* [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-24 8:51 ` Suzuki K Poulose
2016-10-21 17:30 ` [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1 Tyler Baicar
` (8 subsequent siblings)
9 siblings, 1 reply; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
A RAS (Reliability, Availability, Serviceability) controller
may be a separate processor running in parallel with OS
execution, and may generate error records for consumption by
the OS. If the RAS controller produces multiple error records,
then they may be overwritten before the OS has consumed them.
The Generic Hardware Error Source (GHES) v2 structure
introduces the capability for the OS to acknowledge the
consumption of the error record generated by the RAS
controller. A RAS controller supporting GHESv2 shall wait for
the acknowledgment before writing a new error record, thus
eliminating the race condition.
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
---
drivers/acpi/apei/ghes.c | 42 ++++++++++++++++++++++++++++++++++++++++++
drivers/acpi/apei/hest.c | 7 +++++--
include/acpi/ghes.h | 5 ++++-
3 files changed, 51 insertions(+), 3 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 60746ef..7d020b0 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -45,6 +45,7 @@
#include <linux/aer.h>
#include <linux/nmi.h>
+#include <acpi/actbl1.h>
#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/tlbflush.h>
@@ -79,6 +80,10 @@
((struct acpi_hest_generic_status *) \
((struct ghes_estatus_node *)(estatus_node) + 1))
+#define HEST_TYPE_GENERIC_V2(ghes) \
+ ((struct acpi_hest_header *)ghes->generic)->type == \
+ ACPI_HEST_TYPE_GENERIC_ERROR_V2
+
/*
* This driver isn't really modular, however for the time being,
* continuing to use module_param is the easiest way to remain
@@ -248,7 +253,15 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
ghes = kzalloc(sizeof(*ghes), GFP_KERNEL);
if (!ghes)
return ERR_PTR(-ENOMEM);
+
ghes->generic = generic;
+ if (HEST_TYPE_GENERIC_V2(ghes)) {
+ rc = apei_map_generic_address(
+ &ghes->generic_v2->read_ack_register);
+ if (rc)
+ goto err_unmap;
+ }
+
rc = apei_map_generic_address(&generic->error_status_address);
if (rc)
goto err_free;
@@ -270,6 +283,9 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
err_unmap:
apei_unmap_generic_address(&generic->error_status_address);
+ if (HEST_TYPE_GENERIC_V2(ghes))
+ apei_unmap_generic_address(
+ &ghes->generic_v2->read_ack_register);
err_free:
kfree(ghes);
return ERR_PTR(rc);
@@ -279,6 +295,9 @@ static void ghes_fini(struct ghes *ghes)
{
kfree(ghes->estatus);
apei_unmap_generic_address(&ghes->generic->error_status_address);
+ if (HEST_TYPE_GENERIC_V2(ghes))
+ apei_unmap_generic_address(
+ &ghes->generic_v2->read_ack_register);
}
static inline int ghes_severity(int severity)
@@ -648,6 +667,23 @@ static void ghes_estatus_cache_add(
rcu_read_unlock();
}
+static int ghes_do_read_ack(struct acpi_hest_generic_v2 *generic_v2)
+{
+ int rc;
+ u64 val = 0;
+
+ rc = apei_read(&val, &generic_v2->read_ack_register);
+ if (rc)
+ return rc;
+ val &= generic_v2->read_ack_preserve <<
+ generic_v2->read_ack_register.bit_offset;
+ val |= generic_v2->read_ack_write <<
+ generic_v2->read_ack_register.bit_offset;
+ rc = apei_write(val, &generic_v2->read_ack_register);
+
+ return rc;
+}
+
static int ghes_proc(struct ghes *ghes)
{
int rc;
@@ -660,6 +696,12 @@ static int ghes_proc(struct ghes *ghes)
ghes_estatus_cache_add(ghes->generic, ghes->estatus);
}
ghes_do_proc(ghes, ghes->estatus);
+
+ if (HEST_TYPE_GENERIC_V2(ghes)) {
+ rc = ghes_do_read_ack(ghes->generic_v2);
+ if (rc)
+ return rc;
+ }
out:
ghes_clear_estatus(ghes);
return 0;
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index 792a0d9..ef725a9 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -52,6 +52,7 @@ static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
[ACPI_HEST_TYPE_AER_ENDPOINT] = sizeof(struct acpi_hest_aer),
[ACPI_HEST_TYPE_AER_BRIDGE] = sizeof(struct acpi_hest_aer_bridge),
[ACPI_HEST_TYPE_GENERIC_ERROR] = sizeof(struct acpi_hest_generic),
+ [ACPI_HEST_TYPE_GENERIC_ERROR_V2] = sizeof(struct acpi_hest_generic_v2),
};
static int hest_esrc_len(struct acpi_hest_header *hest_hdr)
@@ -146,7 +147,8 @@ static int __init hest_parse_ghes_count(struct acpi_hest_header *hest_hdr, void
{
int *count = data;
- if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR)
+ if (hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR ||
+ hest_hdr->type == ACPI_HEST_TYPE_GENERIC_ERROR_V2)
(*count)++;
return 0;
}
@@ -157,7 +159,8 @@ static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data)
struct ghes_arr *ghes_arr = data;
int rc, i;
- if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR)
+ if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR &&
+ hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR_V2)
return 0;
if (!((struct acpi_hest_generic *)hest_hdr)->enabled)
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 720446c..68f088a 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -13,7 +13,10 @@
#define GHES_EXITING 0x0002
struct ghes {
- struct acpi_hest_generic *generic;
+ union {
+ struct acpi_hest_generic *generic;
+ struct acpi_hest_generic_v2 *generic_v2;
+ };
struct acpi_hest_generic_status *estatus;
u64 buffer_paddr;
unsigned long flags;
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption
2016-10-21 17:30 ` [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption Tyler Baicar
@ 2016-10-24 8:51 ` Suzuki K Poulose
2016-10-24 20:28 ` Baicar, Tyler
0 siblings, 1 reply; 20+ messages in thread
From: Suzuki K Poulose @ 2016-10-24 8:51 UTC (permalink / raw)
To: Tyler Baicar, marc.zyngier, pbonzini, rkrcmar, linux,
catalin.marinas, will.deacon, rjw, lenb, matt, robert.moore,
lv.zheng, nkaje, zjzhang, mark.rutland, james.morse, akpm,
eun.taik.lee, sandeepa.s.prabhu, shijie.huang, rruigrok,
paul.gortmaker, tomasz.nowicki, fu.wei, rostedt, bristot,
linux-arm-kernel, kvmarm, kvm, linux-kernel, linux-acpi,
linux-efi, punit.
On 21/10/16 18:30, Tyler Baicar wrote:
> A RAS (Reliability, Availability, Serviceability) controller
> may be a separate processor running in parallel with OS
> execution, and may generate error records for consumption by
> the OS. If the RAS controller produces multiple error records,
> then they may be overwritten before the OS has consumed them.
>
> The Generic Hardware Error Source (GHES) v2 structure
> introduces the capability for the OS to acknowledge the
> consumption of the error record generated by the RAS
> controller. A RAS controller supporting GHESv2 shall wait for
> the acknowledgment before writing a new error record, thus
> eliminating the race condition.
>
> Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
> Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
> Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
> ---
> drivers/acpi/apei/ghes.c | 42 ++++++++++++++++++++++++++++++++++++++++++
> drivers/acpi/apei/hest.c | 7 +++++--
> include/acpi/ghes.h | 5 ++++-
> 3 files changed, 51 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 60746ef..7d020b0 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -45,6 +45,7 @@
> #include <linux/aer.h>
> #include <linux/nmi.h>
>
> +#include <acpi/actbl1.h>
> #include <acpi/ghes.h>
> #include <acpi/apei.h>
> #include <asm/tlbflush.h>
> @@ -79,6 +80,10 @@
> ((struct acpi_hest_generic_status *) \
> ((struct ghes_estatus_node *)(estatus_node) + 1))
>
> +#define HEST_TYPE_GENERIC_V2(ghes) \
> + ((struct acpi_hest_header *)ghes->generic)->type == \
> + ACPI_HEST_TYPE_GENERIC_ERROR_V2
> +
> /*
> * This driver isn't really modular, however for the time being,
> * continuing to use module_param is the easiest way to remain
> @@ -248,7 +253,15 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
> ghes = kzalloc(sizeof(*ghes), GFP_KERNEL);
> if (!ghes)
> return ERR_PTR(-ENOMEM);
> +
> ghes->generic = generic;
> + if (HEST_TYPE_GENERIC_V2(ghes)) {
> + rc = apei_map_generic_address(
> + &ghes->generic_v2->read_ack_register);
> + if (rc)
> + goto err_unmap;
I think should be goto err_free, see more below.
> + }
> +
> rc = apei_map_generic_address(&generic->error_status_address);
> if (rc)
> goto err_free;
> @@ -270,6 +283,9 @@ static struct ghes *ghes_new(struct acpi_hest_generic *generic)
>
> err_unmap:
> apei_unmap_generic_address(&generic->error_status_address);
> + if (HEST_TYPE_GENERIC_V2(ghes))
> + apei_unmap_generic_address(
> + &ghes->generic_v2->read_ack_register);
We might end up trying to unmap (error_status_address) which is not mapped
if we hit the error in mapping read_ack_register. The read_ack_register unmap
hunk should be moved below to err_free.
> err_free:
> kfree(ghes);
> return ERR_PTR(rc);
> @@ -279,6 +295,9 @@ static void ghes_fini(struct ghes *ghes)
> {
> kfree(ghes->estatus);
> apei_unmap_generic_address(&ghes->generic->error_status_address);
> + if (HEST_TYPE_GENERIC_V2(ghes))
> + apei_unmap_generic_address(
> + &ghes->generic_v2->read_ack_register);
> }
>
> static inline int ghes_severity(int severity)
> @@ -648,6 +667,23 @@ static void ghes_estatus_cache_add(
> rcu_read_unlock();
> }
>
> +static int ghes_do_read_ack(struct acpi_hest_generic_v2 *generic_v2)
nit: We are actually writing something to the read_ack_register. The names
read_ack_register (which may be as per standard) and more importantly the
function name (ghes_do_read_ack) sounds a bit misleading.
