Queues are independent execution streams. The vulkan spec provides no
ordering guarantees for different queues.
By using a single context for all queues, we are forcing all commands
into an unecessary FIFO ordering.
This change is a preparation step to allow our-of-ordering scheduling of
certain work tasks.
As a side effect, vkQueueWaitIdle will be marginally faster. Previously
due to the shared context, vkQueueWaitIdle was equivalent to
vkDeviceWaitIdle.
---
src/amd/vulkan/radv_device.c | 35 ++++++++++++++++++++---------------
src/amd/vulkan/radv_private.h | 2 +-
src/amd/vulkan/radv_wsi.c | 2 +-
3 files changed, 22 insertions(+), 17 deletions(-)
diff --git a/src/amd/vulkan/radv_device.c b/src/amd/vulkan/radv_device.c
index e57a419..d9f9a2b 100644
--- a/src/amd/vulkan/radv_device.c
+++ b/src/amd/vulkan/radv_device.c
@@ -651,7 +651,7 @@ void radv_GetPhysicalDeviceMemoryProperties(
};
}
-static void
+static int
radv_queue_init(struct radv_device *device, struct radv_queue *queue,
int queue_family_index, int idx)
{
@@ -659,11 +659,19 @@ radv_queue_init(struct radv_device *device, struct radv_queue *queue,
queue->device = device;
queue->queue_family_index = queue_family_index;
queue->queue_idx = idx;
+
+ queue->hw_ctx = device->ws->ctx_create(device->ws);
+ if (!queue->hw_ctx)
+ return VK_ERROR_OUT_OF_HOST_MEMORY;
+
+ return VK_SUCCESS;
}
static void
radv_queue_finish(struct radv_queue *queue)
{
+ if (queue->hw_ctx)
+ queue->device->ws->ctx_destroy(queue->hw_ctx);
}
VkResult radv_CreateDevice(
@@ -718,23 +726,21 @@ VkResult radv_CreateDevice(
goto fail;
}
- device->queue_count[qfi] = queue_create->queueCount;
+ memset(device->queues[qfi], 0, queue_create->queueCount * sizeof(struct radv_queue));
- for (unsigned q = 0; q < queue_create->queueCount; q++)
- radv_queue_init(device, &device->queues[qfi][q], qfi, q);
- }
+ device->queue_count[qfi] = queue_create->queueCount;
- device->hw_ctx = device->ws->ctx_create(device->ws);
- if (!device->hw_ctx) {
- result = VK_ERROR_OUT_OF_HOST_MEMORY;
- goto fail;
+ for (unsigned q = 0; q < queue_create->queueCount; q++) {
+ result = radv_queue_init(device, &device->queues[qfi][q], qfi, q);
+ if (result != VK_SUCCESS)
+ goto fail;
+ }
}
result = radv_device_init_meta(device);
- if (result != VK_SUCCESS) {
- device->ws->ctx_destroy(device->hw_ctx);
+ if (result != VK_SUCCESS)
goto fail;
- }
+
device->allow_fast_clears = env_var_as_boolean("RADV_FAST_CLEARS", false);
device->allow_dcc = !env_var_as_boolean("RADV_DCC_DISABLE", false);
device->shader_stats_dump = env_var_as_boolean("RADV_SHADER_STATS", false);
@@ -780,7 +786,6 @@ void radv_DestroyDevice(
{
RADV_FROM_HANDLE(radv_device, device, _device);
- device->ws->ctx_destroy(device->hw_ctx);
for (unsigned i = 0; i < RADV_MAX_QUEUE_FAMILIES; i++) {
for (unsigned q = 0; q < device->queue_count[i]; q++)
radv_queue_finish(&device->queues[i][q]);
@@ -878,7 +883,7 @@ VkResult radv_QueueSubmit(
RADV_FROM_HANDLE(radv_queue, queue, _queue);
RADV_FROM_HANDLE(radv_fence, fence, _fence);
struct radeon_winsys_fence *base_fence = fence ? fence->fence : NULL;
- struct radeon_winsys_ctx *ctx = queue->device->hw_ctx;
+ struct radeon_winsys_ctx *ctx = queue->hw_ctx;
int ret;
for (uint32_t i = 0; i < submitCount; i++) {
@@ -929,7 +934,7 @@ VkResult radv_QueueWaitIdle(
{
RADV_FROM_HANDLE(radv_queue, queue, _queue);
- queue->device->ws->ctx_wait_idle(queue->device->hw_ctx,
+ queue->device->ws->ctx_wait_idle(queue->hw_ctx,
radv_queue_family_to_ring(queue->queue_family_index),
queue->queue_idx);
return VK_SUCCESS;
diff --git a/src/amd/vulkan/radv_private.h b/src/amd/vulkan/radv_private.h
index f76d38d..d316f71 100644
--- a/src/amd/vulkan/radv_private.h
+++ b/src/amd/vulkan/radv_private.h
@@ -456,6 +456,7 @@ enum ring_type radv_queue_family_to_ring(int f);
struct radv_queue {
VK_LOADER_DATA _loader_data;
struct radv_device * device;
+ struct radeon_winsys_ctx *hw_ctx;
int queue_family_index;
int queue_idx;
};
@@ -467,7 +468,6 @@ struct radv_device {
struct radv_instance * instance;
struct radeon_winsys *ws;
- struct radeon_winsys_ctx *hw_ctx;
struct radv_meta_state meta_state;
diff --git a/src/amd/vulkan/radv_wsi.c b/src/amd/vulkan/radv_wsi.c
index 2eb8e45..752efe4 100644
--- a/src/amd/vulkan/radv_wsi.c
+++ b/src/amd/vulkan/radv_wsi.c
@@ -364,7 +364,7 @@ VkResult radv_QueuePresentKHR(
RADV_FROM_HANDLE(radv_fence, fence, swapchain->fences[0]);
struct radeon_winsys_fence *base_fence = fence->fence;
- struct radeon_winsys_ctx *ctx = queue->device->hw_ctx;
+ struct radeon_winsys_ctx *ctx = queue->hw_ctx;
queue->device->ws->cs_submit(ctx, queue->queue_idx,
&queue->device->empty_cs[queue->queue_family_index],
1,
--
2.9.3
