drm/amdgpu: Implement SDMA soft reset directly for v5.x

commit 5c3e7c49538e2ddad10296a318c225bbb3d37d20 upstream.

This patch introduces a new function `amdgpu_sdma_soft_reset` to handle SDMA soft resets directly,
rather than relying on the DPM interface.

1. **New `amdgpu_sdma_soft_reset` Function**:
   - Implements a soft reset for SDMA engines by directly writing to the hardware registers.
   - Handles SDMA versions 4.x and 5.x separately:
     - For SDMA 4.x, the existing `amdgpu_dpm_reset_sdma` function is used for backward compatibility.
     - For SDMA 5.x, the driver directly manipulates the `GRBM_SOFT_RESET` register to reset the specified SDMA instance.

2. **Integration into `amdgpu_sdma_reset_engine`**:
   - The `amdgpu_sdma_soft_reset` function is called during the SDMA reset process, replacing the previous call to `amdgpu_dpm_reset_sdma`.

v2: r should default to an error (Alex)

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Stable-dep-of: 09b585592fa4 ("drm/amdgpu: Fix SDMA engine reset with logical instance ID")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 37 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 529c9696c2f3..b80e80d7ff55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -26,6 +26,8 @@
 #include "amdgpu_sdma.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_reset.h"
+#include "gc/gc_10_1_0_offset.h"
+#include "gc/gc_10_3_0_sh_mask.h"
 
 #define AMDGPU_CSA_SDMA_SIZE 64
 /* SDMA CSA reside in the 3rd page of CSA */
@@ -561,6 +563,40 @@ void amdgpu_sdma_register_on_reset_callbacks(struct amdgpu_device *adev, struct
 	list_add_tail(&funcs->list, &adev->sdma.reset_callback_list);
 }
 
+static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
+{
+	struct amdgpu_sdma_instance *sdma_instance = &adev->sdma.instance[instance_id];
+	int r = -EOPNOTSUPP;
+
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(4, 4, 2):
+	case IP_VERSION(4, 4, 4):
+	case IP_VERSION(4, 4, 5):
+		/* For SDMA 4.x, use the existing DPM interface for backward compatibility */
+		r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+		break;
+	case IP_VERSION(5, 0, 0):
+	case IP_VERSION(5, 0, 1):
+	case IP_VERSION(5, 0, 2):
+	case IP_VERSION(5, 0, 5):
+	case IP_VERSION(5, 2, 0):
+	case IP_VERSION(5, 2, 2):
+	case IP_VERSION(5, 2, 4):
+	case IP_VERSION(5, 2, 5):
+	case IP_VERSION(5, 2, 6):
+	case IP_VERSION(5, 2, 3):
+	case IP_VERSION(5, 2, 1):
+	case IP_VERSION(5, 2, 7):
+		if (sdma_instance->funcs->soft_reset_kernel_queue)
+			r = sdma_instance->funcs->soft_reset_kernel_queue(adev, instance_id);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
 /**
  * amdgpu_sdma_reset_engine - Reset a specific SDMA engine
  * @adev: Pointer to the AMDGPU device
@@ -611,7 +647,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 	}
 
 	/* Perform the SDMA reset for the specified instance */
-	ret = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+	ret = amdgpu_sdma_soft_reset(adev, instance_id);
 	if (ret) {
 		dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
 		goto exit;