torvalds/linux
torvalds/linux
2
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-09-04 20:19:47 +08:00
Code

drm/amdgpu: optimize queue reset and stop logic for sdma_v5_0

Browse Source 
This patch refactors the SDMA v5.0 queue reset and stop logic to improve
code readability, maintainability, and performance. The key changes include:

1. **Generalized `sdma_v5_0_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_0_reset_queue` Function**:
   - Removed redundant loops and checks by directly using the `ring->me` field
     to identify the SDMA instance.
   - Reused the `sdma_v5_0_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>
This commit is contained in:
Jesse.zhang@amd.com 2025-04-16 14:03:02 +08:00 committed by Alex Deucher
parent 47454f2dc0
commit 574f4b5562
1 changed files with 9 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
View File

@ -557,15 +557,15 @@ static void sdma_v5_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se
* sdma_v5_0_gfx_stop - stop the gfx async dma engines * sdma_v5_0_gfx_stop - stop the gfx async dma engines
* *
* @adev: amdgpu_device pointer * @adev: amdgpu_device pointer
* * @inst_mask: mask of dma engine instances to be disabled
* Stop the gfx async dma ring buffers (NAVI10). * Stop the gfx async dma ring buffers (NAVI10).
*/ */
static void sdma_v5_0_gfx_stop(struct amdgpu_device *adev) static void sdma_v5_0_gfx_stop(struct amdgpu_device *adev, uint32_t inst_mask)
{ {
u32 rb_cntl, ib_cntl; u32 rb_cntl, ib_cntl;
int i; 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_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL)); rb_cntl = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL));
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl); WREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
@ -657,9 +657,11 @@ static void sdma_v5_0_enable(struct amdgpu_device *adev, bool enable)
{ {
u32 f32_cntl; u32 f32_cntl;
int i; int i;
uint32_t inst_mask;
inst_mask = GENMASK(adev->sdma.num_instances - 1, 0);
if (!enable) { if (!enable) {
sdma_v5_0_gfx_stop(adev); sdma_v5_0_gfx_stop(adev, 1 << inst_mask);
sdma_v5_0_rlc_stop(adev); sdma_v5_0_rlc_stop(adev);
} }
@ -1546,33 +1548,18 @@ static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v5_0_stop_queue(struct amdgpu_ring *ring) static int sdma_v5_0_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; struct amdgpu_device *adev = ring->adev;
int i, j, r = 0; int i, j, r = 0;
if (amdgpu_sriov_vf(adev)) if (amdgpu_sriov_vf(adev))
return -EINVAL; return -EINVAL;
for (i = 0; i < adev->sdma.num_instances; i++) { i = ring->me;
if (ring == &adev->sdma.instance[i].ring)
break;
}
if (i == adev->sdma.num_instances) {
DRM_ERROR("sdma instance not found\n");
return -EINVAL;
}
amdgpu_gfx_rlc_enter_safe_mode(adev, 0); amdgpu_gfx_rlc_enter_safe_mode(adev, 0);
/* stop queue */ /* stop queue */
ib_cntl = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL)); sdma_v5_0_gfx_stop(adev, 1 << i);
ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_IB_CNTL), ib_cntl);
rb_cntl = RREG32(sdma_v5_0_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_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
/* engine stop SDMA1_F32_CNTL.HALT to 1 and SDMAx_FREEZE freeze bit to 1 */ /* engine stop SDMA1_F32_CNTL.HALT to 1 and SDMAx_FREEZE freeze bit to 1 */
freeze = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE)); freeze = RREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_FREEZE));