by Tyler Baicar

[permalink] [raw]

Subject: Re: [PATCH V2 2/9] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1

Hello Suzuki,

On 4/14/2016 4:22 AM, Suzuki K Poulose wrote:
> On 06/04/16 16:12, Tyler Baicar wrote:
>> Currently when a RAS error is reported it is not timestamped.
>> The ACPI 6.1 spec adds the timestamp field to the generic error
>> data entry v3 structure. The timestamp of when the firmware
>> generated the error is now being reported.
>>
>> Signed-off-by: Jonathan (Zhixiong) Zhang <[email protected]>
>> Signed-off-by: Richard Ruigrok <[email protected]>
>> Signed-off-by: Tyler Baicar <[email protected]>
>> Signed-off-by: Naveen Kaje <[email protected]>
>> ---
>> drivers/acpi/apei/ghes.c | 35 ++++++++++++--
>> drivers/firmware/efi/cper.c | 111
>> +++++++++++++++++++++++++++++++++++++-------
>> 2 files changed, 126 insertions(+), 20 deletions(-)
>>
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index 9b0543e..a6848706 100644
>> --- a/drivers/acpi/apei/ghes.c
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -419,7 +419,15 @@ static void ghes_handle_memory_failure(struct
>> acpi_hest_generic_data *gdata, int
>> int flags = -1;
>> int sec_sev = ghes_severity(gdata->error_severity);
>> struct cper_sec_mem_err *mem_err;
>> - mem_err = (struct cper_sec_mem_err *)(gdata + 1);
>> + struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
>> +
>> + if ((gdata->revision >> 8) >= 0x03)
>
> Could we please make that a macro ? We seem to be using the check
> everywhere.
Yes, I can make this a macro since we do this several times.
>
>> + gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
>> +
>> + if (gdata_v3)
>> + mem_err = (struct cper_sec_mem_err *)(gdata_v3 + 1);
>> + else
>> + mem_err = (struct cper_sec_mem_err *)(gdata + 1);
>>
>> if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
>> return;
>> @@ -449,14 +457,27 @@ static void ghes_do_proc(struct ghes *ghes,
>> {
>> int sev, sec_sev;
>> struct acpi_hest_generic_data *gdata;
>> + struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
>> + uuid_le sec_type;
>>
>> 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->revision >> 8) >= 0x03)
>> + gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
>> +
>> + 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);
>> +
>> + if (gdata_v3)
>> + mem_err = (struct cper_sec_mem_err *)
>> + (gdata_v3 + 1);
>> + else
>> + mem_err = (struct cper_sec_mem_err *)
>> + (gdata + 1);
>> ghes_edac_report_mem_error(ghes, sev, mem_err);
>>
>> arch_apei_report_mem_error(sev, mem_err);
>> @@ -466,7 +487,13 @@ static void ghes_do_proc(struct ghes *ghes,
>> else if (!uuid_le_cmp(*(uuid_le *)gdata->section_type,
>> CPER_SEC_PCIE)) {
>> struct cper_sec_pcie *pcie_err;
>> - pcie_err = (struct cper_sec_pcie *)(gdata+1);
>> +
>> + if (gdata_v3)
>> + pcie_err = (struct cper_sec_pcie *)
>> + (gdata_v3 + 1);
>> + else
>> + pcie_err = (struct cper_sec_pcie *)
>> + (gdata + 1);
>> if (sev == GHES_SEV_RECOVERABLE &&
>> sec_sev == GHES_SEV_RECOVERABLE &&
>> pcie_err->validation_bits &
>> CPER_PCIE_VALID_DEVICE_ID &&
>> diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
>> index d425374..23f62962 100644
>> --- a/drivers/firmware/efi/cper.c
>> +++ b/drivers/firmware/efi/cper.c
>> @@ -32,6 +32,8 @@
>> #include <linux/acpi.h>
>> #include <linux/pci.h>
>> #include <linux/aer.h>
>> +#include <linux/printk.h>
>> +#include <linux/bcd.h>
>>
>> #define INDENT_SP " "
>>
>> @@ -392,6 +394,10 @@ static void cper_estatus_print_section(
>> uuid_le *sec_type = (uuid_le *)gdata->section_type;
>> __u16 severity;
>> char newpfx[64];
>> + struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
>> +
>> + if ((gdata->revision >> 8) >= 0x03)
>> + gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
>>
>> severity = gdata->error_severity;
>> printk("%s""Error %d, type: %s\n", pfx, sec_no,