Rest looks fine to me.
Suzuki
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption
2016-10-24 8:51 ` Suzuki K Poulose
@ 2016-10-24 20:28 ` Baicar, Tyler
0 siblings, 0 replies; 20+ messages in thread
From: Baicar, Tyler @ 2016-10-24 20:28 UTC (permalink / raw)
To: Suzuki K Poulose, marc.zyngier, pbonzini, rkrcmar, linux,
catalin.marinas, will.deacon, rjw, lenb, matt, robert.moore,
lv.zheng, nkaje, zjzhang, mark.rutland, james.morse, akpm,
eun.taik.lee, sandeepa.s.prabhu, shijie.huang, rruigrok,
paul.gortmaker, tomasz.nowicki, fu.wei, rostedt, bristot,
linux-arm-kernel, kvmarm, kvm, linux-kernel, linux-acpi,
linux-efi, punit.agrawal, astone, harba, hanjun.guo
On 10/24/2016 2:51 AM, Suzuki K Poulose wrote:
> On 21/10/16 18:30, Tyler Baicar wrote:
>> A RAS (Reliability, Availability, Serviceability) controller
>> may be a separate processor running in parallel with OS
>> execution, and may generate error records for consumption by
>> the OS. If the RAS controller produces multiple error records,
>> then they may be overwritten before the OS has consumed them.
>>
>> The Generic Hardware Error Source (GHES) v2 structure
>> introduces the capability for the OS to acknowledge the
>> consumption of the error record generated by the RAS
>> controller. A RAS controller supporting GHESv2 shall wait for
>> the acknowledgment before writing a new error record, thus
>> eliminating the race condition.
>>
>> Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
>> Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
>> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
>> Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
>> ---
>> drivers/acpi/apei/ghes.c | 42
>> ++++++++++++++++++++++++++++++++++++++++++
>> drivers/acpi/apei/hest.c | 7 +++++--
>> include/acpi/ghes.h | 5 ++++-
>> 3 files changed, 51 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index 60746ef..7d020b0 100644
>> --- a/drivers/acpi/apei/ghes.c
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -45,6 +45,7 @@
>> #include <linux/aer.h>
>> #include <linux/nmi.h>
>>
>> +#include <acpi/actbl1.h>
>> #include <acpi/ghes.h>
>> #include <acpi/apei.h>
>> #include <asm/tlbflush.h>
>> @@ -79,6 +80,10 @@
>> ((struct acpi_hest_generic_status *) \
>> ((struct ghes_estatus_node *)(estatus_node) + 1))
>>
>> +#define HEST_TYPE_GENERIC_V2(ghes) \
>> + ((struct acpi_hest_header *)ghes->generic)->type == \
>> + ACPI_HEST_TYPE_GENERIC_ERROR_V2
>> +
>> /*
>> * This driver isn't really modular, however for the time being,
>> * continuing to use module_param is the easiest way to remain
>> @@ -248,7 +253,15 @@ static struct ghes *ghes_new(struct
>> acpi_hest_generic *generic)
>> ghes = kzalloc(sizeof(*ghes), GFP_KERNEL);
>> if (!ghes)
>> return ERR_PTR(-ENOMEM);
>> +
>> ghes->generic = generic;
>> + if (HEST_TYPE_GENERIC_V2(ghes)) {
>> + rc = apei_map_generic_address(
>> + &ghes->generic_v2->read_ack_register);
>> + if (rc)
>> + goto err_unmap;
>
> I think should be goto err_free, see more below.
>
>> + }
>> +
>> rc = apei_map_generic_address(&generic->error_status_address);
>> if (rc)
>> goto err_free;
>> @@ -270,6 +283,9 @@ static struct ghes *ghes_new(struct
>> acpi_hest_generic *generic)
>>
>> err_unmap:
>> apei_unmap_generic_address(&generic->error_status_address);
>> + if (HEST_TYPE_GENERIC_V2(ghes))
>> + apei_unmap_generic_address(
>> + &ghes->generic_v2->read_ack_register);
>
> We might end up trying to unmap (error_status_address) which is not
> mapped
> if we hit the error in mapping read_ack_register. The
> read_ack_register unmap
> hunk should be moved below to err_free.
>
This needs to be changed, I'll add a separate label for unmapping
read_ack_register and error_status_address for the case that the
read_ack_register map succeeds but the error_status_address map fails.
err_unmap_status_addr:
apei_unmap_generic_address(&generic->error_status_address);
err_unmap_read_ack_addr:
if (HEST_TYPE_GENERIC_V2(ghes))
apei_unmap_generic_address(
&ghes->generic_v2->read_ack_register);
err_free:
kfree(ghes);
return ERR_PTR(rc);
If mapping read_ack_register fails, goto err_free.
If mapping read_ack_register is successful but mapping
error_status_address fails, goto err_unmap_read_ack_addr.
And if both mappings succeed but the kmalloc fails, then goto
err_unmap_status_addr.
>
>> err_free:
>> kfree(ghes);
>> return ERR_PTR(rc);
>> @@ -279,6 +295,9 @@ static void ghes_fini(struct ghes *ghes)
>> {
>> kfree(ghes->estatus);
>> apei_unmap_generic_address(&ghes->generic->error_status_address);
>> + if (HEST_TYPE_GENERIC_V2(ghes))
>> + apei_unmap_generic_address(
>> + &ghes->generic_v2->read_ack_register);
>> }
>>
>> static inline int ghes_severity(int severity)
>> @@ -648,6 +667,23 @@ static void ghes_estatus_cache_add(
>> rcu_read_unlock();
>> }
>>
>
>> +static int ghes_do_read_ack(struct acpi_hest_generic_v2 *generic_v2)
>
> nit: We are actually writing something to the read_ack_register. The
> names
> read_ack_register (which may be as per standard) and more importantly the
> function name (ghes_do_read_ack) sounds a bit misleading.
It is called "Read Ack Register" in the spec (ACPI 6.1 table 18-344),
but I agree the function name can be improved.
Maybe ghes_acknowledge_error or ghes_ack_error.
Thanks,
Tyler
>
> Rest looks fine to me.
>
> Suzuki
>
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-24 9:50 ` Suzuki K Poulose
2016-10-21 17:30 ` [PATCH V4 03/10] efi: parse ARMv8 processor error Tyler Baicar
` (7 subsequent siblings)
9 siblings, 1 reply; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal
Cc: Tyler Baicar
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 <zjzhang@codeaurora.org>
Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
---
drivers/acpi/apei/ghes.c | 14 +++++++---
drivers/firmware/efi/cper.c | 67 +++++++++++++++++++++++++++++++++++++--------
include/acpi/ghes.h | 10 +++++++
include/linux/cper.h | 12 ++++++++
4 files changed, 88 insertions(+), 15 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 7d020b0..7610f08 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -419,7 +419,8 @@ 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);
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
@@ -449,14 +450,18 @@ static void ghes_do_proc(struct ghes *ghes,
{
int sev, sec_sev;
struct acpi_hest_generic_data *gdata;
+ 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 (!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);
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
ghes_edac_report_mem_error(ghes, sev, mem_err);
arch_apei_report_mem_error(sev, mem_err);
@@ -466,7 +471,8 @@ 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);
+
+ pcie_err = acpi_hest_generic_data_payload(gdata);
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..af7e1e9 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -32,6 +32,9 @@
#include <linux/acpi.h>
#include <linux/pci.h>
#include <linux/aer.h>
+#include <linux/printk.h>
+#include <linux/bcd.h>
+#include <acpi/ghes.h>
#define INDENT_SP " "
@@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
pfx, pcie->bridge.secondary_status, pcie->bridge.control);
}
+static void cper_estatus_print_section_v300(const char *pfx,
+ const struct acpi_hest_generic_data_v300 *gdata)
+{
+ __u8 hour, min, sec, day, mon, year, century, *timestamp;
+
+ if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
+ timestamp = (__u8 *)&(gdata->time_stamp);
+ sec = bcd2bin(timestamp[0]);
+ min = bcd2bin(timestamp[1]);
+ hour = bcd2bin(timestamp[2]);
+ day = bcd2bin(timestamp[4]);
+ mon = bcd2bin(timestamp[5]);
+ year = bcd2bin(timestamp[6]);
+ century = bcd2bin(timestamp[7]);
+ printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
+ 0x01 & *(timestamp + 3) ? "precise" : "", century,
+ year, mon, day, hour, min, sec);
+ }
+}
+
static void cper_estatus_print_section(
- const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
+ const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
{
uuid_le *sec_type = (uuid_le *)gdata->section_type;
__u16 severity;
char newpfx[64];
+ if (acpi_hest_generic_data_version(gdata))
+ cper_estatus_print_section_v300(pfx,
+ (const struct acpi_hest_generic_data_v300 *)gdata);
+
severity = gdata->error_severity;
printk("%s""Error %d, type: %s\n", pfx, sec_no,
cper_severity_str(severity));
@@ -403,14 +430,18 @@ 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;
+
+ proc_err = acpi_hest_generic_data_payload(gdata);
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;
+
+ mem_err = acpi_hest_generic_data_payload(gdata);
printk("%s""section_type: memory error\n", newpfx);
if (gdata->error_data_length >=
sizeof(struct cper_sec_mem_err_old))
@@ -419,7 +450,9 @@ 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;
+
+ pcie = acpi_hest_generic_data_payload(gdata);
printk("%s""section_type: PCIe error\n", newpfx);
if (gdata->error_data_length >= sizeof(*pcie))
cper_print_pcie(newpfx, pcie, gdata);
@@ -438,6 +471,7 @@ void cper_estatus_print(const char *pfx,
const struct acpi_hest_generic_status *estatus)
{
struct acpi_hest_generic_data *gdata;
+ struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
unsigned int data_len, gedata_len;
int sec_no = 0;
char newpfx[64];
@@ -451,12 +485,22 @@ void cper_estatus_print(const char *pfx,
printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
data_len = estatus->data_length;
gdata = (struct acpi_hest_generic_data *)(estatus + 1);
+ if (acpi_hest_generic_data_version(gdata))
+ gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
+
snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+
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;
+ if(gdata_v3) {
+ data_len -= gedata_len + sizeof(*gdata_v3);
+ gdata_v3 = (void *)(gdata_v3 + 1) + gedata_len;
+ gdata = (struct acpi_hest_generic_data *)gdata_v3;
+ } else {
+ data_len -= gedata_len + sizeof(*gdata);
+ gdata = (void *)(gdata + 1) + gedata_len;
+ }
sec_no++;
}
}
@@ -486,12 +530,13 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus)
return rc;
data_len = estatus->data_length;
gdata = (struct acpi_hest_generic_data *)(estatus + 1);
- while (data_len >= sizeof(*gdata)) {
- gedata_len = gdata->error_data_length;
- if (gedata_len > data_len - sizeof(*gdata))
+
+ while (data_len >= acpi_hest_generic_data_size(gdata)) {
+ gedata_len = acpi_hest_generic_data_error_length(gdata);
+ if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
return -EINVAL;
- data_len -= gedata_len + sizeof(*gdata);
- gdata = (void *)(gdata + 1) + gedata_len;
+ data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
+ gdata = acpi_hest_generic_data_next(gdata);
}
if (data_len)
return -EINVAL;
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 68f088a..56b9679 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -73,3 +73,13 @@ static inline void ghes_edac_unregister(struct ghes *ghes)
{
}
#endif
+
+#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 ?
