| Message ID | 20231211-cxl-cper-v2-6-c116900ba658@intel.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | efi/cxl-cper: Report CPER CXL component events through trace events | expand |
On Mon, 11 Dec 2023 at 23:57, Ira Weiny <ira.weiny@intel.com> wrote: > > BIOS can configure memory devices as firmware first. This will send CXL > events to the firmware instead of the OS. The firmware can then send > these events to the OS via UEFI. > > UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) > format for CXL Component Events. The format is mostly the same as the > CXL Common Event Record Format. The difference is a GUID is used in > the Section Type to identify the event type. > > Add EFI support to detect CXL CPER records and call a notifier chain > with the record data blobs to be processed by the CXL code. > > Signed-off-by: Ira Weiny <ira.weiny@intel.com> Acked-by: Ard Biesheuvel <ardb@kernel.org> > > --- > Changes from v1: > [djbw: convert to single notifier callback] > [djbw: append _GUID to guid defines] > [iweiny: clean up function names] > --- > drivers/firmware/efi/cper.c | 15 ++++++++++++ > drivers/firmware/efi/cper_cxl.c | 45 ++++++++++++++++++++++++++++++++++++ > drivers/firmware/efi/cper_cxl.h | 29 +++++++++++++++++++++++ > include/linux/cxl-event.h | 51 +++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 140 insertions(+) > > diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c > index 35c37f667781..39c65733ae9b 100644 > --- a/drivers/firmware/efi/cper.c > +++ b/drivers/firmware/efi/cper.c > @@ -22,6 +22,7 @@ > #include <linux/aer.h> > #include <linux/printk.h> > #include <linux/bcd.h> > +#include <linux/cxl-event.h> > #include <acpi/ghes.h> > #include <ras/ras_event.h> > #include "cper_cxl.h" > @@ -607,6 +608,20 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata > cper_print_prot_err(newpfx, prot_err); > else > goto err_section_too_small; > + } else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) || > + guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) || > + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { > + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); > + > + if (rec->hdr.length <= sizeof(rec->hdr)) > + goto err_section_too_small; > + > + if (rec->hdr.length > sizeof(*rec)) { > + pr_err(FW_WARN "error section length is too big\n"); > + return; > + } > + > + cxl_cper_post_event(newpfx, sec_type, rec); > } else { > const void *err = acpi_hest_get_payload(gdata); > > diff --git a/drivers/firmware/efi/cper_cxl.c b/drivers/firmware/efi/cper_cxl.c > index a55771b99a97..669983f7956f 100644 > --- a/drivers/firmware/efi/cper_cxl.c > +++ b/drivers/firmware/efi/cper_cxl.c > @@ -8,6 +8,7 @@ > */ > > #include <linux/cper.h> > +#include <linux/cxl-event.h> > #include "cper_cxl.h" > > #define PROT_ERR_VALID_AGENT_TYPE BIT_ULL(0) > @@ -187,3 +188,47 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e > sizeof(cxl_ras->header_log), 0); > } > } > + > +DECLARE_RWSEM(cxl_cper_rw_sem); > +static cxl_cper_notifier cper_notifier; > + > +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec) > +{ > + struct cxl_cper_event_data data = { > + .rec = rec, > + }; > + > + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { > + pr_err(FW_WARN "cxl event no Component Event Log present\n"); > + return; > + } > + > + if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) > + data.event_type = CXL_CPER_EVENT_GEN_MEDIA; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) > + data.event_type = CXL_CPER_EVENT_DRAM; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) > + data.event_type = CXL_CPER_EVENT_MEM_MODULE; > + > + down_read(&cxl_cper_rw_sem); > + if (cper_notifier) > + cper_notifier(&data); > + up_read(&cxl_cper_rw_sem); > +} > + > +void cxl_cper_register_notifier(cxl_cper_notifier notifier) > +{ > + down_write(&cxl_cper_rw_sem); > + cper_notifier = notifier; > + up_write(&cxl_cper_rw_sem); > +} > +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_notifier, CXL); > + > +void cxl_cper_unregister_notifier(void) > +{ > + down_write(&cxl_cper_rw_sem); > + cper_notifier = NULL; > + up_write(&cxl_cper_rw_sem); > +} > +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_notifier, CXL); > diff --git a/drivers/firmware/efi/cper_cxl.h b/drivers/firmware/efi/cper_cxl.h > index 86bfcf7909ec..b1b1b0514f6b 100644 > --- a/drivers/firmware/efi/cper_cxl.h > +++ b/drivers/firmware/efi/cper_cxl.h > @@ -10,11 +10,38 @@ > #ifndef LINUX_CPER_CXL_H > #define LINUX_CPER_CXL_H > > +#include <linux/cxl-event.h> > + > /* CXL Protocol Error Section */ > #define CPER_SEC_CXL_PROT_ERR \ > GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78, \ > 0x4B, 0x77, 0x10, 0x48) > > +/* CXL Event record UUIDs are formated at 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) > + > #pragma pack(1) > > /* Compute Express Link Protocol Error Section, UEFI v2.10 sec N.2.13 */ > @@ -62,5 +89,7 @@ struct cper_sec_prot_err { > #pragma pack() > > void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_err); > +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec); > > #endif //__CPER_CXL_ > diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h > index 18dab4d90dc8..c764ff877a6d 100644 > --- a/include/linux/cxl-event.h > +++ b/include/linux/cxl-event.h > @@ -108,4 +108,55 @@ struct cxl_event_record_raw { > union cxl_event event; > } __packed; > > +enum cxl_event_type { > + CXL_CPER_EVENT_GEN_MEDIA, > + CXL_CPER_EVENT_DRAM, > + CXL_CPER_EVENT_MEM_MODULE, > +}; > + > +#pragma pack(1) > + > +#define CPER_CXL_DEVICE_ID_VALID BIT(0) > +#define CPER_CXL_DEVICE_SN_VALID BIT(1) > +#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) > +struct cper_cxl_event_rec { > + struct { > + u32 length; > + u64 validation_bits; > + struct cper_cxl_event_devid { > + u16 vendor_id; > + u16 device_id; > + u8 func_num; > + u8 device_num; > + u8 bus_num; > + u16 segment_num; > + u16 slot_num; /* bits 2:0 reserved */ > + u8 reserved; > + } device_id; > + struct cper_cxl_event_sn { > + u32 lower_dw; > + u32 upper_dw; > + } dev_serial_num; > + } hdr; > + > + union cxl_event event; > +}; > + > +struct cxl_cper_event_data { > + enum cxl_event_type event_type; > + struct cper_cxl_event_rec *rec; > +}; > + > +#pragma pack() > + > +typedef void (*cxl_cper_notifier)(struct cxl_cper_event_data *ev_data); > + > +#ifdef CONFIG_UEFI_CPER > +void cxl_cper_register_notifier(cxl_cper_notifier notifier); > +void cxl_cper_unregister_notifier(void); > +#else > +static inline void cxl_cper_register_notifier(cxl_cper_notifier notifier) { } > +static inline void cxl_cper_unregister_notifier(void) { } > +#endif > + > #endif /* _LINUX_CXL_EVENT_H */ > > -- > 2.43.0 >
Ira Weiny wrote: > BIOS can configure memory devices as firmware first. This will send CXL > events to the firmware instead of the OS. The firmware can then send > these events to the OS via UEFI. > > UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) > format for CXL Component Events. The format is mostly the same as the > CXL Common Event Record Format. The difference is a GUID is used in > the Section Type to identify the event type. > > Add EFI support to detect CXL CPER records and call a notifier chain > with the record data blobs to be processed by the CXL code. It is no longer a notifier chain in this version. I wouldn't even call it a notifier, it's just a registered callback. > > Signed-off-by: Ira Weiny <ira.weiny@intel.com> > > --- > Changes from v1: > [djbw: convert to single notifier callback] > [djbw: append _GUID to guid defines] > [iweiny: clean up function names] > --- > drivers/firmware/efi/cper.c | 15 ++++++++++++ > drivers/firmware/efi/cper_cxl.c | 45 ++++++++++++++++++++++++++++++++++++ > drivers/firmware/efi/cper_cxl.h | 