| Message ID | 20230601-cxl-cper-v2-2-314d9c36ab02@intel.com |
|---|---|
| State | Superseded |
| Headers | show |
| Series | efi/cxl-cper: Report CPER CXL component events through trace events | expand |
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 only difference is the UUID is > passed via the Section Type as a GUID and not included as part of the > record data. > > Add EFI support to detect CXL CPER records and call a notifier chain > with the record data blobs. > > Note that the format of a GUID and UUID are not the same. Therefore the > Section Type GUID defines are duplicated from the CXL code. > > Signed-off-by: Ira Weiny <ira.weiny@intel.com> > > --- > Changes from RFC v1 > [iweiny: use an enum for know record types and skip converting GUID to UUID] > [iweiny: commit to the UUID not being part of the event record data] > [iweiny: use defines for GUID definitions] > --- > drivers/firmware/efi/cper.c | 16 +++++++++++ > drivers/firmware/efi/cper_cxl.c | 40 ++++++++++++++++++++++++++++ > drivers/firmware/efi/cper_cxl.h | 29 ++++++++++++++++++++ > include/linux/efi.h | 59 +++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 144 insertions(+) > > diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c > index 35c37f667781..d6415c94d584 100644 > --- a/drivers/firmware/efi/cper.c > +++ b/drivers/firmware/efi/cper.c > @@ -607,6 +607,22 @@ 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_equal(sec_type, &CPER_SEC_CXL_DRAM) || > + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE)) { > + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); > + > + printk("%ssection type: CXL Event\n", newpfx); I would say that since this is going to be hanlded elsewhere the kernel log can stay silent. > + > + 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; > + } > + > + cper_post_cxl_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..04234884898d 100644 > --- a/drivers/firmware/efi/cper_cxl.c > +++ b/drivers/firmware/efi/cper_cxl.c > @@ -187,3 +187,43 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e > sizeof(cxl_ras->header_log), 0); > } > } > + > +/* CXL CPER notifier chain */ > +static BLOCKING_NOTIFIER_HEAD(cxl_cper_chain_head); > + > +void cper_post_cxl_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec) > +{ > + struct cxl_cper_notifier_data nd = { > + .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)) > + nd.cper_event = CXL_CPER_EVENT_GEN_MEDIA; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM)) > + nd.cper_event = CXL_CPER_EVENT_DRAM; > + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE)) > + nd.cper_event = CXL_CPER_EVENT_MEM_MODULE; > + > + if (blocking_notifier_call_chain(&cxl_cper_chain_head, 0, (void *)&nd) > + == NOTIFY_BAD) > + pr_err(FW_WARN "cxl event notifier chain failed\n"); > +} > + > +int register_cxl_cper_notifier(struct notifier_block *nb) > +{ > + return blocking_notifier_chain_register(&cxl_cper_chain_head, nb); > +} > +EXPORT_SYMBOL(register_cxl_cper_notifier); I think this should be EXPORT_SYMBOL_NS_GPL(..., CXL) since I can't imagine a third-party driver use case for this. > + > +void unregister_cxl_cper_notifier(struct notifier_block *nb) > +{ > + blocking_notifier_chain_unregister(&cxl_cper_chain_head, nb); > +} > +EXPORT_SYMBOL(unregister_cxl_cper_notifier); > + > diff --git a/drivers/firmware/efi/cper_cxl.h b/drivers/firmware/efi/cper_cxl.h > index 86bfcf7909ec..ca26126cd9b8 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/efi.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 used as the 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_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_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_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 cper_post_cxl_event(const char *pfx, guid_t *sec_type, > + struct cper_cxl_event_rec *rec); > > #endif //__CPER_CXL_ > diff --git a/include/linux/efi.h b/include/linux/efi.h > index 80b21d1c6eaf..b5b8b46c8deb 100644 > --- a/include/linux/efi.h > +++ b/include/linux/efi.h > @@ -1355,4 +1355,63 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) > > umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); > > +/* > + * Event log size adjusted for CPER > + * > + * Base table from CXL r3.0 Table 8-42: (30h + 50h) > + * For lack of UUID: - 10h > + * > + * (30h + 50h) - 10h = 70h > + */ > +#define CPER_CXL_COMP_EVENT_LOG_SIZE 0x70 > +#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 { > + 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 { > + u32 lower_dw; > + u32 