Pipes provide better concurrency than queues, therefore we want to make
sure that apps use queues from different pipes whenever possible.
Optimize for the trivial case where an app will consume rings in order,
therefore we don't want adjacent rings to belong to the same pipe.
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 13 ++++++
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 78 +++++++++++++++++++-------------
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 83 +++++++++++++++++++++--------------
3 files changed, 109 insertions(+), 65 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index f9df217..377f58a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1639,20 +1639,33 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
for (i = 0; i < adev->sdma.num_instances; i++)
if (&adev->sdma.instance[i].ring == ring)
break;
if (i < AMDGPU_MAX_SDMA_INSTANCES)
return &adev->sdma.instance[i];
else
return NULL;
}
+static inline bool amdgpu_is_mec_queue_enabled(struct amdgpu_device *adev,
+ int mec, int pipe, int queue)
+{
+ int bit = 0;
+
+ bit += mec * adev->gfx.mec.num_pipe_per_mec
+ * adev->gfx.mec.num_queue_per_pipe;
+ bit += pipe * adev->gfx.mec.num_queue_per_pipe;
+ bit += queue;
+
+ return test_bit(bit, adev->gfx.mec.queue_bitmap);
+}
+
/*
* ASICs macro.
*/
#define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
#define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
#define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
#define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d))
#define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec))
#define amdgpu_get_pcie_lanes(adev) (adev)->asic_funcs->get_pcie_lanes((adev))
#define amdgpu_set_pcie_lanes(adev, l) (adev)->asic_funcs->set_pcie_lanes((adev), (l))
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 68265b7..3ca5519 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4720,25 +4720,56 @@ static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev)
case 2:
gb_addr_config |= (1 << GB_ADDR_CONFIG__ROW_SIZE__SHIFT);
break;
case 4:
gb_addr_config |= (2 << GB_ADDR_CONFIG__ROW_SIZE__SHIFT);
break;
}
adev->gfx.config.gb_addr_config = gb_addr_config;
}
+static int gfx_v7_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
+ int mec, int pipe, int queue)
+{
+ int r;
+ unsigned irq_type;
+ struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id];
+
+ /* mec0 is me1 */
+ ring->me = mec + 1;
+ ring->pipe = pipe;
+ ring->queue = queue;
+
+ ring->ring_obj = NULL;
+ ring->use_doorbell = true;
+ ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + ring_id;
+ sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
+
+ irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP
+ + ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
+ + ring->pipe;
+
+ /* type-2 packets are deprecated on MEC, use type-3 instead */
+ r = amdgpu_ring_init(adev, ring, 1024,
+ &adev->gfx.eop_irq, irq_type);
+ if (r)
+ return r;
+
+
+ return 0;
+}
+
static int gfx_v7_0_sw_init(void *handle)
{
struct amdgpu_ring *ring;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int i, r, ring_id;
+ int i, j, k, r, ring_id;
/* EOP Event */
r = amdgpu_irq_add_id(adev, 181, &adev->gfx.eop_irq);
if (r)
return r;
/* Privileged reg */
r = amdgpu_irq_add_id(adev, 184, &adev->gfx.priv_reg_irq);
if (r)
return r;
@@ -4772,53 +4803,38 @@ static int gfx_v7_0_sw_init(void *handle)
for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
ring = &adev->gfx.gfx_ring[i];
ring->ring_obj = NULL;
sprintf(ring->name, "gfx");
r = amdgpu_ring_init(adev, ring, 1024,
&adev->gfx.eop_irq, AMDGPU_CP_IRQ_GFX_EOP);
if (r)
return r;
}
- /* set up the compute queues */
- for (i = 0, ring_id = 0; i < AMDGPU_MAX_QUEUES; i++) {
- unsigned irq_type;
-
- if (!test_bit(i, adev->gfx.mec.queue_bitmap))
- continue;
-
- ring = &adev->gfx.compute_ring[ring_id];
-
- /* mec0 is me1 */
- ring->me = ((i / adev->gfx.mec.num_queue_per_pipe)
- / adev->gfx.mec.num_pipe_per_mec)
- + 1;
- ring->pipe = (i / adev->gfx.mec.num_queue_per_pipe)
- % adev->gfx.mec.num_pipe_per_mec;
- ring->queue = i % adev->gfx.mec.num_queue_per_pipe;
-
- ring->ring_obj = NULL;
- ring->use_doorbell = true;
- ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + ring_id;
- sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
+ /* set up the compute queues - allocate horizontally across pipes */
+ ring_id = 0;
