diff mbox series

[v4,1/2] efi/cper: add cper_mem_err_status_str to decode error description

Message ID 20220125024939.30635-2-xueshuai@linux.alibaba.com (mailing list archive)
State New, archived
Headers show
Series [v4,1/2] efi/cper: add cper_mem_err_status_str to decode error description | expand

Commit Message

Shuai Xue Jan. 25, 2022, 2:49 a.m. UTC 
Introduce a new helper function cper_mem_err_status_str() which is used to
decode the description of error status, and the cper_print_mem() will call
it and report the details of error status.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
---
 drivers/firmware/efi/cper.c | 29 ++++++++++++++++++++++++++++-
 include/linux/cper.h        |  1 +
 2 files changed, 29 insertions(+), 1 deletion(-)

Comments

Borislav Petkov Jan. 25, 2022, 7:08 p.m. UTC | #1 
On Tue, Jan 25, 2022 at 10:49:38AM +0800, Shuai Xue wrote:
> Introduce a new helper function cper_mem_err_status_str() which is used to
> decode the description of error status, and the cper_print_mem() will call
> it and report the details of error status.
> 
> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
> ---
>  drivers/firmware/efi/cper.c | 29 ++++++++++++++++++++++++++++-
>  include/linux/cper.h        |  1 +
>  2 files changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
> index 6ec8edec6329..7f08d4ea906e 100644
> --- a/drivers/firmware/efi/cper.c
> +++ b/drivers/firmware/efi/cper.c
> @@ -211,6 +211,31 @@ const char *cper_mem_err_type_str(unsigned int etype)
>  }
>  EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
>  
> +const char *cper_mem_err_status_str(u64 status)
> +{
> +	switch ((status >> 8) & 0xff) {
> +	case  1:	return "Error detected internal to the component";
> +	case  4:	return "Storage error in DRAM memory";
> +	case  5:	return "Storage error in TLB";
> +	case  6:	return "Storage error in cache";
> +	case  7:	return "Error in one or more functional units";
> +	case  8:	return "component failed self test";

Well, at least start them all with capital letters: "Component... " And
yes, I know this is how it is in the spec but the spec has typos and
other problems - doesn't mean we have to copy them too.

> +	case  9:	return "Overflow or undervalue of internal queue";
> +	case 16:	return "Error detected in the bus";
> +	case 17:	return "Virtual address not found on IO-TLB or IO-PDIR";
> +	case 18:	return "Improper access error";
> +	case 19:	return "Access to a memory address which is not mapped to any component";
> +	case 20:	return "Loss of Lockstep";
> +	case 21:	return "Response not associated with a request";
> +	case 22:	return "Bus parity error - must also set the A, C, or D Bits";
> +	case 23:	return "Detection of a PATH_ERROR ";

Trailing space here. Also what is PATH_ERROR?

That "PATH_ERROR" is nowhere else explained in that big fat UEFI spec.
2558 pages and they can't explain *that*. Geez.

> +	case 25:	return "Bus operation timeout";
> +	case 26:	return "A read was issued to data that has been poisoned";
> +	default:	return "reserved";
> +	}
> +}
> +EXPORT_SYMBOL_GPL(cper_mem_err_status_str);
> +
>  static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
>  {
>  	u32 len, n;
> @@ -334,7 +359,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
>  		return;
>  	}
>  	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
> -		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
> +		printk("%s""error_status: %s (0x%016llx)\n",

Why do you insist on having two back-to-back strings instead of one
here?

(And don't tell me it is because the other function calls here do it
too.)

FWIW, even checkpatch complains here:

WARNING: Consecutive strings are generally better as a single string
#87: FILE: drivers/firmware/efi/cper.c:362:
+               printk("%s""error_status: %s (0x%016llx)\n",

Btw, please integrate scripts/checkpatch.pl into your patch creation
workflow. Some of the warnings/errors *actually* make sense.
Shuai Xue Jan. 26, 2022, 5:25 a.m. UTC | #2 
Hi, Borislav,

Thank you for your comments.

在 2022/1/26 AM3:08, Borislav Petkov 写道:
> On Tue, Jan 25, 2022 at 10:49:38AM +0800, Shuai Xue wrote:
>> Introduce a new helper function cper_mem_err_status_str() which is used to
>> decode the description of error status, and the cper_print_mem() will call
>> it and report the details of error status.
>>
>> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
>> ---
>>  drivers/firmware/efi/cper.c | 29 ++++++++++++++++++++++++++++-
>>  include/linux/cper.h        |  1 +
>>  2 files changed, 29 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
>> index 6ec8edec6329..7f08d4ea906e 100644
>> --- a/drivers/firmware/efi/cper.c
>> +++ b/drivers/firmware/efi/cper.c
>> @@ -211,6 +211,31 @@ const char *cper_mem_err_type_str(unsigned int etype)
>>  }
>>  EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
>>  
>> +const char *cper_mem_err_status_str(u64 status)
>> +{
>> +	switch ((status >> 8) & 0xff) {
>> +	case  1:	return "Error detected internal to the component";
>> +	case  4:	return "Storage error in DRAM memory";
>> +	case  5:	return "Storage error in TLB";
>> +	case  6:	return "Storage error in cache";
>> +	case  7:	return "Error in one or more functional units";
>> +	case  8:	return "component failed self test";
> 
> Well, at least start them all with capital letters: "Component... " And
> yes, I know this is how it is in the spec but the spec has typos and
> other problems - doesn't mean we have to copy them too.