+ (void *)(((struct acpi_hest_generic_data_v300 *)(gdata)) + 1) :
+ gdata + 1;
+}
diff --git a/include/linux/cper.h b/include/linux/cper.h
index dcacb1a..13ea41c 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -255,6 +255,18 @@ enum {
#define CPER_PCIE_SLOT_SHIFT 3
+#define acpi_hest_generic_data_error_length(gdata) \
+ (((struct acpi_hest_generic_data *)(gdata))->error_data_length)
+#define acpi_hest_generic_data_size(gdata) \
+ ((acpi_hest_generic_data_version(gdata) >= 3) ? \
+ sizeof(struct acpi_hest_generic_data_v300) : \
+ sizeof(struct acpi_hest_generic_data))
+#define acpi_hest_generic_data_record_size(gdata) \
+ (acpi_hest_generic_data_size(gdata) + \
+ acpi_hest_generic_data_error_length(gdata))
+#define acpi_hest_generic_data_next(gdata) \
+ ((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
+
/*
* All tables and structs must be byte-packed to match CPER
* specification, since the tables are provided by the system BIOS
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
2016-10-21 17:30 ` [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1 Tyler Baicar
@ 2016-10-24 9:50 ` Suzuki K Poulose
2016-10-24 20:33 ` Baicar, Tyler
0 siblings, 1 reply; 20+ messages in thread
From: Suzuki K Poulose @ 2016-10-24 9:50 UTC (permalink / raw)
To: Tyler Baicar, marc.zyngier, pbonzini, rkrcmar, linux,
catalin.marinas, will.deacon, rjw, lenb, matt, robert.moore,
lv.zheng, nkaje, zjzhang, mark.rutland, james.morse, akpm,
eun.taik.lee, sandeepa.s.prabhu, shijie.huang, rruigrok,
paul.gortmaker, tomasz.nowicki, fu.wei, rostedt, bristot,
linux-arm-kernel, kvmarm, kvm, linux-kernel, linux-acpi,
linux-efi, punit.
On 21/10/16 18:30, 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 <zjzhang@codeaurora.org>
> Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
> Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
> ---
> drivers/acpi/apei/ghes.c | 14 +++++++---
> drivers/firmware/efi/cper.c | 67 +++++++++++++++++++++++++++++++++++++--------
> include/acpi/ghes.h | 10 +++++++
> include/linux/cper.h | 12 ++++++++
> 4 files changed, 88 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index 7d020b0..7610f08 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -419,7 +419,8 @@ 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);
> +
> + mem_err = acpi_hest_generic_data_payload(gdata);
>
> if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
> return;
> @@ -449,14 +450,18 @@ static void ghes_do_proc(struct ghes *ghes,
> {
> int sev, sec_sev;
> struct acpi_hest_generic_data *gdata;
> + 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 (!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);
> +
> + mem_err = acpi_hest_generic_data_payload(gdata);
> ghes_edac_report_mem_error(ghes, sev, mem_err);
>
> arch_apei_report_mem_error(sev, mem_err);
> @@ -466,7 +471,8 @@ 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);
> +
> + pcie_err = acpi_hest_generic_data_payload(gdata);
> 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..af7e1e9 100644
> --- a/drivers/firmware/efi/cper.c
> +++ b/drivers/firmware/efi/cper.c
> @@ -32,6 +32,9 @@
> #include <linux/acpi.h>
> #include <linux/pci.h>
> #include <linux/aer.h>
> +#include <linux/printk.h>
> +#include <linux/bcd.h>
> +#include <acpi/ghes.h>
>
> #define INDENT_SP " "
>
> @@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
> pfx, pcie->bridge.secondary_status, pcie->bridge.control);
> }
>
> +static void cper_estatus_print_section_v300(const char *pfx,
> + const struct acpi_hest_generic_data_v300 *gdata)
> +{
> + __u8 hour, min, sec, day, mon, year, century, *timestamp;
> +
> + if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
> + timestamp = (__u8 *)&(gdata->time_stamp);
> + sec = bcd2bin(timestamp[0]);
> + min = bcd2bin(timestamp[1]);
> + hour = bcd2bin(timestamp[2]);
> + day = bcd2bin(timestamp[4]);
> + mon = bcd2bin(timestamp[5]);
> + year = bcd2bin(timestamp[6]);
> + century = bcd2bin(timestamp[7]);
> + printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
> + 0x01 & *(timestamp + 3) ? "precise" : "", century,
> + year, mon, day, hour, min, sec);
> + }
> +}
> +
> static void cper_estatus_print_section(
> - const char *pfx, const struct acpi_hest_generic_data *gdata, int sec_no)
> + const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
> {
> uuid_le *sec_type = (uuid_le *)gdata->section_type;
> __u16 severity;
> char newpfx[64];
>
> + if (acpi_hest_generic_data_version(gdata))
> + cper_estatus_print_section_v300(pfx,
> + (const struct acpi_hest_generic_data_v300 *)gdata);
> +
> severity = gdata->error_severity;
> printk("%s""Error %d, type: %s\n", pfx, sec_no,
> cper_severity_str(severity));
> @@ -403,14 +430,18 @@ 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;
> +
> + proc_err = acpi_hest_generic_data_payload(gdata);
> 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;
> +
> + mem_err = acpi_hest_generic_data_payload(gdata);
> printk("%s""section_type: memory error\n", newpfx);
> if (gdata->error_data_length >=
> sizeof(struct cper_sec_mem_err_old))
> @@ -419,7 +450,9 @@ 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;
> +
> + pcie = acpi_hest_generic_data_payload(gdata);
> printk("%s""section_type: PCIe error\n", newpfx);
> if (gdata->error_data_length >= sizeof(*pcie))
> cper_print_pcie(newpfx, pcie, gdata);
> @@ -438,6 +471,7 @@ void cper_estatus_print(const char *pfx,
> const struct acpi_hest_generic_status *estatus)
> {
> struct acpi_hest_generic_data *gdata;
> + struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
> unsigned int data_len, gedata_len;
> int sec_no = 0;
> char newpfx[64];
> @@ -451,12 +485,22 @@ void cper_estatus_print(const char *pfx,
> printk("%s""event severity: %s\n", pfx, cper_severity_str(severity));
> data_len = estatus->data_length;
> gdata = (struct acpi_hest_generic_data *)(estatus + 1);
> + if (acpi_hest_generic_data_version(gdata))
> + gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
I think the acpi_hest_generic_data_version() doesn't check if the version is
V3 or higher ?
> +
> snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
> +
> 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;
> + if(gdata_v3) {
> + data_len -= gedata_len + sizeof(*gdata_v3);
> + gdata_v3 = (void *)(gdata_v3 + 1) + gedata_len;
> + gdata = (struct acpi_hest_generic_data *)gdata_v3;
> + } else {
> + data_len -= gedata_len + sizeof(*gdata);
> + gdata = (void *)(gdata + 1) + gedata_len;
> + }
Could we not use the helpers we define below to unify the code here and avoid the
switch ?
