All errors (new ones prefixed by >>):

   drivers/acpi/apei/ghes.c: In function 'ghes_handle_arm_hw_error':
>> drivers/acpi/apei/ghes.c:566:34: error: implicit declaration of function 'FIELD_GET' [-Werror=implicit-function-declaration]
     566 |                                  FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
         |                                  ^~~~~~~~~
   cc1: some warnings being treated as errors


vim +/FIELD_GET +566 drivers/acpi/apei/ghes.c

   530	
   531	static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
   532					       int sev, bool sync)
   533	{
   534		struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
   535		int flags = sync ? MF_ACTION_REQUIRED : 0;
   536		char error_type[120];
   537		bool queued = false;
   538		int sec_sev, i;
   539		char *p;
   540	
   541		log_arm_hw_error(err);
   542	
   543		sec_sev = ghes_severity(gdata->error_severity);
   544		if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
   545			return false;
   546	
   547		p = (char *)(err + 1);
   548		for (i = 0; i < err->err_info_num; i++) {
   549			struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
   550			bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
   551			bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
   552	
   553			/*
   554			 * The field (err_info->error_info & BIT(26)) is fixed to set to
   555			 * 1 in some old firmware of HiSilicon Kunpeng920. We assume that
   556			 * firmware won't mix corrected errors in an uncorrected section,
   557			 * and don't filter out 'corrected' error here.
   558			 */
   559			if (is_cache && has_pa) {
   560				queued = ghes_do_memory_failure(err_info->physical_fault_addr, flags);
   561				p += err_info->length;
   562				continue;
   563			}
   564	
   565			cper_bits_to_str(error_type, sizeof(error_type),
 > 566					 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
   567					 cper_proc_error_type_strs,
   568					 ARRAY_SIZE(cper_proc_error_type_strs));
   569	
   570			pr_warn_ratelimited(FW_WARN GHES_PFX
   571					    "Unhandled processor error type 0x%02x: %s%s\n",
   572					    err_info->type, error_type,
   573					    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
   574			p += err_info->length;
   575		}
   576	
   577		return queued;
   578	}
   579
diff mbox series

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 623cc0cb4a65..de79cc0a0f1d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -533,6 +533,7 @@  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 {
 	struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
 	int flags = sync ? MF_ACTION_REQUIRED : 0;
+	char error_type[120];
 	bool queued = false;
 	int sec_sev, i;
 	char *p;
@@ -546,9 +547,8 @@  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 	p = (char *)(err + 1);
 	for (i = 0; i < err->err_info_num; i++) {
 		struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p;
-		bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR);
+		bool is_cache = err_info->type & CPER_ARM_CACHE_ERROR;
 		bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR);
-		const char *error_type = "unknown error";
 
 		/*
 		 * The field (err_info->error_info & BIT(26)) is fixed to set to
@@ -562,12 +562,15 @@  static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
 			continue;
 		}
 
-		if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs))
-			error_type = cper_proc_error_type_strs[err_info->type];
+		cper_bits_to_str(error_type, sizeof(error_type),
+				 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
 
 		pr_warn_ratelimited(FW_WARN GHES_PFX
-				    "Unhandled processor error type: %s\n",
-				    error_type);
+				    "Unhandled processor error type 0x%02x: %s%s\n",
+				    err_info->type, error_type,
+				    (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
 		p += err_info->length;
 	}
 
diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index eb7ee6af55f2..52d18490b59e 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -93,15 +93,11 @@  static void cper_print_arm_err_info(const char *pfx, u32 type,
 	bool proc_context_corrupt, corrected, precise_pc, restartable_pc;
 	bool time_out, access_mode;
 
-	/* If the type is unknown, bail. */
-	if (type > CPER_ARM_MAX_TYPE)
-		return;
-
 	/*
 	 * Vendor type errors have error information values that are vendor
 	 * specific.
 	 */
-	if (type == CPER_ARM_VENDOR_ERROR)
+	if (type & CPER_ARM_VENDOR_ERROR)
 		return;
 