+ for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; ++i) {
+ for (j = 0; j < adev->gfx.mec.num_queue_per_pipe; j++) {
+ for (k = 0; k < adev->gfx.mec.num_pipe_per_mec; k++) {
- irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP
- + ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
- + ring->pipe;
+ if (!amdgpu_is_mec_queue_enabled(adev, i, k, j))
+ continue;
- /* type-2 packets are deprecated on MEC, use type-3 instead */
- r = amdgpu_ring_init(adev, ring, 1024,
- &adev->gfx.eop_irq, irq_type);
- if (r)
- return r;
+ r = gfx_v7_0_compute_ring_init(adev,
+ ring_id,
+ i, k, j);
+ if (r)
+ return r;
- ring_id++;
+ ring_id++;
+ }
+ }
}
/* reserve GDS, GWS and OA resource for gfx */
r = amdgpu_bo_create_kernel(adev, adev->gds.mem.gfx_partition_size,
PAGE_SIZE, AMDGPU_GEM_DOMAIN_GDS,
&adev->gds.gds_gfx_bo, NULL, NULL);
if (r)
return r;
r = amdgpu_bo_create_kernel(adev, adev->gds.gws.gfx_partition_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 861334b..edddd86 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2115,23 +2115,56 @@ static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
break;
case 4:
gb_addr_config = REG_SET_FIELD(gb_addr_config, GB_ADDR_CONFIG, ROW_SIZE, 2);
break;
}
adev->gfx.config.gb_addr_config = gb_addr_config;
return 0;
}
+static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
+ int mec, int pipe, int queue)
+{
+ int r;
+ unsigned irq_type;
+ struct amdgpu_ring *ring = &adev->gfx.compute_ring[ring_id];
+
+ ring = &adev->gfx.compute_ring[ring_id];
+
+ /* mec0 is me1 */
+ ring->me = mec + 1;
+ ring->pipe = pipe;
+ ring->queue = queue;
+
+ ring->ring_obj = NULL;
+ ring->use_doorbell = true;
+ ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + ring_id;
+ sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
+
+ irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP
+ + ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
+ + ring->pipe;
+
+ /* type-2 packets are deprecated on MEC, use type-3 instead */
+ r = amdgpu_ring_init(adev, ring, 1024,
+ &adev->gfx.eop_irq, irq_type);
+ if (r)
+ return r;
+
+
+ return 0;
+}
+
static int gfx_v8_0_sw_init(void *handle)
{
- int i, r, ring_id;
+ int i, j, k, r, ring_id;
struct amdgpu_ring *ring;
struct amdgpu_kiq *kiq;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* KIQ event */
r = amdgpu_irq_add_id(adev, 178, &adev->gfx.kiq.irq);
if (r)
return r;
/* EOP Event */
@@ -2192,56 +2225,38 @@ static int gfx_v8_0_sw_init(void *handle)
ring->use_doorbell = true;
ring->doorbell_index = AMDGPU_DOORBELL_GFX_RING0;
}
r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
AMDGPU_CP_IRQ_GFX_EOP);
if (r)
return r;
}
- /* set up the compute queues */
- for (i = 0, ring_id = 0; i < AMDGPU_MAX_QUEUES; i++) {
- unsigned irq_type;
-
- if (!test_bit(i, adev->gfx.mec.queue_bitmap))
- continue;
-
- if (WARN_ON(ring_id >= AMDGPU_MAX_COMPUTE_RINGS))
- break;
-
- ring = &adev->gfx.compute_ring[ring_id];
-
- /* mec0 is me1 */
- ring->me = ((i / adev->gfx.mec.num_queue_per_pipe)
- / adev->gfx.mec.num_pipe_per_mec)
- + 1;
- ring->pipe = (i / adev->gfx.mec.num_queue_per_pipe)
- % adev->gfx.mec.num_pipe_per_mec;
- ring->queue = i % adev->gfx.mec.num_queue_per_pipe;
-
- ring->ring_obj = NULL;
- ring->use_doorbell = true;
- ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + ring_id;
- sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
+ /* set up the compute queues - allocate horizontally across pipes */
+ ring_id = 0;
+ for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; ++i) {
+ for (j = 0; j < adev->gfx.mec.num_queue_per_pipe; j++) {
+ for (k = 0; k < adev->gfx.mec.num_pipe_per_mec; k++) {
- irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP
- + ((ring->me - 1) * adev->gfx.mec.num_pipe_per_mec)
- + ring->pipe;
+ if (!amdgpu_is_mec_queue_enabled(adev, i, k, j))
+ continue;
- /* type-2 packets are deprecated on MEC, use type-3 instead */
- r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
- irq_type);
- if (r)
- return r;
+ r = gfx_v8_0_compute_ring_init(adev,
+ ring_id,
+ i, k, j);
+ if (r)
+ return r;
- ring_id++;
+ ring_id++;
+ }
+ }
}
/* reserve GDS, GWS and OA resource for gfx */
r = amdgpu_bo_create_kernel(adev, adev->gds.mem.gfx_partition_size,
PAGE_SIZE, AMDGPU_GEM_DOMAIN_GDS,
&adev->gds.gds_gfx_bo, NULL, NULL);
if (r)
return r;
r = amdgpu_bo_create_kernel(adev, adev->gds.gws.gfx_partition_size,
--
2.9.3
