drm/amdgpu/gfx8: wait for completion in KIQ init

We need to make sure the various init sequences submitted
to KIQ complete before testing the rings.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2017-03-29 13:15:22 -04:00
parent 4fdca894bb
commit f776952b76
1 changed files with 78 additions and 10 deletions

View File

@ -4639,9 +4639,25 @@ static void gfx_v8_0_kiq_setting(struct amdgpu_ring *ring)
WREG32(mmRLC_CP_SCHEDULERS, tmp);
}
static void gfx_v8_0_kiq_enable(struct amdgpu_ring *ring)
static int gfx_v8_0_kiq_enable(struct amdgpu_ring *ring)
{
amdgpu_ring_alloc(ring, 8);
struct amdgpu_device *adev = ring->adev;
uint32_t scratch, tmp = 0;
int r, i;
r = amdgpu_gfx_scratch_get(adev, &scratch);
if (r) {
DRM_ERROR("Failed to get scratch reg (%d).\n", r);
return r;
}
WREG32(scratch, 0xCAFEDEAD);
r = amdgpu_ring_alloc(ring, 11);
if (r) {
DRM_ERROR("Failed to lock KIQ (%d).\n", r);
amdgpu_gfx_scratch_free(adev, scratch);
return r;
}
/* set resources */
amdgpu_ring_write(ring, PACKET3(PACKET3_SET_RESOURCES, 6));
amdgpu_ring_write(ring, 0); /* vmid_mask:0 queue_type:0 (KIQ) */
@ -4651,20 +4667,53 @@ static void gfx_v8_0_kiq_enable(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, 0); /* gws mask hi */
amdgpu_ring_write(ring, 0); /* oac mask */
amdgpu_ring_write(ring, 0); /* gds heap base:0, gds heap size:0 */
/* write to scratch for completion */
amdgpu_ring_write(ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
amdgpu_ring_write(ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
amdgpu_ring_write(ring, 0xDEADBEEF);
amdgpu_ring_commit(ring);
udelay(50);
for (i = 0; i < adev->usec_timeout; i++) {
tmp = RREG32(scratch);
if (tmp == 0xDEADBEEF)
break;
DRM_UDELAY(1);
}
if (i >= adev->usec_timeout) {
DRM_ERROR("KIQ enable failed (scratch(0x%04X)=0x%08X)\n",
scratch, tmp);
r = -EINVAL;
}
amdgpu_gfx_scratch_free(adev, scratch);
return r;
}
static void gfx_v8_0_map_queue_enable(struct amdgpu_ring *kiq_ring,
struct amdgpu_ring *ring)
static int gfx_v8_0_map_queue_enable(struct amdgpu_ring *kiq_ring,
struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = kiq_ring->adev;
uint64_t mqd_addr, wptr_addr;
uint32_t scratch, tmp = 0;
int r, i;
r = amdgpu_gfx_scratch_get(adev, &scratch);
if (r) {
DRM_ERROR("Failed to get scratch reg (%d).\n", r);
return r;
}
WREG32(scratch, 0xCAFEDEAD);
mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
amdgpu_ring_alloc(kiq_ring, 8);
r = amdgpu_ring_alloc(kiq_ring, 11);
if (r) {
DRM_ERROR("Failed to lock KIQ (%d).\n", r);
amdgpu_gfx_scratch_free(adev, scratch);
return r;
}
/* map queues */
amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
amdgpu_ring_write(kiq_ring, 0x21010000);
@ -4676,8 +4725,26 @@ static void gfx_v8_0_map_queue_enable(struct amdgpu_ring *kiq_ring,
amdgpu_ring_write(kiq_ring, upper_32_bits(mqd_addr));
amdgpu_ring_write(kiq_ring, lower_32_bits(wptr_addr));
amdgpu_ring_write(kiq_ring, upper_32_bits(wptr_addr));
/* write to scratch for completion */
amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_UCONFIG_REG, 1));
amdgpu_ring_write(kiq_ring, (scratch - PACKET3_SET_UCONFIG_REG_START));
amdgpu_ring_write(kiq_ring, 0xDEADBEEF);
amdgpu_ring_commit(kiq_ring);
udelay(50);
for (i = 0; i < adev->usec_timeout; i++) {
tmp = RREG32(scratch);
if (tmp == 0xDEADBEEF)
break;
DRM_UDELAY(1);
}
if (i >= adev->usec_timeout) {
DRM_ERROR("KCQ %d enable failed (scratch(0x%04X)=0x%08X)\n",
ring->idx, scratch, tmp);
r = -EINVAL;
}
amdgpu_gfx_scratch_free(adev, scratch);
return r;
}
static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
@ -4903,6 +4970,7 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
struct vi_mqd *mqd = ring->mqd_ptr;
bool is_kiq = (ring->funcs->type == AMDGPU_RING_TYPE_KIQ);
int mqd_idx = AMDGPU_MAX_COMPUTE_RINGS;
int r;
if (is_kiq) {
gfx_v8_0_kiq_setting(&kiq->ring);
@ -4941,11 +5009,11 @@ static int gfx_v8_0_kiq_init_queue(struct amdgpu_ring *ring)
}
if (is_kiq)
gfx_v8_0_kiq_enable(ring);
r = gfx_v8_0_kiq_enable(ring);
else
gfx_v8_0_map_queue_enable(&kiq->ring, ring);
r = gfx_v8_0_map_queue_enable(&kiq->ring, ring);
return 0;
return r;
}
static int gfx_v8_0_kiq_resume(struct amdgpu_device *adev)