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>

1 files changed, 28 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index ef96ff2f4272..aebc0e5bddc6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/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);