>> @@ -403,14 +409,24 @@ static void cper_estatus_print_section(
>>
>> 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);
>> + struct cper_sec_proc_generic *proc_err;
>> +
>> + if (gdata_v3)
>> + proc_err = (void *)(gdata_v3 + 1);
>> + else
>> + proc_err = (void *)(gdata + 1);
>> printk("%s""section_type: general processor error\n", newpfx);
>> if (gdata->error_data_length >= 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);
>> + struct cper_sec_mem_err *mem_err;
>> +
>> + if (gdata_v3)
>> + mem_err = (void *)(gdata_v3 + 1);
>> + else
>> + 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))
>> @@ -419,7 +435,12 @@ static void cper_estatus_print_section(
>> else
>> goto err_section_too_small;
>> } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
>> - struct cper_sec_pcie *pcie = (void *)(gdata + 1);
>> + struct cper_sec_pcie *pcie;
>> +
>> + if (gdata_v3)
>> + pcie = (void *)(gdata_v3 + 1);
>> + else
>> + pcie = (void *)(gdata + 1);
>
>
> The only use of the gdata_v3 above cases is to get the payload(or
> error_record).
> So instead of spilling these checks all over could we use something
> like :
>
> #define acpi_hest_generic_data_version(gdata) \
> (gdata->revision >> 8)
>
> static inline void *
> acpi_hest_generic_data_payload(struct acpi_hest_generic_data *gdata)
> {
> return acpi_hest_generic_data_version(gdata) >= 3 ?
> ((struct acpi_hest_generic_data_v300 *)(gdata)) + 1 :
> gdata + 1;
> }
>
> And then do :
>
> void *payload = acpi_hest_generic_data_payload(gdata);
>
>
Yes, this should simplify the the code to get the payload. This can also
be done in the ghes.c code above as well.
>> printk("%s""section_type: PCIe error\n", newpfx);
>> if (gdata->error_data_length >= sizeof(*pcie))
>> cper_print_pcie(newpfx, pcie, gdata);
>> @@ -434,10 +455,38 @@ err_section_too_small:
>> pr_err(FW_WARN "error section length is too small\n");
>> }
>>
>> +static void cper_estatus_print_section_v300(const char *pfx,
>> + const struct acpi_hest_generic_data_v300 *gdata, int sec_no)
>> +{
>> + __u8 hour, min, sec, day, mon, year, century, *timestamp;
>> +
>> + if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
>> + timestamp = (__u8 *)&(gdata->time_stamp);
>> + memcpy(&sec, timestamp, 1);
>> + memcpy(&min, timestamp + 1, 1);
>> + memcpy(&hour, timestamp + 2, 1);
>> + memcpy(&day, timestamp + 4, 1);
>> + memcpy(&mon, timestamp + 5, 1);
>> + memcpy(&year, timestamp + 6, 1);
>> + memcpy(&century, timestamp + 7, 1);
>> + printk("%stime: ", pfx);
>> + printk("%7s", 0x01 & *(timestamp + 3) ? "precise" : "");
>> + printk(" %02d:%02d:%02d %02d%02d-%02d-%02d\n",
>> + bcd2bin(hour), bcd2bin(min), bcd2bin(sec),
>> + bcd2bin(century), bcd2bin(year), bcd2bin(mon),
>> + bcd2bin(day));
>> + }
>> +
>> + cper_estatus_print_section(pfx,
>> + (const struct acpi_hest_generic_data *)gdata,
>> + sec_no);
>> +}
>
>
> Wouldn't it be better do the v3 header check from
> cper_erstatus_print_section() and call out
> to cper_erstatus_print_section_v300() ? That way, we can leave the
> callers unaffected,
> even for future changes.
>
>
>> + if (gdata_v3) {
>> + while (data_len >= sizeof(*gdata_v3)) {
>> + gedata_len = gdata_v3->error_data_length;
>> + cper_estatus_print_section_v300(newpfx, gdata_v3,
>> + sec_no);
>> + data_len -= gedata_len + sizeof(*gdata_v3);
>> + gdata_v3 = (void *)(gdata_v3 + 1) + gedata_len;
>> + sec_no++;
>> + }
>> + } else {
>> + while (data_len >= sizeof(*gdata)) {
>> + gedata_len = gdata->error_data_length;
>> + cper_estatus_print_section(newpfx, gdata, sec_no);
>> + data_len -= gedata_len + sizeof(*gdata);
>> + gdata = (void *)(gdata + 1) + gedata_len;
>> + sec_no++;
>> + }
>
> With the change mentioned above and storing the sizeof(), we could
> make this
> hunk a bit more cleaner.
This should certainly clean up this code and I agree it is better to
leave the callers unaffected.

