The ARM processor CPER record was added in UEFI v2.6 and remained
unchanged up to v2.10.
Yet, the original arm_event trace code added by
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 any information from tables N.17 to N.29 of the record.
This is not enough for the user to be able to figure out what has
exactly happened or to take appropriate action.
According to the UEFI v2.9 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, 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 a the ARM tracepoint so
that userspace can properly record the error and take decisions related
to CPU core isolation according to error severity and other info.
The updated ARM trace event now contains the following fields:
====================================== =============================
UEFI field on table N.16 ARM Processor trace fields
====================================== =============================
Validation handled when filling data for
affinity MPIDR and running
state.
ERR_INFO_NUM pei_len
CONTEXT_INFO_NUM ctx_len
Section Length indirectly reported by
pei_len, ctx_len and oem_len
Error affinity level affinity
MPIDR_EL1 mpidr
MIDR_EL1 midr
Running State running_state
PSCI State psci_state
Processor Error Information Structure pei_err - count at pei_len
Processor Context ctx_err- count at ctx_len
Vendor Specific Error Info oem - count at oem_len
====================================== =============================
It should be noted that decoding of tables N.17 to N.29, if needed, will
be handled in userspace. That gives more flexibility, as there won't be
any need to flood the kernel with micro-architecture specific error
decoding.
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 decode them, parsing such tables and
having vendor-specific micro-architecture-specific decoders.
[mchehab: modified description, solved merge conflicts and fixed coding style]
Signed-off-by: Jason Tian <jason@os.amperecomputing.com>
Co-developed-by: Shengwei Luo <luoshengwei@huawei.com>
Signed-off-by: Shengwei Luo <luoshengwei@huawei.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Daniel Ferguson <danielf@os.amperecomputing.com> # rebased
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Fixes: e9279e83ad1f ("trace, ras: add ARM processor error trace event")
Link: https://uefi.org/specs/UEFI/2.10/Apx_N_Common_Platform_Error_Record.html#arm-processor-error-section
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
}
static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata,
- int sev, bool sync)
+ int sev, bool sync)
{
struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata);
int flags = sync ? MF_ACTION_REQUIRED : 0;
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;
arch_apei_report_mem_error(sev, mem_err);
queued = ghes_handle_memory_failure(gdata, sev, sync);
- }
- else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+ } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
ghes_handle_aer(gdata);
- }
- else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
+ } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
queued = ghes_handle_arm_hw_error(gdata, sev, sync);
} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
}
EXPORT_SYMBOL_GPL(log_non_standard_event);
-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);
+ struct cper_arm_err_info *err_info;
+ struct cper_arm_ctx_info *ctx_info;
+ u8 *ven_err_data;
+ u32 ctx_len = 0;
+ int n, sz, cpu;
+ s32 vsei_len;
+ u32 pei_len;
+ u8 *pei_err, *ctx_err;
+
+ pei_len = sizeof(struct cper_arm_err_info) * err->err_info_num;
+ pei_err = (u8 *)(err + 1);
+
+ 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);
+ 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);
}
static int __init ras_init(void)
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);
-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);
#else
static inline void
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 {
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__ */
* 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)
__field(u32, running_state)
__field(u32, psci_state)
__field(u8, affinity)
+ __field(u32, pei_len)
+ __dynamic_array(u8, pei_buf, pei_len)
+ __field(u32, ctx_len)
+ __dynamic_array(u8, ctx_buf, ctx_len)
+ __field(u32, oem_len)
+ __dynamic_array(u8, oem_buf, oem_len)
+ __field(u8, sev)
+ __field(int, cpu)
),
TP_fast_assign(
__entry->running_state = ~0;
__entry->psci_state = ~0;
}
+ __entry->pei_len = pei_len;
+ memcpy(__get_dynamic_array(pei_buf), pei_err, pei_len);
+ __entry->ctx_len = ctx_len;
+ memcpy(__get_dynamic_array(ctx_buf), ctx_err, ctx_len);
+ __entry->oem_len = oem_len;
+ memcpy(__get_dynamic_array(oem_buf), 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(pei_buf), __entry->pei_len),
+ APECIL, __entry->ctx_len, APECID,
+ __print_hex(__get_dynamic_array(ctx_buf), __entry->ctx_len),
+ VSEIL, __entry->oem_len, VSEID,
+ __print_hex(__get_dynamic_array(oem_buf), __entry->oem_len))
);
/*
gentwo / linux / .git / commitdiff