diff mbox series

[v5,7/9] acpi/ghes: Process CXL Component Events

Message ID 20231220-cxl-cper-v5-7-1bb8a4ca2c7a@intel.com
State Accepted
Commit 671a794c33c6e048ca5cedd5ad6af44d52d5d7e5
Headers show
Series efi/cxl-cper: Report CPER CXL component events through trace events | expand

Commit Message

Ira Weiny Dec. 21, 2023, 12:17 a.m. UTC
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 the use of a GUID in
the Section Type rather than a UUID as part of the event itself.

Add GHES support to detect CXL CPER records and call a registered
callback with the event.

A notifier chain was considered for the callback but the complexity did
not justify the use case as only the CXL subsystem requires this event.
Enforce that only one callback can be registered at any time.

Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

---
Ard, Due to Dan's feedback[1] the code is moved to ghes which is
entirely in Rafael's subsystem.  That said I have left you on the CC so
you know what is going on.

Changes for v5
[Smita/djbw: move section type parsing and callback to ghes_do_proc()]
[Smita/djbw: Fix __packed usage]
[djbw/Jonathan: s/notifier/callback/]
[Jonathan: fix typo]
[iweiny: Eliminate parsing the section type a 2nd time]
[iweiny: update error messages]

[1] https://lore.kernel.org/all/6580b21723b2c_269bd294f8@dwillia2-mobl3.amr.corp.intel.com.notmuch/
---
 drivers/acpi/apei/ghes.c  | 88 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/cxl-event.h | 50 +++++++++++++++++++++++++++
 2 files changed, 138 insertions(+)

Comments

Jonathan Cameron Jan. 8, 2024, 1:41 p.m. UTC | #1
On Wed, 20 Dec 2023 16:17:34 -0800
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 the use of a GUID in
> the Section Type rather than a UUID as part of the event itself.
> 
> Add GHES support to detect CXL CPER records and call a registered
> callback with the event.
> 
> A notifier chain was considered for the callback but the complexity did
> not justify the use case as only the CXL subsystem requires this event.
> Enforce that only one callback can be registered at any time.
> 
> Cc: Ard Biesheuvel <ardb@kernel.org>
> Cc: "Rafael J. Wysocki" <rafael@kernel.org>
> Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> 

Very annoying that CXL using UUIDS and UEFI GUIDs (so endian swapped).

Is it worth a general conversion function or just keep the data duplication?

Otherwise LGTM

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
diff mbox series

Patch

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 63ad0541db38..aed465d2fd68 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -26,6 +26,7 @@ 
 #include <linux/interrupt.h>
 #include <linux/timer.h>
 #include <linux/cper.h>
+#include <linux/cxl-event.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/ratelimit.h>
@@ -657,6 +658,78 @@  static void ghes_defer_non_standard_event(struct acpi_hest_generic_data *gdata,
 	schedule_work(&entry->work);
 }
 
+/*
+ * Only a single callback can be registered for CXL CPER events.
+ */
+static DECLARE_RWSEM(cxl_cper_rw_sem);
+static cxl_cper_callback cper_callback;
+
+/* 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)
+
+static void cxl_cper_post_event(enum cxl_event_type event_type,
+				struct cxl_cper_event_rec *rec)
+{
+	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(rwsem_read)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		cper_callback(event_type, rec);
+}
+
+int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (cper_callback)
+		return -EINVAL;
+	cper_callback = callback;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_register_callback, CXL);
+
+int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	guard(rwsem_write)(&cxl_cper_rw_sem);
+	if (callback != cper_callback)
+		return -EINVAL;
+	cper_callback = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_cper_unregister_callback, CXL);
+
 static bool ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
@@ -690,6 +763,21 @@  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);
+		}
+		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 18dab4d90dc8..71e3646f7569 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -108,4 +108,54 @@  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,
+};
+
+#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 cxl_cper_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;
+		} __packed device_id;
+		struct cper_cxl_event_sn {
+			u32 lower_dw;
+			u32 upper_dw;
+		} __packed dev_serial_num;
+	} __packed hdr;
+
+	union cxl_event event;
+} __packed;
+
+typedef void (*cxl_cper_callback)(enum cxl_event_type type,
+				  struct cxl_cper_event_rec *rec);
+
+#ifdef CONFIG_ACPI_APEI_GHES
+int cxl_cper_register_callback(cxl_cper_callback callback);
+int cxl_cper_unregister_callback(cxl_cper_callback callback);
+#else
+static inline int cxl_cper_register_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+
+static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
+{
+	return 0;
+}
+#endif
+
 #endif /* _LINUX_CXL_EVENT_H */