29 +++++++++++++++++++++++ > include/linux/cxl-event.h | 51 +++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 140 insertions(+) > > diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c > index 35c37f667781..39c65733ae9b 100644 > --- a/drivers/firmware/efi/cper.c > +++ b/drivers/firmware/efi/cper.c > @@ -22,6 +22,7 @@ > #include <linux/aer.h> > #include <linux/printk.h> > #include <linux/bcd.h> > +#include <linux/cxl-event.h> > #include <acpi/ghes.h> > #include <ras/ras_event.h> > #include "cper_cxl.h" > @@ -607,6 +608,20 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata > cper_print_prot_err(newpfx, prot_err); > else > goto err_section_too_small; > + } else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) || > + guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) || > + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { > + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); > + > + if (rec->hdr.length <= sizeof(rec->hdr)) > + goto err_section_too_small; > + > + if (rec->hdr.length > sizeof(*rec)) { > + pr_err(FW_WARN "error section length is too big\n"); > + return; > + } > + > + cxl_cper_post_event(newpfx, sec_type, rec); > } else { > const void *err = acpi_hest_get_payload(gdata); > > diff --git a/drivers/firmware/efi/cper_cxl.c b/drivers/firmware/efi/cper_cxl.c > index a55771b99a97..669983f7956f 100644 > --- a/drivers/firmware/efi/cper_cxl.c > +++ b/drivers/firmware/efi/cper_cxl.c > @@ -8,6 +8,7 @@ > */ > > #include <linux/cper.h> > +#include <linux/cxl-event.h> > #include "cper_cxl.h" > > #define PROT_ERR_VALID_AGENT_TYPE BIT_ULL(0) > @@ -187,3 +188,47 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e > sizeof(cxl_ras->header_log), 0); > } > } > + > +DECLARE_RWSEM(cxl_cper_rw_sem); > +static cxl_cper_notifier cper_notifier; > + > +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec) > +{ > + struct cxl_cper_event_data data = { > + .rec = rec, > + }; > + > + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { > + pr_err(FW_WARN "cxl event no Component Event Log present\n"); > + return; > + } > + > + if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) > + data.event_type = CXL_CPER_EVENT_GEN_MEDIA; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) > + data.event_type = CXL_CPER_EVENT_DRAM; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) > + data.event_type = CXL_CPER_EVENT_MEM_MODULE; > + > + down_read(&cxl_cper_rw_sem); guard(rwsem_read)(&cxl_cper_rw_sem); > + if (cper_notifier) > + cper_notifier(&data); > + up_read(&cxl_cper_rw_sem); > +} > + > +void cxl_cper_register_notifier(cxl_cper_notifier notifier) > +{ > + down_write(&cxl_cper_rw_sem); guard(rwsem_write)(&cxl_cper_rw_sem); > + cper_notifier = notifier; I would enforce that there is only one registrant and explicitly fail attempts to assign more than one. > + up_write(&cxl_cper_rw_sem); > +} > +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_notifier, CXL); > + > +void cxl_cper_unregister_notifier(void) > +{ > + down_write(&cxl_cper_rw_sem); guard(rwsem_write)(&cxl_cper_rw_sem); > + cper_notifier = NULL; This could enforce that the same callback specified at registration time must also be passed at unregistration to disallow anonymous unregistration. Makes the code self documenting that the registrant is a singleton, and that unregistration must precede the next registration. > + up_write(&cxl_cper_rw_sem); > +} > +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_notifier, CXL); > diff --git a/drivers/firmware/efi/cper_cxl.h b/drivers/firmware/efi/cper_cxl.h > index 86bfcf7909ec..b1b1b0514f6b 100644 > --- a/drivers/firmware/efi/cper_cxl.h > +++ b/drivers/firmware/efi/cper_cxl.h > @@ -10,11 +10,38 @@ > #ifndef LINUX_CPER_CXL_H > #define LINUX_CPER_CXL_H > > +#include <linux/cxl-event.h> > + > /* CXL Protocol Error Section */ > #define CPER_SEC_CXL_PROT_ERR \ > GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78, \ > 0x4B, 0x77, 0x10, 0x48) > > +/* CXL Event record UUIDs are formated at 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) > + > #pragma pack(1) > > /* Compute Express Link Protocol Error Section, UEFI v2.10 sec N.2.13 */ > @@ -62,5 +89,7 @@ struct cper_sec_prot_err { > #pragma pack() > > void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_err); > +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec); > > #endif //__CPER_CXL_ > diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h > index 18dab4d90dc8..c764ff877a6d 100644 > --- a/include/linux/cxl-event.h > +++ b/include/linux/cxl-event.h > @@ -108,4 +108,55 @@ struct cxl_event_record_raw { > union cxl_event event; > } __packed; > > +enum cxl_event_type { > + CXL_CPER_EVENT_GEN_MEDIA, > + CXL_CPER_EVENT_DRAM, > + CXL_CPER_EVENT_MEM_MODULE, > +}; > + > +#pragma pack(1) Looks like there is usage of __packed a few lines up, just pick one-style. Prefer __packed vs #pragma when only a small handful of structures need annotation as that is easier to check for correctness in patch form. > + > +#define CPER_CXL_DEVICE_ID_VALID BIT(0) > +#define CPER_CXL_DEVICE_SN_VALID BIT(1) > +#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) > +struct cper_cxl_event_rec { > + struct { > + u32 length; > + u64 validation_bits; > + struct cper_cxl_event_devid { > + u16 vendor_id; > + u16 device_id; > + u8 func_num; > + u8 device_num; > + u8 bus_num; > + u16 segment_num; > + u16 slot_num; /* bits 2:0 reserved */ > + u8 reserved; > + } device_id; > + struct cper_cxl_event_sn { > + u32 lower_dw; > + u32 upper_dw; > + } dev_serial_num; > + } hdr; > + > + union cxl_event event; > +}; > + > +struct cxl_cper_event_data { > + enum cxl_event_type event_type; > + struct cper_cxl_event_rec *rec; > +}; > + > +#pragma pack() > + > +typedef void (*cxl_cper_notifier)(struct cxl_cper_event_data *ev_data); > + > +#ifdef CONFIG_UEFI_CPER > +void cxl_cper_register_notifier(cxl_cper_notifier notifier); > +void cxl_cper_unregister_notifier(void); > +#else > +static inline void cxl_cper_register_notifier(cxl_cper_notifier notifier) { } > +static inline void cxl_cper_unregister_notifier(void) { } > +#endif > + > #endif /* _LINUX_CXL_EVENT_H */ > > -- > 2.43.0 >
Dan Williams wrote: > Ira Weiny wrote: > > BIOS can configure memory devices as firmware first. This will send CXL > > events to the firmware instead of the OS. The firmware can then send > > these events to the OS via UEFI. > > > > UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) > > format for CXL Component Events. The format is mostly the same as the > > CXL Common Event Record Format. The difference is a GUID is used in > > the Section Type to identify the event type. > > > > Add EFI support to detect CXL CPER records and call a notifier chain > > with the record data blobs to be processed by the CXL code. > > It is no longer a notifier chain in this version. I wouldn't even call > it a notifier, it's just a registered callback. Ah yea I missed that in my rework sorry. [snip] > > +DECLARE_RWSEM(cxl_cper_rw_sem); > > +static cxl_cper_notifier cper_notifier; > > + > > +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, > > + struct cper_cxl_event_rec *rec) > > +{ > > + struct cxl_cper_event_data data = { > > + .rec = rec, > > + }; > > + > > + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { > > + pr_err(FW_WARN "cxl event no Component Event Log present\n"); > > + return; > > + } > > + > > + if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) > > + data.event_type = CXL_CPER_EVENT_GEN_MEDIA; > > + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) > > + data.event_type = CXL_CPER_EVENT_DRAM; > > + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) > > + data.event_type = CXL_CPER_EVENT_MEM_MODULE; > > + > > + down_read(&cxl_cper_rw_sem); > > guard(rwsem_read)(&cxl_cper_rw_sem); Much