linux-acpi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com>
To: "Chen, Gong" <gong.chen@linux.intel.com>,
	tony.luck@intel.com, bp@alien8.de, joe@perches.com,
	m.chehab@samsung.com
Cc: arozansk@redhat.com, linux-acpi@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH v3 8/9] ACPI, APEI, CPER: Cleanup CPER memory error output format
Date: Fri, 18 Oct 2013 17:31:21 +0530	[thread overview]
Message-ID: <52612311.2000303@linux.vnet.ibm.com> (raw)
In-Reply-To: <1382084624-10857-9-git-send-email-gong.chen@linux.intel.com>

On 10/18/2013 01:53 PM, Chen, Gong wrote:
> Keep up only the most important fields for memory error
> reporting. The detail information will be moved to perf/trace
> interface.
>
> Suggested-by: Tony Luck <tony.luck@intel.com>
> Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
> Reviewed-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
> ---
>   drivers/acpi/apei/cper.c | 67 ++++++++++++++++++++++--------------------------
>   1 file changed, 31 insertions(+), 36 deletions(-)
>
> diff --git a/drivers/acpi/apei/cper.c b/drivers/acpi/apei/cper.c
> index b1a8a55..9dd54e1 100644
> --- a/drivers/acpi/apei/cper.c
> +++ b/drivers/acpi/apei/cper.c
> @@ -33,6 +33,7 @@
>   #include <linux/pci.h>
>   #include <linux/aer.h>
>
> +#define INDENT_SP	" "
>   /*
>    * CPER record ID need to be unique even after reboot, because record
>    * ID is used as index for ERST storage, while CPER records from
> @@ -206,29 +207,29 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
>   		printk("%s""physical_address_mask: 0x%016llx\n",
>   		       pfx, mem->physical_addr_mask);

Can you also change the above address mask to pr_debug(). I don't think 
this is useful at all if set, since we always deal at a page granularity.

>   	if (mem->validation_bits & CPER_MEM_VALID_NODE)
> -		printk("%s""node: %d\n", pfx, mem->node);
> +		pr_debug("node: %d\n", mem->node);
>   	if (mem->validation_bits & CPER_MEM_VALID_CARD)
> -		printk("%s""card: %d\n", pfx, mem->card);
> +		pr_debug("card: %d\n", mem->card);
>   	if (mem->validation_bits & CPER_MEM_VALID_MODULE)
> -		printk("%s""module: %d\n", pfx, mem->module);
> +		pr_debug("module: %d\n", mem->module);
>   	if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER)
> -		printk("%s""rank: %d\n", pfx, mem->rank);
> +		pr_debug("rank: %d\n", mem->rank);
>   	if (mem->validation_bits & CPER_MEM_VALID_BANK)
> -		printk("%s""bank: %d\n", pfx, mem->bank);
> +		pr_debug("bank: %d\n", mem->bank);
>   	if (mem->validation_bits & CPER_MEM_VALID_DEVICE)
> -		printk("%s""device: %d\n", pfx, mem->device);
> +		pr_debug("device: %d\n", mem->device);
>   	if (mem->validation_bits & CPER_MEM_VALID_ROW)
> -		printk("%s""row: %d\n", pfx, mem->row);
> +		pr_debug("row: %d\n", mem->row);
>   	if (mem->validation_bits & CPER_MEM_VALID_COLUMN)
> -		printk("%s""column: %d\n", pfx, mem->column);
> +		pr_debug("column: %d\n", mem->column);
>   	if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION)
> -		printk("%s""bit_position: %d\n", pfx, mem->bit_pos);
> +		pr_debug("bit_position: %d\n", mem->bit_pos);
>   	if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID)
> -		printk("%s""requestor_id: 0x%016llx\n", pfx, mem->requestor_id);
> +		pr_debug("requestor_id: 0x%016llx\n", mem->requestor_id);
>   	if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID)
> -		printk("%s""responder_id: 0x%016llx\n", pfx, mem->responder_id);
> +		pr_debug("responder_id: 0x%016llx\n", mem->responder_id);
>   	if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID)
> -		printk("%s""target_id: 0x%016llx\n", pfx, mem->target_id);
> +		pr_debug("target_id: 0x%016llx\n", mem->target_id);
>   	if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
>   		u8 etype = mem->error_type;
>   		printk("%s""error_type: %d, %s\n", pfx, etype,
> @@ -296,55 +297,45 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
>   	pfx, pcie->bridge.secondary_status, pcie->bridge.control);
>   }
>
> -static const char * const cper_estatus_section_flag_strs[] = {
> -	"primary",
> -	"containment warning",
> -	"reset",
> -	"error threshold exceeded",
> -	"resource not accessible",
> -	"latent error",
> -};
> -
>   static void cper_estatus_print_section(
>   	const char *pfx, const struct acpi_generic_data *gdata, int sec_no)
>   {
>   	uuid_le *sec_type = (uuid_le *)gdata->section_type;
>   	__u16 severity;
> +	char newpfx[64];
>
>   	severity = gdata->error_severity;
> -	printk("%s""section: %d, severity: %d, %s\n", pfx, sec_no, severity,
> +	printk("%s""Error %d, type: %s\n", pfx, sec_no,