> sec_no++;
> }
> }
> @@ -486,12 +530,13 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus)
> return rc;
> data_len = estatus->data_length;
> gdata = (struct acpi_hest_generic_data *)(estatus + 1);
> - while (data_len >= sizeof(*gdata)) {
> - gedata_len = gdata->error_data_length;
> - if (gedata_len > data_len - sizeof(*gdata))
> +
> + while (data_len >= acpi_hest_generic_data_size(gdata)) {
> + gedata_len = acpi_hest_generic_data_error_length(gdata);
> + if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
> return -EINVAL;
> - data_len -= gedata_len + sizeof(*gdata);
> - gdata = (void *)(gdata + 1) + gedata_len;
> + data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
> + gdata = acpi_hest_generic_data_next(gdata);
> }
> if (data_len)
> return -EINVAL;
> diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
> index 68f088a..56b9679 100644
> --- a/include/acpi/ghes.h
> +++ b/include/acpi/ghes.h
> @@ -73,3 +73,13 @@ static inline void ghes_edac_unregister(struct ghes *ghes)
> {
> }
> #endif
> +
> +#define acpi_hest_generic_data_version(gdata) \
> + (gdata->revision >> 8)
> +
>
> +#define acpi_hest_generic_data_error_length(gdata) \
> + (((struct acpi_hest_generic_data *)(gdata))->error_data_length)
> +#define acpi_hest_generic_data_size(gdata) \
> + ((acpi_hest_generic_data_version(gdata) >= 3) ? \
> + sizeof(struct acpi_hest_generic_data_v300) : \
> + sizeof(struct acpi_hest_generic_data))
> +#define acpi_hest_generic_data_record_size(gdata) \
> + (acpi_hest_generic_data_size(gdata) + \
> + acpi_hest_generic_data_error_length(gdata))
> +#define acpi_hest_generic_data_next(gdata) \
> + ((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
> +
Rest looks good
Cheers
Suzuki
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1
2016-10-24 9:50 ` Suzuki K Poulose
@ 2016-10-24 20:33 ` Baicar, Tyler
0 siblings, 0 replies; 20+ messages in thread
From: Baicar, Tyler @ 2016-10-24 20:33 UTC (permalink / raw)
To: Suzuki K Poulose, marc.zyngier, pbonzini, rkrcmar, linux,
catalin.marinas, will.deacon, rjw, lenb, matt, robert.moore,
lv.zheng, nkaje, zjzhang, mark.rutland, james.morse, akpm,
eun.taik.lee, sandeepa.s.prabhu, shijie.huang, rruigrok,
paul.gortmaker, tomasz.nowicki, fu.wei, rostedt, bristot,
linux-arm-kernel, kvmarm, kvm, linux-kernel, linux-acpi,
linux-efi, punit.agrawal, astone, harba, hanjun.guo
On 10/24/2016 3:50 AM, Suzuki K Poulose wrote:
> On 21/10/16 18:30, 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 <zjzhang@codeaurora.org>
>> Signed-off-by: Richard Ruigrok <rruigrok@codeaurora.org>
>> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
>> Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
>> ---
>> drivers/acpi/apei/ghes.c | 14 +++++++---
>> drivers/firmware/efi/cper.c | 67
>> +++++++++++++++++++++++++++++++++++++--------
>> include/acpi/ghes.h | 10 +++++++
>> include/linux/cper.h | 12 ++++++++
>> 4 files changed, 88 insertions(+), 15 deletions(-)
>>
>> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
>> index 7d020b0..7610f08 100644
>> --- a/drivers/acpi/apei/ghes.c
>> +++ b/drivers/acpi/apei/ghes.c
>> @@ -419,7 +419,8 @@ 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);
>> +
>> + mem_err = acpi_hest_generic_data_payload(gdata);
>>
>> if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
>> return;
>> @@ -449,14 +450,18 @@ static void ghes_do_proc(struct ghes *ghes,
>> {
>> int sev, sec_sev;
>> struct acpi_hest_generic_data *gdata;
>> + 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 (!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);
>> +
>> + mem_err = acpi_hest_generic_data_payload(gdata);
>> ghes_edac_report_mem_error(ghes, sev, mem_err);
>>
>> arch_apei_report_mem_error(sev, mem_err);
>> @@ -466,7 +471,8 @@ 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);
>> +
>> + pcie_err = acpi_hest_generic_data_payload(gdata);
>> 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..af7e1e9 100644
>> --- a/drivers/firmware/efi/cper.c
>> +++ b/drivers/firmware/efi/cper.c
>> @@ -32,6 +32,9 @@
>> #include <linux/acpi.h>
>> #include <linux/pci.h>
>> #include <linux/aer.h>
>> +#include <linux/printk.h>
>> +#include <linux/bcd.h>
>> +#include <acpi/ghes.h>
>>
>> #define INDENT_SP " "
>>
>> @@ -386,13 +389,37 @@ static void cper_print_pcie(const char *pfx,
>> const struct cper_sec_pcie *pcie,
>> pfx, pcie->bridge.secondary_status, pcie->bridge.control);
>> }
>>
>> +static void cper_estatus_print_section_v300(const char *pfx,
>> + const struct acpi_hest_generic_data_v300 *gdata)
>> +{
>> + __u8 hour, min, sec, day, mon, year, century, *timestamp;
>> +
>> + if (gdata->validation_bits & ACPI_HEST_GEN_VALID_TIMESTAMP) {
>> + timestamp = (__u8 *)&(gdata->time_stamp);
>> + sec = bcd2bin(timestamp[0]);
>> + min = bcd2bin(timestamp[1]);
>> + hour = bcd2bin(timestamp[2]);
>> + day = bcd2bin(timestamp[4]);
>> + mon = bcd2bin(timestamp[5]);
>> + year = bcd2bin(timestamp[6]);
>> + century = bcd2bin(timestamp[7]);
>> + printk("%stime: %7s %02d%02d-%02d-%02d %02d:%02d:%02d\n", pfx,
>> + 0x01 & *(timestamp + 3) ? "precise" : "", century,
>> + year, mon, day, hour, min, sec);
>> + }
>> +}
>> +
>> static void cper_estatus_print_section(
>> - const char *pfx, const struct acpi_hest_generic_data *gdata, int
>> sec_no)
>> + const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no)
>> {
>> uuid_le *sec_type = (uuid_le *)gdata->section_type;
>> __u16 severity;
>> char newpfx[64];
>>
>> + if (acpi_hest_generic_data_version(gdata))
>> + cper_estatus_print_section_v300(pfx,
>> + (const struct acpi_hest_generic_data_v300 *)gdata);
>> +
>> severity = gdata->error_severity;
>> printk("%s""Error %d, type: %s\n", pfx, sec_no,
>> cper_severity_str(severity));
>> @@ -403,14 +430,18 @@ 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;
>> +
>> + proc_err = acpi_hest_generic_data_payload(gdata);
>> 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;
>> +
>> + mem_err = acpi_hest_generic_data_payload(gdata);
>> printk("%s""section_type: memory error\n", newpfx);
>> if (gdata->error_data_length >=
>> sizeof(struct cper_sec_mem_err_old))
>> @@ -419,7 +450,9 @@ 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;
>> +
>> + pcie = acpi_hest_generic_data_payload(gdata);
>> printk("%s""section_type: PCIe error\n", newpfx);
>> if (gdata->error_data_length >= sizeof(*pcie))
>> cper_print_pcie(newpfx, pcie, gdata);
>> @@ -438,6 +471,7 @@ void cper_estatus_print(const char *pfx,
>> const struct acpi_hest_generic_status *estatus)
>> {
>> struct acpi_hest_generic_data *gdata;
>> + struct acpi_hest_generic_data_v300 *gdata_v3 = NULL;
>> unsigned int data_len, gedata_len;
>> int sec_no = 0;
>> char newpfx[64];
>> @@ -451,12 +485,22 @@ void cper_estatus_print(const char *pfx,
>> printk("%s""event severity: %s\n", pfx,
>> cper_severity_str(severity));
>> data_len = estatus->data_length;
>> gdata = (struct acpi_hest_generic_data *)(estatus + 1);
>> + if (acpi_hest_generic_data_version(gdata))
>> + gdata_v3 = (struct acpi_hest_generic_data_v300 *)gdata;
>
> I think the acpi_hest_generic_data_version() doesn't check if the
> version is
> V3 or higher ?
Oops :) I need to make sure that returns 3.
>
>> +
>> snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
>> +
>> 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;
>> + if(gdata_v3) {
>> + data_len -= gedata_len + sizeof(*gdata_v3);
>> + gdata_v3 = (void *)(gdata_v3 + 1) + gedata_len;
>> + gdata = (struct acpi_hest_generic_data *)gdata_v3;
>> + } else {
>> + data_len -= gedata_len + sizeof(*gdata);
>> + gdata = (void *)(gdata + 1) + gedata_len;
>> + }
>
> Could we not use the helpers we define below to unify the code here
> and avoid the
> switch ?
>
Yes, those helpers should be able to reduce the code here, I'll update this.
>
>> sec_no++;
>> }
>> }
>> @@ -486,12 +530,13 @@ int cper_estatus_check(const struct
>> acpi_hest_generic_status *estatus)
>> return rc;
>> data_len = estatus->data_length;
>> gdata = (struct acpi_hest_generic_data *)(estatus + 1);
>> - while (data_len >= sizeof(*gdata)) {
>> - gedata_len = gdata->error_data_length;
>> - if (gedata_len > data_len - sizeof(*gdata))
>> +
>> + while (data_len >= acpi_hest_generic_data_size(gdata)) {
>> + gedata_len = acpi_hest_generic_data_error_length(gdata);
>> + if (gedata_len > data_len - acpi_hest_generic_data_size(gdata))
>> return -EINVAL;
>> - data_len -= gedata_len + sizeof(*gdata);
>> - gdata = (void *)(gdata + 1) + gedata_len;
>> + data_len -= gedata_len + acpi_hest_generic_data_size(gdata);
>> + gdata = acpi_hest_generic_data_next(gdata);
>> }
>> if (data_len)
>> return -EINVAL;
>> diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
>> index 68f088a..56b9679 100644
>> --- a/include/acpi/ghes.h
>> +++ b/include/acpi/ghes.h
>> @@ -73,3 +73,13 @@ static inline void ghes_edac_unregister(struct
>> ghes *ghes)
>> {
>> }
>> #endif
>> +
>> +#define acpi_hest_generic_data_version(gdata) \
>> + (gdata->revision >> 8)
>> +
>
>
>>
>> +#define acpi_hest_generic_data_error_length(gdata) \
>> + (((struct acpi_hest_generic_data *)(gdata))->error_data_length)
>> +#define acpi_hest_generic_data_size(gdata) \
>> + ((acpi_hest_generic_data_version(gdata) >= 3) ? \
>> + sizeof(struct acpi_hest_generic_data_v300) : \
>> + sizeof(struct acpi_hest_generic_data))
>> +#define acpi_hest_generic_data_record_size(gdata) \
>> + (acpi_hest_generic_data_size(gdata) + \
>> + acpi_hest_generic_data_error_length(gdata))
>> +#define acpi_hest_generic_data_next(gdata) \
>> + ((void *)(gdata) + acpi_hest_generic_data_record_size(gdata))
>> +
>
> Rest looks good
>
> Cheers
> Suzuki
Thanks,
Tyler
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH V4 03/10] efi: parse ARMv8 processor error
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 01/10] acpi: apei: read ack upon ghes record consumption Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 02/10] ras: acpi/apei: cper: generic error data entry v3 per ACPI 6.1 Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 04/10] arm64: exception: handle Synchronous External Abort Tyler Baicar
` (6 subsequent siblings)
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
Add support for ARMv8 Common Platform Error Record (CPER).
