From: "Jonathan (Zhixiong) Zhang" zjzhang@codeaurora.org
Currently the kernel ignores CPER records that are unrecognized. On the other hand, UEFI spec allows for non-standard (eg. vendor proprietary) error section type in CPER (Common Platform Error Record), as defined in section N2.3 of UEFI version 2.5. Therefore, user is not able to see hardware error data of non-standard section.
If section Type field of Generic Error Data Entry is unrecognized, prints out the raw data in dmesg buffer, and also adds a tracepoint for reporting such hardware error.
V2: 1. Handle all unrecognized CPER records instead of matching with section type that is known to be vendor proprietary. (Borislav)
Jonathan (Zhixiong) Zhang (2): efi: print unrecognized CPER section ras: acpi/apei: generate trace event for unrecognized CPER section
drivers/acpi/apei/ghes.c | 23 +++++++++++++++++++++-- drivers/firmware/efi/cper.c | 39 +++++++++++++++++++++++++++++++-------- drivers/ras/ras.c | 1 + include/ras/ras_event.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 98 insertions(+), 10 deletions(-)
From: "Jonathan (Zhixiong) Zhang" zjzhang@codeaurora.org
UEFI spec allows for non-standard section in Common Platform Error Record. This is defined in section N.2.3 of UEFI version 2.5.
Currently if the CPER section's type (UUID) does not match with one of the section types that the kernel knows how to parse, the section is skipped. Therefore, user is not able to see such CPER data, for instace, error record of non-standard section.
For above mentioned case, this change prints out the raw data in hex in dmesg buffer. Data length is taken from Error Data length field of Generic Error Data Entry.
Following is a sample output from dmesg: [ 115.771702] {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 2 [ 115.779042] {1}[Hardware Error]: It has been corrected by h/w and requires no further action [ 115.787456] {1}[Hardware Error]: event severity: corrected [ 115.792927] {1}[Hardware Error]: Error 0, type: corrected [ 115.798415] {1}[Hardware Error]: fru_id: 00000000-0000-0000-0000-000000000000 [ 115.805596] {1}[Hardware Error]: fru_text: [ 115.816105] {1}[Hardware Error]: section type: d2e2621c-f936-468d-0d84-15a4ed015c8b [ 115.823880] {1}[Hardware Error]: section length: 88 [ 115.828779] {1}[Hardware Error]: 00000000: 01000001 00000002 5f434345 525f4543 [ 115.836153] {1}[Hardware Error]: 00000010: 0000574d 00000000 00000000 00000000 [ 115.843531] {1}[Hardware Error]: 00000020: 00000000 00000000 00000000 00000000 [ 115.850908] {1}[Hardware Error]: 00000030: 00000000 00000000 00000000 00000000 [ 115.858288] {1}[Hardware Error]: 00000040: fe800000 00000000 00000004 5f434345 [ 115.865665] {1}[Hardware Error]: 00000050: 525f4543 0000574d
Change-Id: I663a6e3ae6dcf68e4e389f76d555e9106ffee165 Signed-off-by: Jonathan (Zhixiong) Zhang zjzhang@codeaurora.org --- drivers/firmware/efi/cper.c | 39 +++++++++++++++++++++++++++++++-------- 1 file changed, 31 insertions(+), 8 deletions(-)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index d42537425438..8a58b2927408 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -32,12 +32,31 @@ #include <linux/acpi.h> #include <linux/pci.h> #include <linux/aer.h> +#include <linux/printk.h>
#define INDENT_SP " "
+#define ROW_SIZE 16 +#define GROUP_SIZE 4 + static char rcd_decode_str[CPER_REC_LEN];