Nit: Isn't the original text more appropriate here? We are printing each 
section in the error status block. So, section 0, 1 makes better sense 
for me rather than calling these as errors. Each of these sub-sections 
(if more than one) refer to the same error event per the ACPI spec.

>   	       cper_severity_str(severity));
> -	printk("%s""flags: 0x%02x\n", pfx, gdata->flags);
> -	cper_print_bits(pfx, gdata->flags, cper_estatus_section_flag_strs,
> -			ARRAY_SIZE(cper_estatus_section_flag_strs));
>   	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
>   		printk("%s""fru_id: %pUl\n", pfx, (uuid_le *)gdata->fru_id);
>   	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
>   		printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
>
> +	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
>   	if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_GENERIC)) {
>   		struct cper_sec_proc_generic *proc_err = (void *)(gdata + 1);
> -		printk("%s""section_type: general processor error\n", pfx);
> +		printk("%s""section_type: general processor error\n", newpfx);
>   		if (gdata->error_data_length >= sizeof(*proc_err))
> -			cper_print_proc_generic(pfx, proc_err);
> +			cper_print_proc_generic(newpfx, proc_err);
>   		else
>   			goto err_section_too_small;
>   	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
>   		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
> -		printk("%s""section_type: memory error\n", pfx);
> +		printk("%s""section_type: memory error\n", newpfx);
>   		if (gdata->error_data_length >= sizeof(*mem_err))
> -			cper_print_mem(pfx, mem_err);
> +			cper_print_mem(newpfx, mem_err);
>   		else
>   			goto err_section_too_small;
>   	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
>   		struct cper_sec_pcie *pcie = (void *)(gdata + 1);
> -		printk("%s""section_type: PCIe error\n", pfx);
> +		printk("%s""section_type: PCIe error\n", newpfx);
>   		if (gdata->error_data_length >= sizeof(*pcie))
> -			cper_print_pcie(pfx, pcie, gdata);
> +			cper_print_pcie(newpfx, pcie, gdata);
>   		else
>   			goto err_section_too_small;
>   	} else
> -		printk("%s""section type: unknown, %pUl\n", pfx, sec_type);
> +		printk("%s""section type: unknown, %pUl\n", newpfx, sec_type);
>
>   	return;
>
> @@ -358,17 +349,21 @@ void cper_estatus_print(const char *pfx,
>   	struct acpi_generic_data *gdata;
>   	unsigned int data_len, gedata_len;
>   	int sec_no = 0;
> +	char newpfx[64];
>   	__u16 severity;
>
> -	printk("%s""Generic Hardware Error Status\n", pfx);
>   	severity = estatus->error_severity;
> -	printk("%s""severity: %d, %s\n", pfx, severity,
> -	       cper_severity_str(severity));
> +	if (severity != CPER_SEV_FATAL)

Shouldn't this just be (severity == CPER_SEV_CORRECTED)?