UEFI 2.6 specification adds support for ARMv8 specific
processor error information to be reported as part of the
CPER records. This provides more detail on for processor error logs.
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
---
drivers/firmware/efi/cper.c | 135 ++++++++++++++++++++++++++++++++++++++++++++
include/linux/cper.h | 72 +++++++++++++++++++++++
2 files changed, 207 insertions(+)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index af7e1e9..8264eed 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -110,12 +110,15 @@ void cper_print_bits(const char *pfx, unsigned int bits,
static const char * const proc_type_strs[] = {
"IA32/X64",
"IA64",
+ "ARMv8",
};
static const char * const proc_isa_strs[] = {
"IA32",
"IA64",
"X64",
+ "ARM A32/T32",
+ "ARM A64",
};
static const char * const proc_error_type_strs[] = {
@@ -184,6 +187,129 @@ static void cper_print_proc_generic(const char *pfx,
printk("%s""IP: 0x%016llx\n", pfx, proc->ip);
}
+static void cper_print_proc_armv8(const char *pfx,
+ const struct cper_sec_proc_armv8 *proc)
+{
+ int i, len;
+ struct cper_armv8_err_info *err_info;
+ __u64 *qword = NULL;
+ char newpfx[64];
+
+ printk("%ssection length: %d\n", pfx, proc->section_length);
+ printk("%sMIDR: 0x%016llx\n", pfx, proc->midr);
+
+ len = proc->section_length - (sizeof(*proc) +
+ proc->err_info_num * (sizeof(*err_info)));
+ if (len < 0) {
+ printk("%ssection length is too small.\n", pfx);
+ printk("%sERR_INFO_NUM is %d.\n", pfx, proc->err_info_num);
+ return;
+ }
+
+ if (proc->validation_bits & CPER_ARMV8_VALID_MPIDR)
+ printk("%sMPIDR: 0x%016llx\n", pfx, proc->mpidr);
+ if (proc->validation_bits & CPER_ARMV8_VALID_AFFINITY_LEVEL)
+ printk("%serror affinity level: %d\n", pfx,
+ proc->affinity_level);
+ if (proc->validation_bits & CPER_ARMV8_VALID_RUNNING_STATE) {
+ printk("%srunning state: %d\n", pfx, proc->running_state);
+ printk("%sPSCI state: %d\n", pfx, proc->psci_state);
+ }
+
+ snprintf(newpfx, sizeof(newpfx), "%s%s", pfx, INDENT_SP);
+
+ err_info = (struct cper_armv8_err_info *)(proc + 1);
+ for (i = 0; i < proc->err_info_num; i++) {
+ printk("%sError info structure %d:\n", pfx, i);
+ printk("%sversion:%d\n", newpfx, err_info->version);
+ printk("%slength:%d\n", newpfx, err_info->length);
+ if (err_info->validation_bits &
+ CPER_ARMV8_INFO_VALID_MULTI_ERR) {
+ if (err_info->multiple_error == 0)
+ printk("%ssingle error.\n", newpfx);
+ else if (err_info->multiple_error == 1)
+ printk("%smultiple errors.\n", newpfx);
+ else
+ printk("%smultiple errors count:%d.\n",
+ newpfx, err_info->multiple_error);
+ }
+ if (err_info->validation_bits & CPER_ARMV8_INFO_VALID_FLAGS) {
+ if (err_info->flags & CPER_ARMV8_INFO_FLAGS_FIRST)
+ printk("%sfirst error captured.\n", newpfx);
+ if (err_info->flags & CPER_ARMV8_INFO_FLAGS_LAST)
+ printk("%slast error captured.\n", newpfx);
+ if (err_info->flags & CPER_ARMV8_INFO_FLAGS_PROPAGATED)
+ printk("%spropagated error captured.\n",
+ newpfx);
+ }
+ printk("%serror_type: %d, %s\n", newpfx, err_info->type,
+ err_info->type < ARRAY_SIZE(proc_error_type_strs) ?
+ proc_error_type_strs[err_info->type] : "unknown");
+ printk("%serror_info: 0x%016llx\n", newpfx,
+ err_info->error_info);
+ if (err_info->validation_bits & CPER_ARMV8_INFO_VALID_VIRT_ADDR)
+ printk("%svirtual fault address: 0x%016llx\n",
+ newpfx, err_info->virt_fault_addr);
+ if (err_info->validation_bits &
+ CPER_ARMV8_INFO_VALID_PHYSICAL_ADDR)
+ printk("%sphysical fault address: 0x%016llx\n",
+ newpfx, err_info->physical_fault_addr);
+ err_info += 1;
+ }
+
+ if (len < sizeof(*qword) && proc->context_info_num > 0) {
+ printk("%ssection length is too small.\n", pfx);
+ printk("%sCTX_INFO_NUM is %d.\n", pfx, proc->context_info_num);
+ return;
+ }
+ for (i = 0; i < proc->context_info_num; i++) {
+ qword = (__u64 *)err_info;
+ printk("%sProcessor context info structure %d:\n", pfx, i);
+ printk("%sException level %d.\n", newpfx,
+ (int)((*qword & CPER_ARMV8_CTX_EL_MASK)
+ >> CPER_ARMV8_CTX_EL_SHIFT));
+ printk("%sSecure bit: %d.\n", newpfx,
+ (int)((*qword & CPER_ARMV8_CTX_NS_MASK)
+ >> CPER_ARMV8_CTX_NS_SHIFT));
+ if ((*qword & CPER_ARMV8_CTX_TYPE_MASK) == 0) {
+ if (len < CPER_AARCH32_CTX_LEN) {
+ printk("%ssection length is too small.\n", pfx);
+ printk("%sremaining length is %d.\n", pfx, len);
+ return;
+ }
+ printk("%sAArch32 execution context.\n", newpfx);
+ qword++;
+ print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4,
+ qword, CPER_AARCH32_CTX_LEN - sizeof(*qword),
+ 0);
+ len -= CPER_AARCH32_CTX_LEN;
+ } else if ((*qword & CPER_ARMV8_CTX_TYPE_MASK) == 1) {
+ if (len < CPER_AARCH64_CTX_LEN) {
+ printk("%ssection length is too small.\n", pfx);
+ printk("%sremaining length is %d.\n", pfx, len);
+ return;
+ }
+ printk("%sAArch64 execution context.\n", newpfx);
+ qword++;
+ print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4,
+ qword, CPER_AARCH64_CTX_LEN - sizeof(*qword),
+ 0);
+ len -= CPER_AARCH64_CTX_LEN;
+ } else {
+ printk("%scontext type is incorrect 0x%016llx.\n",
+ pfx, *qword);
+ return;
+ }
+ }
+
+ if (len > 0) {
+ printk("%sVendor specific error info has %d bytes.\n", pfx,
+ len);
+ print_hex_dump(pfx, "", DUMP_PREFIX_OFFSET, 16, 4, qword, len,
+ 0);
+ }
+}
+
static const char * const mem_err_type_strs[] = {
"unknown",
"no error",
@@ -458,6 +584,15 @@ static void cper_estatus_print_section(
cper_print_pcie(newpfx, pcie, gdata);
else
goto err_section_too_small;
+ } else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARMV8)) {
+ struct cper_sec_proc_armv8 *armv8_err;
+
+ armv8_err = acpi_hest_generic_data_payload(gdata);
+ printk("%ssection_type: ARMv8 processor error\n", newpfx);
+ if (gdata->error_data_length >= sizeof(*armv8_err))
+ cper_print_proc_armv8(newpfx, armv8_err);
+ else
+ goto err_section_too_small;
} else
printk("%s""section type: unknown, %pUl\n", newpfx, sec_type);
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 13ea41c..2a9d553 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -162,6 +162,11 @@ enum {
* corrective action before the data is consumed
*/
#define CPER_SEC_LATENT_ERROR 0x0020
+/*
+ * If set, the section contains an error that is propagated. The error
+ * did not originate from the hardware associated with this section.
