We already allocate this as part of the ring structure,
use that instead.
Cc: Frank Min <Frank.Min at amd.com>
Reviewed-by: Christian König <christian.koenig at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 -
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 45 +++++++---------------------------
2 files changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9533aed..27ccdde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1205,7 +1205,6 @@ struct amdgpu_sdma_instance {
struct amdgpu_ring ring;
bool burst_nop;
- uint32_t poll_mem_offs;
};
struct amdgpu_sdma {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index c76727b..85b8561 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -287,8 +287,6 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
*/
static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
{
- int i;
- u32 offset;
struct amdgpu_device *adev = ring->adev;
DRM_DEBUG("Setting write pointer\n");
@@ -306,16 +304,6 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
WRITE_ONCE(*wb, (ring->wptr << 2));
DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
ring->doorbell_index, ring->wptr << 2);
-
- if (amdgpu_sriov_vf(adev)) {
- for (i = 0; i < adev->sdma.num_instances; i++) {
- if (&adev->sdma.instance[i].ring == ring) {
- offset = adev->sdma.instance[i].poll_mem_offs;
- atomic64_set((atomic64_t *)&adev->wb.wb[offset],
- (ring->wptr << 2));
- }
- }
- }
WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
} else {
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
@@ -586,12 +574,13 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable)
static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
{
struct amdgpu_ring *ring;
- u32 rb_cntl, ib_cntl, wptr_poll_addr_lo, wptr_poll_addr_hi, wptr_poll_cntl;
+ u32 rb_cntl, ib_cntl, wptr_poll_cntl;
u32 rb_bufsz;
- u32 wb_offset, poll_offset;
+ u32 wb_offset;
u32 doorbell;
u32 doorbell_offset;
u32 temp;
+ u64 wptr_gpu_addr;
int i, r;
for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -702,17 +691,14 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
amdgpu_ttm_set_active_vram_size(adev, adev->mc.real_vram_size);
if (amdgpu_sriov_vf(adev)) {
- poll_offset = adev->sdma.instance[i].poll_mem_offs * 4;
-
+ wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
- wptr_poll_addr_lo = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO));
- wptr_poll_addr_lo = REG_SET_FIELD(wptr_poll_addr_lo, SDMA0_GFX_RB_WPTR_POLL_ADDR_LO, ADDR,
- lower_32_bits(adev->wb.gpu_addr + poll_offset) >> 2);
- wptr_poll_addr_hi = upper_32_bits(adev->wb.gpu_addr + poll_offset);
wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
- WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO), wptr_poll_addr_lo);
- WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI), wptr_poll_addr_hi);
+ WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
+ lower_32_bits(wptr_gpu_addr));
+ WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
+ upper_32_bits(wptr_gpu_addr));
WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
}
}
@@ -1275,15 +1261,6 @@ static int sdma_v4_0_sw_init(void *handle)
(i == 0) ?
AMDGPU_SDMA_IRQ_TRAP0 :
AMDGPU_SDMA_IRQ_TRAP1);
-
- if (amdgpu_sriov_vf(adev)) {
- r = amdgpu_wb_get(adev,
- &adev->sdma.instance[i].poll_mem_offs);
- if (r) {
- dev_err(adev->dev, "(%d) failed to allocate SDMA poll mem wb.\n", r);
- return r;
- }
- }
if (r)
return r;
}
@@ -1296,13 +1273,9 @@ static int sdma_v4_0_sw_fini(void *handle)
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i;
- for (i = 0; i < adev->sdma.num_instances; i++) {
+ for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
- if (amdgpu_sriov_vf(adev))
- amdgpu_wb_free(adev,
- adev->sdma.instance[i].poll_mem_offs);
- }
return 0;
}
--
2.5.5
