lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-id: <20131017072306.5839d500@samsung.com>
Date:	Thu, 17 Oct 2013 07:23:06 -0300
From:	Mauro Carvalho Chehab <m.chehab@...sung.com>
To:	"Chen, Gong" <gong.chen@...ux.intel.com>
Cc:	tony.luck@...el.com, bp@...en8.de, joe@...ches.com,
	naveen.n.rao@...ux.vnet.ibm.com, arozansk@...hat.com,
	linux-acpi@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 6/9] ACPI, APEI,
 CPER: Add UEFI 2.4 support for memory error

Em Wed, 16 Oct 2013 10:56:03 -0400
"Chen, Gong" <gong.chen@...ux.intel.com> escreveu:

> In latest UEFI spec(by now it is 2.4) memory error definition
> for CPER (UEFI 2.4 Appendix N Common Platform Error Record)
> adds some new fields. These fields help people to locate
> memory error on actual DIMM location.
> 
> Original-author: Tony Luck <tony.luck@...el.com>
> Signed-off-by: Chen, Gong <gong.chen@...ux.intel.com>
> Reviewed-by: Borislav Petkov <bp@...e.de>
> ---
>  arch/x86/kernel/cpu/mcheck/mce-apei.c |  3 +--
>  drivers/acpi/apei/cper.c              |  7 ++++---
>  drivers/acpi/apei/ghes.c              |  4 ++--
>  drivers/edac/ghes_edac.c              |  5 ++---
>  include/linux/cper.h                  | 11 +++++++++--
>  5 files changed, 18 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
> index cd8b166..de8b60a 100644
> --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
> +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
> @@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
>  	struct mce m;
>  
>  	/* Only corrected MC is reported */
> -	if (!corrected || !(mem_err->validation_bits &
> -				CPER_MEM_VALID_PHYSICAL_ADDRESS))
> +	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
>  		return;
>  
>  	mce_setup(&m);
> diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
> index eb5f6d6..946ef52 100644
> --- a/drivers/acpi/apei/cper.c
> +++ b/drivers/acpi/apei/cper.c
> @@ -8,7 +8,7 @@
>   * various tables, such as ERST, BERT and HEST etc.
>   *
>   * For more information about CPER, please refer to Appendix N of UEFI
> - * Specification version 2.3.
> + * Specification version 2.4.
>   *
>   * This program is free software; you can redistribute it and/or
>   * modify it under the terms of the GNU General Public License version
> @@ -191,16 +191,17 @@ static const char *cper_mem_err_type_strs[] = {
>  	"memory sparing",
>  	"scrub corrected error",
>  	"scrub uncorrected error",
> +	"physical memory map-out event",
>  };
>  
>  static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
>  {
>  	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
>  		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
> -	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)
> +	if (mem->validation_bits & CPER_MEM_VALID_PA)
>  		printk("%s""physical_address: 0x%016llx\n",
>  		       pfx, mem->physical_addr);
> -	if (mem->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK)
> +	if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
>  		printk("%s""physical_address_mask: 0x%016llx\n",
>  		       pfx, mem->physical_addr_mask);
>  	if (mem->validation_bits & CPER_MEM_VALID_NODE)
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 0db6e4f..a30bc31 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -419,7 +419,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
>  
>  	if (sec_sev == GHES_SEV_CORRECTED &&
>  	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
> -	    (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) {
> +	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
>  		pfn = mem_err->physical_addr >> PAGE_SHIFT;
>  		if (pfn_valid(pfn))
>  			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
> @@ -430,7 +430,7 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
>  	}
>  	if (sev == GHES_SEV_RECOVERABLE &&
>  	    sec_sev == GHES_SEV_RECOVERABLE &&
> -	    mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
> +	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
>  		pfn = mem_err->physical_addr >> PAGE_SHIFT;
>  		memory_failure_queue(pfn, 0, 0);
>  	}
> diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
> index bb53467..0ad797b 100644
> --- a/drivers/edac/ghes_edac.c
> +++ b/drivers/edac/ghes_edac.c
> @@ -297,15 +297,14 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
>  	}
>  
>  	/* Error address */
> -	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) {
> +	if (mem_err->validation_bits & CPER_MEM_VALID_PA) {
>  		e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT;
>  		e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK;
>  	}
>  
>  	/* Error grain */
> -	if (mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK) {
> +	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
>  		e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK);
> -	}
>  
>  	/* Memory error location, mapped on e->location */
>  	p = e->location;
> diff --git a/include/linux/cper.h b/include/linux/cper.h
> index 09ebe21..2fc0ec3 100644
> --- a/include/linux/cper.h
> +++ b/include/linux/cper.h
> @@ -218,8 +218,8 @@ enum {
>  #define CPER_PROC_VALID_IP			0x1000
>  
>  #define CPER_MEM_VALID_ERROR_STATUS		0x0001
> -#define CPER_MEM_VALID_PHYSICAL_ADDRESS		0x0002
> -#define CPER_MEM_VALID_PHYSICAL_ADDRESS_MASK	0x0004
> +#define CPER_MEM_VALID_PA			0x0002
> +#define CPER_MEM_VALID_PA_MASK			0x0004
>  #define CPER_MEM_VALID_NODE			0x0008
>  #define CPER_MEM_VALID_CARD			0x0010
>  #define CPER_MEM_VALID_MODULE			0x0020
> @@ -232,6 +232,9 @@ enum {
>  #define CPER_MEM_VALID_RESPONDER_ID		0x1000
>  #define CPER_MEM_VALID_TARGET_ID		0x2000
>  #define CPER_MEM_VALID_ERROR_TYPE		0x4000
> +#define CPER_MEM_VALID_RANK_NUMBER		0x8000
> +#define CPER_MEM_VALID_CARD_HANDLE		0x10000
> +#define CPER_MEM_VALID_MODULE_HANDLE		0x20000
>  
>  #define CPER_PCIE_VALID_PORT_TYPE		0x0001
>  #define CPER_PCIE_VALID_VERSION			0x0002
> @@ -347,6 +350,10 @@ struct cper_sec_mem_err {
>  	__u64	responder_id;
>  	__u64	target_id;
>  	__u8	error_type;
> +	__u8	reserved;
> +	__u16	rank;
> +	__u16	mem_array_handle;	/* card handle in UEFI 2.4 */
> +	__u16	mem_dev_handle;		/* module handle in UEFI 2.4 */

Hmm... you're adding 3 new types here and the corresponding space inside the
structure (rank, card_handle and module_handle), but the code that parses and
prints it is missing, at apei_mce_report_mem_error(), cper_print_mem(),
ghes_handle_memory_failure() and ghes_edac_report_mem_error().


>  };
>  
>  struct cper_sec_pcie {


-- 

Cheers,
Mauro
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