accel/ivpu: Add coredump support

[ Upstream commit bade0340526827d03d9c293450c0422beba77f04 ]

Use coredump (if available) to collect FW logs in case of a FW crash.
This makes dmesg more readable and allows to collect more log data.

Signed-off-by: Karol Wachowski <karol.wachowski@intel.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240930195322.461209-8-jacek.lawrynowicz@linux.intel.com
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Stable-dep-of: 41a2d8286c90 ("accel/ivpu: Fix error handling in recovery/reset")
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/accel/ivpu/Kconfig

@@ -8,6 +8,7 @@ config DRM_ACCEL_IVPU
 	select FW_LOADER
 	select DRM_GEM_SHMEM_HELPER
 	select GENERIC_ALLOCATOR
+	select WANT_DEV_COREDUMP
 	help
 	  Choose this option if you have a system with an 14th generation
 	  Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU)

drivers/accel/ivpu/Makefile

@@ -19,5 +19,6 @@ intel_vpu-y := \
 	ivpu_sysfs.o
 
 intel_vpu-$(CONFIG_DEBUG_FS) += ivpu_debugfs.o
+intel_vpu-$(CONFIG_DEV_COREDUMP) += ivpu_coredump.o
 
 obj-$(CONFIG_DRM_ACCEL_IVPU) += intel_vpu.o

drivers/accel/ivpu/ivpu_coredump.c

@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+
+#include "ivpu_coredump.h"
+#include "ivpu_fw.h"
+#include "ivpu_gem.h"
+#include "vpu_boot_api.h"
+
+#define CRASH_DUMP_HEADER "Intel NPU crash dump"
+#define CRASH_DUMP_HEADERS_SIZE SZ_4K
+
+void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_print_iterator pi = {};
+	struct drm_printer p;
+	size_t coredump_size;
+	char *coredump;
+
+	coredump_size = CRASH_DUMP_HEADERS_SIZE + FW_VERSION_HEADER_SIZE +
+			ivpu_bo_size(vdev->fw->mem_log_crit) + ivpu_bo_size(vdev->fw->mem_log_verb);
+	coredump = vmalloc(coredump_size);
+	if (!coredump)
+		return;
+
+	pi.data = coredump;
+	pi.remain = coredump_size;
+	p = drm_coredump_printer(&pi);
+
+	drm_printf(&p, "%s\n", CRASH_DUMP_HEADER);
+	drm_printf(&p, "FW version: %s\n", vdev->fw->version);
+	ivpu_fw_log_print(vdev, false, &p);
+
+	dev_coredumpv(vdev->drm.dev, coredump, pi.offset, GFP_KERNEL);
+}

drivers/accel/ivpu/ivpu_coredump.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+#ifndef __IVPU_COREDUMP_H__
+#define __IVPU_COREDUMP_H__
+
+#include <drm/drm_print.h>
+
+#include "ivpu_drv.h"
+#include "ivpu_fw_log.h"
+
+#ifdef CONFIG_DEV_COREDUMP
+void ivpu_dev_coredump(struct ivpu_device *vdev);
+#else
+static inline void ivpu_dev_coredump(struct ivpu_device *vdev)
+{
+	struct drm_printer p = drm_info_printer(vdev->drm.dev);
+
+	ivpu_fw_log_print(vdev, false, &p);
+}
+#endif
+
+#endif /* __IVPU_COREDUMP_H__ */

drivers/accel/ivpu/ivpu_drv.c

@@ -14,7 +14,7 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_prime.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_debugfs.h"
 #include "ivpu_drv.h"
 #include "ivpu_fw.h"
@@ -29,6 +29,7 @@
 #include "ivpu_ms.h"
 #include "ivpu_pm.h"
 #include "ivpu_sysfs.h"
+#include "vpu_boot_api.h"
 
 #ifndef DRIVER_VERSION_STR
 #define DRIVER_VERSION_STR __stringify(DRM_IVPU_DRIVER_MAJOR) "." \
@@ -382,7 +383,7 @@ int ivpu_boot(struct ivpu_device *vdev)
 		ivpu_err(vdev, "Failed to boot the firmware: %d\n", ret);
 		ivpu_hw_diagnose_failure(vdev);
 		ivpu_mmu_evtq_dump(vdev);
-		ivpu_fw_log_dump(vdev);
+		ivpu_dev_coredump(vdev);
 		return ret;
 	}
 

drivers/accel/ivpu/ivpu_fw_log.h

@@ -8,8 +8,6 @@
 
 #include <linux/types.h>
 
-#include <drm/drm_print.h>
-
 #include "ivpu_drv.h"
 
 #define IVPU_FW_LOG_DEFAULT 0
@@ -28,11 +26,5 @@ extern unsigned int ivpu_log_level;
 void ivpu_fw_log_print(struct ivpu_device *vdev, bool only_new_msgs, struct drm_printer *p);
 void ivpu_fw_log_clear(struct ivpu_device *vdev);
 
-static inline void ivpu_fw_log_dump(struct ivpu_device *vdev)
-{
-	struct drm_printer p = drm_info_printer(vdev->drm.dev);
-
-	ivpu_fw_log_print(vdev, false, &p);
-}
 
 #endif /* __IVPU_FW_LOG_H__ */

drivers/accel/ivpu/ivpu_pm.c

@@ -9,17 +9,18 @@
 #include <linux/pm_runtime.h>
 #include <linux/reboot.h>
 
-#include "vpu_boot_api.h"
+#include "ivpu_coredump.h"
 #include "ivpu_drv.h"
-#include "ivpu_hw.h"
 #include "ivpu_fw.h"
 #include "ivpu_fw_log.h"
+#include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
 #include "ivpu_ms.h"
 #include "ivpu_pm.h"
+#include "vpu_boot_api.h"
 
 static bool ivpu_disable_recovery;
 module_param_named_unsafe(disable_recovery, ivpu_disable_recovery, bool, 0644);
@@ -123,7 +124,7 @@ static void ivpu_pm_recovery_work(struct work_struct *work)
 	if (ret)
 		ivpu_err(vdev, "Failed to resume NPU: %d\n", ret);
 
-	ivpu_fw_log_dump(vdev);
+	ivpu_dev_coredump(vdev);
 
 	atomic_inc(&vdev->pm->reset_counter);
 	atomic_set(&vdev->pm->reset_pending, 1);
@@ -262,7 +263,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 	if (!is_idle || ret_d0i3) {
 		ivpu_err(vdev, "Forcing cold boot due to previous errors\n");
 		atomic_inc(&vdev->pm->reset_counter);
-		ivpu_fw_log_dump(vdev);
+		ivpu_dev_coredump(vdev);
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
 		ivpu_pm_prepare_warm_boot(vdev);