On Wed, 31 Jan 2024 17:17:00 -0800
Alison Schofield <alison.schofield@xxxxxxxxx> wrote:
> On Wed, Jan 31, 2024 at 03:55:38PM -0800, Ira Weiny wrote:
> > Jonathan reports that CXL CPER events dump an extra generic error
> > message.
> >
> > {1}[Hardware Error]: Hardware error from APEI Generic Hardware Error Source: 1
> > {1}[Hardware Error]: event severity: recoverable
> > {1}[Hardware Error]: Error 0, type: recoverable
> > {1}[Hardware Error]: section type: unknown, fbcd0a77-c260-417f-85a9-088b1621eba6
> > {1}[Hardware Error]: section length: 0x90
> > {1}[Hardware Error]: 00000000: 00000090 00000007 00000000 0d938086 ................
> > {1}[Hardware Error]: 00000010: 00100000 00000000 00040000 00000000 ................
> > ...
> >
> > CXL events were rerouted though the CXL subsystem for additional
> > processing. However, when that work was done it was missed that
> > cper_estatus_print_section() continued with a generic error message
> > which is confusing.
> >
> > Teach CPER print code to ignore printing details of some section types.
> > Assign the CXL event GUIDs to this set to prevent confusing unknown
> > prints.
>
> Reviewed-by: Alison Schofield <alison.schofield@xxxxxxxxx>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
>
>
> >
> > Reported-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
> > Suggested-by: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
> > Signed-off-by: Ira Weiny <ira.weiny@xxxxxxxxx>
> > ---
> > drivers/acpi/apei/ghes.c | 26 --------------------------
> > drivers/firmware/efi/cper.c | 19 +++++++++++++++++++
> > include/linux/cper.h | 23 +++++++++++++++++++++++
> > 3 files changed, 42 insertions(+), 26 deletions(-)
> >
> > diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> > index 7b7c605166e0..fe825a432c5b 100644
> > --- a/drivers/acpi/apei/ghes.c
> > +++ b/drivers/acpi/apei/ghes.c
> > @@ -680,32 +680,6 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
> > static DECLARE_RWSEM(cxl_cper_rw_sem);
> > static cxl_cper_callback cper_callback;
> >
> > -/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
> > -
> > -/*
> > - * General Media Event Record
> > - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
> > - */
> > -#define CPER_SEC_CXL_GEN_MEDIA_GUID \
> > - GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \
> > - 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
> > -
> > -/*
> > - * DRAM Event Record
> > - * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
> > - */
> > -#define CPER_SEC_CXL_DRAM_GUID \
> > - GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \
> > - 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
> > -
> > -/*
> > - * Memory Module Event Record
> > - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
> > - */
> > -#define CPER_SEC_CXL_MEM_MODULE_GUID \
> > - GUID_INIT(0xfe927475, 0xdd59, 0x4339, \
> > - 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
> > -
> > static void cxl_cper_post_event(enum cxl_event_type event_type,
> > struct cxl_cper_event_rec *rec)
> > {
> > diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
> > index 35c37f667781..9b3884ff81e6 100644
> > --- a/drivers/firmware/efi/cper.c
> > +++ b/drivers/firmware/efi/cper.c
> > @@ -523,6 +523,17 @@ static void cper_print_tstamp(const char *pfx,
> > }
> > }
> >
> > +struct ignore_section {
> > + guid_t guid;
> > + const char *name;
> > +};
> > +
> > +static const struct ignore_section ignore_sections[] = {
> > + { .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" },
> > + { .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" },
> > + { .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" },
> > +};
> > +
> > static void
> > cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata,
> > int sec_no)
> > @@ -543,6 +554,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
> > printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text);
> >
> > snprintf(newpfx, sizeof(newpfx), "%s ", pfx);
> > +
> > + for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) {
> > + if (guid_equal(sec_type, &ignore_sections[i].guid)) {
> > + printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name);
> > + return;
> > + }
> > + }
> > +
> > if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) {
> > struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata);
> >
> > diff --git a/include/linux/cper.h b/include/linux/cper.h
> > index c1a7dc325121..265b0f8fc0b3 100644
> > --- a/include/linux/cper.h
> > +++ b/include/linux/cper.h
> > @@ -90,6 +90,29 @@ enum {
> > GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \
> > 0x72, 0x2D, 0xEB, 0x41)
> >
> > +/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
> > +/*
> > + * General Media Event Record
> > + * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
> > + */
> > +#define CPER_SEC_CXL_GEN_MEDIA_GUID \
> > + GUID_INIT(0xfbcd0a77, 0xc260, 0x417f, \
> > + 0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
> > +/*
> > + * DRAM Event Record
> > + * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
> > + */
> > +#define CPER_SEC_CXL_DRAM_GUID \
> > + GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab, \
> > + 0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
> > +/*
> > + * Memory Module Event Record
> > + * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
> > + */
> > +#define CPER_SEC_CXL_MEM_MODULE_GUID \
> > + GUID_INIT(0xfe927475, 0xdd59, 0x4339, \
> > + 0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
> > +
> > /*
> > * Flags bits definitions for flags in struct cper_record_header
> > * If set, the error has been recovered
> >
> > --
> > 2.43.0
> >
>
