diff mbox series

[RFC,5/9] ACPI: APEI: GHES: Use ERST to serialize APEI generic error before panic

Message ID 20230916130316.65815-6-xueshuai@linux.alibaba.com
State Superseded
Headers show
Series Use ERST for persistent storage of MCE and APEI errors | expand

Commit Message

Shuai Xue Sept. 16, 2023, 1:03 p.m. UTC
In certain scenarios (ie. hosts/guests with root filesystems on
NFS/iSCSI where networking software and/or hardware fails, and thus
kdump fails), it is necessary to serialize hardware error information
available for post-mortem debugging.

Save the hardware error log into flash via ERST before go panic, the
hardware error log can be gotten from the flash after system boot
successful again, which is very useful in production.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
---
 drivers/acpi/apei/ghes.c | 44 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
diff mbox series

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d14e00751161..16701f889b73 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -41,6 +41,7 @@ 
 #include <linux/uuid.h>
 #include <linux/ras.h>
 #include <linux/task_work.h>
+#include <linux/pstore.h>
 
 #include <acpi/actbl1.h>
 #include <acpi/ghes.h>
@@ -636,6 +637,43 @@  static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+static int ghes_serialize_estatus(struct acpi_hest_generic_data *gdata, u8 notify_type)
+{
+	void *err = acpi_hest_get_payload(gdata);
+	int data_len = gdata->error_data_length;
+	struct cper_pstore_record *rcd;
+	int record_len = data_len + sizeof(*rcd);
+
+	rcd = kmalloc(record_len, GFP_KERNEL);
+	memset(rcd, 0, sizeof(rcd));
+
+	memcpy(rcd->hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
+	rcd->hdr.revision = CPER_RECORD_REV;
+	rcd->hdr.signature_end = CPER_SIG_END;
+	rcd->hdr.section_count = 1;
+	rcd->hdr.error_severity = CPER_SEV_FATAL;
+	/* timestamp, platform_id, partition_id are all invalid */
+	rcd->hdr.validation_bits = 0;
+	rcd->hdr.record_length = record_len;
+	rcd->hdr.creator_id = CPER_CREATOR_PSTORE;
+	rcd->hdr.notification_type = CPER_NOTIFY_MCE;
+	rcd->hdr.record_id = cper_next_record_id();
+	rcd->hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;
+
+	rcd->sec_hdr.section_offset = (void *)&rcd->data - (void *)&rcd;
+	rcd->sec_hdr.section_length = data_len;
+	rcd->sec_hdr.revision = CPER_SEC_REV;
+	/* ->ru_id and fru_text is invalid */
+	rcd->sec_hdr.validation_bits = 0;
+	rcd->sec_hdr.flags = CPER_SEC_PRIMARY;
+	rcd->sec_hdr.section_type = gdata->section_type;
+	rcd->sec_hdr.section_severity = gdata->error_severity;
+
+	memcpy(&rcd->data, err, data_len);
+
+	return erst_write(&rcd->hdr);
+}
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -861,10 +899,16 @@  static void __ghes_panic(struct ghes *ghes,
 			 struct acpi_hest_generic_status *estatus,
 			 u64 buf_paddr, enum fixed_addresses fixmap_idx)
 {
+	struct acpi_hest_generic_data *gdata;
+	u8 notify_type = ghes->generic->notify.type;
+
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
+	apei_estatus_for_each_section(estatus, gdata)
+		ghes_serialize_estatus(gdata, notify_type);
+
 	/* reboot to log the error! */
 	if (!panic_timeout)
 		panic_timeout = ghes_panic_timeout;