Re: [RFC PATCH 6/6] ACPI: extlog: add Memory Error Section 2 trace event

[Jonathan Cameron]

On Mon, 19 Oct 2026 16:56:13 +0200
Pierre Gondois <pierre.gondois@xxxxxxx> wrote:

> Add a separte handling for Memory Error Section 2 trace events with:
> - extlog_mem2_event()
> - extlog_mem2 trace event
> The fields of the record are individually printed so userspace
> can discover the layout more dynamically if a new field is added.

How useful are the pair of handles?

Otherwise I'm fine with this - subject to same comment as on patch 1.

Reviewed-by: Jonathan Cameron <jonathan.cameron@xxxxxxxxxxxxxxxx>

> 
> Signed-off-by: Pierre Gondois <pierre.gondois@xxxxxxx>
> ---
>  drivers/acpi/acpi_extlog.c |  16 ++++++
>  drivers/ras/ras.c          |   1 +
>  include/ras/ras_event.h    | 102 +++++++++++++++++++++++++++++++++++++
>  3 files changed, 119 insertions(+)
> 
> diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
> index e764d61f71ca..9c0b932e22bc 100644
> --- a/drivers/acpi/acpi_extlog.c
> +++ b/drivers/acpi/acpi_extlog.c
> @@ -189,6 +189,15 @@ extlog_mem_err_event(struct cper_sec_mem_err *mem, u32 err_seq,
>  #endif
>  }
> 
> +static void
> +extlog_mem_err2_event(struct cper_sec_mem_err2 *mem, u32 err_seq,
> +		      const guid_t *fru_id, const char *fru_text, u8 sev)
> +{
> +#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)

Same comment as earlier patch about oddity of protecting stuff in a file
that is normally only built if they are set.


