r600g: fix hang on RV740 by using DX_RASTERIZATION_KILL instead of SX_MISC

Changing SX_MISC hangs RV740. When we're at it, let's use DX_RASTERIZATION_KILL
on all R700 and later chipsets.

Cc: 10.0 10.1 mesa-stable@lists.freedesktop.org
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

src/gallium/drivers/r600/evergreen_state.c

@@ -474,7 +474,8 @@ static void *evergreen_create_rs_state(struct pipe_context *ctx,
 		S_028810_PS_UCP_MODE(3) |
 		S_028810_ZCLIP_NEAR_DISABLE(!state->depth_clip) |
 		S_028810_ZCLIP_FAR_DISABLE(!state->depth_clip) |
-		S_028810_DX_LINEAR_ATTR_CLIP_ENA(1);
+		S_028810_DX_LINEAR_ATTR_CLIP_ENA(1) |
+		S_028810_DX_RASTERIZATION_KILL(state->rasterizer_discard);
 	rs->multisample_enable = state->multisample;
 
 	/* offset */
@@ -543,7 +544,6 @@ static void *evergreen_create_rs_state(struct pipe_context *ctx,
 						  state->fill_back != PIPE_POLYGON_MODE_FILL) |
 			       S_028814_POLYMODE_FRONT_PTYPE(r600_translate_fill(state->fill_front)) |
 			       S_028814_POLYMODE_BACK_PTYPE(r600_translate_fill(state->fill_back)));
-	r600_store_context_reg(&rs->buffer, R_028350_SX_MISC, S_028350_MULTIPASS(state->rasterizer_discard));
 	return rs;
 }
 
@@ -2195,7 +2195,9 @@ void cayman_init_common_regs(struct r600_command_buffer *cb,
 
 	r600_store_context_reg(cb, R_028A4C_PA_SC_MODE_CNTL_1, 0);
 
-	r600_store_context_reg(cb, R_028354_SX_SURFACE_SYNC, S_028354_SURFACE_SYNC_MASK(0xf));
+	r600_store_context_reg_seq(cb, R_028350_SX_MISC, 2);
+	r600_store_value(cb, 0);
+	r600_store_value(cb, S_028354_SURFACE_SYNC_MASK(0xf));
 
 	r600_store_context_reg(cb, R_028800_DB_DEPTH_CONTROL, 0);
 }
@@ -2472,7 +2474,9 @@ void evergreen_init_common_regs(struct r600_command_buffer *cb,
 	/* The cs checker requires this register to be set. */
 	r600_store_context_reg(cb, R_028800_DB_DEPTH_CONTROL, 0);
 
-	r600_store_context_reg(cb, R_028354_SX_SURFACE_SYNC, S_028354_SURFACE_SYNC_MASK(0xf));
+	r600_store_context_reg_seq(cb, R_028350_SX_MISC, 2);
+	r600_store_value(cb, 0);
+	r600_store_value(cb, S_028354_SURFACE_SYNC_MASK(0xf));
 
 	return;
 }

src/gallium/drivers/r600/evergreend.h

@@ -582,6 +582,9 @@
 #define   S_028810_VTX_KILL_OR(x)                      (((x) & 0x1) << 21)
 #define   G_028810_VTX_KILL_OR(x)                      (((x) >> 21) & 0x1)
 #define   C_028810_VTX_KILL_OR                         0xFFDFFFFF
+#define   S_028810_DX_RASTERIZATION_KILL(x)            (((x) & 0x1) << 22)
+#define   G_028810_DX_RASTERIZATION_KILL(x)            (((x) >> 22) & 0x1)
+#define   C_028810_DX_RASTERIZATION_KILL               0xFFBFFFFF
 #define   S_028810_DX_LINEAR_ATTR_CLIP_ENA(x)          (((x) & 0x1) << 24)
 #define   G_028810_DX_LINEAR_ATTR_CLIP_ENA(x)          (((x) >> 24) & 0x1)
 #define   C_028810_DX_LINEAR_ATTR_CLIP_ENA             0xFEFFFFFF

src/gallium/drivers/r600/r600_hw_context.c

@@ -81,7 +81,7 @@ void r600_need_cs_space(struct r600_context *ctx, unsigned num_dw,
 	}
 
