From: Jesse.zhang@amd.com <Jesse.zhang@amd.com>
Date: Wed, 16 Apr 2025 06:13:30 +0000 (+0800)
Subject: drm/amdgpu: optimize queue reset and stop logic for sdma_v5_2
X-Git-Tag: v6.16-rc1~144^2~10^2~168
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=6a07ac702f022dc85b186e7d2bec6216a0c260b0;p=thirdparty%2Fkernel%2Flinux.git

drm/amdgpu: optimize queue reset and stop logic for sdma_v5_2

This patch refactors the SDMA v5.2 queue reset and stop logic to improve
code readability, maintainability, and performance. The key changes include:

1. **Generalized `sdma_v5_2_gfx_stop` Function**:
   - Added an `inst_mask` parameter to allow stopping specific SDMA instances
     instead of all instances. This is useful for resetting individual queues.

2. **Simplified `sdma_v5_2_reset_queue` Function**:
   - Removed redundant loops and checks by directly using the `ring->me` field
     to identify the SDMA instance.
   - Reused the `sdma_v5_2_gfx_stop` function to stop the queue, reducing code
     duplication.

v1: The general coding style is to declare variables like "i" or "r" last. E.g. longest lines first and short lasts. (Chritian)

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>
---

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index fc95c2875ba59..a6e612b4a8928 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -407,15 +407,15 @@ static void sdma_v5_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
  * sdma_v5_2_gfx_stop - stop the gfx async dma engines
  *
  * @adev: amdgpu_device pointer
- *
+ * @inst_mask: mask of dma engine instances to be disabled
  * Stop the gfx async dma ring buffers.
  */
-static void sdma_v5_2_gfx_stop(struct amdgpu_device *adev)
+static void sdma_v5_2_gfx_stop(struct amdgpu_device *adev,  uint32_t inst_mask)
 {
 	u32 rb_cntl, ib_cntl;
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
+	for_each_inst(i, inst_mask) {
 		rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
 		WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
@@ -506,9 +506,11 @@ static void sdma_v5_2_enable(struct amdgpu_device *adev, bool enable)
 {
 	u32 f32_cntl;
 	int i;
+	uint32_t inst_mask;
 
+	inst_mask = GENMASK(adev->sdma.num_instances - 1, 0);
 	if (!enable) {
-		sdma_v5_2_gfx_stop(adev);
+		sdma_v5_2_gfx_stop(adev, inst_mask);
 		sdma_v5_2_rlc_stop(adev);
 	}
 
@@ -1459,33 +1461,18 @@ static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 
 static int sdma_v5_2_stop_queue(struct amdgpu_ring *ring)
 {
-	u32 rb_cntl, ib_cntl, f32_cntl, freeze, cntl, stat1_reg;
+	u32 f32_cntl, freeze, cntl, stat1_reg;
 	struct amdgpu_device *adev = ring->adev;
 	int i, j, r = 0;
 
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (ring == &adev->sdma.instance[i].ring)
-			break;
-	}
-
-	if (i == adev->sdma.num_instances) {
-		DRM_ERROR("sdma instance not found\n");
-		return -EINVAL;
-	}
-
+	i = ring->me;
 	amdgpu_gfx_rlc_enter_safe_mode(adev, 0);
 
 	/* stop queue */
-	ib_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL));
-	ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
-	WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
-
-	rb_cntl = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
-	rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
-	WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
+	sdma_v5_2_gfx_stop(adev, 1 << i);
 
 	/*engine stop SDMA1_F32_CNTL.HALT to 1 and SDMAx_FREEZE freeze bit to 1 */
 	freeze = RREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_FREEZE));