You are right, I will fix it in next version.

>> +	case  9:	return "Overflow or undervalue of internal queue";
>> +	case 16:	return "Error detected in the bus";
>> +	case 17:	return "Virtual address not found on IO-TLB or IO-PDIR";
>> +	case 18:	return "Improper access error";
>> +	case 19:	return "Access to a memory address which is not mapped to any component";
>> +	case 20:	return "Loss of Lockstep";
>> +	case 21:	return "Response not associated with a request";
>> +	case 22:	return "Bus parity error - must also set the A, C, or D Bits";
>> +	case 23:	return "Detection of a PATH_ERROR ";
> 
> Trailing space here.

Sorry, will delete it.

> Also what is PATH_ERROR?
> 
> That "PATH_ERROR" is nowhere else explained in that big fat UEFI spec.
> 2558 pages and they can't explain *that*. Geez.

I don't know either. A related item I found is "iSCSI Device Path error".
Section 10 defines the device path protocol, but I don't know if "PATH_ERROR"
means the path of the device is not found, or something else.

>> +	case 25:	return "Bus operation timeout";
>> +	case 26:	return "A read was issued to data that has been poisoned";
>> +	default:	return "reserved";
>> +	}
>> +}
>> +EXPORT_SYMBOL_GPL(cper_mem_err_status_str);
>> +
>>  static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
>>  {
>>  	u32 len, n;
>> @@ -334,7 +359,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
>>  		return;
>>  	}
>>  	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
>> -		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
>> +		printk("%s""error_status: %s (0x%016llx)\n",
> 
> Why do you insist on having two back-to-back strings instead of one
> here?
> 
> (And don't tell me it is because the other function calls here do it
> too.)
> 
> FWIW, even checkpatch complains here:
> 
> WARNING: Consecutive strings are generally better as a single string
> #87: FILE: drivers/firmware/efi/cper.c:362:
> +               printk("%s""error_status: %s (0x%016llx)\n",
> 
> Btw, please integrate scripts/checkpatch.pl into your patch creation
> workflow. Some of the warnings/errors *actually* make sense.

Sorry, I did integrate scripts/checkpatch.pl before sending patch. And as you see,
other function calls here do the same, so I ignored the warnings. I will change as
your comments in next version:

-		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
+		printk("%s error_status: %s (0x%016llx)\n",


Best regards,
Shuai
diff mbox series

Patch

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 6ec8edec6329..7f08d4ea906e 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -211,6 +211,31 @@  const char *cper_mem_err_type_str(unsigned int etype)
 }
 EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
 
+const char *cper_mem_err_status_str(u64 status)
+{
+	switch ((status >> 8) & 0xff) {
+	case  1:	return "Error detected internal to the component";
+	case  4:	return "Storage error in DRAM memory";
+	case  5:	return "Storage error in TLB";
+	case  6:	return "Storage error in cache";
+	case  7:	return "Error in one or more functional units";
+	case  8:	return "component failed self test";
+	case  9:	return "Overflow or undervalue of internal queue";
+	case 16:	return "Error detected in the bus";
+	case 17:	return "Virtual address not found on IO-TLB or IO-PDIR";
+	case 18:	return "Improper access error";
+	case 19:	return "Access to a memory address which is not mapped to any component";
+	case 20:	return "Loss of Lockstep";
+	case 21:	return "Response not associated with a request";
+	case 22:	return "Bus parity error - must also set the A, C, or D Bits";
+	case 23:	return "Detection of a PATH_ERROR ";
+	case 25:	return "Bus operation timeout";
+	case 26:	return "A read was issued to data that has been poisoned";
+	default:	return "reserved";
+	}
+}
+EXPORT_SYMBOL_GPL(cper_mem_err_status_str);
+
 static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
 {
 	u32 len, n;
@@ -334,7 +359,9 @@  static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
 		return;
 	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
-		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
+		printk("%s""error_status: %s (0x%016llx)\n",
+		       pfx, cper_mem_err_status_str(mem->error_status),
+		       mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
 		printk("%s""physical_address: 0x%016llx\n",
 		       pfx, mem->physical_addr);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 6a511a1078ca..5b1dd27b317d 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -558,6 +558,7 @@  extern const char *const cper_proc_error_type_strs[4];
 u64 cper_next_record_id(void);
 const char *cper_severity_str(unsigned int);
 const char *cper_mem_err_type_str(unsigned int);
+const char *cper_mem_err_status_str(u64 status);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
 void cper_mem_err_pack(const struct cper_sec_mem_err *,