+ */
+#define CPER_SEC_PROPAGATED 0x0040
/*
* Section type definitions, used in section_type field in struct
@@ -180,6 +185,10 @@ enum {
#define CPER_SEC_PROC_IPF \
UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \
0x80, 0xC7, 0x3C, 0x88, 0x81)
+/* Processor Specific: ARMv8 */
+#define CPER_SEC_PROC_ARMV8 \
+ UUID_LE(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \
+ 0x1D, 0x5D, 0x46, 0xB0)
/* Platform Memory */
#define CPER_SEC_PLATFORM_MEM \
UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \
@@ -255,6 +264,34 @@ enum {
#define CPER_PCIE_SLOT_SHIFT 3
+#define CPER_ARMV8_ERR_INFO_NUM_MASK 0x00000000000000FF
+#define CPER_ARMV8_CTX_INFO_NUM_MASK 0x0000000000FFFF00
+#define CPER_ARMV8_CTX_INFO_NUM_SHIFT 8
+
+#define CPER_ARMV8_VALID_MPIDR 0x00000001
+#define CPER_ARMV8_VALID_AFFINITY_LEVEL 0x00000002
+#define CPER_ARMV8_VALID_RUNNING_STATE 0x00000004
+#define CPER_ARMV8_VALID_VENDOR_INFO 0x00000008
+
+#define CPER_ARMV8_INFO_VALID_MULTI_ERR 0x0001
+#define CPER_ARMV8_INFO_VALID_FLAGS 0x0002
+#define CPER_ARMV8_INFO_VALID_ERR_INFO 0x0004
+#define CPER_ARMV8_INFO_VALID_VIRT_ADDR 0x0008
+#define CPER_ARMV8_INFO_VALID_PHYSICAL_ADDR 0x0010
+
+#define CPER_ARMV8_INFO_FLAGS_FIRST 0x0001
+#define CPER_ARMV8_INFO_FLAGS_LAST 0x0002
+#define CPER_ARMV8_INFO_FLAGS_PROPAGATED 0x0004
+
+#define CPER_AARCH64_CTX_LEN 368
+#define CPER_AARCH32_CTX_LEN 256
+
+#define CPER_ARMV8_CTX_TYPE_MASK 0x000000000000000F
+#define CPER_ARMV8_CTX_EL_MASK 0x0000000000000070
+#define CPER_ARMV8_CTX_NS_MASK 0x0000000000000080
+#define CPER_ARMV8_CTX_EL_SHIFT 4
+#define CPER_ARMV8_CTX_NS_SHIFT 7
+
#define acpi_hest_generic_data_error_length(gdata) \
(((struct acpi_hest_generic_data *)(gdata))->error_data_length)
#define acpi_hest_generic_data_size(gdata) \
@@ -352,6 +389,41 @@ struct cper_ia_proc_ctx {
__u64 mm_reg_addr;
};
+/* ARMv8 Processor Error Section */
+struct cper_sec_proc_armv8 {
+ __u32 validation_bits;
+ __u16 err_info_num; /* Number of Processor Error Info */
+ __u16 context_info_num; /* Number of Processor Context Info Records*/
+ __u32 section_length;
+ __u8 affinity_level;
+ __u8 reserved[3]; /* must be zero */
+ __u64 mpidr;
+ __u64 midr;
+ __u32 running_state; /* Bit 0 set - Processor running. PSCI = 0 */
+ __u32 psci_state;
+};
+
+/* ARMv8 Processor Error Information Structure */
+struct cper_armv8_err_info {
+ __u8 version;
+ __u8 length;
+ __u16 validation_bits;
+ __u8 type;
+ __u16 multiple_error;
+ __u8 flags;
+ __u64 error_info;
+ __u64 virt_fault_addr;
+ __u64 physical_fault_addr;
+};
+
+/* ARMv8 AARCH64 Processor Context Information Structure */
+struct cper_armv8_aarch64_ctx {
+ __u8 type_el_ns;
+ __u8 reserved[7]; /* must be zero */
+ __u8 gpr[288];
+ __u8 spr[68];
+};
+
/* Old Memory Error Section UEFI 2.1, 2.2 */
struct cper_sec_mem_err_old {
__u64 validation_bits;
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 04/10] arm64: exception: handle Synchronous External Abort
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (2 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 03/10] efi: parse ARMv8 processor error Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 05/10] acpi: apei: handle SEA notification type for ARMv8 Tyler Baicar
` (5 subsequent siblings)
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
SEA exceptions are often caused by an uncorrected hardware
error, and are handled when data abort and instruction abort
exception classes have specific values for their Fault Status
Code.
When SEA occurs, before killing the process, go through
the handlers registered in the notification list.
Update fault_info[] with specific SEA faults so that the
new SEA handler is used.
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
---
arch/arm64/include/asm/system_misc.h | 13 ++++++++
arch/arm64/mm/fault.c | 58 +++++++++++++++++++++++++++++-------
2 files changed, 61 insertions(+), 10 deletions(-)
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 57f110b..9040e1d 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -64,4 +64,17 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
#endif /* __ASSEMBLY__ */
+/*
+ * The functions below are used to register and unregister callbacks
+ * that are to be invoked when a Synchronous External Abort (SEA)
+ * occurs. An SEA is raised by certain fault status codes that have
+ * either data or instruction abort as the exception class, and
+ * callbacks may be registered to parse or handle such hardware errors.
+ *
+ * Registered callbacks are run in an interrupt/atomic context. They
+ * are not allowed to block or sleep.
+ */
+int register_synchronous_ext_abort_notifier(struct notifier_block *nb);
+void unregister_synchronous_ext_abort_notifier(struct notifier_block *nb);
+
#endif /* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 05d2bd7..fcc49f1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -39,6 +39,22 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
+/*
+ * GHES SEA handler code may register a notifier call here to
+ * handle HW error record passed from platform.
+ */
+static ATOMIC_NOTIFIER_HEAD(sea_handler_chain);
+
+int register_synchronous_ext_abort_notifier(struct notifier_block *nb)
+{
+ return atomic_notifier_chain_register(&sea_handler_chain, nb);
+}
+
+void unregister_synchronous_ext_abort_notifier(struct notifier_block *nb)
+{
+ atomic_notifier_chain_unregister(&sea_handler_chain, nb);
+}
+
static const char *fault_name(unsigned int esr);
#ifdef CONFIG_KPROBES
@@ -480,6 +496,28 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
return 1;
}
+/*
+ * This abort handler deals with Synchronous External Abort.
+ * It calls notifiers, and then returns "fault".
+ */
+static int do_synch_ext_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+ struct siginfo info;
+
+ atomic_notifier_call_chain(&sea_handler_chain, 0, NULL);
+
+ pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
+ fault_name(esr), esr, addr);
+
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = 0;
+ info.si_addr = (void __user *)addr;
+ arm64_notify_die("", regs, &info, esr);
+
+ return 0;
+}
+
static const struct fault_info {
int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
int sig;
@@ -502,22 +540,22 @@ static const struct fault_info {
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
- { do_bad, SIGBUS, 0, "synchronous external abort" },
+ { do_synch_ext_abort, SIGBUS, 0, "synchronous external abort" },
{ do_bad, SIGBUS, 0, "unknown 17" },
{ do_bad, SIGBUS, 0, "unknown 18" },
{ do_bad, SIGBUS, 0, "unknown 19" },
- { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous parity error" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 0 SEA (trans tbl walk)" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 1 SEA (trans tbl walk)" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 2 SEA (trans tbl walk)" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 3 SEA (trans tbl walk)" },
+ { do_synch_ext_abort, SIGBUS, 0, "synchronous parity or ECC err" },
{ do_bad, SIGBUS, 0, "unknown 25" },
{ do_bad, SIGBUS, 0, "unknown 26" },
{ do_bad, SIGBUS, 0, "unknown 27" },
- { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
- { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 0 synch parity error" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 1 synch parity error" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 2 synch parity error" },
+ { do_synch_ext_abort, SIGBUS, 0, "level 3 synch parity error" },
{ do_bad, SIGBUS, 0, "unknown 32" },
{ do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
{ do_bad, SIGBUS, 0, "unknown 34" },
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 05/10] acpi: apei: handle SEA notification type for ARMv8
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (3 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 04/10] arm64: exception: handle Synchronous External Abort Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 06/10] acpi: apei: panic OS with fatal error status block Tyler Baicar
` (4 subsequent siblings)
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
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 <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Naveen Kaje <nkaje@codeaurora.org>
---
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 b380c87..ae34349 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -53,6 +53,7 @@ config ARM64
select HANDLE_DOMAIN_IRQ
select HARDIRQS_SW_RESEND
select HAVE_ACPI_APEI if (ACPI && EFI)
+ select HAVE_ACPI_APEI_SEA if (ACPI && EFI)
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig
index b0140c8..fb99c1c 100644
--- a/drivers/acpi/apei/Kconfig
+++ b/drivers/acpi/apei/Kconfig
@@ -4,6 +4,21 @@ config HAVE_ACPI_APEI
config HAVE_ACPI_APEI_NMI
bool
+config HAVE_ACPI_APEI_SEA
+ bool "APEI Synchronous External Abort logging/recovering support"
+ depends on ARM64
+ 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 7610f08..cec201b 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: "
@@ -769,6 +773,62 @@ 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))
+ register_synchronous_ext_abort_notifier(&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))
+ unregister_synchronous_ext_abort_notifier(&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
@@ -1013,6 +1073,14 @@ 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",
@@ -1024,6 +1092,13 @@ 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);
@@ -1078,6 +1153,11 @@ 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;
@@ -1120,6 +1200,9 @@ 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 Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 06/10] acpi: apei: panic OS with fatal error status block
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (4 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 05/10] acpi: apei: handle SEA notification type for ARMv8 Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 07/10] efi: print unrecognized CPER section Tyler Baicar
` (3 subsequent siblings)
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
From: "Jonathan (Zhixiong) Zhang" <zjzhang@codeaurora.org>
Even if an error status block's severity is fatal, the kernel does not
honor the severity level and panic.
With the firmware first model, the platform could inform the OS about a
fatal hardware error through the non-NMI GHES notification type. The OS
should panic when a hardware error record is received with this
severity.
Call panic() after CPER data in error status block is printed if
severity is fatal, before each error section is handled.
