From 0e081a0ec04df58ac9caec1916ae6d9d048d50a7 Mon Sep 17 00:00:00 2001 From: Sangyun Kim Date: Wed, 17 Apr 2024 12:50:43 +0900 Subject: cxl/cxl-event: include missing and The linux/cxl-event.h header file uses the u8, u16, and uuid_t types, but it doesn't include the necessary header files, and . Currently, cxl-event.h is only used by drivers/cxl/cxlmem.h, and it doesn't cause any errors because cxlmem.h indirectly includes the required types. However, cxl-event.h may be used by other CXL-related code in the future, so it's important to fix this issue by including the missing header files directly in cxl-event.h. Signed-off-by: Sangyun Kim Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/20240417035043.2791431-1-sangyun.kim@snu.ac.kr Signed-off-by: Dave Jiang --- include/linux/cxl-event.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 03fa6d50d46f..812ed16ffc2f 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -3,6 +3,9 @@ #ifndef _LINUX_CXL_EVENT_H #define _LINUX_CXL_EVENT_H +#include +#include + /* * Common Event Record Format * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 -- cgit From 6aec00139d3a83e2394d4bcb0084e872b4036e8f Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Tue, 30 Apr 2024 10:28:06 -0700 Subject: cxl/core: Add region info to cxl_general_media and cxl_dram events User space may need to know which region, if any, maps the DPAs (device physical addresses) reported in a cxl_general_media or cxl_dram event. Since the mapping can change, the kernel provides this information at the time the event occurs. This informs user space that at event this mapped this to this . Add the same region info that is included in the cxl_poison trace event: the DPA->HPA translation, region name, and region uuid. The new fields are inserted in the trace event and no existing fields are modified. If the DPA is not mapped, user will see: hpa=ULLONG_MAX, region="", and uuid=0 This work must be protected by dpa_rwsem & region_rwsem since it is looking up region mappings. Signed-off-by: Alison Schofield Reviewed-by: Dan Williams Reviewed-by: Ira Weiny Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/dd8d708b7a7ebfb64a27020a5eb338091336b34d.1714496730.git.alison.schofield@intel.com Signed-off-by: Dave Jiang --- drivers/cxl/core/mbox.c | 36 ++++++++++++++++++++++++++++++------ drivers/cxl/core/trace.h | 44 +++++++++++++++++++++++++++++++++++--------- include/linux/cxl-event.h | 10 ++++++++++ 3 files changed, 75 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 65185c9fa001..97e938657773 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -842,14 +842,38 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd, enum cxl_event_type event_type, const uuid_t *uuid, union cxl_event *evt) { - if (event_type == CXL_CPER_EVENT_GEN_MEDIA) - trace_cxl_general_media(cxlmd, type, &evt->gen_media); - else if (event_type == CXL_CPER_EVENT_DRAM) - trace_cxl_dram(cxlmd, type, &evt->dram); - else if (event_type == CXL_CPER_EVENT_MEM_MODULE) + if (event_type == CXL_CPER_EVENT_MEM_MODULE) { trace_cxl_memory_module(cxlmd, type, &evt->mem_module); - else + return; + } + if (event_type == CXL_CPER_EVENT_GENERIC) { trace_cxl_generic_event(cxlmd, type, uuid, &evt->generic); + return; + } + + if (trace_cxl_general_media_enabled() || trace_cxl_dram_enabled()) { + u64 dpa, hpa = ULLONG_MAX; + struct cxl_region *cxlr; + + /* + * These trace points are annotated with HPA and region + * translations. Take topology mutation locks and lookup + * { HPA, REGION } from { DPA, MEMDEV } in the event record. + */ + guard(rwsem_read)(&cxl_region_rwsem); + guard(rwsem_read)(&cxl_dpa_rwsem); + + dpa = le64_to_cpu(evt->common.phys_addr) & CXL_DPA_MASK; + cxlr = cxl_dpa_to_region(cxlmd, dpa); + if (cxlr) + hpa = cxl_trace_hpa(cxlr, cxlmd, dpa); + + if (event_type == CXL_CPER_EVENT_GEN_MEDIA) + trace_cxl_general_media(cxlmd, type, cxlr, hpa, + &evt->gen_media); + else if (event_type == CXL_CPER_EVENT_DRAM) + trace_cxl_dram(cxlmd, type, cxlr, hpa, &evt->dram); + } } EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index