Re: [RFC PATCH 7/8] EDAC, mce_amd: Add a simple tracepoint dumping a decoded string

[Steven Rostedt]

On Tue, 25 Jul 2017 17:46:00 +0200
Borislav Petkov <bp@xxxxxxxxx> wrote:

> From: Borislav Petkov <bp@xxxxxxx>
> 
> It is a single string which gets dynamically generated when the error
> gets decoded. Dump it to userspace through that tracepoint so that
> consumers can get the already decoded string and the kernel has the
> decoding functionality too, even if there are no userspace consumers.
> 
> Signed-off-by: Borislav Petkov <bp@xxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>

Acked-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>

-- Steve

> ---
>  drivers/edac/mce_amd.c  |  7 ++++++-
>  drivers/ras/ras.c       |  1 +
>  include/ras/ras_event.h | 16 ++++++++++++++++
>  3 files changed, 23 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
> index 1f5e9bb161f3..ce7e20ca6773 100644
> --- a/drivers/edac/mce_amd.c
> +++ b/drivers/edac/mce_amd.c
> @@ -1,6 +1,8 @@
>  #include <linux/seq_buf.h>
>  #include <linux/module.h>
>  #include <linux/slab.h>
> +#include <linux/ras.h>
> +#include <ras/ras_event.h>
>  
>  #include <asm/cpu.h>
>  
> @@ -1053,7 +1055,10 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
>   err_code:
>  	amd_decode_err_code(m->status & 0xffff);
>  
> -	pr_emerg("%.*s\n", (int)sb.len, sb.buffer);
> +	if (ras_userspace_consumers())
> +		trace_mce_decode(sb.buffer);
> +	else
> +		pr_emerg("%.*s\n", (int)sb.len, sb.buffer);
>  
>  	seq_buf_clear_buf(&sb);
>  
> diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
> index 5429d3795732..a09e39b3f711 100644
> --- a/drivers/ras/ras.c
> +++ b/drivers/ras/ras.c
> @@ -42,6 +42,7 @@ 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);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(mce_decode);
>  
>  static int __init parse_ras_param(char *str)
>  {
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index 429f46fb61e4..113df73f7ba0 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -407,6 +407,22 @@ TRACE_EVENT(memory_failure_event,
>  	)
>  );
>  #endif /* CONFIG_MEMORY_FAILURE */
> +
> +TRACE_EVENT(mce_decode,
> +	TP_PROTO(const char *param_str),
> +
> +	TP_ARGS(param_str),
> +
> +	TP_STRUCT__entry(
> +		__string(str, param_str)
> +	),
> +
> +	TP_fast_assign(
> +		__assign_str(str, param_str);
> +	),
> +
> +	TP_printk("%s", __get_str(str))
> +);
>  #endif /* _TRACE_HW_EVENT_MC_H */
>  
>  /* This part must be outside protection */