[PATCH v5] trace: ras: add ARM processor error information trace event

[Steven Rostedt]

On Sat, 24 Jun 2017 11:38:23 +0800
Xie XiuQi <xiexiuqi at huawei.com> wrote:

> diff --git a/include/linux/cper.h b/include/linux/cper.h
> index 4c671fc..17546bf 100644
> --- a/include/linux/cper.h
> +++ b/include/linux/cper.h
> @@ -275,6 +275,11 @@ enum {
>  #define CPER_ARM_INFO_FLAGS_PROPAGATED		BIT(2)
>  #define CPER_ARM_INFO_FLAGS_OVERFLOW		BIT(3)
>  
> +#define CPER_ARM_INFO_TYPE_CACHE		0
> +#define CPER_ARM_INFO_TYPE_TLB			1
> +#define CPER_ARM_INFO_TYPE_BUS			2
> +#define CPER_ARM_INFO_TYPE_UARCH		3
> +
>  /*
>   * All tables and structs must be byte-packed to match CPER
>   * specification, since the tables are provided by the system BIOS
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index 429f46f..dd91ba8 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -206,6 +206,85 @@
>  		  __entry->running_state, __entry->psci_state)
>  );
>  
> +#define ARM_PROC_ERR_TYPE	\
> +	EM ( CPER_ARM_INFO_TYPE_CACHE, "cache error" )	\
> +	EM ( CPER_ARM_INFO_TYPE_TLB,  "TLB error" )	\
> +	EM ( CPER_ARM_INFO_TYPE_BUS, "bus error" )	\
> +	EMe ( CPER_ARM_INFO_TYPE_UARCH, "micro-architectural error" )

These are all defines. As the name suggests, the TRACE_DEFINE_ENUM() is
for use with enums, not defines. You can nuke this part.

> +
> +/*
> + * First define the enums in MM_ACTION_RESULT to be exported to userspace
> + * via TRACE_DEFINE_ENUM().
> + */
> +#undef EM
> +#undef EMe
> +#define EM(a, b) TRACE_DEFINE_ENUM(a);
> +#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
> +
> +ARM_PROC_ERR_TYPE
> +
> +/*
> + * Now redefine the EM() and EMe() macros to map the enums to the strings
> + * that will be printed in the output.
> + */
> +#undef EM
> +#undef EMe
> +#define EM(a, b)		{ a, b },
> +#define EMe(a, b)	{ a, b }

All the EM* and friends above are not needed. The macro below will
translate into numbers not names in the format files in tracefs.

-- Steve


> +
> +#define show_proc_err_flags(flags) __print_flags(flags, "|",			\
> +	{ CPER_ARM_INFO_FLAGS_FIRST,		"First error captured" },	\
> +	{ CPER_ARM_INFO_FLAGS_LAST,		"Last error captured" },	\
> +	{ CPER_ARM_INFO_FLAGS_PROPAGATED,	"Propagated" },			\
> +	{ CPER_ARM_INFO_FLAGS_OVERFLOW,		"Overflow" })
> +
> +TRACE_EVENT(arm_err_info_event,
> +
> +	TP_PROTO(const struct cper_arm_err_info *err),
> +
> +	TP_ARGS(err),
> +
> +	TP_STRUCT__entry(
> +		__field(u8, type)
> +		__field(u8, flags)
> +		__field(u16, multiple_error)
> +		__field(u64, error_info)
> +		__field(u64, virt_fault_addr)
> +		__field(u64, physical_fault_addr)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->type = err->type;
> +		memset(&__entry->flags, 0,
> +			sizeof(*__entry) - offsetof(typeof(*__entry), flags));
> +		__entry->multiple_error = ~0;
> +
> +		if (err->validation_bits & CPER_ARM_INFO_VALID_MULTI_ERR)
> +			__entry->multiple_error = err->multiple_error;
> +
> +		if (err->validation_bits & CPER_ARM_INFO_VALID_FLAGS)
> +			__entry->flags = err->flags;
> +
> +		if (err->validation_bits & CPER_ARM_INFO_VALID_ERR_INFO)
> +			__entry->error_info = err->error_info;
> +
> +		if (err->validation_bits & CPER_ARM_INFO_VALID_VIRT_ADDR)
> +			__entry->virt_fault_addr = err->virt_fault_addr;
> +
> +		if (err->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR)
> +			__entry->physical_fault_addr = err->physical_fault_addr;
> +	),
> +
> +	TP_printk("type: %s; count: %u; flags: %s;"
> +		  " error info: %016llx; virtual address: %016llx;"
> +		  " physical address: %016llx",
> +		  __print_symbolic(__entry->type, ARM_PROC_ERR_TYPE),
> +		  __entry->multiple_error,
> +		  show_proc_err_flags(__entry->flags),
> +		  __entry->error_info, __entry->virt_fault_addr,
> +		  __entry->physical_fault_addr)
> +);
> +
>  /*
>   * Non-Standard Section Report
>   *