/* + * cper_print_hex - print hex from a CPER data buffer + * @pfx: prefix for each line, including log level and prefix string + * @buf: buffer pointer + * @len: size of buffer + * + * print_hex_dump() expects log level and prefix string to be passed + * in two different paramters. Internally it concatenates them. In + * our case, those two are already concatenated in pfx. + */ +#define cper_print_hex(pfx, buf, len) \ + print_hex_dump(pfx, "", \ + DUMP_PREFIX_OFFSET, ROW_SIZE, GROUP_SIZE, \ + buf, len, 0) + +/* * CPER record ID need to be unique even after reboot, because record * ID is used as index for ERST storage, while CPER records from * multiple boot may co-exist in ERST. @@ -392,7 +411,9 @@ static void cper_estatus_print_section( uuid_le *sec_type = (uuid_le *)gdata->section_type; __u16 severity; char newpfx[64]; + u32 len;
+ len = gdata->error_data_length; severity = gdata->error_severity; printk("%s""Error %d, type: %s\n", pfx, sec_no, cper_severity_str(severity)); @@ -405,28 +426,30 @@ static void cper_estatus_print_section( 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", newpfx); - if (gdata->error_data_length >= sizeof(*proc_err)) + if (len >= sizeof(*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", newpfx); - if (gdata->error_data_length >= - sizeof(struct cper_sec_mem_err_old)) - cper_print_mem(newpfx, mem_err, - gdata->error_data_length); + if (len >= sizeof(struct cper_sec_mem_err_old)) + cper_print_mem(newpfx, mem_err, len); 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", newpfx); - if (gdata->error_data_length >= sizeof(*pcie)) + if (len >= sizeof(*pcie)) cper_print_pcie(newpfx, pcie, gdata); else goto err_section_too_small; - } else - printk("%s""section type: unknown, %pUl\n", newpfx, sec_type); + } else { + const void *raw_err = gdata + 1; + printk("%ssection type: %pUl\n", pfx, sec_type); + printk("%ssection length: %d\n", pfx, len); + cper_print_hex(newpfx, raw_err, len); + }
return;
On 09/08/2015 04:29 PM, Jonathan (Zhixiong) Zhang wrote:
Change-Id: I663a6e3ae6dcf68e4e389f76d555e9106ffee165
You need to strip out the Change-Id's before posting the patch.
(buf), (len), 0)
is safer
You don't need raw_err. This should work fine:
cper_print_hex(newpfx, gdata + 1, len);
On Tue, Sep 08, 2015 at 02:29:20PM -0700, Jonathan (Zhixiong) Zhang wrote:
instace?
Introduce a spellchecker into your workflow, pls.
As already noted, no internal cset IDs or whatever other markup.
Why?
First argument of print_hex_dump() is @level and second is @prefix_str. But you're calling print_hex_dump() with "" as a second arg...
This doesn't make any sense, why?
And WTH are you defining a macro for, to use exactly *once*?! Why can't you simply use print_hex_dump() like normal kids would do? Same with those ROW_SIZE and GROUP_SIZE defines... Kill them. Kill it all.
This and the changes it brings with it are unrelated to this patch - needs to be a separate patch.
From: "Jonathan (Zhixiong) Zhang" zjzhang@codeaurora.org
UEFI spec allows for non-standard section in Common Platform Error Record. This is defined in section N.2.3 of UEFI version 2.5.
Currently if the CPER section's type (UUID) does not match with any section type that the kernel knows how to parse, trace event is not generated for such section. And thus user is not able to know happening of such hardware error, including error record of non-standard section.
This commit generates a trace event which contains raw error data for unrecognized CPER section.
