From: Monk Liu <Monk.Liu@amd.com>
Date: Mon, 1 May 2017 18:09:22 +0800
Subject: drm/amdgpu:use FRAME_CNTL for new GFX ucode (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 3b4d68e993d941ec993660f10bacdfd556731dc7
Patch-mainline: v4.13-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

AI affected:

CP/HW team requires KMD insert FRAME_CONTROL(end) after
the last IB and before the fence of this DMAframe.

this is to make sure the cache are flushed, and it's a must
change no matter MCBP/SR-IOV or bare-metal case because new
CP hw won't do the cache flush for each IB anymore, it just
leaves it to KMD now.

with this patch, certain MCBP hang issue when rendering
vulkan/chained-ib are resolved.

v2: drop gfx8 changes.  gfx8 is not affected (Alex)

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h      |    1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c   |    3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h |    1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c    |    1 -
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c    |    7 +++++++
 5 files changed, 12 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1815,6 +1815,7 @@ amdgpu_get_sdma_instance(struct amdgpu_r
 #define amdgpu_ring_emit_cntxcntl(r, d) (r)->funcs->emit_cntxcntl((r), (d))
 #define amdgpu_ring_emit_rreg(r, d) (r)->funcs->emit_rreg((r), (d))
 #define amdgpu_ring_emit_wreg(r, d, v) (r)->funcs->emit_wreg((r), (d), (v))
+#define amdgpu_ring_emit_tmz(r, b) (r)->funcs->emit_tmz((r), (b))
 #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))
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -208,6 +208,9 @@ int amdgpu_ib_schedule(struct amdgpu_rin
 		need_ctx_switch = false;
 	}
 
+	if (ring->funcs->emit_tmz)
+		amdgpu_ring_emit_tmz(ring, false);
+
 	if (ring->funcs->emit_hdp_invalidate
 #ifdef CONFIG_X86_64
 	    && !(adev->flags & AMD_IS_APU)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -142,6 +142,7 @@ struct amdgpu_ring_funcs {
 	void (*emit_cntxcntl) (struct amdgpu_ring *ring, uint32_t flags);
 	void (*emit_rreg)(struct amdgpu_ring *ring, uint32_t reg);
 	void (*emit_wreg)(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+	void (*emit_tmz)(struct amdgpu_ring *ring, bool start);
 };
 
 struct amdgpu_ring {
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6597,7 +6597,6 @@ static void gfx_v8_0_ring_emit_patch_con
 		ring->ring[offset] = (ring->ring_size >> 2) - offset + cur;
 }
 
-
 static void gfx_v8_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg)
 {
 	struct amdgpu_device *adev = ring->adev;
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3237,6 +3237,12 @@ static void gfx_v9_0_ring_emit_patch_con
 		ring->ring[offset] = (ring->ring_size>>2) - offset + cur;
 }
 
+static void gfx_v9_0_ring_emit_tmz(struct amdgpu_ring *ring, bool start)
+{
+	amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0));
+	amdgpu_ring_write(ring, FRAME_CMD(start ? 0 : 1)); /* frame_end */
+}
+
 static void gfx_v9_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -3571,6 +3577,7 @@ static const struct amdgpu_ring_funcs gf
 	.emit_cntxcntl = gfx_v9_ring_emit_cntxcntl,
 	.init_cond_exec = gfx_v9_0_ring_emit_init_cond_exec,
 	.patch_cond_exec = gfx_v9_0_ring_emit_patch_cond_exec,
+	.emit_tmz = gfx_v9_0_ring_emit_tmz,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {