Commit ed27b5df authored by Shuai Xue's avatar Shuai Xue Committed by Borislav Petkov
Browse files

EDAC/ghes: Unify CPER memory error location reporting 



Switch the GHES EDAC memory error reporting functions to use the common
CPER ones and get rid of code duplication.

  [ bp:
      - rewrite commit message, remove useless text
      - rip out useless reformatting
      - align function params on the opening brace
      - rename function to a more descriptive name
      - drop useless function exports
      - handle buffer lengths properly when printing other detail
      - remove useless casting
  ]

Signed-off-by: default avatarShuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: default avatarBorislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20220308144053.49090-3-xueshuai@linux.alibaba.com
parent bdae7965

drivers/edac/Kconfig

+1 −0
Original line number Original line Diff line number Diff line
@@ -55,6 +55,7 @@ config EDAC_DECODE_MCE 
config EDAC_GHES

config EDAC_GHES

	bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"

	bool "Output ACPI APEI/GHES BIOS detected errors via EDAC"

	depends on ACPI_APEI_GHES && (EDAC=y)

	depends on ACPI_APEI_GHES && (EDAC=y)

	select UEFI_CPER

	help

	help

	  Not all machines support hardware-driven error report. Some of those

	  Not all machines support hardware-driven error report. Some of those

	  provide a BIOS-driven error report mechanism via ACPI, using the

	  provide a BIOS-driven error report mechanism via ACPI, using the

drivers/edac/ghes_edac.c

+37 −163
Original line number Original line Diff line number Diff line
@@ -15,11 +15,13 @@ 
#include "edac_module.h"

#include "edac_module.h"

#include <ras/ras_event.h>

#include <ras/ras_event.h>





#define OTHER_DETAIL_LEN	400



struct ghes_pvt {

struct ghes_pvt {

	struct mem_ctl_info *mci;

	struct mem_ctl_info *mci;





	/* Buffers for the error handling routine */

	/* Buffers for the error handling routine */

	char other_detail[400];

	char other_detail[OTHER_DETAIL_LEN];

	char msg[80];

	char msg[80];

};

};
@@ -235,8 +237,34 @@ static void ghes_scan_system(void) 
	system_scanned = true;

	system_scanned = true;

}

}





static int print_mem_error_other_detail(const struct cper_sec_mem_err *mem, char *msg,

					const char *location, unsigned int len)

{

	u32 n;



	if (!msg)

		return 0;



	n = 0;

	len -= 1;



	n += scnprintf(msg + n, len - n, "APEI location: %s ", location);



	if (!(mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS))

		goto out;



	n += scnprintf(msg + n, len - n, "status(0x%016llx): ", mem->error_status);

	n += scnprintf(msg + n, len - n, "%s ", cper_mem_err_status_str(mem->error_status));



out:

	msg[n] = '\0';



	return n;

}



void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)

void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err)

{

{

	struct cper_mem_err_compact cmem;

	struct edac_raw_error_desc *e;

	struct edac_raw_error_desc *e;

	struct mem_ctl_info *mci;

	struct mem_ctl_info *mci;

	struct ghes_pvt *pvt;

	struct ghes_pvt *pvt;
@@ -292,60 +320,10 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) 




	/* Error type, mapped on e->msg */

	/* Error type, mapped on e->msg */

	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {

	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {

		u8 etype = mem_err->error_type;



		p = pvt->msg;

		p = pvt->msg;

		switch (mem_err->error_type) {

		p += snprintf(p, sizeof(pvt->msg), "%s", cper_mem_err_type_str(etype));

		case 0:

			p += sprintf(p, "Unknown");

			break;

		case 1:

			p += sprintf(p, "No error");

			break;

		case 2:

			p += sprintf(p, "Single-bit ECC");

			break;

		case 3:

			p += sprintf(p, "Multi-bit ECC");

			break;

		case 4:

			p += sprintf(p, "Single-symbol ChipKill ECC");

			break;

		case 5:

			p += sprintf(p, "Multi-symbol ChipKill ECC");

			break;

		case 6:

			p += sprintf(p, "Master abort");

			break;

		case 7:

			p += sprintf(p, "Target abort");

			break;

		case 8:

			p += sprintf(p, "Parity Error");

			break;

		case 9:

			p += sprintf(p, "Watchdog timeout");

			break;

		case 10:

			p += sprintf(p, "Invalid address");

			break;

		case 11:

			p += sprintf(p, "Mirror Broken");

			break;

		case 12:

			p += sprintf(p, "Memory Sparing");

			break;

		case 13:

			p += sprintf(p, "Scrub corrected error");

			break;

		case 14:

			p += sprintf(p, "Scrub uncorrected error");

			break;

		case 15:

			p += sprintf(p, "Physical Memory Map-out event");

			break;

		default:

			p += sprintf(p, "reserved error (%d)",

				     mem_err->error_type);

		}

	} else {

	} else {

		strcpy(pvt->msg, "unknown error");

		strcpy(pvt->msg, "unknown error");

	}

	}
@@ -362,52 +340,19 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) 




	/* Memory error location, mapped on e->location */

	/* Memory error location, mapped on e->location */

	p = e->location;

	p = e->location;

	if (mem_err->validation_bits & CPER_MEM_VALID_NODE)

	cper_mem_err_pack(mem_err, &cmem);

		p += sprintf(p, "node:%d ", mem_err->node);

	p += cper_mem_err_location(&cmem, p);

	if (mem_err->validation_bits & CPER_MEM_VALID_CARD)



		p += sprintf(p, "card:%d ", mem_err->card);

	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE)

		p += sprintf(p, "module:%d ", mem_err->module);

	if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER)

		p += sprintf(p, "rank:%d ", mem_err->rank);

	if (mem_err->validation_bits & CPER_MEM_VALID_BANK)

		p += sprintf(p, "bank:%d ", mem_err->bank);

	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_GROUP)

		p += sprintf(p, "bank_group:%d ",

			     mem_err->bank >> CPER_MEM_BANK_GROUP_SHIFT);

	if (mem_err->validation_bits & CPER_MEM_VALID_BANK_ADDRESS)

		p += sprintf(p, "bank_address:%d ",

			     mem_err->bank & CPER_MEM_BANK_ADDRESS_MASK);

	if (mem_err->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) {

		u32 row = mem_err->row;



		row |= cper_get_mem_extension(mem_err->validation_bits, mem_err->extended);

		p += sprintf(p, "row:%d ", row);

	}

	if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN)

		p += sprintf(p, "col:%d ", mem_err->column);

	if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION)

		p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos);

	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {

	if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) {

		const char *bank = NULL, *device = NULL;

		struct dimm_info *dimm;

		struct dimm_info *dimm;





		dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device);

		p += cper_dimm_err_location(&cmem, p);

		if (bank != NULL && device != NULL)

			p += sprintf(p, "DIMM location:%s %s ", bank, device);

		else

			p += sprintf(p, "DIMM DMI handle: 0x%.4x ",

				     mem_err->mem_dev_handle);



		dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle);

		dimm = find_dimm_by_handle(mci, mem_err->mem_dev_handle);

		if (dimm) {

		if (dimm) {

			e->top_layer = dimm->idx;

			e->top_layer = dimm->idx;

			strcpy(e->label, dimm->label);

			strcpy(e->label, dimm->label);

		}

		}

	}

	}

	if (mem_err->validation_bits & CPER_MEM_VALID_CHIP_ID)

		p += sprintf(p, "chipID: %d ",

			     mem_err->extended >> CPER_MEM_CHIP_ID_SHIFT);

	if (p > e->location)

	if (p > e->location)

		*(p - 1) = '\0';

		*(p - 1) = '\0';
@@ -416,78 +361,7 @@ void ghes_edac_report_mem_error(int sev, struct cper_sec_mem_err *mem_err) 




	/* All other fields are mapped on e->other_detail */

	/* All other fields are mapped on e->other_detail */

	p = pvt->other_detail;

	p = pvt->other_detail;

	p += snprintf(p, sizeof(pvt->other_detail),

	p += print_mem_error_other_detail(mem_err, p, e->location, OTHER_DETAIL_LEN);

		"APEI location: %s ", e->location);

	if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) {

		u64 status = mem_err->error_status;



		p += sprintf(p, "status(0x%016llx): ", (long long)status);

		switch ((status >> 8) & 0xff) {

		case 1:

			p += sprintf(p, "Error detected internal to the component ");

			break;

		case 16:

			p += sprintf(p, "Error detected in the bus ");

			break;

		case 4:

			p += sprintf(p, "Storage error in DRAM memory ");

			break;

		case 5:

			p += sprintf(p, "Storage error in TLB ");

			break;

		case 6:

			p += sprintf(p, "Storage error in cache ");

			break;

		case 7:

			p += sprintf(p, "Error in one or more functional units ");

			break;

		case 8:

			p += sprintf(p, "component failed self test ");

			break;

		case 9:

			p += sprintf(p, "Overflow or undervalue of internal queue ");

			break;

		case 17:

			p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR ");

			break;

		case 18:

			p += sprintf(p, "Improper access error ");

			break;

		case 19:

			p += sprintf(p, "Access to a memory address which is not mapped to any component ");

			break;

		case 20:

			p += sprintf(p, "Loss of Lockstep ");

			break;

		case 21:

			p += sprintf(p, "Response not associated with a request ");

			break;

		case 22:

			p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits ");

			break;

		case 23:

			p += sprintf(p, "Detection of a PATH_ERROR ");

			break;

		case 25:

			p += sprintf(p, "Bus operation timeout ");

			break;

		case 26:

			p += sprintf(p, "A read was issued to data that has been poisoned ");

			break;

		default:

			p += sprintf(p, "reserved ");

			break;

		}

	}

	if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)

		p += sprintf(p, "requestorID: 0x%016llx ",

			     (long long)mem_err->requestor_id);

	if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID)

		p += sprintf(p, "responderID: 0x%016llx ",

			     (long long)mem_err->responder_id);

	if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID)

		p += sprintf(p, "targetID: 0x%016llx ",

			     (long long)mem_err->responder_id);

	if (p > pvt->other_detail)

	if (p > pvt->other_detail)

		*(p - 1) = '\0';

		*(p - 1) = '\0';

drivers/firmware/efi/cper.c

+2 −2
Original line number Original line Diff line number Diff line
@@ -237,7 +237,7 @@ const char *cper_mem_err_status_str(u64 status) 
}

}

EXPORT_SYMBOL_GPL(cper_mem_err_status_str);

EXPORT_SYMBOL_GPL(cper_mem_err_status_str);





static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)

int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)

{

{

	u32 len, n;

	u32 len, n;
@@ -291,7 +291,7 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) 
	return n;

	return n;

}

}





static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)

int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)

{

{

	u32 len, n;

	u32 len, n;

	const char *bank = NULL, *device = NULL;

	const char *bank = NULL, *device = NULL;

include/linux/cper.h

+2 −0
Original line number Original line Diff line number Diff line
@@ -569,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, 
			 const struct cper_sec_proc_arm *proc);

			 const struct cper_sec_proc_arm *proc);

void cper_print_proc_ia(const char *pfx,

void cper_print_proc_ia(const char *pfx,

			const struct cper_sec_proc_ia *proc);

			const struct cper_sec_proc_ia *proc);

int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg);

int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg);





#endif
 
#endif