| 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
| ||
|
Date: Wed, 28 May 2014 11:28:32 -0400
From: Steven Rostedt <rostedt@...dmis.org>
To: "Chen, Gong" <gong.chen@...ux.intel.com>
Cc: bp@...en8.de, tony.luck@...el.com, m.chehab@...sung.com,
linux-acpi@...r.kernel.org, LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 5/7 v6] trace, RAS: Add eMCA trace event interface
Added LKML
On Tue, 27 May 2014 23:32:18 -0400
"Chen, Gong" <gong.chen@...ux.intel.com> wrote:
> Add trace interface to elaborate all H/W error related information.
>
> v6 -> v5: format adjustment.
> v5 -> v4: Add physical mask(LSB) in trace.
> v4 -> v3: change ras trace dependency rule.
> v3 -> v2: minor adjustment according to the suggestion from Boris.
> v2 -> v1: spinlock is not needed anymore.
>
> Signed-off-by: Chen, Gong <gong.chen@...ux.intel.com>
> ---
> drivers/acpi/Kconfig | 4 +++-
> drivers/acpi/acpi_extlog.c | 54 +++++++++++++++++++++++++++++++++++++++---
> drivers/ras/ras.c | 1 +
> include/ras/ras_event.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++
> 4 files changed, 114 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
> index a34a228..099a2d5 100644
> --- a/drivers/acpi/Kconfig
> +++ b/drivers/acpi/Kconfig
> @@ -370,6 +370,7 @@ config ACPI_EXTLOG
> tristate "Extended Error Log support"
> depends on X86_MCE && X86_LOCAL_APIC
> select UEFI_CPER
> + select RAS_TRACE
> default n
> help
> Certain usages such as Predictive Failure Analysis (PFA) require
> @@ -384,6 +385,7 @@ config ACPI_EXTLOG
>
> Enhanced MCA Logging allows firmware to provide additional error
> information to system software, synchronous with MCE or CMCI. This
> - driver adds support for that functionality.
> + driver adds support for that functionality with corresponding
> + tracepoint which carries that information to userspace.
>
> endif # ACPI
> diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
> index c4a5d87..8815b73 100644
> --- a/drivers/acpi/acpi_extlog.c
> +++ b/drivers/acpi/acpi_extlog.c
> @@ -16,6 +16,7 @@
> #include <asm/mce.h>
>
> #include "apei/apei-internal.h"
> +#include <ras/ras_event.h>
>
> #define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */
>
> @@ -43,6 +44,9 @@ struct extlog_l1_head {
>
> static int old_edac_report_status;
>
> +static char mem_location[CPER_REC_LEN];
> +static char dimm_location[CPER_REC_LEN];
> +
> static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
>
> /* L1 table related physical address */
> @@ -69,6 +73,30 @@ static u32 l1_percpu_entry;
> #define ELOG_ENTRY_ADDR(phyaddr) \
> (phyaddr - elog_base + (u8 *)elog_addr)
>
> +static void __trace_mem_error(const uuid_le *fru_id, char *fru_text,
> + u32 err_number, u8 severity,
> + struct cper_sec_mem_err *mem)
> +{
> + u8 etype = ~0, pa_mask_lsb = ~0;
> + u64 pa = ~0ull;
> +
> + if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
> + etype = mem->error_type;
> +
> + if (mem->validation_bits & CPER_MEM_VALID_PA)
> + pa = mem->physical_addr;
> +
> + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
> + pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask);
> +
> + memset(mem_location, 0, CPER_REC_LEN);
> + cper_mem_err_location(mem, mem_location);
> + memset(dimm_location, 0, CPER_REC_LEN);
> + cper_dimm_err_location(mem, dimm_location);
> + trace_extlog_mem_event(err_number, etype, severity, pa, pa_mask_lsb,
> + fru_id, dimm_location, mem_location, fru_text);
This seems like a lot of work for a tracepoint. Why all the strings?
Ideally, you want to record in the fast path the minimum raw data and
reconstruct it at the time it is read.
