Merge tag 'amd-drm-next-6.7-2023-10-20' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.7-2023-10-20:

amdgpu:
- SMU 13 updates
- UMSCH updates
- DC MPO fixes
- RAS updates
- MES 11 fixes
- Fix possible memory leaks in error pathes
- GC 11.5 fixes
- Kernel doc updates
- PSP updates
- APU IMU fixes
- Misc code cleanups
- SMU 11 fixes
- OD fix
- Frame size warning fixes
- SR-IOV fixes
- NBIO 7.11 updates
- NBIO 7.7 updates
- XGMI fixes
- devcoredump updates

amdkfd:
- Misc code cleanups
- SVM fixes

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231020195043.4937-1-alexander.deucher@amd.com

1 files changed, 80 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index 970bfece775c..4baa300121d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -21,6 +21,9 @@
  *
  */
 
+#include <linux/devcoredump.h>
+#include <generated/utsrelease.h>
+
 #include "amdgpu_reset.h"
 #include "aldebaran.h"
 #include "sienna_cichlid.h"
@@ -159,5 +162,82 @@ void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain)
 	up_write(&reset_domain->sem);
 }
 
+#ifndef CONFIG_DEV_COREDUMP
+void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
+		     struct amdgpu_reset_context *reset_context)
+{
+}
+#else
+static ssize_t
+amdgpu_devcoredump_read(char *buffer, loff_t offset, size_t count,
+			void *data, size_t datalen)
+{
+	struct drm_printer p;
+	struct amdgpu_coredump_info *coredump = data;
+	struct drm_print_iterator iter;
+	int i;
+
+	iter.data = buffer;
+	iter.offset = 0;
+	iter.start = offset;
+	iter.remain = count;
+
+	p = drm_coredump_printer(&iter);
+
+	drm_printf(&p, "**** AMDGPU Device Coredump ****\n");
+	drm_printf(&p, "version: " AMDGPU_COREDUMP_VERSION "\n");
+	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
+	drm_printf(&p, "time: %lld.%09ld\n", coredump->reset_time.tv_sec,
+			coredump->reset_time.tv_nsec);
+
+	if (coredump->reset_task_info.pid)
+		drm_printf(&p, "process_name: %s PID: %d\n",
+			   coredump->reset_task_info.process_name,
+			   coredump->reset_task_info.pid);
+
+	if (coredump->reset_vram_lost)
+		drm_printf(&p, "VRAM is lost due to GPU reset!\n");
+	if (coredump->adev->reset_info.num_regs) {
+		drm_printf(&p, "AMDGPU register dumps:\nOffset:     Value:\n");
+
+		for (i = 0; i < coredump->adev->reset_info.num_regs; i++)
+			drm_printf(&p, "0x%08x: 0x%08x\n",
+				   coredump->adev->reset_info.reset_dump_reg_list[i],
+				   coredump->adev->reset_info.reset_dump_reg_value[i]);
+	}
+
+	return count - iter.remain;
+}
 
+static void amdgpu_devcoredump_free(void *data)
+{
+	kfree(data);
+}
 
+void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost,
+		     struct amdgpu_reset_context *reset_context)
+{
+	struct amdgpu_coredump_info *coredump;
+	struct drm_device *dev = adev_to_drm(adev);
+
+	coredump = kzalloc(sizeof(*coredump), GFP_NOWAIT);
+
+	if (!coredump) {
+		DRM_ERROR("%s: failed to allocate memory for coredump\n", __func__);
+		return;
+	}
+
+	coredump->reset_vram_lost = vram_lost;
+
+	if (reset_context->job && reset_context->job->vm)
+		coredump->reset_task_info = reset_context->job->vm->task_info;
+
+	coredump->adev = adev;
+
+	ktime_get_ts64(&coredump->reset_time);
+
+	dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT,
+		      amdgpu_devcoredump_read, amdgpu_devcoredump_free);
+}
+#endif