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
drivers/acpi/apei/ghes.c | 19 ++++++++++++++-----
1 file changed, 14 insertions(+), 5 deletions(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index cec201b..64e573d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -141,6 +141,8 @@ static unsigned long ghes_estatus_pool_size_request;
static struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE];
static atomic_t ghes_estatus_cache_alloced;
+static int ghes_panic_timeout __read_mostly = 30;
+
static int ghes_ioremap_init(void)
{
ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES,
@@ -694,6 +696,13 @@ static int ghes_do_read_ack(struct acpi_hest_generic_v2 *generic_v2)
return rc;
}
+static void __ghes_call_panic(void)
+{
+ if (panic_timeout == 0)
+ panic_timeout = ghes_panic_timeout;
+ panic("Fatal hardware error!");
+}
+
static int ghes_proc(struct ghes *ghes)
{
int rc;
@@ -705,6 +714,10 @@ static int ghes_proc(struct ghes *ghes)
if (ghes_print_estatus(NULL, ghes->generic, ghes->estatus))
ghes_estatus_cache_add(ghes->generic, ghes->estatus);
}
+ if (ghes_severity(ghes->estatus->error_severity) >= GHES_SEV_PANIC) {
+ __ghes_call_panic();
+ }
+
ghes_do_proc(ghes, ghes->estatus);
if (HEST_TYPE_GENERIC_V2(ghes)) {
@@ -849,8 +862,6 @@ static atomic_t ghes_in_nmi = ATOMIC_INIT(0);
static LIST_HEAD(ghes_nmi);
-static int ghes_panic_timeout __read_mostly = 30;
-
static void ghes_proc_in_irq(struct irq_work *irq_work)
{
struct llist_node *llnode, *next;
@@ -943,9 +954,7 @@ static void __ghes_panic(struct ghes *ghes)
__ghes_print_estatus(KERN_EMERG, ghes->generic, ghes->estatus);
/* reboot to log the error! */
- if (panic_timeout == 0)
- panic_timeout = ghes_panic_timeout;
- panic("Fatal hardware error!");
+ __ghes_call_panic();
}
static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 07/10] efi: print unrecognized CPER section
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (5 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 06/10] acpi: apei: panic OS with fatal error status block Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 08/10] ras: acpi / apei: generate trace event for " Tyler Baicar
` (2 subsequent siblings)
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
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 instance, 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
Signed-off-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
drivers/firmware/efi/cper.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 8264eed..866a623 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -593,8 +593,16 @@ static void cper_estatus_print_section(
cper_print_proc_armv8(newpfx, armv8_err);
else
goto err_section_too_small;
- } else
- printk("%s""section type: unknown, %pUl\n", newpfx, sec_type);
+ } else {
+ const void *unknown_err;
+
+ unknown_err = acpi_hest_generic_data_payload(gdata);
+ printk("%ssection type: %pUl\n", newpfx, sec_type);
+ printk("%ssection length: %d\n", newpfx,
+ gdata->error_data_length);
+ print_hex_dump(newpfx, "", DUMP_PREFIX_OFFSET, 16, 4,
+ unknown_err, gdata->error_data_length, 0);
+ }
return;
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 08/10] ras: acpi / apei: generate trace event for unrecognized CPER section
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (6 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 07/10] efi: print unrecognized CPER section Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 09/10] trace, ras: add ARM processor error trace event Tyler Baicar
2016-10-21 17:30 ` [PATCH V4 10/10] arm64: KVM: add guest SEA support Tyler Baicar
9 siblings, 0 replies; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal, astone, harba, hanjun.guo
Cc: Tyler Baicar
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>
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
drivers/acpi/apei/ghes.c | 16 +++++++++++++++-
drivers/ras/ras.c | 1 +
include/ras/ras_event.h | 45 +++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 61 insertions(+), 1 deletion(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 64e573d..b1a1edb 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -49,6 +49,7 @@
#include <acpi/ghes.h>
#include <acpi/apei.h>
#include <asm/tlbflush.h>
+#include <ras/ras_event.h>
#ifdef CONFIG_HAVE_ACPI_APEI_SEA
#include <asm/system_misc.h>
@@ -457,12 +458,19 @@ 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 = &NULL_UUID_LE;
+ char *fru_text = "";
sev = ghes_severity(estatus->error_severity);
apei_estatus_for_each_section(estatus, gdata) {
sec_sev = ghes_severity(gdata->error_severity);
sec_type = *(uuid_le *)gdata->section_type;
+ 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;
+
if (!uuid_le_cmp(sec_type,
CPER_SEC_PLATFORM_MEM)) {
struct cper_sec_mem_err *mem_err;
@@ -474,7 +482,7 @@ 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;
@@ -507,6 +515,12 @@ static void ghes_do_proc(struct ghes *ghes,
}
#endif
+ else {
+ void *unknown_err = acpi_hest_generic_data_payload(gdata);
+ trace_unknown_sec_event(&sec_type,
+ fru_id, fru_text, sec_sev,
+ unknown_err, gdata->error_data_length);
+ }
}
}
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index b67dd36..fb2500b 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(unknown_sec_event);
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 1791a12..5861b6f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -162,6 +162,51 @@ TRACE_EVENT(mc_event,
);
/*
+ * Unknown Section 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(unknown_sec_event,
+
+ TP_PROTO(const uuid_le *sec_type,
+ const uuid_le *fru_id,
+ const char *fru_text,
+ const 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
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH V4 09/10] trace, ras: add ARM processor error trace event
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (7 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 08/10] ras: acpi / apei: generate trace event for " Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-21 20:34 ` Steven Rostedt
2016-10-21 17:30 ` [PATCH V4 10/10] arm64: KVM: add guest SEA support Tyler Baicar
9 siblings, 1 reply; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal
Cc: Tyler Baicar
Currently there are trace events for the various RAS
errors with the exception of ARM processor type errors.
Add a new trace event for such errors so that the user
will know when they occur. These trace events are
consistent with the ARM processor error section type
defined in UEFI 2.6 spec section N.2.4.4.
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
drivers/acpi/apei/ghes.c | 9 +++++++-
drivers/firmware/efi/cper.c | 1 +
drivers/ras/ras.c | 1 +
include/ras/ras_event.h | 55 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 65 insertions(+), 1 deletion(-)
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index b1a1edb..ae6dedb 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -515,7 +515,14 @@ static void ghes_do_proc(struct ghes *ghes,
}
#endif
- else {
+ else if (!uuid_le_cmp(sec_type, CPER_SEC_PROC_ARMV8)) {
+ struct cper_sec_proc_armv8 *armv8_err;
+ struct cper_armv8_err_info *err_info;
+
+ armv8_err = acpi_hest_generic_data_payload(gdata);
+ err_info = (void *)(armv8_err +1);
+ trace_arm_event(armv8_err, err_info);
+ } else {
void *unknown_err = acpi_hest_generic_data_payload(gdata);
trace_unknown_sec_event(&sec_type,
fru_id, fru_text, sec_sev,
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 866a623..3a1a867 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -35,6 +35,7 @@
#include <linux/printk.h>
#include <linux/bcd.h>
#include <acpi/ghes.h>
+#include <ras/ras_event.h>
#define INDENT_SP " "
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index fb2500b..8ba5a94 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -28,3 +28,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
#endif
EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
EXPORT_TRACEPOINT_SYMBOL_GPL(unknown_sec_event);
+EXPORT_TRACEPOINT_SYMBOL_GPL(arm_event);
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 5861b6f..0060bba 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -162,6 +162,61 @@ TRACE_EVENT(mc_event,
);
/*
+ * ARM Processor Events Report
+ *
+ * This event is generated when hardware detects an ARM processor error
+ * has occurred. UEFI 2.6 spec section N.2.4.4.
+ */
+TRACE_EVENT(arm_event,
+
+ TP_PROTO(const struct cper_sec_proc_armv8 *proc,
+ struct cper_armv8_err_info *err_info),
+
+ TP_ARGS(proc, err_info),
+
+ TP_STRUCT__entry(
+ __field(u64, mpidr)
+ __field(u64, midr)
+ __field(u64, info)
+ __field(u64, virt_fault_addr)
+ __field(u64, phys_fault_addr)
+ __field(u32, running_state)
+ __field(u32, psci_state)
+ __field(u16, err_count)
+ __field(u8, affinity)
+ __field(u8, version)
+ __field(u8, type)
+ __field(u8, flags)
+ ),
+
+ TP_fast_assign(
+ __entry->affinity = proc->affinity_level;
+ __entry->mpidr = proc->mpidr;
+ __entry->midr = proc->midr;
+ __entry->running_state = proc->running_state;
+ __entry->psci_state = proc->psci_state;
+ __entry->version = err_info->version;
+ __entry->type = err_info->type;
+ __entry->err_count = err_info->multiple_error;
+ __entry->flags = err_info->flags;
+ __entry->info = err_info->error_info;
+ __entry->virt_fault_addr = err_info->virt_fault_addr;
+ __entry->phys_fault_addr = err_info->physical_fault_addr;
+ ),
+
+ TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
+ "running state: %d; PSCI state: %d; version: %d; type: %d; "
+ "error count: 0x%04x; flags: 0x%02x; info: %016llx; "
+ "virtual fault address: %016llx; "
+ "physical fault address: %016llx",
+ __entry->affinity, __entry->mpidr, __entry->midr,
+ __entry->running_state, __entry->psci_state, __entry->version,
+ __entry->type, __entry->err_count, __entry->flags,
+ __entry->info, __entry->virt_fault_addr,
+ __entry->phys_fault_addr)
+);
+
+/*
* Unknown Section Report
*
* This event is generated when hardware detected a hardware
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH V4 09/10] trace, ras: add ARM processor error trace event
2016-10-21 17:30 ` [PATCH V4 09/10] trace, ras: add ARM processor error trace event Tyler Baicar
@ 2016-10-21 20:34 ` Steven Rostedt
2016-10-24 17:21 ` Baicar, Tyler
0 siblings, 1 reply; 20+ messages in thread
From: Steven Rostedt @ 2016-10-21 20:34 UTC (permalink / raw)
To: Tyler Baicar
Cc: linux-efi, kvm, matt, catalin.marinas, will.deacon, robert.moore,
paul.gortmaker, lv.zheng, kvmarm, fu.wei, zjzhang, linux,
linux-acpi, eun.taik.lee, shijie.huang, lenb, harba,
marc.zyngier, punit.agrawal, tomasz.nowicki, nkaje,
sandeepa.s.prabhu, linux-arm-kernel, rjw, rruigrok, linux-kernel,
astone, hanjun.guo, pbonzini, akpm, bristot
On Fri, 21 Oct 2016 11:30:12 -0600
Tyler Baicar <tbaicar@codeaurora.org> wrote:
> Currently there are trace events for the various RAS
> errors with the exception of ARM processor type errors.
> Add a new trace event for such errors so that the user
> will know when they occur. These trace events are
> consistent with the ARM processor error section type
> defined in UEFI 2.6 spec section N.2.4.4.
>
> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Tracing part looks fine to me.