e303e618aa05..07a0394b1d99 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -316,9 +316,9 @@ TRACE_EVENT(cxl_generic_event, TRACE_EVENT(cxl_general_media, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, - struct cxl_event_gen_media *rec), + struct cxl_region *cxlr, u64 hpa, struct cxl_event_gen_media *rec), - TP_ARGS(cxlmd, log, rec), + TP_ARGS(cxlmd, log, cxlr, hpa, rec), TP_STRUCT__entry( CXL_EVT_TP_entry @@ -330,10 +330,13 @@ TRACE_EVENT(cxl_general_media, __field(u8, channel) __field(u32, device) __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) - __field(u16, validity_flags) /* Following are out of order to pack trace record */ + __field(u64, hpa) + __field_struct(uuid_t, region_uuid) + __field(u16, validity_flags) __field(u8, rank) __field(u8, dpa_flags) + __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), TP_fast_assign( @@ -354,18 +357,28 @@ TRACE_EVENT(cxl_general_media, memcpy(__entry->comp_id, &rec->component_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE); __entry->validity_flags = get_unaligned_le16(&rec->validity_flags); + __entry->hpa = hpa; + if (cxlr) { + __assign_str(region_name, dev_name(&cxlr->dev)); + uuid_copy(&__entry->region_uuid, &cxlr->params.uuid); + } else { + __assign_str(region_name, ""); + uuid_copy(&__entry->region_uuid, &uuid_null); + } ), CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \ "descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \ - "device=%x comp_id=%s validity_flags='%s'", + "device=%x comp_id=%s validity_flags='%s' " \ + "hpa=%llx region=%s region_uuid=%pUb", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_mem_event_type(__entry->type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->device, __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), - show_valid_flags(__entry->validity_flags) + show_valid_flags(__entry->validity_flags), + __entry->hpa, __get_str(region_name), &__entry->region_uuid ) ); @@ -400,9 +413,9 @@ TRACE_EVENT(cxl_general_media, TRACE_EVENT(cxl_dram, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, - struct cxl_event_dram *rec), + struct cxl_region *cxlr, u64 hpa, struct cxl_event_dram *rec), - TP_ARGS(cxlmd, log, rec), + TP_ARGS(cxlmd, log, cxlr, hpa, rec), TP_STRUCT__entry( CXL_EVT_TP_entry @@ -417,10 +430,13 @@ TRACE_EVENT(cxl_dram, __field(u32, nibble_mask) __field(u32, row) __array(u8, cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE) + __field(u64, hpa) + __field_struct(uuid_t, region_uuid) __field(u8, rank) /* Out of order to pack trace record */ __field(u8, bank_group) /* Out of order to pack trace record */ __field(u8, bank) /* Out of order to pack trace record */ __field(u8, dpa_flags) /* Out of order to pack trace record */ + __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), TP_fast_assign( @@ -444,12 +460,21 @@ TRACE_EVENT(cxl_dram, __entry->column = get_unaligned_le16(rec->column); memcpy(__entry->cor_mask, &rec->correction_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE); + __entry->hpa = hpa; + if (cxlr) { + __assign_str(region_name, dev_name(&cxlr->dev)); + uuid_copy(&__entry->region_uuid, &cxlr->params.uuid); + } else { + __assign_str(region_name, ""); + uuid_copy(&__entry->region_uuid, &uuid_null); + } ), CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \ "transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \ "bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \ - "validity_flags='%s'", + "validity_flags='%s' " \ + "hpa=%llx region=%s region_uuid=%pUb", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_mem_event_type(__entry->type), @@ -458,7 +483,8 @@ TRACE_EVENT(cxl_dram, __entry->bank_group, __entry->bank, __entry->row, __entry->column, __print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE), - show_dram_valid_flags(__entry->validity_flags) + show_dram_valid_flags(__entry->validity_flags), + __entry->hpa, __get_str(region_name), &__entry->region_uuid ) ); diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 03fa6d50d46f..5342755777cc 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -91,11 +91,21 @@ struct