better. Done throughout. > > > + if (cper_notifier) > > + cper_notifier(&data); > > + up_read(&cxl_cper_rw_sem); > > +} > > + > > +void cxl_cper_register_notifier(cxl_cper_notifier notifier) > > +{ > > + down_write(&cxl_cper_rw_sem); > > guard(rwsem_write)(&cxl_cper_rw_sem); > > > + cper_notifier = notifier; > > I would enforce that there is only one registrant and explicitly fail > attempts to assign more than one. Done. > > > + up_write(&cxl_cper_rw_sem); > > +} > > +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_notifier, CXL); > > + > > +void cxl_cper_unregister_notifier(void) > > +{ > > + down_write(&cxl_cper_rw_sem); > > guard(rwsem_write)(&cxl_cper_rw_sem); > > > + cper_notifier = NULL; > > This could enforce that the same callback specified at registration time > must also be passed at unregistration to disallow anonymous > unregistration. > > Makes the code self documenting that the registrant is a singleton, and > that unregistration must precede the next registration. But what do we do if it does not match? Returning an error will be ignored by the cxl_pci_driver_exit() and if we enforce the singleton in the registration I don't see a lot of room for error here. [snip] > > diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h > > index 18dab4d90dc8..c764ff877a6d 100644 > > --- a/include/linux/cxl-event.h > > +++ b/include/linux/cxl-event.h > > @@ -108,4 +108,55 @@ struct cxl_event_record_raw { > > union cxl_event event; > > } __packed; > > > > +enum cxl_event_type { > > + CXL_CPER_EVENT_GEN_MEDIA, > > + CXL_CPER_EVENT_DRAM, > > + CXL_CPER_EVENT_MEM_MODULE, > > +}; > > + > > +#pragma pack(1) > > Looks like there is usage of __packed a few lines up, just pick > one-style. Prefer __packed vs #pragma when only a small handful of > structures need annotation as that is easier to check for correctness in > patch form. Ok I'll change it. Smita requested the use of pragma but keeping the __packed is redundant right now. And I'll go with your preference of __packed. Ira
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 35c37f667781..39c65733ae9b 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -22,6 +22,7 @@ #include <linux/aer.h> #include <linux/printk.h> #include <linux/bcd.h> +#include <linux/cxl-event.h> #include <acpi/ghes.h> #include <ras/ras_event.h> #include "cper_cxl.h" @@ -607,6 +608,20 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata cper_print_prot_err(newpfx, prot_err); else goto err_section_too_small; + } else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); + + if (rec->hdr.length <= sizeof(rec->hdr)) + goto err_section_too_small; + + if (rec->hdr.length > sizeof(*rec)) { + pr_err(FW_WARN "error section length is too big\n"); + return; + } + + cxl_cper_post_event(newpfx, sec_type, rec); } else { const void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/firmware/efi/cper_cxl.c b/drivers/firmware/efi/cper_cxl.c index a55771b99a97..669983f7956f 100644 --- a/drivers/firmware/efi/cper_cxl.c +++ b/drivers/firmware/efi/cper_cxl.c @@ -8,6 +8,7 @@ */ #include <linux/cper.h> +#include <linux/cxl-event.h> #include "cper_cxl.h" #define PROT_ERR_VALID_AGENT_TYPE BIT_ULL(0) @@ -187,3 +188,47 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e sizeof(cxl_ras->header_log), 0); } } + +DECLARE_RWSEM(cxl_cper_rw_sem); +static cxl_cper_notifier cper_notifier; + +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, + struct cper_cxl_event_rec *rec) +{ + struct cxl_cper_event_data data = { + .rec = rec, + }; + + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { + pr_err(FW_WARN "cxl event no Component Event Log present\n"); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) + data.event_type = CXL_CPER_EVENT_GEN_MEDIA; + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) + data.event_type = CXL_CPER_EVENT_DRAM; + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) + data.event_type = CXL_CPER_EVENT_MEM_MODULE; + + down_read(&cxl_cper_rw_sem); + if (cper_notifier) + cper_notifier(&data); + up_read(&cxl_cper_rw_sem); +} + +void cxl_cper_register_notifier(cxl_cper_notifier notifier) +{ + down_write(&cxl_cper_rw_sem); + cper_notifier = notifier; + up_write(&cxl_cper_rw_sem); +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_notifier, CXL); + +void cxl_cper_unregister_notifier(void) +{ + down_write(&cxl_cper_rw_sem); + cper_notifier = NULL; + up_write(&cxl_cper_rw_sem); +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_notifier, CXL); diff --git a/drivers/firmware/efi/cper_cxl.h b/drivers/firmware/efi/cper_cxl.h index 86bfcf7909ec..b1b1b0514f6b 100644 --- a/drivers/firmware/efi/cper_cxl.h +++ b/drivers/firmware/efi/cper_cxl.h @@ -10,11 +10,38 @@ #ifndef LINUX_CPER_CXL_H #define LINUX_CPER_CXL_H +#include <linux/cxl-event.h> + /* CXL Protocol Error Section */ #define CPER_SEC_CXL_PROT_ERR \ GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78, \ 0x4B, 0x77, 0x10, 0x48) +/* CXL Event record UUIDs are formated at 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) + #pragma pack(1) /* Compute Express Link Protocol Error Section, UEFI v2.10 sec N.2.13 */ @@ -62,5 +89,7 @@ struct cper_sec_prot_err { #pragma pack() void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_err); +void cxl_cper_post_event(const char *pfx, guid_t *sec_type, + struct cper_cxl_event_rec *rec); #endif //__CPER_CXL_ diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 18dab4d90dc8..c764ff877a6d 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -108,4 +108,55 @@ struct cxl_event_record_raw { union cxl_event event; } __packed; +enum cxl_event_type { + CXL_CPER_EVENT_GEN_MEDIA, + CXL_CPER_EVENT_DRAM, + CXL_CPER_EVENT_MEM_MODULE, +}; + +#pragma pack(1) + +#define CPER_CXL_DEVICE_ID_VALID BIT(0) +#define CPER_CXL_DEVICE_SN_VALID BIT(1) +#define CPER_CXL_COMP_EVENT_LOG_VALID BIT(2) +struct cper_cxl_event_rec { + struct { + u32 length; + u64 validation_bits; + struct cper_cxl_event_devid { + u16 vendor_id; + u16 device_id; + u8 func_num; + u8 device_num; + u8 bus_num; + u16 segment_num; + u16 slot_num; /* bits 2:0 reserved */ + u8 reserved; + } device_id; + struct cper_cxl_event_sn { + u32 lower_dw; + u32 upper_dw; + } dev_serial_num; + } hdr; + + union cxl_event event; +}; + +struct cxl_cper_event_data { + enum cxl_event_type event_type; + struct cper_cxl_event_rec *rec; +}; + +#pragma pack() + +typedef void (*cxl_cper_notifier)(struct cxl_cper_event_data *ev_data); + +#ifdef CONFIG_UEFI_CPER +void cxl_cper_register_notifier(cxl_cper_notifier notifier); +void cxl_cper_unregister_notifier(void); +#else +static inline void cxl_cper_register_notifier(cxl_cper_notifier notifier) { } +static inline void cxl_cper_unregister_notifier(void) { } +#endif + #endif /* _LINUX_CXL_EVENT_H */
BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then send these events to the OS via UEFI. UEFI v2.10 section N.2.14 defines a Common Platform Error Record (CPER) format for CXL Component Events. The format is mostly the same as the CXL Common Event Record Format. The difference is a GUID is used in the Section Type to identify the event type. Add EFI support to detect CXL CPER records and call a notifier chain with the record data blobs to be processed by the CXL code. Signed-off-by: Ira Weiny <ira.weiny@intel.com> --- Changes from v1: [djbw: convert to single notifier callback] [djbw: append _GUID to guid defines] [iweiny: clean up function names] --- drivers/firmware/efi/cper.c | 15 ++++++++++++ drivers/firmware/efi/cper_cxl.c | 45 ++++++++++++++++++++++++++++++++++++ drivers/firmware/efi/cper_cxl.h | 29 +++++++++++++++++++++++ include/linux/cxl-event.h | 51 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 140 insertions(+)