CXL device can find&report memory problems, even before MCE is detected
by CPU. AFAIK, the current kernel only traces POISON error event
from FW-First/OS-First path, but it doesn't handle them, neither
notify processes who are using the POISON page like MCE does.
Thus, user have to read logs from trace and find out which device
reported the error and which applications are affected. That is not
an easy work and cannot be handled in time. Thus, it is needed to add
the feature to make the work done automatically and quickly. Once CXL
device reports the POISON error (via FW-First/OS-First), kernel
handles it immediately, similar to the flow when a MCE is triggered.
The current call trace of error reporting&handling looks like this:
```
1. MCE (interrupt #18, while CPU consuming POISON)
-> do_machine_check()
-> mce_log()
-> notify chain (x86_mce_decoder_chain)
-> memory_failure()
2.a FW-First (optional, CXL device proactively find&report)
-> CXL device -> Firmware
-> OS: ACPI->APEI->GHES->CPER -> CXL driver -> trace
\-> memory_failure()
^----- ADD
2.b OS-First (optional, CXL device proactively find&report)
-> CXL device -> MSI
-> OS: CXL driver -> trace
\-> memory_failure()
^------------------------------- ADD
```
This patch adds calling memory_failure() while CXL device reporting
error is received, marked as "ADD" in figure above.
Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
---
drivers/cxl/core/mbox.c | 75 ++++++++++++++++++++++++++++++++-------
drivers/cxl/cxlmem.h | 8 ++---
drivers/cxl/pci.c | 4 +--
include/linux/cxl-event.h | 16 ++++++++-
4 files changed, 83 insertions(+), 20 deletions(-)
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index e5cdeafdf76e..0cb6ef2e6600 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -849,10 +849,55 @@ int cxl_enumerate_cmds(struct cxl_memdev_state *mds)
}
EXPORT_SYMBOL_NS_GPL(cxl_enumerate_cmds, CXL);
-void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
- enum cxl_event_log_type type,
- enum cxl_event_type event_type,
- const uuid_t *uuid, union cxl_event *evt)
+static void cxl_report_poison(struct cxl_memdev *cxlmd, u64 hpa)
+{
+ unsigned long pfn = PHYS_PFN(hpa);
+
+ memory_failure_queue(pfn, 0);
+}
+
+static void cxl_event_handle_general_media(struct cxl_memdev *cxlmd,
+ enum cxl_event_log_type type,
+ u64 hpa,
+ struct cxl_event_gen_media *rec)
+{
+ if (type == CXL_EVENT_TYPE_FAIL) {
+ switch (rec->media_hdr.transaction_type) {
+ case CXL_EVENT_TRANSACTION_READ:
+ case CXL_EVENT_TRANSACTION_WRITE:
+ case CXL_EVENT_TRANSACTION_SCAN_MEDIA:
+ case CXL_EVENT_TRANSACTION_INJECT_POISON:
+ cxl_report_poison(cxlmd, hpa);
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+static void cxl_event_handle_dram(struct cxl_memdev *cxlmd,
+ enum cxl_event_log_type type,
+ u64 hpa,
+ struct cxl_event_dram *rec)
+{
+ if (type == CXL_EVENT_TYPE_FAIL) {
+ switch (rec->media_hdr.transaction_type) {
+ case CXL_EVENT_TRANSACTION_READ:
+ case CXL_EVENT_TRANSACTION_WRITE:
+ case CXL_EVENT_TRANSACTION_SCAN_MEDIA:
+ case CXL_EVENT_TRANSACTION_INJECT_POISON:
+ cxl_report_poison(cxlmd, hpa);
+ break;
+ default:
+ break;
+ }
+ }
+}
+
+void cxl_event_handle_record(struct cxl_memdev *cxlmd,
+ enum cxl_event_log_type type,
+ enum cxl_event_type event_type,
+ const uuid_t *uuid, union cxl_event *evt)
{
if (event_type == CXL_CPER_EVENT_MEM_MODULE) {
trace_cxl_memory_module(cxlmd, type, &evt->mem_module);
@@ -880,18 +925,22 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
if (cxlr)
hpa = cxl_dpa_to_hpa(cxlr, cxlmd, dpa);
- if (event_type == CXL_CPER_EVENT_GEN_MEDIA)
+ 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)
+ cxl_event_handle_general_media(cxlmd, type, hpa,
+ &evt->gen_media);
