when shadowing enabled, tesselation app will trigger
vm fault because below three tesselation registers:
VGT_TF_RING_SIZE__CI__VI,
VGT_HS_OFFCHIP_PARAM__CI__VI,
VGT_TF_MEMORY_BASE__CI__VI,
need to be programed after vgt-flush.
Tesselation picture vm fault disappeared after vgt-flush
introduced.
v2:implement vgt-flush for CI & SI.
Change-Id: I77d87d93ce6580e559e734fb41d97ee8c59d245b
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 5 ++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 1 +
drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 8 ++++++++
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 13 +++++++++++++
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 13 +++++++++++++
6 files changed, 40 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 15015bc..f46e96b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1630,6 +1630,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
#define amdgpu_ring_emit_fence(r, addr, seq, flags) (r)->funcs->emit_fence((r), (addr), (seq), (flags))
#define amdgpu_ring_emit_gds_switch(r, v, db, ds, wb, ws, ab, as) (r)->funcs->emit_gds_switch((r), (v), (db), (ds), (wb), (ws), (ab), (as))
#define amdgpu_ring_emit_hdp_flush(r) (r)->funcs->emit_hdp_flush((r))
+#define amdgpu_ring_emit_vgt_flush(r) (r)->funcs->emit_vgt_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))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index acf48de..c039890 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -175,11 +175,14 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
if (ring->funcs->emit_hdp_flush)
amdgpu_ring_emit_hdp_flush(ring);
+ need_ctx_switch = ring->current_ctx != fence_ctx;
+ if (ring->funcs->emit_vgt_flush && need_ctx_switch)
+ amdgpu_ring_emit_vgt_flush(ring);
+
/* always set cond_exec_polling to CONTINUE */
*ring->cond_exe_cpu_addr = 1;
skip_preamble = ring->current_ctx == fence_ctx;
- need_ctx_switch = ring->current_ctx != fence_ctx;
if (job && ring->funcs->emit_cntxcntl) {
if (need_ctx_switch)
status |= AMDGPU_HAVE_CTX_SWITCH;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 92bc89b..c3a7329 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -116,6 +116,7 @@ struct amdgpu_ring_funcs {
void (*emit_vm_flush)(struct amdgpu_ring *ring, unsigned vm_id,
uint64_t pd_addr);
void (*emit_hdp_flush)(struct amdgpu_ring *ring);
+ void (*emit_vgt_flush)(struct amdgpu_ring *ring);
void (*emit_hdp_invalidate)(struct amdgpu_ring *ring);
void (*emit_gds_switch)(struct amdgpu_ring *ring, uint32_t vmid,
uint32_t gds_base, uint32_t gds_size,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 9423501..77f906e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -1463,6 +1463,13 @@ static void gfx_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, 0x1);
}
+static void gfx_v6_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+ amdgpu_ring_write(ring, EVENT_TYPE(VGT_FLUSH) |
+ EVENT_INDEX(0));
+}
+
/**
* gfx_v6_0_ring_emit_hdp_invalidate - emit an hdp invalidate on the cp
*
@@ -3272,6 +3279,7 @@ static const struct amdgpu_ring_funcs gfx_v6_0_ring_funcs_gfx = {
.emit_pipeline_sync = gfx_v6_0_ring_emit_pipeline_sync,
.emit_vm_flush = gfx_v6_0_ring_emit_vm_flush,
.emit_hdp_flush = gfx_v6_0_ring_emit_hdp_flush,
+ .emit_vgt_flush = gfx_v6_0_ring_emit_vgt_flush,
.emit_hdp_invalidate = gfx_v6_0_ring_emit_hdp_invalidate,
.test_ring = gfx_v6_0_ring_test_ring,
.test_ib = gfx_v6_0_ring_test_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index bd9a6c8..01e5ad4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2105,6 +2105,18 @@ static void gfx_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, 0x20); /* poll interval */
}
+static void gfx_v7_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+ amdgpu_ring_write(ring, EVENT_TYPE(VS_PARTIAL_FLUSH) |
+ EVENT_INDEX(4));
+
+ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+ amdgpu_ring_write(ring, EVENT_TYPE(VGT_FLUSH) |
+ EVENT_INDEX(0));
+}
+
+
/**
* gfx_v7_0_ring_emit_hdp_invalidate - emit an hdp invalidate on the cp
*
@@ -5155,6 +5167,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = {
.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
.emit_gds_switch = gfx_v7_0_ring_emit_gds_switch,
.emit_hdp_flush = gfx_v7_0_ring_emit_hdp_flush,
+ .emit_vgt_flush = gfx_v7_0_ring_emit_vgt_flush,
.emit_hdp_invalidate = gfx_v7_0_ring_emit_hdp_invalidate,
.test_ring = gfx_v7_0_ring_test_ring,
.test_ib = gfx_v7_0_ring_test_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 9017803..1d407d76 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6187,6 +6187,18 @@ static void gfx_v8_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, 0x20); /* poll interval */
}
+static void gfx_v8_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+ amdgpu_ring_write(ring, EVENT_TYPE(VS_PARTIAL_FLUSH) |
+ EVENT_INDEX(4));
+
+ amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+ amdgpu_ring_write(ring, EVENT_TYPE(VGT_FLUSH) |
+ EVENT_INDEX(0));
+}
+
+
static void gfx_v8_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
{
amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
@@ -6590,6 +6602,7 @@ static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_gfx = {
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_switch_buffer = gfx_v8_ring_emit_sb,
.emit_cntxcntl = gfx_v8_ring_emit_cntxcntl,
+ .emit_vgt_flush = gfx_v8_0_ring_emit_vgt_flush,
};
static const struct amdgpu_ring_funcs gfx_v8_0_ring_funcs_compute = {
--
1.9.1
