Add a trace event for hardware errors reported by the ARMv8 RAS extension registers. Signed-off-by: Tyler Baicar <baicar@xxxxxxxxxxxxxxxxxxxxxx> Signed-off-by: Ruidong Tian <tianruidong@xxxxxxxxxxxxxxxxx> --- drivers/acpi/arm64/aest.c | 2 + drivers/ras/aest/aest-core.c | 6 +++ drivers/ras/ras.c | 3 ++ include/ras/ras_event.h | 71 ++++++++++++++++++++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/drivers/acpi/arm64/aest.c b/drivers/acpi/arm64/aest.c index 312ddd5c15f5..adc12174f4e0 100644 --- a/drivers/acpi/arm64/aest.c +++ b/drivers/acpi/arm64/aest.c @@ -11,6 +11,8 @@ #include "init.h" +#include <ras/ras_event.h> + #undef pr_fmt #define pr_fmt(fmt) "ACPI AEST: " fmt diff --git a/drivers/ras/aest/aest-core.c b/drivers/ras/aest/aest-core.c index 0530880ded3e..e72df9a79b96 100644 --- a/drivers/ras/aest/aest-core.c +++ b/drivers/ras/aest/aest-core.c @@ -13,6 +13,8 @@ #include <linux/genalloc.h> #include <linux/ras.h> +#include <ras/ras_event.h> + #include "aest.h" DEFINE_PER_CPU(struct aest_device, percpu_adev); @@ -90,6 +92,10 @@ static void aest_print(struct aest_event *event) pr_err("%s ERR%dMISC3: 0x%llx\n", pfx_seq, index, regs->err_misc[3]); } + + trace_arm_ras_ext_event(event->type, event->id0, event->id1, + event->index, event->hid, &event->regs, + event->vendor_data, event->vendor_data_size); } static void aest_handle_memory_failure(u64 addr) diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index e5f23a8279c2..2a5a440e4c29 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -72,6 +72,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event); EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event); EXPORT_TRACEPOINT_SYMBOL_GPL(non_standard_event); EXPORT_TRACEPOINT_SYMBOL_GPL(arm_event); +#ifdef CONFIG_ARM64_RAS_EXTN +EXPORT_TRACEPOINT_SYMBOL_GPL(arm_ras_ext_event); +#endif static int __init parse_ras_param(char *str) { diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index e5f7ee0864e7..119e8c4e6d20 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -338,6 +338,77 @@ TRACE_EVENT(aer_event, "Not available") ); +/* + * ARM RAS Extension Events Report + * + * This event is generated when an error reported by the ARM RAS extension + * hardware is detected. + */ + +#ifdef CONFIG_ARM64_RAS_EXTN +#include <asm/ras.h> +TRACE_EVENT(arm_ras_ext_event, + + TP_PROTO(const u8 type, + const u32 id0, + const u32 id1, + const u32 index, + char *hid, + struct ras_ext_regs *regs, + const u8 *data, + const u32 len), + + TP_ARGS(type, id0, id1, index, hid, regs, data, len), + + TP_STRUCT__entry( + __field(u8, type) + __field(u32, id0) + __field(u32, id1) + __field(u32, index) + __field(char *, hid) + __field(u64, err_fr) + __field(u64, err_ctlr) + __field(u64, err_status) + __field(u64, err_addr) + __field(u64, err_misc0) + __field(u64, err_misc1) + __field(u64, err_misc2) + __field(u64, err_misc3) + __field(u32, len) + __dynamic_array(u8, buf, len) + ), + + TP_fast_assign( + __entry->type = type; + __entry->id0 = id0; + __entry->id1 = id1; + __entry->index = index; + __entry->hid = hid; + __entry->err_fr = regs->err_fr; + __entry->err_ctlr = regs->err_ctlr; + __entry->err_status = regs->err_status; + __entry->err_addr = regs->err_addr; + __entry->err_misc0 = regs->err_misc[0]; + __entry->err_misc1 = regs->err_misc[1]; + __entry->err_misc2 = regs->err_misc[2]; + __entry->err_misc3 = regs->err_misc[3]; + __entry->len = len; + memcpy(__get_dynamic_array(buf), data, len); + ), + + TP_printk("type: %d; id0: %d; id1: %d; index: %d; hid: %s; " + "ERR_FR: %llx; ERR_CTLR: %llx; ERR_STATUS: %llx; " + "ERR_ADDR: %llx; ERR_MISC0: %llx; ERR_MISC1: %llx; " + "ERR_MISC2: %llx; ERR_MISC3: %llx; data len:%d; raw data:%s", + __entry->type, __entry->id0, __entry->id1, __entry->index, + __entry->hid, __entry->err_fr, __entry->err_ctlr, + __entry->err_status, __entry->err_addr, __entry->err_misc0, + __entry->err_misc1, __entry->err_misc2, __entry->err_misc3, + __entry->len, + __print_hex(__get_dynamic_array(buf), __entry->len)) +); +#endif + /* * memory-failure recovery action result event * -- 2.33.1