upper_dw; > + } dev_serial_num; > + } hdr; > + > + u8 comp_event_log[CPER_CXL_COMP_EVENT_LOG_SIZE]; Rather than define CPER_CXL_COMP_EVENT_LOG_SIZE I would prefer that CXL and EFI share a common struct definition for these common fields. That would also remove the need for BUILD_BUG_ON() since they literally can not disagree on the size in that case. > +}; > +#define CPER_CXL_REC_LEN(rec) (rec->hdr.length - sizeof(rec->hdr)) > + > +enum cxl_cper_event { > + CXL_CPER_EVENT_GEN_MEDIA, > + CXL_CPER_EVENT_DRAM, > + CXL_CPER_EVENT_MEM_MODULE, > +}; It follows from defining that common data structure above that this enum would be a generic CXL namespace that drops "_CPER_". I.e. the CPER notification handler and the native driver translate the event to this common generic sub-structure that gets emitted. > + > +struct cxl_cper_notifier_data { > + enum cxl_cper_event cper_event; > + struct cper_cxl_event_rec *rec; > +}; > + > +#ifdef CONFIG_EFI > +int register_cxl_cper_notifier(struct notifier_block *nb); > +void unregister_cxl_cper_notifier(struct notifier_block *nb); > +#else > +static inline int register_cxl_cper_notifier(struct notifier_block *nb) > +{ > + return 0; > +} > + > +static inline void unregister_cxl_cper_notifier(struct notifier_block *nb) { } > +#endif > + > #endif /* _LINUX_EFI_H */ > > -- > 2.41.0 >
Dan Williams wrote: > Ira Weiny wrote: [snip] > > > > diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c > > index 35c37f667781..d6415c94d584 100644 > > --- a/drivers/firmware/efi/cper.c > > +++ b/drivers/firmware/efi/cper.c > > @@ -607,6 +607,22 @@ 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_equal(sec_type, &CPER_SEC_CXL_DRAM) || > > + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE)) { > > + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); > > + > > + printk("%ssection type: CXL Event\n", newpfx); > > I would say that since this is going to be hanlded elsewhere the kernel > log can stay silent. Yep, bad cargo cult. Removed. [snip] > > + > > +int register_cxl_cper_notifier(struct notifier_block *nb) > > +{ > > + return blocking_notifier_chain_register(&cxl_cper_chain_head, nb); > > +} > > +EXPORT_SYMBOL(register_cxl_cper_notifier); > > I think this should be EXPORT_SYMBOL_NS_GPL(..., CXL) since I can't > imagine a third-party driver use case for this. Good point. Done. [snip] > > > > +/* > > + * Event log size adjusted for CPER > > + * > > + * Base table from CXL r3.0 Table 8-42: (30h + 50h) > > + * For lack of UUID: - 10h > > + * > > + * (30h + 50h) - 10h = 70h > > + */ > > +#define CPER_CXL_COMP_EVENT_LOG_SIZE 0x70 > > +#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 { > > + 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 { > > + u32 lower_dw; > > + u32 upper_dw; > > + } dev_serial_num; > > + } hdr; > > + > > + u8 comp_event_log[CPER_CXL_COMP_EVENT_LOG_SIZE]; > > Rather than define CPER_CXL_COMP_EVENT_LOG_SIZE I would prefer that CXL > and EFI share a common struct definition for these common fields. > > That would also remove the need for BUILD_BUG_ON() since they literally > can not disagree on the size in that case. I don't know if we discussed this publicly or internally but I had versions which lifted the CXL structs to the core. But your opinion at that time was it was not needed. Looking at it again I might get away with the main event record struct defined here. But it is kind of odd to be in efi.h IMO. > > > +}; > > +#define CPER_CXL_REC_LEN(rec) (rec->hdr.length - sizeof(rec->hdr)) > > + > > +enum cxl_cper_event { > > + CXL_CPER_EVENT_GEN_MEDIA, > > + CXL_CPER_EVENT_DRAM, > > + CXL_CPER_EVENT_MEM_MODULE, > > +}; > > It follows from defining that common data structure above that this enum > would be a generic CXL namespace that drops "_CPER_". I.e. the CPER > notification handler and the native driver translate the event to this > common generic sub-structure that gets emitted. Ok this would be along the lines of promoting the definitions to a common header. Again I kept things pretty separate because it seemed that was the direction you wanted to go. I don't particularly like the memcpy which Smita flagged either. But I think this will require reworking the trace code to take a 'non-uuid' structure equal to the payload 'comp_event_log' above. Based on these comments I'll add some header promotion of common record structures and see how it works out with the modified trace code. Do you have any opinions on the name of the core header? Ira
