drm/amdgpu: Fix SDMA engine reset with logical instance ID

commit 09b585592fa481384597c81388733aed4a04dd05 upstream.

This commit makes the following improvements to SDMA engine reset handling:

1. Clarifies in the function documentation that instance_id refers to a logical ID
2. Adds conversion from logical to physical instance ID before performing reset
   using GET_INST(SDMA0, instance_id) macro
3. Improves error messaging to indicate when a logical instance reset fails
4. Adds better code organization with blank lines for readability

The change ensures proper SDMA engine reset by using the correct physical
instance ID while maintaining the logical ID interface for callers.

V2: Remove harvest_config check and convert directly to physical instance (Lijo)

Suggested-by: Jonathan Kim <jonathan.kim@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>
(cherry picked from commit 5efa6217c239ed1ceec0f0414f9b6f6927387dfc)
Cc: stable@vger.kernel.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index b80e80d7ff557af3dba93c5613ae20821ca2b20b..c2242bd5ecc4de7133c3767036b1e1f665687ec2 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -572,8 +572,10 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
        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);
+               /* For SDMA 4.x, use the existing DPM interface for backward compatibility,
+                * we need to convert the logical instance ID to physical instance ID before reset.
+                */
+               r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, instance_id));
                break;
        case IP_VERSION(5, 0, 0):
        case IP_VERSION(5, 0, 1):
@@ -600,7 +602,7 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
 /**
  * amdgpu_sdma_reset_engine - Reset a specific SDMA engine
  * @adev: Pointer to the AMDGPU device
- * @instance_id: ID of the SDMA engine instance to reset
+ * @instance_id: Logical ID of the SDMA engine instance to reset
  *
  * This function performs the following steps:
  * 1. Calls all registered pre_reset callbacks to allow KFD and AMDGPU to save their state.
@@ -649,7 +651,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
        /* Perform the SDMA reset for the specified instance */
        ret = amdgpu_sdma_soft_reset(adev, instance_id);
        if (ret) {
-               dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
+               dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id);
                goto exit;
        }