drm/amdgpu/gfx9: impl gfx9 meta data emit

Insert ce meta prior to cntx_cntl and de follow it.
Signed-off-by: Xiangliang Yu <Xiangliang.Yu@amd.com>
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3195,10 +3195,54 @@ static void gfx_v9_ring_emit_sb(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0);
 }
 
+static void gfx_v9_0_ring_emit_ce_meta(struct amdgpu_ring *ring)
+{
+	static struct v9_ce_ib_state ce_payload = {0};
+	uint64_t csa_addr;
+	int cnt;
+
+	cnt = (sizeof(ce_payload) >> 2) + 4 - 2;
+	csa_addr = AMDGPU_VA_RESERVED_SIZE - 2 * 4096;
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt));
+	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(2) |
+				 WRITE_DATA_DST_SEL(8) |
+				 WR_CONFIRM) |
+				 WRITE_DATA_CACHE_POLICY(0));
+	amdgpu_ring_write(ring, lower_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, ce_payload)));
+	amdgpu_ring_write(ring, upper_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, ce_payload)));
+	amdgpu_ring_write_multiple(ring, (void *)&ce_payload, sizeof(ce_payload) >> 2);
+}
+
+static void gfx_v9_0_ring_emit_de_meta(struct amdgpu_ring *ring)
+{
+	static struct v9_de_ib_state de_payload = {0};
+	uint64_t csa_addr, gds_addr;
+	int cnt;
+
+	csa_addr = AMDGPU_VA_RESERVED_SIZE - 2 * 4096;
+	gds_addr = csa_addr + 4096;
+	de_payload.gds_backup_addrlo = lower_32_bits(gds_addr);
+	de_payload.gds_backup_addrhi = upper_32_bits(gds_addr);
+
+	cnt = (sizeof(de_payload) >> 2) + 4 - 2;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, cnt));
+	amdgpu_ring_write(ring, (WRITE_DATA_ENGINE_SEL(1) |
+				 WRITE_DATA_DST_SEL(8) |
+				 WR_CONFIRM) |
+				 WRITE_DATA_CACHE_POLICY(0));
+	amdgpu_ring_write(ring, lower_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, de_payload)));
+	amdgpu_ring_write(ring, upper_32_bits(csa_addr + offsetof(struct v9_gfx_meta_data, de_payload)));
+	amdgpu_ring_write_multiple(ring, (void *)&de_payload, sizeof(de_payload) >> 2);
+}
+
 static void gfx_v9_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)
 {
 	uint32_t dw2 = 0;
 
+	if (amdgpu_sriov_vf(ring->adev))
+		gfx_v9_0_ring_emit_ce_meta(ring);
+
 	dw2 |= 0x80000000; /* set load_enable otherwise this package is just NOPs */
 	if (flags & AMDGPU_HAVE_CTX_SWITCH) {
 		/* set load_global_config & load_global_uconfig */
@@ -3222,6 +3266,9 @@ static void gfx_v9_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)
 	amdgpu_ring_write(ring, PACKET3(PACKET3_CONTEXT_CONTROL, 1));
 	amdgpu_ring_write(ring, dw2);
 	amdgpu_ring_write(ring, 0);
+
+	if (amdgpu_sriov_vf(ring->adev))
+		gfx_v9_0_ring_emit_de_meta(ring);
 }
 
 static unsigned gfx_v9_0_ring_emit_init_cond_exec(struct amdgpu_ring *ring)

drivers/gpu/drm/amd/include/v9_structs.h

@@ -672,4 +672,72 @@ struct v9_mqd {
 	uint32_t reserved_511;
 };
 
+/* from vega10 all CSA format is shifted to chain ib compatible mode */
+struct v9_ce_ib_state {
+    /* section of non chained ib part */
+    uint32_t ce_ib_completion_status;
+    uint32_t ce_constegnine_count;
+    uint32_t ce_ibOffset_ib1;
+    uint32_t ce_ibOffset_ib2;
+
+    /* section of chained ib */
+    uint32_t ce_chainib_addrlo_ib1;
+    uint32_t ce_chainib_addrlo_ib2;
+    uint32_t ce_chainib_addrhi_ib1;
+    uint32_t ce_chainib_addrhi_ib2;
+    uint32_t ce_chainib_size_ib1;
+    uint32_t ce_chainib_size_ib2;
+}; /* total 10 DWORD */
+
+struct v9_de_ib_state {
+    /* section of non chained ib part */
+    uint32_t ib_completion_status;
+    uint32_t de_constEngine_count;
+    uint32_t ib_offset_ib1;
+    uint32_t ib_offset_ib2;
+
+    /* section of chained ib */
+    uint32_t chain_ib_addrlo_ib1;
+    uint32_t chain_ib_addrlo_ib2;
+    uint32_t chain_ib_addrhi_ib1;
+    uint32_t chain_ib_addrhi_ib2;
+    uint32_t chain_ib_size_ib1;
+    uint32_t chain_ib_size_ib2;
+
+    /* section of non chained ib part */
+    uint32_t preamble_begin_ib1;
+    uint32_t preamble_begin_ib2;
+    uint32_t preamble_end_ib1;
+    uint32_t preamble_end_ib2;
+
+    /* section of chained ib */
+    uint32_t chain_ib_pream_addrlo_ib1;
+    uint32_t chain_ib_pream_addrlo_ib2;
+    uint32_t chain_ib_pream_addrhi_ib1;
+    uint32_t chain_ib_pream_addrhi_ib2;
+
+    /* section of non chained ib part */
+    uint32_t draw_indirect_baseLo;
+    uint32_t draw_indirect_baseHi;
+    uint32_t disp_indirect_baseLo;
+    uint32_t disp_indirect_baseHi;
+    uint32_t gds_backup_addrlo;
+    uint32_t gds_backup_addrhi;
+    uint32_t index_base_addrlo;
+    uint32_t index_base_addrhi;
+    uint32_t sample_cntl;
+}; /* Total of 27 DWORD */
+
+struct v9_gfx_meta_data {
+    /* 10 DWORD, address must be 4KB aligned */
+    struct v9_ce_ib_state ce_payload;
+    uint32_t reserved1[54];
+    /* 27 DWORD, address must be 64B aligned */
+    struct v9_de_ib_state de_payload;
+    /* PFP IB base address which get pre-empted */
+    uint32_t DeIbBaseAddrLo;
+    uint32_t DeIbBaseAddrHi;
+    uint32_t reserved2[931];
+}; /* Total of 4K Bytes */
+
 #endif /* V9_STRUCTS_H_ */