Signed-off-by: Jonathan (Zhixiong) Zhang zjzhang@codeaurora.org --- drivers/acpi/apei/ghes.c | 23 +++++++++++++++++++++-- drivers/ras/ras.c | 1 + include/ras/ras_event.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 67 insertions(+), 2 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 23981ac1c6c2..a3aa3b046a37 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -48,6 +48,7 @@ #include <acpi/ghes.h> #include <acpi/apei.h> #include <asm/tlbflush.h> +#include <ras/ras_event.h>
#include "apei-internal.h"
@@ -421,11 +422,23 @@ static void ghes_do_proc(struct ghes *ghes, { int sev, sec_sev; struct acpi_hest_generic_data *gdata; + uuid_le *sec_type; + uuid_le *fru_id; + char *fru_text = ""; + void *raw_err;
sev = ghes_severity(estatus->error_severity); apei_estatus_for_each_section(estatus, gdata) { sec_sev = ghes_severity(gdata->error_severity); - if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, + sec_type = (uuid_le *)gdata->section_type; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (uuid_le *)gdata->fru_id; + else + fru_id = &NULL_UUID_LE; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + + if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem_err; mem_err = (struct cper_sec_mem_err *)(gdata+1); @@ -435,7 +448,7 @@ static void ghes_do_proc(struct ghes *ghes, ghes_handle_memory_failure(gdata, sev); } #ifdef CONFIG_ACPI_APEI_PCIEAER - else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, + else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) { struct cper_sec_pcie *pcie_err; pcie_err = (struct cper_sec_pcie *)(gdata+1); @@ -467,6 +480,12 @@ static void ghes_do_proc(struct ghes *ghes,
} #endif + else { + raw_err = gdata + 1; + trace_raw_event(sec_type, + fru_id, fru_text, sec_sev, + raw_err, gdata->error_data_length); + } } }
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index b67dd362b7b6..6623ae366df9 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -27,3 +27,4 @@ subsys_initcall(ras_init); EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); #endif EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); +EXPORT_TRACEPOINT_SYMBOL_GPL(raw_event); diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 1443d79e4fe6..fd357e9815f5 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -162,6 +162,51 @@ TRACE_EVENT(mc_event, );
/* + * Raw Events Report + * + * This event is generated when hardware detected a hardware + * error event, which may be of non-standard section as defined + * in UEFI spec appendix "Common Platform Error Record", or may + * be of sections for which TRACE_EVENT is not defined. + * + */ +TRACE_EVENT(raw_event, + + TP_PROTO(const uuid_le *sec_type, + const uuid_le *fru_id, + const char *fru_text, + u8 sev, + const u8 *err, + const u32 len), + + TP_ARGS(sec_type, fru_id, fru_text, sev, err, len), + + TP_STRUCT__entry( + __array(char, sec_type, 16) + __array(char, fru_id, 16) + __string(fru_text, fru_text) + __field(u8, sev) + __field(u32, len) + __dynamic_array(u8, buf, len) + ), + + TP_fast_assign( + memcpy(__entry->sec_type, sec_type, sizeof(uuid_le)); + memcpy(__entry->fru_id, fru_id, sizeof(uuid_le)); + __assign_str(fru_text, fru_text); + __entry->sev = sev; + __entry->len = len; + memcpy(__get_dynamic_array(buf), err, len); + ), + + TP_printk("severity: %d; sec type:%pU; FRU: %pU %s; data len:%d; raw data:%s", + __entry->sev, __entry->sec_type, + __entry->fru_id, __get_str(fru_text), + __entry->len, + __print_hex(__get_dynamic_array(buf), __entry->len)) +); + +/* * PCIe AER Trace event * * These events are generated when hardware detects a corrected or
On Tue, Sep 08, 2015 at 02:29:21PM -0700, Jonathan (Zhixiong) Zhang wrote:
This is not a raw event - this is an event which has a section type, FRU ID, text, etc, etc.
A raw event is one which takes exactly two arguments: bytes and count. What it does is, it dumps the bytes of length count in a block or other amicably formatted output, most likely hex, similar to hexdump or other tools; *without* any attempt to interpret it whatsoever.
Its *consumers* do the interpretation. So that that raw_event tracepoint can be used as a fallback in all cases where the error information is of unknown structure to the kernel.
Btw, @count should be sanity-checked before calling the tracepoint with insane values.
-
Borislav Petkov -
Jonathan (Zhixiong) Zhang -
Timur Tabi