drm/amdgpu:implement CONTEXT_CONTROL (v5)
v1:
for gfx8, use CONTEXT_CONTROL package to dynamically
skip preamble CEIB and other load_xxx command in sequence.
v2:
support GFX7 as well.
remove cntxcntl in compute ring funcs because CPC doesn't
support this packet.
v3: fix reduntant judgement in cntxcntl.
v4: some cleanups, don't change cs_submit()
v5: keep old MESA supported & bump up KMS version.
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Ack-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 10ec29c..717c3b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -320,6 +320,7 @@
void (*begin_use)(struct amdgpu_ring *ring);
void (*end_use)(struct amdgpu_ring *ring);
void (*emit_switch_buffer) (struct amdgpu_ring *ring);
+ void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
};
/*
@@ -966,6 +967,7 @@
spinlock_t ring_lock;
struct fence **fences;
struct amdgpu_ctx_ring rings[AMDGPU_MAX_RINGS];
+ bool preamble_presented;
};
struct amdgpu_ctx_mgr {
@@ -1231,6 +1233,10 @@
struct amdgpu_bo_list_entry uf_entry;
};
+#define AMDGPU_PREAMBLE_IB_PRESENT (1 << 0) /* bit set means command submit involves a preamble IB */
+#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST (1 << 1) /* bit set means preamble IB is first presented in belonging context */
+#define AMDGPU_HAVE_CTX_SWITCH (1 << 2) /* bit set means context switch occured */
+
struct amdgpu_job {
struct amd_sched_job base;
struct amdgpu_device *adev;
@@ -1239,6 +1245,7 @@
struct amdgpu_sync sync;
struct amdgpu_ib *ibs;
struct fence *fence; /* the hw fence */
+ uint32_t preamble_status;
uint32_t num_ibs;
void *owner;
uint64_t fence_ctx; /* the fence_context this job uses */
@@ -2276,6 +2283,7 @@
#define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((r))
#define amdgpu_ring_emit_hdp_invalidate(r) (r)->funcs->emit_hdp_invalidate((r))
#define amdgpu_ring_emit_switch_buffer(r) (r)->funcs->emit_switch_buffer((r))
+#define amdgpu_ring_emit_cntxcntl(r, d) (r)->funcs->emit_cntxcntl((r), (d))
#define amdgpu_ring_pad_ib(r, ib) ((r)->funcs->pad_ib((r), (ib)))
#define amdgpu_ring_init_cond_exec(r) (r)->funcs->init_cond_exec((r))
#define amdgpu_ring_patch_cond_exec(r,o) (r)->funcs->patch_cond_exec((r),(o))