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index 35c37f667781..d6415c94d584 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -607,6 +607,22 @@ 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_equal(sec_type, &CPER_SEC_CXL_DRAM) || + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE)) { + struct cper_cxl_event_rec *rec = acpi_hest_get_payload(gdata); + + printk("%ssection type: CXL Event\n", newpfx); + + 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; + } + + cper_post_cxl_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..04234884898d 100644 --- a/drivers/firmware/efi/cper_cxl.c +++ b/drivers/firmware/efi/cper_cxl.c @@ -187,3 +187,43 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e sizeof(cxl_ras->header_log), 0); } } + +/* CXL CPER notifier chain */ +static BLOCKING_NOTIFIER_HEAD(cxl_cper_chain_head); + +void cper_post_cxl_event(const char *pfx, guid_t *sec_type, + struct cper_cxl_event_rec *rec) +{ + struct cxl_cper_notifier_data nd = { + .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)) + nd.cper_event = CXL_CPER_EVENT_GEN_MEDIA; + else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM)) + nd.cper_event = CXL_CPER_EVENT_DRAM; + else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE)) + nd.cper_event = CXL_CPER_EVENT_MEM_MODULE; + + if (blocking_notifier_call_chain(&cxl_cper_chain_head, 0, (void *)&nd) + == NOTIFY_BAD) + pr_err(FW_WARN "cxl event notifier chain failed\n"); +} + +int register_cxl_cper_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&cxl_cper_chain_head, nb); +} +EXPORT_SYMBOL(register_cxl_cper_notifier); + +void unregister_cxl_cper_notifier(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&cxl_cper_chain_head, nb); +} +EXPORT_SYMBOL(unregister_cxl_cper_notifier); + diff --git a/drivers/firmware/efi/cper_cxl.h b/drivers/firmware/efi/cper_cxl.h index 86bfcf7909ec..ca26126cd9b8 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/efi.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 used as the 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_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_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_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 cper_post_cxl_event(const char *pfx, guid_t *sec_type, + struct cper_cxl_event_rec *rec); #endif //__CPER_CXL_ diff --git a/include/linux/efi.h b/include/linux/efi.h index 80b21d1c6eaf..b5b8b46c8deb 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1355,4 +1355,63 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table) umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n); +/* + * Event log size adjusted for CPER + * + * Base table from CXL r3.0 Table 8-42: (30h + 50h) + * For lack of UUID: - 10h + * + * (30h + 50h) - 10h = 70h + */ +#define CPER_CXL_COMP_EVENT_LOG_SIZE 0x70 +#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 { + 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 { + u32 lower_dw; + u32 upper_dw; + } dev_serial_num; + } hdr; + + u8 comp_event_log[CPER_CXL_COMP_EVENT_LOG_SIZE]; +}; +#define CPER_CXL_REC_LEN(rec) (rec->hdr.length - sizeof(rec->hdr)) + +enum cxl_cper_event { + CXL_CPER_EVENT_GEN_MEDIA, + CXL_CPER_EVENT_DRAM, + CXL_CPER_EVENT_MEM_MODULE, +}; + +struct cxl_cper_notifier_data { + enum cxl_cper_event cper_event; + struct cper_cxl_event_rec *rec; +}; + +#ifdef CONFIG_EFI +int register_cxl_cper_notifier(struct notifier_block *nb); +void unregister_cxl_cper_notifier(struct notifier_block *nb); +#else +static inline int register_cxl_cper_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline void unregister_cxl_cper_notifier(struct notifier_block *nb) { } +#endif + #endif /* _LINUX_EFI_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 only difference is the UUID is passed via the Section Type as a GUID and not included as part of the record data. Add EFI support to detect CXL CPER records and call a notifier chain with the record data blobs. Note that the format of a GUID and UUID are not the same. Therefore the Section Type GUID defines are duplicated from the CXL code. Signed-off-by: Ira Weiny <ira.weiny@intel.com> --- Changes from RFC v1 [iweiny: use an enum for know record types and skip converting GUID to UUID] [iweiny: commit to the UUID not being part of the event record data] [iweiny: use defines for GUID definitions] --- drivers/firmware/efi/cper.c | 16 +++++++++++ drivers/firmware/efi/cper_cxl.c | 40 ++++++++++++++++++++++++++++ drivers/firmware/efi/cper_cxl.h | 29 ++++++++++++++++++++ include/linux/efi.h | 59 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 144 insertions(+)