i965: Pass number of components explicitly to brw_untyped_atomic and _surface_read.

[mesa.git] / src / mesa / drivers / dri / i965 / gen6_clip_state.c

diff --git a/src/mesa/drivers/dri/i965/gen6_clip_state.c b/src/mesa/drivers/dri/i965/gen6_clip_state.c
index 25dfb60612df95c6d5b619632b8401f38261ee8d..e8c16ca62c9bbbb526b42f7783247d62906286cb 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen6_clip_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_clip_state.c
@@ -43,7 +43,7 @@ upload_clip_state(struct brw_context *brw)
    /* _NEW_BUFFERS */
    struct gl_framebuffer *fb = ctx->DrawBuffer;
 
-   /* CACHE_NEW_WM_PROG */
+   /* BRW_NEW_FS_PROG_DATA */
    if (brw->wm.prog_data->barycentric_interp_modes &
        BRW_WM_NONPERSPECTIVE_BARYCENTRIC_BITS) {
       dw2 |= GEN6_CLIP_NON_PERSPECTIVE_BARYCENTRIC_ENABLE;
@@ -69,8 +69,7 @@ upload_clip_state(struct brw_context *brw)
             dw1 |= GEN7_CLIP_CULLMODE_BOTH;
             break;
          default:
-            assert(!"Should not get here: invalid CullFlag");
-            break;
+            unreachable("Should not get here: invalid CullFlag");
          }
       } else {
          dw1 |= GEN7_CLIP_CULLMODE_NONE;
@@ -98,20 +97,61 @@ upload_clip_state(struct brw_context *brw)
            GEN6_USER_CLIP_CLIP_DISTANCES_SHIFT);
 
    dw2 |= GEN6_CLIP_GB_TEST;
+
+   /* We need to disable guardband clipping if the guardband (which we always
+    * program to the maximum screen-space bounding box of 8K x 8K) will be
+    * smaller than the viewport.
+    *
+    * Closely examining the clip determination formulas in the documentation
+    * reveals that objects will be discarded entirely if they're outside the
+    * (small) guardband, even if they're within the (large) viewport:
+    *
+    *     TR = TR_GB || TR_VPXY || TR_VPZ || TR_UC || TR_NEGW
+    *     TA   = !TR && TA_GB && TA_VPZ && TA_NEGW
+    *     MC = !(TA || TR)
+    *
+    * (TA is "Trivial Accept", TR is "Trivial Reject", MC is "Must Clip".)
+    *
+    * Disabling guardband clipping removes the TR_GB condition, which means
+    * they'll be considered MC ("Must Clip") unless they're rejected for
+    * some other reason.
+    *
+    * Note that there is no TA_VPXY condition.  If there were, objects entirely
+    * inside a 16384x16384 viewport would be trivially accepted, breaking the
+    * "objects must have a screenspace bounding box not exceeding 8K in the X
+    * or Y direction" restriction.  Instead, they're clipped.
+    */
    for (unsigned i = 0; i < ctx->Const.MaxViewports; i++) {
-      if (ctx->ViewportArray[i].X != 0 ||
-          ctx->ViewportArray[i].Y != 0 ||
-          ctx->ViewportArray[i].Width != (float) fb->Width ||
-          ctx->ViewportArray[i].Height != (float) fb->Height) {
+      if (ctx->ViewportArray[i].Width > 8192 ||
+          ctx->ViewportArray[i].Height > 8192) {
          dw2 &= ~GEN6_CLIP_GB_TEST;
-         if (brw->gen >= 8) {
-            perf_debug("Disabling GB clipping due to lack of Gen8 viewport "
-                       "clipping setup code.  This should be fixed.\n");
-         }
          break;
       }
    }
 
+   /* If the viewport dimensions are smaller than the drawable dimensions,
+    * we have to disable guardband clipping prior to Gen8.  We always program
+    * the guardband to a fixed size, which is almost always larger than the
+    * viewport.  Any geometry which intersects the viewport but lies within
+    * the guardband would bypass the 3D clipping stage, so it wouldn't be
+    * clipped to the viewport.  Rendering would happen beyond the viewport,
+    * but still inside the drawable.
+    *
+    * Gen8+ introduces a viewport extents test which restricts rendering to
+    * the viewport, so we can ignore this restriction.
+    */
+   if (brw->gen < 8) {
+      for (unsigned i = 0; i < ctx->Const.MaxViewports; i++) {
+         if (ctx->ViewportArray[i].X != 0 ||
+             ctx->ViewportArray[i].Y != 0 ||
+             ctx->ViewportArray[i].Width != (float) fb->Width ||
+             ctx->ViewportArray[i].Height != (float) fb->Height) {
+            dw2 &= ~GEN6_CLIP_GB_TEST;
+            break;
+         }
+      }
+   }
+
    /* BRW_NEW_RASTERIZER_DISCARD */
    if (ctx->RasterDiscard) {
       dw2 |= GEN6_CLIP_MODE_REJECT_ALL;
@@ -120,10 +160,16 @@ upload_clip_state(struct brw_context *brw)
                  "having the GS not write primitives would likely");
    }
 
+   uint32_t enable;
+   if (brw->primitive == _3DPRIM_RECTLIST)
+      enable = 0;
+   else
+      enable = GEN6_CLIP_ENABLE;
+
    BEGIN_BATCH(4);
    OUT_BATCH(_3DSTATE_CLIP << 16 | (4 - 2));
    OUT_BATCH(dw1);
-   OUT_BATCH(GEN6_CLIP_ENABLE |
+   OUT_BATCH(enable |
             GEN6_CLIP_API_OGL |
             GEN6_CLIP_MODE_NORMAL |
             GEN6_CLIP_XY_TEST |
@@ -137,22 +183,27 @@ upload_clip_state(struct brw_context *brw)
 
 const struct brw_tracked_state gen6_clip_state = {
    .dirty = {
-      .mesa  = _NEW_TRANSFORM | _NEW_LIGHT | _NEW_BUFFERS,
+      .mesa  = _NEW_BUFFERS |
+               _NEW_LIGHT |
+               _NEW_TRANSFORM,
       .brw   = BRW_NEW_CONTEXT |
+               BRW_NEW_FS_PROG_DATA |
                BRW_NEW_META_IN_PROGRESS |
                BRW_NEW_RASTERIZER_DISCARD,
-      .cache = CACHE_NEW_WM_PROG
    },
    .emit = upload_clip_state,
 };
 
 const struct brw_tracked_state gen7_clip_state = {
    .dirty = {
-      .mesa  = _NEW_BUFFERS | _NEW_LIGHT | _NEW_POLYGON | _NEW_TRANSFORM,
+      .mesa  = _NEW_BUFFERS |
+               _NEW_LIGHT |
+               _NEW_POLYGON |
+               _NEW_TRANSFORM,
       .brw   = BRW_NEW_CONTEXT |
+               BRW_NEW_FS_PROG_DATA |
                BRW_NEW_META_IN_PROGRESS |
                BRW_NEW_RASTERIZER_DISCARD,
-      .cache = CACHE_NEW_WM_PROG
    },
    .emit = upload_clip_state,
 };