I'll add all these suggested changes in my next patch-set.

Thanks,
Tyler
>
>
> Suzuki

--
Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project

2016-04-20 21:38:36

by Tyler Baicar

[permalink] [raw]

Subject: Re: [PATCH V2 6/9] acpi: apei: handle SEA notification type for ARMv8

This patch currently breaks compilation of "allyesconfig" for x86
because HAVE_ACPI_APEI_SEA is really only supported for ARM64 at this
point. Is making this config dependent on ARM64 the correct way to go
about fixing this? Then, in the future when this support is added for
other architectures, whomever adds the support can say this config
depends on either ARM64 or whatever other architecture they add support for.

If this is not the correct way to go about this, please suggest how to
get around this compilation failure.

Thanks,
Tyler

On 4/6/2016 9:12 AM, Tyler Baicar wrote:
> ARM APEI extension proposal added SEA (Synchrounous External
> Abort) notification type for ARMv8.
> Add a new GHES error source handling function for SEA. If an error
> source's notification type is SEA, then this function can be registered
> into the SEA exception handler. That way GHES will parse and report
> SEA exceptions when they occur.
>
> Signed-off-by: Jonathan (Zhixiong) Zhang <[email protected]>
> Signed-off-by: Tyler Baicar <[email protected]>
> Signed-off-by: Naveen Kaje <[email protected]>
> ---
> arch/arm64/Kconfig | 1 +
> drivers/acpi/apei/Kconfig | 14 ++++++++
> drivers/acpi/apei/ghes.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 98 insertions(+)
>
> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> index 08952ec..6a7e166 100644
> --- a/arch/arm64/Kconfig
> +++ b/arch/arm64/Kconfig
> @@ -4,6 +4,7 @@ config ARM64
> select ACPI_GENERIC_GSI if ACPI
> select ACPI_REDUCED_HARDWARE_ONLY if ACPI
> select HAVE_ACPI_APEI if ACPI
> + select HAVE_ACPI_APEI_SEA if ACPI
> select ARCH_HAS_DEVMEM_IS_ALLOWED
> select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
> select ARCH_HAS_ELF_RANDOMIZE
> diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
> index b0140c8..2d6cd9b 100644
> --- a/drivers/acpi/apei/Kconfig
> +++ b/drivers/acpi/apei/Kconfig
> @@ -4,6 +4,20 @@ config HAVE_ACPI_APEI
> config HAVE_ACPI_APEI_NMI
> bool
>
> +config HAVE_ACPI_APEI_SEA
> + bool "APEI Synchronous External Abort logging/recovering support"
> + help
> + This option should be enabled if the system supports
> + firmware first handling of SEA (Synchronous External Abort).
> + SEA happens with certain faults of data abort or instruction
> + abort synchronous exceptions on ARMv8 systems. If a system
> + supports firmware first handling of SEA, the platform analyzes
> + and handles hardware error notifications with SEA, and it may then
> + form a HW error record for the OS to parse and handle. This
> + option allows the OS to look for such HW error record, and
> + take appropriate action.
> +
> config ACPI_APEI
> bool "ACPI Platform Error Interface (APEI)"
> select MISC_FILESYSTEMS
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index a6848706..aae5ca0 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -50,6 +50,10 @@
> #include <acpi/apei.h>
> #include <asm/tlbflush.h>
>
> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA
> +#include <asm/system_misc.h>
> +#endif
> +
> #include "apei-internal.h"
>
> #define GHES_PFX "GHES: "
> @@ -789,6 +793,62 @@ static struct notifier_block ghes_notifier_sci = {
> .notifier_call = ghes_notify_sci,
> };
>
> +#ifdef CONFIG_HAVE_ACPI_APEI_SEA