cxl_event_mem_module { u8 reserved[0x3d]; } __packed; +/* + * General Media or DRAM Event Common Fields + * - provides common access to phys_addr + */ +struct cxl_event_common { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; +} __packed; + union cxl_event { struct cxl_event_generic generic; struct cxl_event_gen_media gen_media; struct cxl_event_dram dram; struct cxl_event_mem_module mem_module; + struct cxl_event_common common; } __packed; /* -- cgit From 5e4a264bf8b55d5a1b4c8cd96ac10b99f98d7487 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 26 Apr 2024 20:34:00 -0700 Subject: acpi/ghes: Process CXL Component Events BIOS can configure memory devices as firmware first. This will send CXL events to the firmware instead of the OS. The firmware can then inform the OS of these events 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 lies in the use of a GUID as the CPER Section Type which matches the UUID defined in CXL 3.1 Table 8-43. Currently a configuration such as this will trace a non standard event in the log omitting useful details of the event. In addition the CXL sub-system contains additional region and HPA information useful to the user.[0] The CXL code is required to be called from process context as it needs to take a device lock. The GHES code may be in interrupt context. This complicated the use of a callback. Dan Williams suggested the use of work items as an atomic way of switching between the callback execution and a default handler.[1] The use of a kfifo simplifies queue processing by providing lock free fifo operations. cxl_cper_kfifo_get() allows easier management of the kfifo between the ghes and cxl modules. CXL 3.1 Table 8-127 requires a device to have a queue depth of 1 for each of the four event logs. A combined queue depth of 32 is chosen to provide room for 8 entries of each log type. Add GHES support to detect CXL CPER records. Add the ability for the CXL sub-system to register a work queue to process the events. This patch adds back the functionality which was removed to fix the report by Dan Carpenter[2]. Cc: Ard Biesheuvel Cc: Rafael J. Wysocki Cc: Tony Luck Cc: Borislav Petkov Suggested-by: Dan Carpenter Suggested-by: Dan Williams Link: http://lore.kernel.org/r/cover.1711598777.git.alison.schofield@intel.com [0] Link: http://lore.kernel.org/r/65d111eb87115_6c745294ac@dwillia2-xfh.jf.intel.com.notmuch [1] Link: http://lore.kernel.org/r/b963c490-2c13-4b79-bbe7-34c6568423c7@moroto.mountain [2] Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Reviewed-by: Jonathan Cameron Reviewed-by: Tony Luck Tested-by: Smita Koralahalli Link: https://lore.kernel.org/r/20240426-cxl-cper3-v4-1-58076cce1624@intel.com Signed-off-by: Dave Jiang --- drivers/acpi/apei/ghes.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/cxl-event.h | 27 ++++++++++++ 2 files changed, 137 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 512067cac170..2247a1535b52 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -26,6 +26,8 @@ #include #include #include +#include +#include #include #include #include @@ -33,6 +35,7 @@ #include #include #include +#include #include #include #include @@ -673,6 +676,101 @@ static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata, schedule_work(&entry->work); } +/* CXL Event record UUIDs are formated 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) + +/* Room for 8 entries for each of the 4 event log queues */ +#define CXL_CPER_FIFO_DEPTH 32 +DEFINE_KFIFO(cxl_cper_fifo, struct cxl_cper_work_data, CXL_CPER_FIFO_DEPTH); + +/* Synchronize schedule_work() with cxl_cper_work changes */ +static DEFINE_SPINLOCK(cxl_cper_work_lock); +struct work_struct *cxl_cper_work; + +static void cxl_cper_post_event(enum cxl_event_type event_type, + struct cxl_cper_event_rec *rec) +{ + struct cxl_cper_work_data wd; + + if (rec->hdr.length <= sizeof(rec->hdr) || + rec->hdr.length > sizeof(*rec)) { + pr_err(FW_WARN "CXL CPER Invalid section length (%u)\n", + rec->hdr.length); + return; + } + + if (!