+ } else if (event_type == CXL_CPER_EVENT_DRAM) {
trace_cxl_dram(cxlmd, type, cxlr, hpa, &evt->dram);
+ cxl_event_handle_dram(cxlmd, type, hpa, &evt->dram);
+ }
}
}
-EXPORT_SYMBOL_NS_GPL(cxl_event_trace_record, CXL);
+EXPORT_SYMBOL_NS_GPL(cxl_event_handle_record, CXL);
-static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
- enum cxl_event_log_type type,
- struct cxl_event_record_raw *record)
+static void __cxl_event_handle_record(struct cxl_memdev *cxlmd,
+ enum cxl_event_log_type type,
+ struct cxl_event_record_raw *record)
{
enum cxl_event_type ev_type = CXL_CPER_EVENT_GENERIC;
const uuid_t *uuid = &record->id;
@@ -903,7 +952,7 @@ static void __cxl_event_trace_record(const struct cxl_memdev *cxlmd,
else if (uuid_equal(uuid, &CXL_EVENT_MEM_MODULE_UUID))
ev_type = CXL_CPER_EVENT_MEM_MODULE;
- cxl_event_trace_record(cxlmd, type, ev_type, uuid, &record->event);
+ cxl_event_handle_record(cxlmd, type, ev_type, uuid, &record->event);
}
static int cxl_clear_event_record(struct cxl_memdev_state *mds,
@@ -1012,8 +1061,8 @@ static void cxl_mem_get_records_log(struct cxl_memdev_state *mds,
break;
for (i = 0; i < nr_rec; i++)
- __cxl_event_trace_record(cxlmd, type,
- &payload->records[i]);
+ __cxl_event_handle_record(cxlmd, type,
+ &payload->records[i]);
if (payload->flags & CXL_GET_EVENT_FLAG_OVERFLOW)
trace_cxl_overflow(cxlmd, type, payload);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index afb53d058d62..5c4810dcbdeb 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -826,10 +826,10 @@ void set_exclusive_cxl_commands(struct cxl_memdev_state *mds,
void clear_exclusive_cxl_commands(struct cxl_memdev_state *mds,
unsigned long *cmds);
void cxl_mem_get_event_records(struct cxl_memdev_state *mds, u32 status);
-void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
- enum cxl_event_log_type type,
- enum cxl_event_type event_type,
- const uuid_t *uuid, union cxl_event *evt);
+void cxl_event_handle_record(struct cxl_memdev *cxlmd,
+ enum cxl_event_log_type type,
+ enum cxl_event_type event_type,
+ const uuid_t *uuid, union cxl_event *evt);
int cxl_set_timestamp(struct cxl_memdev_state *mds);
int cxl_poison_state_init(struct cxl_memdev_state *mds);
int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 4be35dc22202..6e65ca89f666 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -1029,8 +1029,8 @@ static void cxl_handle_cper_event(enum cxl_event_type ev_type,
hdr_flags = get_unaligned_le24(rec->event.generic.hdr.flags);
log_type = FIELD_GET(CXL_EVENT_HDR_FLAGS_REC_SEVERITY, hdr_flags);
- cxl_event_trace_record(cxlds->cxlmd, log_type, ev_type,
- &uuid_null, &rec->event);
+ cxl_event_handle_record(cxlds->cxlmd, log_type, ev_type,
+ &uuid_null, &rec->event);
}
static void cxl_cper_work_fn(struct work_struct *work)
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 0bea1afbd747..be4342a2b597 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -7,6 +7,20 @@
#include <linux/uuid.h>
#include <linux/workqueue_types.h>
+/*
+ * Event transaction type
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+enum cxl_event_transaction_type {
+ CXL_EVENT_TRANSACTION_UNKNOWN = 0X00,
+ CXL_EVENT_TRANSACTION_READ,
+ CXL_EVENT_TRANSACTION_WRITE,
+ CXL_EVENT_TRANSACTION_SCAN_MEDIA,
+ CXL_EVENT_TRANSACTION_INJECT_POISON,
+ CXL_EVENT_TRANSACTION_MEDIA_SCRUB,
+ CXL_EVENT_TRANSACTION_MEDIA_MANAGEMENT,
+};
+
/*
* Common Event Record Format
* CXL rev 3.0 section 8.2.9.2.1; Table 8-42
@@ -26,7 +40,7 @@ struct cxl_event_media_hdr {
__le64 phys_addr;
u8 descriptor;
u8 type;
- u8 transaction_type;
+ u8 transaction_type; /* enum cxl_event_transaction_type */
/*
* The meaning of Validity Flags from bit 2 is
* different across DRAM and General Media records
--
2.34.1
