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, 8 insertions, 88 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 0f98f720d9ca..9340e8dc0413 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -32,8 +32,6 @@
 #include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/pci.h>
-#include <linux/devcoredump.h>
-#include <generated/utsrelease.h>
 #include <linux/pci-p2pdma.h>
 #include <linux/apple-gmux.h>
 
@@ -3578,9 +3576,7 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 		if (adev->asic_reset_res)
 			goto fail;
 
-		if (adev->mmhub.ras && adev->mmhub.ras->ras_block.hw_ops &&
-		    adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count)
-			adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count(adev);
+		amdgpu_ras_reset_error_count(adev, AMDGPU_RAS_BLOCK__MMHUB);
 	} else {
 
 		task_barrier_full(&hive->tb);
@@ -5050,90 +5046,16 @@ static int amdgpu_reset_reg_dumps(struct amdgpu_device *adev)
 
 	lockdep_assert_held(&adev->reset_domain->sem);
 
-	for (i = 0; i < adev->num_regs; i++) {
-		adev->reset_dump_reg_value[i] = RREG32(adev->reset_dump_reg_list[i]);
-		trace_amdgpu_reset_reg_dumps(adev->reset_dump_reg_list[i],
-					     adev->reset_dump_reg_value[i]);
-	}
-
-	return 0;
-}
-
-#ifndef CONFIG_DEV_COREDUMP
-static 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, "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->num_regs) {
-		drm_printf(&p, "AMDGPU register dumps:\nOffset:     Value:\n");
-
-		for (i = 0; i < coredump->adev->num_regs; i++)
-			drm_printf(&p, "0x%08x: 0x%08x\n",
-				   coredump->adev->reset_dump_reg_list[i],
-				   coredump->adev->reset_dump_reg_value[i]);
-	}
+	for (i = 0; i < adev->reset_info.num_regs; i++) {
+		adev->reset_info.reset_dump_reg_value[i] =
+			RREG32(adev->reset_info.reset_dump_reg_list[i]);
 
-	return count - iter.remain;
-}
-
-static void amdgpu_devcoredump_free(void *data)
-{
-	kfree(data);
-}
-
-static 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;
+		trace_amdgpu_reset_reg_dumps(adev->reset_info.reset_dump_reg_list[i],
+					     adev->reset_info.reset_dump_reg_value[i]);
 	}
 
-	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);
+	return 0;
 }
-#endif
 
 int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 			 struct amdgpu_reset_context *reset_context)
@@ -5201,9 +5123,7 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 
 	if (!r && amdgpu_ras_intr_triggered()) {
 		list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-			if (tmp_adev->mmhub.ras && tmp_adev->mmhub.ras->ras_block.hw_ops &&
-			    tmp_adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count)
-				tmp_adev->mmhub.ras->ras_block.hw_ops->reset_ras_error_count(tmp_adev);
+			amdgpu_ras_reset_error_count(tmp_adev, AMDGPU_RAS_BLOCK__MMHUB);
 		}
 
 		amdgpu_ras_intr_cleared();