> +	trace_extlog_mem2_event(mem, err_seq, fru_id, fru_text, sev);
> +#endif
> +}
> +
>  static int extlog_print(struct notifier_block *nb, unsigned long val,
>  			void *data)
>  {
> @@ -241,6 +250,13 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
>  				extlog_mem_err_event(mem, err_seq, fru_id,
>  						     fru_text,
>  						     (u8)gdata->error_severity);
> +		} else if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM2)) {
> +			struct cper_sec_mem_err2 *mem = acpi_hest_get_payload(gdata);
> +
> +			if (gdata->error_data_length >= sizeof(*mem))
> +				extlog_mem_err2_event(mem, err_seq, fru_id,
> +						      fru_text,
> +						      (u8)gdata->error_severity);
>  		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
>  			struct cxl_cper_sec_prot_err *prot_err =
>  				acpi_hest_get_payload(gdata);
> diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c
> index 03df3db62334..c6b14202a5e9 100644
> --- a/drivers/ras/ras.c
> +++ b/drivers/ras/ras.c
> @@ -111,6 +111,7 @@ subsys_initcall(ras_init);
> 
>  #if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)
>  EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem_event);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(extlog_mem2_event);
>  #endif
>  EXPORT_TRACEPOINT_SYMBOL_GPL(mc_event);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(non_standard_event);
> diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h
> index fdb785fa4613..0c0dbe068dc8 100644
> --- a/include/ras/ras_event.h
> +++ b/include/ras/ras_event.h
> @@ -74,6 +74,108 @@ TRACE_EVENT(extlog_mem_event,
>  		  &__entry->fru_id,
>  		  __get_str(fru_text))
>  );
> +
> +/*
> + * Memory Error Section 2 exposes each field separately so userspace can
> + * discover its layout. Validation bits use the UEFI Section 2 assignments.
> + */
> +TRACE_EVENT(extlog_mem2_event,
> +	TP_PROTO(const struct cper_sec_mem_err2 *mem,
> +		 u32 err_seq,
> +		 const guid_t *fru_id,
> +		 const char *fru_text,
> +		 u8 sev),
> +
> +	TP_ARGS(mem, err_seq, fru_id, fru_text, sev),
> +
> +	TP_STRUCT__entry(
> +		__field(u32, err_seq)
> +		__field(u8, sev)
> +		__field_struct(guid_t, fru_id)
> +		__string(fru_text, fru_text)
> +		__field(u64, validation_bits)
> +		__field(u64, error_status)
> +		__field(u64, physical_addr)
> +		__field(u64, physical_addr_mask)
> +		__field(u16, node)
> +		__field(u16, card)
> +		__field(u16, module)
> +		__field(u16, bank)
> +		__field(u32, device)
> +		__field(u32, row)
> +		__field(u32, column)
> +		__field(u32, rank)
> +		__field(u32, bit_pos)
> +		__field(u8, chip_id)
> +		__field(u8, error_type)
> +		__field(u8, status)
> +		__field(u64, requestor_id)
> +		__field(u64, responder_id)
> +		__field(u64, target_id)
> +		__field(u32, mem_array_handle)
> +		__field(u32, mem_dev_handle)
> +	),
> +
> +	TP_fast_assign(
> +		__entry->err_seq = err_seq;
> +		__entry->sev = sev;
> +		__entry->fru_id = *fru_id;
> +		__assign_str(fru_text);
> +		__entry->validation_bits = mem->validation_bits;
> +		__entry->error_status = mem->error_status;
> +		__entry->physical_addr = mem->physical_addr;
> +		__entry->physical_addr_mask = mem->physical_addr_mask;
> +		__entry->node = mem->node;
> +		__entry->card = mem->card;
> +		__entry->module = mem->module;
> +		__entry->bank = mem->bank;
> +		__entry->device = mem->device;
> +		__entry->row = mem->row;
> +		__entry->column = mem->column;
> +		__entry->rank = mem->rank;
> +		__entry->bit_pos = mem->bit_pos;
> +		__entry->chip_id = mem->chip_id;
> +		__entry->error_type = mem->error_type;
> +		__entry->status = mem->status;
> +		__entry->requestor_id = mem->requestor_id;
> +		__entry->responder_id = mem->responder_id;
> +		__entry->target_id = mem->target_id;
> +		__entry->mem_array_handle = mem->mem_array_handle;
> +		__entry->mem_dev_handle = mem->mem_dev_handle;
> +	),
> +
> +	TP_printk("{%u} %s error: validation_bits: 0x%llx "
> +		  "error_status: 0x%llx physical_addr: 0x%llx "
> +		  "physical_addr_mask: 0x%llx node: %u card: %u "
> +		  "module: %u bank: %u device: %u row: %u column: %u "
> +		  "rank: %u bit_pos: %u chip_id: %u error_type: %u "
> +		  "status: 0x%x requestor_id: 0x%llx responder_id: 0x%llx "
> +		  "target_id: 0x%llx mem_array_handle: 0x%x "
> +		  "mem_dev_handle: 0x%x FRU: %pUl %.20s",
> +		  __entry->err_seq, cper_severity_str(__entry->sev),
> +		  __entry->validation_bits,
> +		  __entry->error_status,
> +		  __entry->physical_addr,
> +		  __entry->physical_addr_mask,
> +		  __entry->node,
> +		  __entry->card,
> +		  __entry->module,
> +		  __entry->bank,
> +		  __entry->device,
> +		  __entry->row,
> +		  __entry->column,
> +		  __entry->rank,
> +		  __entry->bit_pos,
> +		  __entry->chip_id,
> +		  __entry->error_type,
> +		  __entry->status,
> +		  __entry->requestor_id,
> +		  __entry->responder_id,
> +		  __entry->target_id,
> +		  __entry->mem_array_handle,
> +		  __entry->mem_dev_handle,
> +		  &__entry->fru_id, __get_str(fru_text))
> +);
>  #endif
> 
>  /*
> --
> 2.43.0