RAS: Report all ARM processor CPER information to userspace
The ARM processor CPER record was added at UEFI 2.6, and hasn't
any changes up to UEFI 2.10 on its struct.
Yet, the original arm_event trace code added on changeset
e9279e83ad1f ("trace, ras: add ARM processor error trace event") is
incomplete, as it only traces some fields of UAPI 2.6 table N.16,
not exporting at all any information from tables N.17 to N.29 of
the record.
This is not enough for user to take appropriate action or to log
what exactly happened.
According to UEFI_2_9 specification chapter N2.4.4, the ARM processor
error section includes:
- several (ERR_INFO_NUM) ARM processor error information structures
(Tables N.17 to N.20);
- several (CONTEXT_INFO_NUM) ARM processor context information
structures (Tables N.21 to N.29);
- several vendor specific error information structures. The
size is given by Section Length minus the size of the other
fields.
In addition to those data, it also exports two fields that are
parsed by the GHES driver when firmware reports it, e. g.:
- error severity
- cpu logical index
Report all of these information to userspace via trace uAPI, So that
userspace can properly record the error and take decisions related
to cpu core isolation according to error severity and other info.
After this patch, all the data from ARM Processor record from table
N.16 is sent to userspace:
====================================== =============================
UEFI field on table N.16 ARM Processor trace event
====================================== =============================
Validation handled when filling data for
affinity MPIDR and running
state.
ERR_INFO_NUM pei_len field
CONTEXT_INFO_NUM ctx_len field
Section Length indirectly reported when
handling vendor-specific data
size
Error affinity level affinity
MPIDR_EL1 mpidr field
MIDR_EL1 midr field
Running State running_state field
PSCI State psci_state field
Processor Error Information Structure reported as hex values via
__print_hex()
Processor Context reported as hex values via
__print_hex()
Vendor Specific Error Info reported as hex values via
__print_hex()
====================================== =============================
It should be noticed that decoding of tables N.17 to N.29, if needed,
will be handled on userspace. That gives more flexibility, as there
won't be any need to flood the Kernel with micro-architecture specific
error decoding (as found at vendor-specific field of the record).
Also, decoding the other fields require a complex logic, and should
be done for each of the several values inside the record field.
So, let userspace daemons like rasdaemon to decode them, parsing such
tables and having vendor-specific micro-architecture-specific decoders.
Link: https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#arm-processor-error-section
Fixes: e9279e83ad1f ("trace, ras: add ARM processor error trace event")
[mchehab: modified the description to properly describe the change]
Signed-off-by: Shengwei Luo <luoshengwei@huawei.com>
Signed-off-by: Jason Tian <jason@os.amperecomputing.com>
Signed-off-by: Daniel Ferguson <danielf@os.amperecomputing.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0beb8d9..87e87d7 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -540,9 +540,8 @@ static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
int sec_sev, i;
char *p;
- log_arm_hw_error(err);
-
sec_sev = ghes_severity(gdata->error_severity);
+ log_arm_hw_error(err, sec_sev);
if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE)
return false;
diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
index 249dce2..3e2beed 100644
--- a/drivers/ras/ras.c
+++ b/drivers/ras/ras.c
@@ -53,9 +53,51 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id,
}
#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-void log_arm_hw_error(struct cper_sec_proc_arm *err)
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev)
{
- trace_arm_event(err);
+ u32 pei_len;
+ u32 ctx_len = 0;
+ s32 vsei_len;
+ u8 *pei_err;
+ u8 *ctx_err;
+ u8 *ven_err_data;
+ struct cper_arm_err_info *err_info;
+ struct cper_arm_ctx_info *ctx_info;
+ int n, sz;
+ int cpu;
+
+ pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
+ pei_err = (u8 *)err + sizeof(struct cper_sec_proc_arm);
+
+ err_info = (struct cper_arm_err_info *)(err + 1);
+ ctx_info = (struct cper_arm_ctx_info *)(err_info + err->err_info_num);
+ ctx_err = (u8 *)ctx_info;
+ for (n = 0; n < err->context_info_num; n++) {
+ sz = sizeof(struct cper_arm_ctx_info) + ctx_info->size;
+ ctx_info = (struct cper_arm_ctx_info *)((long)ctx_info + sz);
+ ctx_len += sz;
+ }
+
+ vsei_len = err->section_length - (sizeof(struct cper_sec_proc_arm) +
+ pei_len + ctx_len);
+ if (vsei_len < 0) {
+ pr_warn(FW_BUG
+ "section length: %d\n", err->section_length);
+ pr_warn(FW_BUG
+ "section length is too small\n");
+ pr_warn(FW_BUG
+ "firmware-generated error record is incorrect\n");
+ vsei_len = 0;
+ }
+ ven_err_data = (u8 *)ctx_info;
+
+ cpu = GET_LOGICAL_INDEX(err->mpidr);
+ /* when return value is invalid, set cpu index to -1 */
+ if (cpu < 0)
+ cpu = -1;
+
+ trace_arm_event(err, pei_err, pei_len, ctx_err, ctx_len,
+ ven_err_data, (u32)vsei_len, sev, cpu);
}
#endif
diff --git a/include/linux/ras.h b/include/linux/ras.h
index eb36827..402c944 100644
--- a/include/linux/ras.h
+++ b/include/linux/ras.h
@@ -25,7 +25,7 @@ void log_non_standard_event(const guid_t *sec_type,
const guid_t *fru_id, const char *fru_text,
const u8 sev, const u8 *err, const u32 len);
#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
-void log_arm_hw_error(struct cper_sec_proc_arm *err);
+void log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev);
#endif
#else
static inline void
@@ -34,7 +34,7 @@ log_non_standard_event(const guid_t *sec_type,
const u8 sev, const u8 *err, const u32 len)
{ return; }
static inline void
-log_arm_hw_error(struct cper_sec_proc_arm *err) { return; }
+log_arm_hw_error(struct cper_sec_proc_arm *err, const u8 sev) { return; }
#endif
struct atl_err {
@@ -53,5 +53,14 @@ static inline void amd_retire_dram_row(struct atl_err *err) { }
static inline unsigned long
amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; }
#endif /* CONFIG_AMD_ATL */
-
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+#include <asm/smp_plat.h>
+/*
+ * Include ARM specific SMP header which provides a function mapping mpidr to
+ * cpu logical index.