 	/* SX_MISC */
-	if (ctx->b.chip_class <= R700) {
+	if (ctx->b.chip_class == R600) {
 		num_dw += 3;
 	}
 
@@ -264,7 +264,7 @@ void r600_context_gfx_flush(void *context, unsigned flags,
 	r600_flush_emit(ctx);
 
 	/* old kernels and userspace don't set SX_MISC, so we must reset it to 0 here */
-	if (ctx->b.chip_class <= R700) {
+	if (ctx->b.chip_class == R600) {
 		r600_write_context_reg(cs, R_028350_SX_MISC, 0);
 	}
 

src/gallium/drivers/r600/r600_state.c

@@ -460,6 +460,10 @@ static void *r600_create_rs_state(struct pipe_context *ctx,
 		S_028810_ZCLIP_NEAR_DISABLE(!state->depth_clip) |
 		S_028810_ZCLIP_FAR_DISABLE(!state->depth_clip) |
 		S_028810_DX_LINEAR_ATTR_CLIP_ENA(1);
+	if (rctx->b.chip_class == R700) {
+		rs->pa_cl_clip_cntl |=
+			S_028810_DX_RASTERIZATION_KILL(state->rasterizer_discard);
+	}
 	rs->multisample_enable = state->multisample;
 
 	/* offset */
@@ -532,7 +536,10 @@ static void *r600_create_rs_state(struct pipe_context *ctx,
 	if (rctx->b.chip_class == R700) {
 		r600_store_context_reg(&rs->buffer, R_028814_PA_SU_SC_MODE_CNTL, rs->pa_su_sc_mode_cntl);
 	}
-	r600_store_context_reg(&rs->buffer, R_028350_SX_MISC, S_028350_MULTIPASS(state->rasterizer_discard));
+	if (rctx->b.chip_class == R600) {
+		r600_store_context_reg(&rs->buffer, R_028350_SX_MISC,
+				       S_028350_MULTIPASS(state->rasterizer_discard));
+	}
 	return rs;
 }
 
@@ -2397,8 +2404,11 @@ void r600_init_atom_start_cs(struct r600_context *rctx)
 
 	r600_store_context_reg(cb, R_0288A4_SQ_PGM_RESOURCES_FS, 0);
 
+	if (rctx->b.chip_class == R700)
+		r600_store_context_reg(cb, R_028350_SX_MISC, 0);
 	if (rctx->b.chip_class == R700 && rctx->screen->b.has_streamout)
 		r600_store_context_reg(cb, R_028354_SX_SURFACE_SYNC, S_028354_SURFACE_SYNC_MASK(0xf));
+
 	r600_store_context_reg(cb, R_028800_DB_DEPTH_CONTROL, 0);
 	if (rctx->screen->b.has_streamout) {
 		r600_store_context_reg(cb, R_028B28_VGT_STRMOUT_DRAW_OPAQUE_OFFSET, 0);

src/gallium/drivers/r600/r600d.h

@@ -543,6 +543,9 @@
 #define   S_028810_VTX_KILL_OR(x)                      (((x) & 0x1) << 21)
 #define   G_028810_VTX_KILL_OR(x)                      (((x) >> 21) & 0x1)
 #define   C_028810_VTX_KILL_OR                         0xFFDFFFFF
+#define   S_028810_DX_RASTERIZATION_KILL(x)            (((x) & 0x1) << 22) /* R700 only? */
+#define   G_028810_DX_RASTERIZATION_KILL(x)            (((x) >> 22) & 0x1)
+#define   C_028810_DX_RASTERIZATION_KILL               0xFFBFFFFF
 #define   S_028810_DX_LINEAR_ATTR_CLIP_ENA(x)          (((x) & 0x1) << 24)
 #define   G_028810_DX_LINEAR_ATTR_CLIP_ENA(x)          (((x) >> 24) & 0x1)
 #define   C_028810_DX_LINEAR_ATTR_CLIP_ENA             0xFEFFFFFF