[Mesa-dev] [PATCH 7/8] gallium/u_threaded: implement pin_threads_to_L3_cache

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

---
 .../auxiliary/util/u_threaded_context.c       | 23 +++++++++++++++++++
 .../auxiliary/util/u_threaded_context.h       |  1 +
 .../auxiliary/util/u_threaded_context_calls.h |  1 +
 3 files changed, 25 insertions(+)

diff --git a/src/gallium/auxiliary/util/u_threaded_context.c b/src/gallium/auxiliary/util/u_threaded_context.c
index fc7eb138835..95b98514a12 100644
--- a/src/gallium/auxiliary/util/u_threaded_context.c
+++ b/src/gallium/auxiliary/util/u_threaded_context.c
@@ -1892,20 +1892,42 @@ tc_create_video_codec(UNUSED struct pipe_context *_pipe,
 }
 
 static struct pipe_video_buffer *
 tc_create_video_buffer(UNUSED struct pipe_context *_pipe,
                        UNUSED const struct pipe_video_buffer *templ)
 {
    unreachable("Threaded context should not be enabled for video APIs");
    return NULL;
 }
 
+static void
+tc_call_pin_threads_to_L3_cache(struct pipe_context *pipe,
+                                union tc_payload *payload)
+{
+   pipe->pin_threads_to_L3_cache(pipe, payload->uint);
+}
+
+static void
+tc_pin_threads_to_L3_cache(struct pipe_context *_pipe,
+                           unsigned cache)
+{
+   struct threaded_context *tc = threaded_context(_pipe);
+   union tc_payload *payload =
+      tc_add_small_call(tc, TC_CALL_pin_threads_to_L3_cache);
+
+   payload->uint = cache;
+
+   /* Pin the gallium thread as requested. */
+   util_pin_thread_to_L3(tc->queue.threads[0], cache,
+                         util_cpu_caps.cores_per_L3);
+}
+
 
 /********************************************************************
  * draw, launch, clear, blit, copy, flush
  */
 
 struct tc_flush_payload {
    struct threaded_context *tc;
    struct pipe_fence_handle *fence;
    unsigned flags;
 };
@@ -2683,20 +2705,21 @@ threaded_context_create(struct pipe_context *pipe,
    CTX_INIT(create_fence_fd);
    CTX_INIT(fence_server_sync);
    CTX_INIT(fence_server_signal);
    CTX_INIT(get_timestamp);
    CTX_INIT(create_texture_handle);
    CTX_INIT(delete_texture_handle);
    CTX_INIT(make_texture_handle_resident);
    CTX_INIT(create_image_handle);
    CTX_INIT(delete_image_handle);
    CTX_INIT(make_image_handle_resident);
+   CTX_INIT(pin_threads_to_L3_cache);
 #undef CTX_INIT
 
    if (out)
       *out = tc;
 
    return &tc->base;
 
 fail:
    tc_destroy(&tc->base);
    return NULL;
diff --git a/src/gallium/auxiliary/util/u_threaded_context.h b/src/gallium/auxiliary/util/u_threaded_context.h
index be6933d05a4..e3cb05318b2 100644
--- a/src/gallium/auxiliary/util/u_threaded_context.h
+++ b/src/gallium/auxiliary/util/u_threaded_context.h
@@ -304,20 +304,21 @@ struct threaded_query {
 /* This is the second half of tc_call containing call data.
  * Most calls will typecast this to the type they need, typically larger
  * than 8 bytes.
  */
 union tc_payload {
    struct pipe_query *query;
    struct pipe_resource *resource;
    struct pipe_transfer *transfer;
    struct pipe_fence_handle *fence;
    uint64_t handle;
+   unsigned uint;
 };
 
 #ifdef _MSC_VER
 #define ALIGN16 __declspec(align(16))
 #else
 #define ALIGN16 __attribute__((aligned(16)))
 #endif
 
 /* Each call slot should be aligned to its own size for optimal cache usage. */
 struct ALIGN16 tc_call {
diff --git a/src/gallium/auxiliary/util/u_threaded_context_calls.h b/src/gallium/auxiliary/util/u_threaded_context_calls.h
index 921b86a67f0..42f244f1c67 100644
--- a/src/gallium/auxiliary/util/u_threaded_context_calls.h
+++ b/src/gallium/auxiliary/util/u_threaded_context_calls.h
@@ -42,20 +42,21 @@ CALL(set_stencil_ref)
 CALL(set_clip_state)
 CALL(set_sample_mask)
 CALL(set_min_samples)
 CALL(set_polygon_stipple)
 CALL(texture_barrier)
 CALL(memory_barrier)
 CALL(delete_texture_handle)
 CALL(make_texture_handle_resident)
 CALL(delete_image_handle)
 CALL(make_image_handle_resident)
+CALL(pin_threads_to_L3_cache)
 
 CALL(bind_blend_state)
 CALL(bind_rasterizer_state)
 CALL(bind_depth_stencil_alpha_state)
 CALL(bind_compute_state)
 CALL(bind_fs_state)
 CALL(bind_vs_state)
 CALL(bind_gs_state)
 CALL(bind_tcs_state)
 CALL(bind_tes_state)
-- 
2.17.1