Acked-by: Steven Rostedt <rostedt@goodmis.org>
-- Steve
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH V4 09/10] trace, ras: add ARM processor error trace event
2016-10-21 20:34 ` Steven Rostedt
@ 2016-10-24 17:21 ` Baicar, Tyler
0 siblings, 0 replies; 20+ messages in thread
From: Baicar, Tyler @ 2016-10-24 17:21 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-efi, kvm, matt, catalin.marinas, will.deacon, robert.moore,
paul.gortmaker, lv.zheng, kvmarm, fu.wei, zjzhang, linux,
linux-acpi, eun.taik.lee, shijie.huang, lenb, harba,
marc.zyngier, punit.agrawal, tomasz.nowicki, nkaje,
sandeepa.s.prabhu, linux-arm-kernel, rjw, rruigrok, linux-kernel,
astone, hanjun.guo, pbonzini, akpm, bristot
On 10/21/2016 2:34 PM, Steven Rostedt wrote:
> On Fri, 21 Oct 2016 11:30:12 -0600
> Tyler Baicar <tbaicar@codeaurora.org> wrote:
>
>> Currently there are trace events for the various RAS
>> errors with the exception of ARM processor type errors.
>> Add a new trace event for such errors so that the user
>> will know when they occur. These trace events are
>> consistent with the ARM processor error section type
>> defined in UEFI 2.6 spec section N.2.4.4.
>>
>> Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
> Tracing part looks fine to me.
>
> Acked-by: Steven Rostedt <rostedt@goodmis.org>
>
> -- Steve
Thank you Steve!
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH V4 10/10] arm64: KVM: add guest SEA support
2016-10-21 17:30 [PATCH V4 00/10] Add UEFI 2.6 and ACPI 6.1 updates for RAS on ARM64 Tyler Baicar
` (8 preceding siblings ...)
2016-10-21 17:30 ` [PATCH V4 09/10] trace, ras: add ARM processor error trace event Tyler Baicar
@ 2016-10-21 17:30 ` Tyler Baicar
2016-10-31 10:02 ` Russell King - ARM Linux
9 siblings, 1 reply; 20+ messages in thread
From: Tyler Baicar @ 2016-10-21 17:30 UTC (permalink / raw)
To: marc.zyngier, pbonzini, rkrcmar, linux, catalin.marinas,
will.deacon, rjw, lenb, matt, robert.moore, lv.zheng, nkaje,
zjzhang, mark.rutland, james.morse, akpm, eun.taik.lee,
sandeepa.s.prabhu, shijie.huang, rruigrok, paul.gortmaker,
tomasz.nowicki, fu.wei, rostedt, bristot, linux-arm-kernel,
kvmarm, kvm, linux-kernel, linux-acpi, linux-efi, Suzuki.Poulose,
punit.agrawal
Cc: Tyler Baicar
Currently external aborts are unsupported by the guest abort
handling. Add handling for SEAs so that the host kernel reports
SEAs which occur in the guest kernel.
Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
---
arch/arm/include/asm/kvm_arm.h | 1 +
arch/arm/include/asm/system_misc.h | 5 +++++
arch/arm/kvm/mmu.c | 18 ++++++++++++++++--
arch/arm64/include/asm/kvm_arm.h | 1 +
arch/arm64/include/asm/system_misc.h | 2 ++
arch/arm64/mm/fault.c | 13 +++++++++++++
6 files changed, 38 insertions(+), 2 deletions(-)
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index e22089f..33a77509 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -187,6 +187,7 @@
#define FSC_FAULT (0x04)
#define FSC_ACCESS (0x08)
#define FSC_PERM (0x0c)
+#define FSC_EXTABT (0x10)
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~0xf)
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index a3d61ad..86e1faa 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -24,4 +24,9 @@ extern unsigned int user_debug;
#endif /* !__ASSEMBLY__ */
+inline int handle_guest_sea(unsigned long addr, unsigned int esr)
+{
+ return -1;
+}
+
#endif /* __ASM_ARM_SYSTEM_MISC_H */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index e9a5c0e..1152966 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -29,6 +29,7 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/virt.h>
+#include <asm/system_misc.h>
#include "trace.h"
@@ -1441,8 +1442,21 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
/* Check the stage-2 fault is trans. fault or write fault */
fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
- if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
- fault_status != FSC_ACCESS) {
+
+ /* The host kernel will handle the synchronous external abort. There
+ * is no need to pass the error into the guest.
+ */
+ if (fault_status == FSC_EXTABT) {
+ if(handle_guest_sea((unsigned long)fault_ipa,
+ kvm_vcpu_get_hsr(vcpu))) {
+ kvm_err("Failed to handle guest SEA, FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+ kvm_vcpu_trap_get_class(vcpu),
+ (unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+ (unsigned long)kvm_vcpu_get_hsr(vcpu));
+ return -EFAULT;
+ }
+ } else if (fault_status != FSC_FAULT && fault_status != FSC_PERM &&
+ fault_status != FSC_ACCESS) {
kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
kvm_vcpu_trap_get_class(vcpu),
(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 4b5c977..be0efb6 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -201,6 +201,7 @@
#define FSC_FAULT ESR_ELx_FSC_FAULT
#define FSC_ACCESS ESR_ELx_FSC_ACCESS
#define FSC_PERM ESR_ELx_FSC_PERM
+#define FSC_EXTABT ESR_ELx_FSC_EXTABT
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 9040e1d..3a142a5 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -77,4 +77,6 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
int register_synchronous_ext_abort_notifier(struct notifier_block *nb);
void unregister_synchronous_ext_abort_notifier(struct notifier_block *nb);
+int handle_guest_sea(unsigned long addr, unsigned int esr);
+
#endif /* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index fcc49f1..691399e 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -597,6 +597,19 @@ static const char *fault_name(unsigned int esr)
}
/*
+ * Handle Synchronous External Aborts that occur in a guest kernel.
+ */
+int handle_guest_sea(unsigned long addr, unsigned int esr)
+{
+ atomic_notifier_call_chain(&sea_handler_chain, 0, NULL);
+
+ pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
+ fault_name(esr), esr, addr);
+
+ return 0;
+}
+
+/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH V4 10/10] arm64: KVM: add guest SEA support
2016-10-21 17:30 ` [PATCH V4 10/10] arm64: KVM: add guest SEA support Tyler Baicar
@ 2016-10-31 10:02 ` Russell King - ARM Linux
2016-10-31 22:36 ` Baicar, Tyler
0 siblings, 1 reply; 20+ messages in thread
From: Russell King - ARM Linux @ 2016-10-31 10:02 UTC (permalink / raw)
To: Tyler Baicar
Cc: linux-efi, kvm, matt, catalin.marinas, will.deacon, linux-kernel,
paul.gortmaker, lv.zheng, kvmarm, fu.wei, zjzhang, robert.moore,
linux-acpi, eun.taik.lee, shijie.huang, lenb, harba,
marc.zyngier, punit.agrawal, tomasz.nowicki, nkaje, rostedt,
sandeepa.s.prabhu, linux-arm-kernel, rjw, rruigrok, astone,
hanjun.guo, pbonzini, akpm, bristot
The subject line on this patch is misleading - it's not only ARM64
specific...
On Fri, Oct 21, 2016 at 11:30:13AM -0600, Tyler Baicar wrote:
> diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
> index a3d61ad..86e1faa 100644
> --- a/arch/arm/include/asm/system_misc.h
> +++ b/arch/arm/include/asm/system_misc.h
> @@ -24,4 +24,9 @@ extern unsigned int user_debug;
>
> #endif /* !__ASSEMBLY__ */
>
> +inline int handle_guest_sea(unsigned long addr, unsigned int esr)
This needs to be static.
> +{
> + return -1;
> +}
> +
> #endif /* __ASM_ARM_SYSTEM_MISC_H */
--
RMK's Patch system: http://www.armlinux.org.uk/developer/patches/
FTTC broadband for 0.8mile line: currently at 9.6Mbps down 400kbps up
according to speedtest.net.
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH V4 10/10] arm64: KVM: add guest SEA support
2016-10-31 10:02 ` Russell King - ARM Linux
@ 2016-10-31 22:36 ` Baicar, Tyler
[not found] ` <85443ee1-9981-c7e8-fe88-a3aac48c3e80-sgV2jX0FEOL9JmXXK+q4OQ@public.gmane.org>
0 siblings, 1 reply; 20+ messages in thread
From: Baicar, Tyler @ 2016-10-31 22:36 UTC (permalink / raw)
To: Russell King - ARM Linux
Cc: marc.zyngier, pbonzini, rkrcmar, catalin.marinas, will.deacon,
rjw, lenb, matt, robert.moore, lv.zheng, nkaje, zjzhang,
mark.rutland, james.morse, akpm, eun.taik.lee, sandeepa.s.prabhu,
shijie.huang, rruigrok, paul.gortmaker, tomasz.nowicki, fu.wei,
rostedt, bristot, linux-arm-kernel, kvmarm, kvm, linux-kernel,
linux-acpi, linux-efi, Suzuki.Poulose, punit.agrawal, astone
Hello Russell,
On 10/31/2016 4:02 AM, Russell King - ARM Linux wrote:
> The subject line on this patch is misleading - it's not only ARM64
> specific...
Thank you for the feedback!
I only put ARM64 in the subject line because this patch only really adds
guest SEA support for the ARM64 KVM code. The ARM code had to be edited
since both the ARM and ARM64 KVM code use arch/arm/kvm/mmu.c. I can
change the subject line to "arm/arm64: KVM: add guest SEA support" if
you think that is better.
> On Fri, Oct 21, 2016 at 11:30:13AM -0600, Tyler Baicar wrote:
>> diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
>> index a3d61ad..86e1faa 100644
>> --- a/arch/arm/include/asm/system_misc.h
>> +++ b/arch/arm/include/asm/system_misc.h
>> @@ -24,4 +24,9 @@ extern unsigned int user_debug;
>>
>> #endif /* !__ASSEMBLY__ */
>>
>> +inline int handle_guest_sea(unsigned long addr, unsigned int esr)
> This needs to be static.
I'll make this static.
Thanks,
Tyler
>> +{
>> + return -1;
>> +}
>> +
>> #endif /* __ASM_ARM_SYSTEM_MISC_H */
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project.
^ permalink raw reply [flat|nested] 20+ messages in thread