Thanks,
Naveen

> +		printk("%s%s\n", pfx,
> +		       "It has been corrected by h/w "
> +		       "and requires no further action");
> +	printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
>   	data_len = estatus->data_length;
>   	gdata = (struct acpi_generic_data *)(estatus + 1);
> +	snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
>   	while (data_len >= sizeof(*gdata)) {
>   		gedata_len = gdata->error_data_length;
> -		cper_estatus_print_section(pfx, gdata, sec_no);
> +		cper_estatus_print_section(newpfx, gdata, sec_no);
>   		data_len -= gedata_len + sizeof(*gdata);
>   		gdata = (void *)(gdata + 1) + gedata_len;
>   		sec_no++;
>


  reply	other threads:[~2013-10-18 12:01 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-10-18  8:23 [PATCH v3 0/9] Extended H/W error log driver Chen, Gong
2013-10-18  8:23 ` [PATCH v3 1/9] ACPI, APEI, CPER: Fix status check during error printing Chen, Gong
2013-10-18  8:23 ` [PATCH v3 2/9] ACPI, CPER: Update cper info Chen, Gong
2013-10-18 12:39   ` Naveen N. Rao
2013-10-18  8:23 ` [PATCH v3 3/9] bitops: Introduce a more generic BITMASK macro Chen, Gong
2013-10-18  8:23 ` [PATCH v3 4/9] ACPI, x86: Extended error log driver for x86 platform Chen, Gong
2013-10-18 12:37   ` Naveen N. Rao
2013-10-18 12:53     ` Borislav Petkov
2013-10-18 20:57       ` Luck, Tony
2013-10-18 21:27         ` Borislav Petkov
2013-10-18 22:22           ` Luck, Tony
2013-10-19  9:57             ` Borislav Petkov
2013-10-21 19:03               ` Luck, Tony
2013-10-21 22:39                 ` Tony Luck
2013-10-22  8:37                   ` Borislav Petkov
2013-10-22  9:32                 ` Naveen N. Rao
2013-10-19 11:31     ` Chen Gong
2013-10-20  7:06     ` Chen Gong
2013-10-20  8:21       ` Borislav Petkov
2013-10-21 16:27         ` Naveen N. Rao
2013-10-20  7:25     ` [PATCH V4 " Chen, Gong
2014-06-27  5:34     ` [PATCH v3 " Xie XiuQi
2014-06-27  9:22       ` Borislav Petkov
2014-06-27 20:43         ` Luck, Tony
2014-06-27 21:14           ` Borislav Petkov
2014-06-27 22:10             ` Luck, Tony
2014-06-27 22:14               ` Borislav Petkov
2014-06-30  6:35               ` Xie XiuQi
2013-10-18  8:23 ` [PATCH v3 5/9] DMI: Parse memory device (type 17) in SMBIOS Chen, Gong
2013-10-18  8:23 ` [PATCH v3 6/9] ACPI, APEI, CPER: Add UEFI 2.4 support for memory error Chen, Gong
2013-10-18  8:23 ` [PATCH v3 7/9] ACPI, APEI, CPER: Enhance memory reporting capability Chen, Gong
2013-10-18  8:23 ` [PATCH v3 8/9] ACPI, APEI, CPER: Cleanup CPER memory error output format Chen, Gong
2013-10-18 12:01   ` Naveen N. Rao [this message]
2013-10-19 11:26     ` Chen Gong
2013-10-21 16:22       ` Naveen N. Rao
2013-10-21 17:14         ` Luck, Tony
2013-10-22  8:42           ` Borislav Petkov
2013-10-18  8:23 ` [PATCH v3 9/9] EDAC, GHES: Update ghes error record info Chen, Gong
2013-10-18  9:20 ` [PATCH v3 0/9] Extended H/W error log driver Borislav Petkov
2013-10-18 16:17   ` Tony Luck

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=52612311.2000303@linux.vnet.ibm.com \
    --to=naveen.n.rao@linux.vnet.ibm.com \
    --cc=arozansk@redhat.com \
    --cc=bp@alien8.de \
    --cc=gong.chen@linux.intel.com \
    --cc=joe@perches.com \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=m.chehab@samsung.com \
    --cc=tony.luck@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).