| 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
| ||
|
Message-ID: <20140611190214.GE14923@pd.tnic>
Date: Wed, 11 Jun 2014 21:02:15 +0200
From: Borislav Petkov <bp@...en8.de>
To: "Chen, Gong" <gong.chen@...ux.intel.com>
Cc: tony.luck@...el.com, m.chehab@...sung.com, rostedt@...dmis.org,
linux-acpi@...r.kernel.org, lkml <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 5/7 v7] trace, RAS: Add eMCA trace event interface
On Wed, Jun 11, 2014 at 04:34:49AM -0400, Chen, Gong wrote:
> Add trace interface to elaborate all H/W error related information.
>
> v7 -> v6: compact trace info to save trace buffer space.
> 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 | 27 ++++++++++++++++---
> drivers/firmware/efi/cper.c | 48 +++++++++++++++++++++++++++++++---
> drivers/ras/ras.c | 1 +
> include/linux/cper.h | 21 +++++++++++++++
> include/ras/ras_event.h | 63 +++++++++++++++++++++++++++++++++++++++++++++
> 6 files changed, 156 insertions(+), 8 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 1853341..e61da95 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 */
>
> @@ -137,8 +138,12 @@ 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_seq;
>
> estatus = extlog_elog_entry_check(cpu, bank);
> if (estatus == NULL)
> @@ -148,7 +153,23 @@ 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_seq++;
> + 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 = (void *)(gdata + 1);
> + if (gdata->error_data_length >= sizeof(*mem))
> + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
> + (u8)gdata->error_severity);
> + }
>
> return NOTIFY_STOP;
> }
> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
> index 83b56b61..85d6d30 100644
> --- a/drivers/firmware/efi/cper.c
> +++ b/drivers/firmware/efi/cper.c
> @@ -207,7 +207,7 @@ const char *cper_mem_err_type_str(unsigned int etype)
> }
> EXPORT_SYMBOL_GPL(cper_mem_err_type_str);
>
> -int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg)
> +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg)
> {
> u32 len, n;
>
> @@ -249,7 +249,7 @@ int cper_mem_err_location(const struct cper_sec_mem_err *mem, char *msg)
> return n;
> }
>
> -int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg)
> +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg)
> {
> u32 len, n;
> const char *bank = NULL, *device = NULL;
> @@ -271,8 +271,47 @@ int cper_dimm_err_location(const struct cper_sec_mem_err *mem, char *msg)
> return n;
> }
>
> +void cper_mem_err_pack(const struct cper_sec_mem_err *mem, void *data)
> +{
> + struct cper_mem_err_compact *cmem = (struct cper_mem_err_compact *)data;
> +
> + cmem->validation_bits = mem->validation_bits;
> + cmem->node = mem->node;
> + cmem->card = mem->card;
> + cmem->module = mem->module;
> + cmem->bank = mem->bank;
> + cmem->device = mem->device;
> + cmem->row = mem->row;
> + cmem->column = mem->column;
> + cmem->bit_pos = mem->bit_pos;
> + cmem->requestor_id = mem->requestor_id;
> + cmem->responder_id = mem->responder_id;
> + cmem->target_id = mem->target_id;
> + cmem->rank = mem->rank;
> + cmem->mem_array_handle = mem->mem_array_handle;
> + cmem->mem_dev_handle = mem->mem_dev_handle;
> +}
> +EXPORT_SYMBOL_GPL(cper_mem_err_pack);
Why do we export this one and the one below? What .config warrants this?
CONFIG_ACPI_EXTLOG=m doesn't need them, AFAICT.