> +static LIST_HEAD(ghes_sea);
> +
> +static int ghes_notify_sea(struct notifier_block *this,
> + unsigned long event, void *data)
> +{
> + struct ghes *ghes;
> + int ret = NOTIFY_DONE;
> +
> + rcu_read_lock();
> + list_for_each_entry_rcu(ghes, &ghes_sea, list) {
> + if (!ghes_proc(ghes))
> + ret = NOTIFY_OK;
> + }
> + rcu_read_unlock();
> +
> + return ret;
> +}
> +
> +static struct notifier_block ghes_notifier_sea = {
> + .notifier_call = ghes_notify_sea,
> +};
> +
> +static int ghes_sea_add(struct ghes *ghes)
> +{
> + mutex_lock(&ghes_list_mutex);
> + if (list_empty(&ghes_sea))
> + sea_register_handler_chain(&ghes_notifier_sea);
> + list_add_rcu(&ghes->list, &ghes_sea);
> + mutex_unlock(&ghes_list_mutex);
> + return 0;
> +}
> +
> +static void ghes_sea_remove(struct ghes *ghes)
> +{
> + mutex_lock(&ghes_list_mutex);
> + list_del_rcu(&ghes->list);
> + if (list_empty(&ghes_sea))
> + sea_unregister_handler_chain(&ghes_notifier_sea);
> + mutex_unlock(&ghes_list_mutex);
> +}
> +#else /* CONFIG_HAVE_ACPI_APEI_SEA */
> +static inline int ghes_sea_add(struct ghes *ghes)
> +{
> + pr_err(GHES_PFX "ID: %d, trying to add SEA notification which is not supported\n",
> + ghes->generic->header.source_id);
> + return -ENOTSUPP;
> +}
> +
> +static inline void ghes_sea_remove(struct ghes *ghes)
> +{
> + pr_err(GHES_PFX "ID: %d, trying to remove SEA notification which is not supported\n",
> + ghes->generic->header.source_id);
> +}
> +#endif /* CONFIG_HAVE_ACPI_APEI_SEA */
> +
> #ifdef CONFIG_HAVE_ACPI_APEI_NMI
> /*
> * printk is not safe in NMI context. So in NMI handler, we allocate
> @@ -1033,6 +1093,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
> case ACPI_HEST_NOTIFY_EXTERNAL:
> case ACPI_HEST_NOTIFY_SCI:
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_SEA)) {
> + pr_warn(GHES_PFX "Generic hardware error source: %d notified via SEA is not supported\n",
> + generic->header.source_id);
> + rc = -ENOTSUPP;
> + goto err;
> + }
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) {
> pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n",
> @@ -1044,6 +1112,13 @@ static int ghes_probe(struct platform_device *ghes_dev)
> pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n",
> generic->header.source_id);
> goto err;
> + case ACPI_HEST_NOTIFY_GPIO:
> + case ACPI_HEST_NOTIFY_SEI:
> + case ACPI_HEST_NOTIFY_GSIV:
> + pr_warn(GHES_PFX "Generic hardware error source: %d notified via notification type %u is not supported\n",
> + generic->header.source_id, generic->header.source_id);
> + rc = -ENOTSUPP;
> + goto err;
> default:
> pr_warning(FW_WARN GHES_PFX "Unknown notification type: %u for generic hardware error source: %d\n",
> generic->notify.type, generic->header.source_id);
> @@ -1098,6 +1173,11 @@ static int ghes_probe(struct platform_device *ghes_dev)
> list_add_rcu(&ghes->list, &ghes_sci);
> mutex_unlock(&ghes_list_mutex);
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + rc = ghes_sea_add(ghes);
> + if (rc)
> + goto err_edac_unreg;
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> ghes_nmi_add(ghes);
> break;
> @@ -1140,6 +1220,9 @@ static int ghes_remove(struct platform_device *ghes_dev)
> unregister_acpi_hed_notifier(&ghes_notifier_sci);
> mutex_unlock(&ghes_list_mutex);
> break;
> + case ACPI_HEST_NOTIFY_SEA:
> + ghes_sea_remove(ghes);
> + break;
> case ACPI_HEST_NOTIFY_NMI:
> ghes_nmi_remove(ghes);
> break;

--
Qualcomm Innovation Center, Inc.
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project