+ */
+#define GET_LOGICAL_INDEX(mpidr) get_logical_index(mpidr & MPIDR_HWID_BITMASK)
+#else
+#define GET_LOGICAL_INDEX(mpidr) -EINVAL
+#endif /* CONFIG_ARM || CONFIG_ARM64 */
#endif /* __RAS_H__ */
diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
index 7c47151..ce5214f 100644
--- a/include/ras/ras_event.h
+++ b/include/ras/ras_event.h
@@ -168,11 +168,24 @@ TRACE_EVENT(mc_event,
* This event is generated when hardware detects an ARM processor error
* has occurred. UEFI 2.6 spec section N.2.4.4.
*/
+#define APEIL "ARM Processor Err Info data len"
+#define APEID "ARM Processor Err Info raw data"
+#define APECIL "ARM Processor Err Context Info data len"
+#define APECID "ARM Processor Err Context Info raw data"
+#define VSEIL "Vendor Specific Err Info data len"
+#define VSEID "Vendor Specific Err Info raw data"
TRACE_EVENT(arm_event,
- TP_PROTO(const struct cper_sec_proc_arm *proc),
+ TP_PROTO(const struct cper_sec_proc_arm *proc, const u8 *pei_err,
+ const u32 pei_len,
+ const u8 *ctx_err,
+ const u32 ctx_len,
+ const u8 *oem,
+ const u32 oem_len,
+ u8 sev,
+ int cpu),
- TP_ARGS(proc),
+ TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu),
TP_STRUCT__entry(
__field(u64, mpidr)
@@ -180,6 +193,14 @@ TRACE_EVENT(arm_event,
__field(u32, running_state)
__field(u32, psci_state)
__field(u8, affinity)
+ __field(u32, pei_len)
+ __dynamic_array(u8, buf, pei_len)
+ __field(u32, ctx_len)
+ __dynamic_array(u8, buf1, ctx_len)
+ __field(u32, oem_len)
+ __dynamic_array(u8, buf2, oem_len)
+ __field(u8, sev)
+ __field(int, cpu)
),
TP_fast_assign(
@@ -199,12 +220,29 @@ TRACE_EVENT(arm_event,
__entry->running_state = ~0;
__entry->psci_state = ~0;
}
+ __entry->pei_len = pei_len;
+ memcpy(__get_dynamic_array(buf), pei_err, pei_len);
+ __entry->ctx_len = ctx_len;
+ memcpy(__get_dynamic_array(buf1), ctx_err, ctx_len);
+ __entry->oem_len = oem_len;
+ memcpy(__get_dynamic_array(buf2), oem, oem_len);
+ __entry->sev = sev;
+ __entry->cpu = cpu;
),
- TP_printk("affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
- "running state: %d; PSCI state: %d",
+ TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
+ "running state: %d; PSCI state: %d; "
+ "%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s",
+ __entry->cpu,
+ __entry->sev,
__entry->affinity, __entry->mpidr, __entry->midr,
- __entry->running_state, __entry->psci_state)
+ __entry->running_state, __entry->psci_state,
+ APEIL, __entry->pei_len, APEID,
+ __print_hex(__get_dynamic_array(buf), __entry->pei_len),
+ APECIL, __entry->ctx_len, APECID,
+ __print_hex(__get_dynamic_array(buf1), __entry->ctx_len),
+ VSEIL, __entry->oem_len, VSEID,
+ __print_hex(__get_dynamic_array(buf2), __entry->oem_len))
);
/*