 	if (error_info & CPER_ARM_ERR_VALID_TRANSACTION_TYPE) {
@@ -116,43 +112,38 @@  static void cper_print_arm_err_info(const char *pfx, u32 type,
 	if (error_info & CPER_ARM_ERR_VALID_OPERATION_TYPE) {
 		op_type = ((error_info >> CPER_ARM_ERR_OPERATION_SHIFT)
 			   & CPER_ARM_ERR_OPERATION_MASK);
-		switch (type) {
-		case CPER_ARM_CACHE_ERROR:
+		if (type & CPER_ARM_CACHE_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_cache_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%scache error, operation type: %s\n", pfx,
 				       arm_cache_err_op_strs[op_type]);
 			}
-			break;
-		case CPER_ARM_TLB_ERROR:
+		}
+		if (type & CPER_ARM_TLB_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_tlb_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%sTLB error, operation type: %s\n", pfx,
 				       arm_tlb_err_op_strs[op_type]);
 			}
-			break;
-		case CPER_ARM_BUS_ERROR:
+		}
+		if (type & CPER_ARM_BUS_ERROR) {
 			if (op_type < ARRAY_SIZE(arm_bus_err_op_strs)) {
-				printk("%soperation type: %s\n", pfx,
+				printk("%sbus error, operation type: %s\n", pfx,
 				       arm_bus_err_op_strs[op_type]);
 			}
-			break;
 		}
 	}
 
 	if (error_info & CPER_ARM_ERR_VALID_LEVEL) {
 		level = ((error_info >> CPER_ARM_ERR_LEVEL_SHIFT)
 			 & CPER_ARM_ERR_LEVEL_MASK);
-		switch (type) {
-		case CPER_ARM_CACHE_ERROR:
+		if (type & CPER_ARM_CACHE_ERROR)
 			printk("%scache level: %d\n", pfx, level);
-			break;
-		case CPER_ARM_TLB_ERROR:
+
+		if (type & CPER_ARM_TLB_ERROR)
 			printk("%sTLB level: %d\n", pfx, level);
-			break;
-		case CPER_ARM_BUS_ERROR:
+
+		if (type & CPER_ARM_BUS_ERROR)
 			printk("%saffinity level at which the bus error occurred: %d\n",
 			       pfx, level);
-			break;
-		}
 	}
 
 	if (error_info & CPER_ARM_ERR_VALID_PROC_CONTEXT_CORRUPT) {
@@ -241,6 +232,7 @@  void cper_print_proc_arm(const char *pfx,
 	struct cper_arm_err_info *err_info;
 	struct cper_arm_ctx_info *ctx_info;
 	char newpfx[64], infopfx[ARRAY_SIZE(newpfx) + 1];
+	char error_type[120];
 
 	printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
 
@@ -289,9 +281,15 @@  void cper_print_proc_arm(const char *pfx,
 				       newpfx);
 		}
 
-		printk("%serror_type: %d, %s\n", newpfx, err_info->type,
-			err_info->type < ARRAY_SIZE(cper_proc_error_type_strs) ?
-			cper_proc_error_type_strs[err_info->type] : "unknown");
+		cper_bits_to_str(error_type, sizeof(error_type),
+				 FIELD_GET(CPER_ARM_ERR_TYPE_MASK, err_info->type),
+				 cper_proc_error_type_strs,
+				 ARRAY_SIZE(cper_proc_error_type_strs));
+
+		printk("%serror_type: 0x%02x: %s%s\n", newpfx, err_info->type,
+		       error_type,
+		       (err_info->type & ~CPER_ARM_ERR_TYPE_MASK) ? " with reserved bit(s)" : "");
+
 		if (err_info->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO) {
 			printk("%serror_info: 0x%016llx\n", newpfx,
 			       err_info->error_info);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index c2f14b916bfb..fc62a80575e8 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -293,11 +293,11 @@  enum {
 #define CPER_ARM_INFO_FLAGS_PROPAGATED		BIT(2)
 #define CPER_ARM_INFO_FLAGS_OVERFLOW		BIT(3)
 
-#define CPER_ARM_CACHE_ERROR			0
-#define CPER_ARM_TLB_ERROR			1
-#define CPER_ARM_BUS_ERROR			2
-#define CPER_ARM_VENDOR_ERROR			3
-#define CPER_ARM_MAX_TYPE			CPER_ARM_VENDOR_ERROR
+#define CPER_ARM_ERR_TYPE_MASK			GENMASK(4,1)
+#define CPER_ARM_CACHE_ERROR			BIT(1)
+#define CPER_ARM_TLB_ERROR			BIT(2)
+#define CPER_ARM_BUS_ERROR			BIT(3)
+#define CPER_ARM_VENDOR_ERROR			BIT(4)
 
 #define CPER_ARM_ERR_VALID_TRANSACTION_TYPE	BIT(0)
 #define CPER_ARM_ERR_VALID_OPERATION_TYPE	BIT(1)