> +}
> +
> static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank)
> {
> int idx;
> @@ -137,8 +165,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
> struct mce *mce = (struct mce *)data;
> int bank = mce->bank;
> int cpu = mce->extcpu;
> - struct acpi_generic_status *estatus;
> - int rc;
> + struct acpi_generic_status *estatus, *tmp;
> + struct acpi_generic_data *gdata;
> + const uuid_le *fru_id = &NULL_UUID_LE;
> + char *fru_text = "";
> + uuid_le *sec_type;
> + static u32 err_number;
>
> estatus = extlog_elog_entry_check(cpu, bank);
> if (estatus == NULL)
> @@ -148,7 +180,23 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
> /* clear record status to enable BIOS to update it again */
> estatus->block_status = 0;
>
> - rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
> + tmp = (struct acpi_generic_status *)elog_buf;
> + print_extlog_rcd(NULL, tmp, cpu);
> +
> + /* log event via trace */
> + err_number++;
> + gdata = (struct acpi_generic_data *)(tmp + 1);
> + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
> + fru_id = (uuid_le *)gdata->fru_id;
> + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
> + fru_text = gdata->fru_text;
> + sec_type = (uuid_le *)gdata->section_type;
> + if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
> + struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
> + if (gdata->error_data_length >= sizeof(*mem_err))
> + __trace_mem_error(fru_id, fru_text, err_number,
> + (u8)gdata->error_severity, mem_err);
> + }
>
> return NOTIFY_STOP;
> }
> diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
> index 4cac43a..da227a3 100644
> --- a/drivers/ras/ras.c
> +++ b/drivers/ras/ras.c
> @@ -23,4 +23,5 @@ static int __init ras_init(void)
> }
> subsys_initcall(ras_init);
>
> +EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
> EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index acbcbb8..4d3bc92 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -9,6 +9,65 @@
> #include <linux/edac.h>
> #include <linux/ktime.h>
> #include <linux/aer.h>
> +#include <linux/cper.h>
> +
> +
> +/*
> + * MCE Extended Error Log trace event
> + *
> + * These events are generated when hardware detects a corrected or
> + * uncorrected event.
> + */
> +
> +/* memory trace event */
> +
> +TRACE_EVENT(extlog_mem_event,
> + TP_PROTO(u32 error_number,
> + u8 etype,
> + u8 severity,
> + u64 pa,
> + u8 pa_mask_lsb,
> + const uuid_le *fru_id,
> + const char *dimm_info,
> + const char *mem_loc,
> + const char *fru_text),
> +
> + TP_ARGS(error_number, etype, severity, pa, pa_mask_lsb, fru_id,
> + dimm_info, mem_loc, fru_text),
> +
> + TP_STRUCT__entry(
> + __field(u32, error_number)
> + __field(u8, etype)
> + __field(u8, severity)
> + __field(u64, pa)
> + __field(u8, pa_mask_lsb)
> + __string(dimm_info, dimm_info)
> + __string(mem_loc, mem_loc)
> + __dynamic_array(char, fru, CPER_REC_LEN)
> + ),
> +
> + TP_fast_assign(
> + __entry->error_number = error_number;
> + __entry->etype = etype;
> + __entry->severity = severity;
> + __entry->pa = pa;
> + __entry->pa_mask_lsb = pa_mask_lsb;
> + __assign_str(dimm_info, dimm_info);
> + __assign_str(mem_loc, mem_loc);
> + snprintf(__get_dynamic_array(fru), CPER_REC_LEN - 1,
> + "FRU: %pUl %.20s", fru_id, fru_text);
For example, here don't use snprintf(). Save that processing for the
TP_printk(), as that is done at time of read. Again, only store the
minimum raw data, and reconstruct it later. Why slow down the fast path?
-- Steve
> + ),
> +
> + TP_printk("%d %s error: %s %s physical addr: %016llx (mask lsb: %x), %s%s",
> + __entry->error_number,
> + cper_severity_str(__entry->severity),
> + cper_mem_err_type_str(__entry->etype),
> + __get_str(dimm_info),
> + __entry->pa,
> + __entry->pa_mask_lsb,
> + __get_str(mem_loc),
> + __get_str(fru))
> +);
>
> /*
> * Hardware Events Report
--
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