> +const char *cper_mem_err_unpack(struct trace_seq *p, void *data)
> +{
> + struct cper_mem_err_compact *cmem = (struct cper_mem_err_compact *)data;
> + const char *ret = p->buffer + p->len;
> +
> + if (cper_mem_err_location(cmem, rcd_decode_str))
> + trace_seq_printf(p, "%s", rcd_decode_str);
> + if (cper_dimm_err_location(cmem, rcd_decode_str))
> + trace_seq_printf(p, "%s", rcd_decode_str);
> + trace_seq_putc(p, '\0');
> +
> + return ret;
> +}
> +EXPORT_SYMBOL_GPL(cper_mem_err_unpack);
> +
> static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
> {
> + struct cper_mem_err_compact cmem;
> +
> 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_PA)
> @@ -281,14 +320,15 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
> if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
> printk("%s""physical_address_mask: 0x%016llx\n",
> pfx, mem->physical_addr_mask);
> - if (cper_mem_err_location(mem, rcd_decode_str))
> + cper_mem_err_pack(mem, &cmem);
> + if (cper_mem_err_location(&cmem, rcd_decode_str))
> printk("%s%s\n", pfx, rcd_decode_str);
> if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE) {
> u8 etype = mem->error_type;
> printk("%s""error_type: %d, %s\n", pfx, etype,
> cper_mem_err_type_str(etype));
> }
> - if (cper_dimm_err_location(mem, rcd_decode_str))
> + if (cper_dimm_err_location(&cmem, rcd_decode_str))
> printk("%s%s\n", pfx, rcd_decode_str);
> }
>
> 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/linux/cper.h b/include/linux/cper.h
> index ed088b9..3548160 100644
> --- a/include/linux/cper.h
> +++ b/include/linux/cper.h
> @@ -22,6 +22,7 @@
> #define LINUX_CPER_H
>
> #include <linux/uuid.h>
> +#include <linux/trace_seq.h>
>
> /* CPER record signature and the size */
> #define CPER_SIG_RECORD "CPER"
> @@ -363,6 +364,24 @@ struct cper_sec_mem_err {
> __u16 mem_dev_handle; /* module handle in UEFI 2.4 */
> };
>
> +struct cper_mem_err_compact {
> + __u64 validation_bits;
> + __u16 node;
> + __u16 card;
> + __u16 module;
> + __u16 bank;
> + __u16 device;
> + __u16 row;
> + __u16 column;
> + __u16 bit_pos;
> + __u64 requestor_id;
> + __u64 responder_id;
> + __u64 target_id;
> + __u16 rank;
> + __u16 mem_array_handle;
> + __u16 mem_dev_handle;
> +};
> +
> struct cper_sec_pcie {
> __u64 validation_bits;
> __u32 port_type;
> @@ -406,5 +425,7 @@ const char *cper_severity_str(unsigned int);
> const char *cper_mem_err_type_str(unsigned int);
> 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 *, void *);
> +const char *cper_mem_err_unpack(struct trace_seq *, void *);
>
> #endif
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index acbcbb8..c5e58db 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -9,6 +9,69 @@
> #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(struct cper_sec_mem_err *mem,
> + u32 err_seq,
> + const uuid_le *fru_id,
> + const char *fru_text,
> + u8 sev),
> +
> + TP_ARGS(mem, err_seq, fru_id, fru_text, sev),
> +
> + TP_STRUCT__entry(
> + __field(u32, err_seq)
> + __field(u8, etype)
> + __field(u8, sev)
> + __field(u64, pa)
> + __field(u8, pa_mask_lsb)
> + __array(u8, fru_id, 40)
How did you come up with this magic number? Why isn't that sizeof(uuid_le)?
> + __string(fru_text, fru_text)
> + __array(u8, data, sizeof(struct cper_mem_err_compact))
> + ),
> +
> + TP_fast_assign(
> + __entry->err_seq = err_seq;
> + if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
> + __entry->etype = mem->error_type;
> + else
> + __entry->etype = ~0;
> + __entry->sev = sev;
> + if (mem->validation_bits & CPER_MEM_VALID_PA)
> + __entry->pa = mem->physical_addr;
> + else
> + __entry->pa = ~0ull;
> +
> + if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
> + __entry->pa_mask_lsb =
> + (u8)__ffs64(mem->physical_addr_mask);
No need for the linebreak here - just let it stick out.
> + else
> + __entry->pa_mask_lsb = ~0;
> + snprintf(__entry->fru_id, 39, "%pUl", fru_id);
Yeah, I didn't catch the reasoning behind why we need to convert the FRU
into a string and not leave it simply as u8[16]...
> + __assign_str(fru_text, fru_text);
> + cper_mem_err_pack(mem, __entry->data);
> + ),
> +
> + TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %s %.20s",
> + __entry->err_seq,
> + cper_severity_str(__entry->sev),
> + cper_mem_err_type_str(__entry->etype),
> + __entry->pa,
> + __entry->pa_mask_lsb,
> + cper_mem_err_unpack(p, __entry->data),
> + __entry->fru_id,
> + __get_str(fru_text))
> +);
>
> /*
> * Hardware Events Report
> --
> 2.0.0.rc2
>
>
--
Regards/Gruss,
Boris.
Sent from a fat crate under my desk. Formatting is fine.
--
--
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