drm/amdgpu: add gfx shadow CS IOCTL support

Add support for submitting the shadow update packet
when submitting an IB.  Needed for MCBP on GFX11.

v2: update API for CSA (Alex)
v3: fix ordering; SET_Q_PREEMPTION_MODE most come before COND_EXEC
    Add missing check for AMDGPU_CHUNK_ID_CP_GFX_SHADOW in
    amdgpu_cs_pass1()
    Only initialize shadow on first use
    (Alex)
v4: Pass parameters rather than job to new ring callback (Alex)
v5: squash in change to call SET_Q_PREEMPTION_MODE/COND_EXEC
    before RELEASE_MEM to complete the UMDs use of the shadow (Alex)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -288,6 +288,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p,
 		case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
+		case AMDGPU_CHUNK_ID_CP_GFX_SHADOW:
 			break;
 
 		default:
@@ -578,6 +579,26 @@ static int amdgpu_cs_p2_syncobj_timeline_signal(struct amdgpu_cs_parser *p,
 	return 0;
 }
 
+static int amdgpu_cs_p2_shadow(struct amdgpu_cs_parser *p,
+			       struct amdgpu_cs_chunk *chunk)
+{
+	struct drm_amdgpu_cs_chunk_cp_gfx_shadow *shadow = chunk->kdata;
+	int i;
+
+	if (shadow->flags & ~AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW)
+		return -EINVAL;
+
+	for (i = 0; i < p->gang_size; ++i) {
+		p->jobs[i]->shadow_va = shadow->shadow_va;
+		p->jobs[i]->csa_va = shadow->csa_va;
+		p->jobs[i]->gds_va = shadow->gds_va;
+		p->jobs[i]->init_shadow =
+			shadow->flags & AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW;
+	}
+
+	return 0;
+}
+
 static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p)
 {
 	unsigned int ce_preempt = 0, de_preempt = 0;
@@ -620,6 +641,11 @@ static int amdgpu_cs_pass2(struct amdgpu_cs_parser *p)
 			if (r)
 				return r;
 			break;
+		case AMDGPU_CHUNK_ID_CP_GFX_SHADOW:
+			r = amdgpu_cs_p2_shadow(p, chunk);
+			if (r)
+				return r;
+			break;
 		}
 	}
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

@@ -136,7 +136,9 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	uint64_t fence_ctx;
 	uint32_t status = 0, alloc_size;
 	unsigned fence_flags = 0;
-	bool secure;
+	bool secure, init_shadow;
+	u64 shadow_va, csa_va, gds_va;
+	int vmid = AMDGPU_JOB_GET_VMID(job);
 
 	unsigned i;
 	int r = 0;
@@ -150,9 +152,17 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		vm = job->vm;
 		fence_ctx = job->base.s_fence ?
 			job->base.s_fence->scheduled.context : 0;
+		shadow_va = job->shadow_va;
+		csa_va = job->csa_va;
+		gds_va = job->gds_va;
+		init_shadow = job->init_shadow;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
+		shadow_va = 0;
+		csa_va = 0;
+		gds_va = 0;
+		init_shadow = false;
 	}
 
 	if (!ring->sched.ready && !ring->is_mes_queue) {
@@ -212,6 +222,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	}
 
 	amdgpu_ring_ib_begin(ring);
+
+	if (job && ring->funcs->emit_gfx_shadow)
+		amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va,
+					    init_shadow, vmid);
+
 	if (job && ring->funcs->init_cond_exec)
 		patch_offset = amdgpu_ring_init_cond_exec(ring);
 
@@ -263,6 +278,18 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
 	}
 
+	if (ring->funcs->emit_gfx_shadow) {
+		amdgpu_ring_emit_gfx_shadow(ring, 0, 0, 0, false, 0);
+
+		if (ring->funcs->init_cond_exec) {
+			unsigned ce_offset = ~0;
+
+			ce_offset = amdgpu_ring_init_cond_exec(ring);
+			if (ce_offset != ~0 && ring->funcs->patch_cond_exec)
+				amdgpu_ring_patch_cond_exec(ring, ce_offset);
+		}
+	}
+
 	r = amdgpu_fence_emit(ring, f, job, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);

drivers/gpu/drm/amd/amdgpu/amdgpu_job.h

@@ -67,6 +67,12 @@ struct amdgpu_job {
 	uint64_t		uf_addr;
 	uint64_t		uf_sequence;
 
+	/* virtual addresses for shadow/GDS/CSA */
+	uint64_t		shadow_va;
+	uint64_t		csa_va;
+	uint64_t		gds_va;
+	bool			init_shadow;
+
 	/* job_run_counter >= 1 means a resubmit job */
 	uint32_t		job_run_counter;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h

@@ -212,6 +212,8 @@ struct amdgpu_ring_funcs {
 	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);
+	void (*emit_gfx_shadow)(struct amdgpu_ring *ring, u64 shadow_va, u64 csa_va,
+				u64 gds_va, bool init_shadow, int vmid);
 	void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg,
 			  uint32_t reg_val_offs);
 	void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
@@ -309,6 +311,7 @@ struct amdgpu_ring {
 #define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((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_emit_gfx_shadow(r, s, c, g, i, v) ((r)->funcs->emit_gfx_shadow((r), (s), (c), (g), (i), (v)))
 #define amdgpu_ring_emit_rreg(r, d, o) (r)->funcs->emit_rreg((r), (d), (o))
 #define amdgpu_ring_emit_wreg(r, d, v) (r)->funcs->emit_wreg((r), (d), (v))
 #define amdgpu_ring_emit_reg_wait(r, d, v, m) (r)->funcs->emit_reg_wait((r), (d), (v), (m))