(rec->hdr.validation_bits & CPER_CXL_COMP_EVENT_LOG_VALID)) { + pr_err(FW_WARN "CXL CPER invalid event\n"); + return; + } + + guard(spinlock_irqsave)(&cxl_cper_work_lock); + + if (!cxl_cper_work) + return; + + wd.event_type = event_type; + memcpy(&wd.rec, rec, sizeof(wd.rec)); + + if (!kfifo_put(&cxl_cper_fifo, wd)) { + pr_err_ratelimited("CXL CPER kfifo overflow\n"); + return; + } + + schedule_work(cxl_cper_work); +} + +int cxl_cper_register_work(struct work_struct *work) +{ + if (cxl_cper_work) + return -EINVAL; + + guard(spinlock)(&cxl_cper_work_lock); + cxl_cper_work = work; + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_register_work, CXL); + +int cxl_cper_unregister_work(struct work_struct *work) +{ + if (cxl_cper_work != work) + return -EINVAL; + + guard(spinlock)(&cxl_cper_work_lock); + cxl_cper_work = NULL; + return 0; +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_work, CXL); + +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) +{ + return kfifo_get(&cxl_cper_fifo, wd); +} +EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, CXL); + static bool ghes_do_proc(struct ghes *ghes, const struct acpi_hest_generic_status *estatus) { @@ -707,6 +805,18 @@ static bool ghes_do_proc(struct ghes *ghes, } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { queued = ghes_handle_arm_hw_error(gdata, sev, sync); + } else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) { + struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_GEN_MEDIA, rec); + } else if (guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID)) { + struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_DRAM, rec); + } else if (guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { + struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata); + + cxl_cper_post_event(CXL_CPER_EVENT_MEM_MODULE, rec); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 03fa6d50d46f..a0067c49e2ca 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -3,6 +3,8 @@ #ifndef _LINUX_CXL_EVENT_H #define _LINUX_CXL_EVENT_H +#include + /* * Common Event Record Format * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 @@ -140,4 +142,29 @@ struct cxl_cper_event_rec { union cxl_event event; } __packed; +struct cxl_cper_work_data { + enum cxl_event_type event_type; + struct cxl_cper_event_rec rec; +}; + +#ifdef CONFIG_ACPI_APEI_GHES +int cxl_cper_register_work(struct work_struct *work); +int cxl_cper_unregister_work(struct work_struct *work); +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); +#else +static inline int cxl_cper_register_work(struct work_struct *work); +{ + return 0; +} + +static inline int cxl_cper_unregister_work(struct work_struct *work); +{ + return 0; +} +static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) +{ + return 0; +} +#endif + #endif /* _LINUX_CXL_EVENT_H */ -- cgit From 55111470b4416a6225abfdb4e1f0b8a8c8c52fdc Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 1 May 2024 11:40:23 -0700 Subject: cxl/cper: Fix non-ACPI-APEI-GHES build If ACPI_APEI_GHES is not configured the [un]register work functions are not properly declared. 0day notices that the cxl_cper_register_work() declaration in the CONFIG_ACPI_APEI_GHES=n is broken, fix it to be typical nop stub. Reported-by: kernel test robot Closes: http://lore.kernel.org/r/202405012230.6kXItWen-lkp@intel.com Reviewed-by: Dan Williams Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20240501-cper-fix-0day-v1-1-c0b0056eafbc@intel.com Signed-off-by: Dave Jiang --- include/linux/cxl-event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 855908792ef8..60b25020281f 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -164,12 +164,12 @@ int cxl_cper_register_work(struct work_struct *work); int cxl_cper_unregister_work(struct work_struct *work); int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); #else -static inline int cxl_cper_register_work(struct work_struct *work); +static inline int cxl_cper_register_work(struct work_struct *work) { return 0; } -static inline int cxl_cper_unregister_work(struct work_struct *work); +static inline int cxl_cper_unregister_work(struct work_struct *work) { return 0; } -- cgit