Received-SPF: pass (google.com: domain of linux-kernel+bounces-14540-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
To: <linux-efi@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<linux-cxl@vger.kernel.org>
CC: Ard Biesheuvel <ardb@kernel.org>, Alison Schofield
	<alison.schofield@intel.com>, Vishal Verma <vishal.l.verma@intel.com>, "Ira
 Weiny" <ira.weiny@intel.com>, Dan Williams <dan.j.williams@intel.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>, Yazen Ghannam
	<yazen.ghannam@amd.com>, Smita Koralahalli
	<Smita.KoralahalliChannabasappa@amd.com>
Subject: [PATCH 3/4] acpi/ghes, efi/cper: Recognize and process CXL Protocol Errors.
Date: Tue, 2 Jan 2024 15:09:32 +0000
Message-ID: <20240102150933.161009-4-Smita.KoralahalliChannabasappa@amd.com>
In-Reply-To: <20240102150933.161009-1-Smita.KoralahalliChannabasappa@amd.com>
References: <20240102150933.161009-1-Smita.KoralahalliChannabasappa@amd.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 02 Jan 2024 15:09:47.5654
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: f8d2e612-3d56-4166-0b03-08dc0ba4dc37
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource:
	SJ1PEPF00001CDE.namprd05.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL1PR12MB5333

UEFI v2.10 section N.2.13 defines a CPER record for CXL Protocol errors.

Add GHES support to detect CXL CPER Protocol record and cache error
severity, device_id, serial number and a pointer to CXL RAS capability
struct in struct cxl_cper_rec_data.

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
---
 drivers/acpi/apei/ghes.c        | 15 ++++++++++
 drivers/firmware/efi/cper_cxl.c | 52 +++++++++++++++++++++++++++++++++
 include/linux/cxl-event.h       |  6 ++++
 3 files changed, 73 insertions(+)

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index d6a85fbc0a8b..6471584b2e79 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -714,6 +714,18 @@ static void cxl_cper_post_event(enum cxl_event_type event_type,
 		cper_callback(event_type, &data);
 }
 
+void cxl_cper_handle_prot_err(struct acpi_hest_generic_data *gdata)
+{
+	struct cxl_cper_rec_data data;
+
+	memset(&data, 0, sizeof(data));
+
+	if (cxl_cper_handle_prot_err_info(gdata, &data))
+		return;
+
+	data.severity = gdata->error_severity;
+}
+
 int cxl_cper_register_callback(cxl_cper_callback callback)
 {
 	guard(rwsem_write)(&cxl_cper_rw_sem);
@@ -768,6 +780,9 @@ 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_PROT_ERR)) {
+			cxl_cper_handle_prot_err(gdata);
+		}
 		else if (guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID)) {
 			struct cxl_cper_event_rec *rec = acpi_hest_get_payload(gdata);
 
diff --git a/drivers/firmware/efi/cper_cxl.c b/drivers/firmware/efi/cper_cxl.c
index 4fd8d783993e..3bc0b9f28c9e 100644
--- a/drivers/firmware/efi/cper_cxl.c
+++ b/drivers/firmware/efi/cper_cxl.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/cper.h>
+#include <acpi/ghes.h>
 #include "cper_cxl.h"
 
 #define PROT_ERR_VALID_AGENT_TYPE		BIT_ULL(0)
@@ -176,3 +177,54 @@ void cper_print_prot_err(const char *pfx, const struct cper_sec_prot_err *prot_e
 			       sizeof(cxl_ras->header_log), 0);
 	}
 }
+
+int cxl_cper_handle_prot_err_info(struct acpi_hest_generic_data *gdata,
+				  struct cxl_cper_rec_data *data)
+{
+	struct cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata);
+	struct cper_cxl_event_devid *device_id = &data->rec.hdr.device_id;
+	struct cper_cxl_event_sn *dev_serial_num =  &data->rec.hdr.dev_serial_num;
+	size_t size = sizeof(*prot_err) + prot_err->dvsec_len;
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_ERROR_LOG)) {
+		pr_err(FW_WARN "Not a valid protocol error log\n");
+		return -EINVAL;
+	}
+
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_DEVICE_ID)) {
+		pr_err(FW_WARN "Not a valid Device ID\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The device ID or agent address is only valid for CXL 1.1 device,
+	 * CXL 2.0 device, CXL 2.0 Logical device, CXL 2.0 Fabric Manager
+	 * Managed Logical Device, CXL Root Port, CXL Downstream Switch
+	 * Port, or CXL Upstream Switch Port.
+	 */
+	if (prot_err->agent_type <= 0x7 && prot_err->agent_type != RCH_DP) {
+		device_id->segment_num = prot_err->agent_addr.segment;
+		device_id->bus_num = prot_err->agent_addr.bus;
+		device_id->device_num = prot_err->agent_addr.device;
+		device_id->func_num = prot_err->agent_addr.function;
+	} else {
+		pr_err(FW_WARN "Not a valid agent type\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * The device serial number is only valid for CXL 1.1 device, CXL
+	 * 2.0 device, CXL 2.0 Logical device, or CXL 2.0 Fabric Manager
+	 * Managed Logical Device.
+	 */
+	if (!(prot_err->valid_bits & PROT_ERR_VALID_SERIAL_NUMBER) ||
+	      prot_err->agent_type > 0x4 || prot_err->agent_type == RCH_DP)
+		pr_warn(FW_WARN "No valid serial number present\n");
+
+	dev_serial_num->lower_dw = prot_err->dev_serial_num.lower_dw;
+	dev_serial_num->upper_dw = prot_err->dev_serial_num.upper_dw;
+
+	data->cxl_ras = (struct cxl_ras_capability_regs *)((long)prot_err + size);
+
+	return 0;
+}
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 90d8390a73cb..7ba2dfd6619e 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -154,11 +154,17 @@ struct cxl_ras_capability_regs {
 
 struct cxl_cper_rec_data {
 	struct cxl_cper_event_rec rec;
+	struct cxl_ras_capability_regs *cxl_ras;
+	int severity;
 };
 
 typedef void (*cxl_cper_callback)(enum cxl_event_type type,
 				  struct cxl_cper_rec_data *data);
 
+struct acpi_hest_generic_data;
+int cxl_cper_handle_prot_err_info(struct acpi_hest_generic_data *gdata,
+				  struct cxl_cper_rec_data *data);
+
 #ifdef CONFIG_ACPI_APEI_GHES
 int cxl_cper_register_callback(cxl_cper_callback callback);
 int cxl_cper_unregister_callback(cxl_cper_callback callback);
-- 
2.17.1