st/mesa: optionally apply texture swizzle to border color v2

This is the only sane solution for nv50 and nvc0 (really, trust me),
but since on other hardware the border colour is tightly coupled with
texture state they'd have to undo the swizzle, so I've added a cap.

The dependency of update_sampler on the texture updates was
introduced to avoid doing the apply_depthmode to the swizzle twice.

v2: Moved swizzling helper to u_format.c, extended the CAP to
provide more accurate information.

20 files changed, 115 insertions, 7 deletions

diff --git a/src/gallium/auxiliary/util/u_format.c b/src/gallium/auxiliary/util/u_format.c
index 18456371c0a..9bdc2eabf11 100644
--- a/src/gallium/auxiliary/util/u_format.c
+++ b/src/gallium/auxiliary/util/u_format.c
@@ -632,6 +632,40 @@ void util_format_compose_swizzles(const unsigned char swz1[4],
    }
 }
 
+void util_format_apply_color_swizzle(union pipe_color_union *dst,
+                                     const union pipe_color_union *src,
+                                     const unsigned char swz[4],
+                                     const boolean is_integer)
+{
+   unsigned c;
+
+   if (is_integer) {
+      for (c = 0; c < 4; ++c) {
+         switch (swz[c]) {
+         case PIPE_SWIZZLE_RED:   dst->ui[c] = src->ui[0]; break;
+         case PIPE_SWIZZLE_GREEN: dst->ui[c] = src->ui[1]; break;
+         case PIPE_SWIZZLE_BLUE:  dst->ui[c] = src->ui[2]; break;
+         case PIPE_SWIZZLE_ALPHA: dst->ui[c] = src->ui[3]; break;
+         default:
+            dst->ui[c] = (swz[c] == PIPE_SWIZZLE_ONE) ? 1 : 0;
+            break;
+         }
+      }
+   } else {
+      for (c = 0; c < 4; ++c) {
+         switch (swz[c]) {
+         case PIPE_SWIZZLE_RED:   dst->f[c] = src->f[0]; break;
+         case PIPE_SWIZZLE_GREEN: dst->f[c] = src->f[1]; break;
+         case PIPE_SWIZZLE_BLUE:  dst->f[c] = src->f[2]; break;
+         case PIPE_SWIZZLE_ALPHA: dst->f[c] = src->f[3]; break;
+         default:
+            dst->f[c] = (swz[c] == PIPE_SWIZZLE_ONE) ? 1.0f : 0.0f;
+            break;
+         }
+      }
+   }
+}
+
 void util_format_swizzle_4f(float *dst, const float *src,
                             const unsigned char swz[4])
 {
diff --git a/src/gallium/auxiliary/util/u_format.h b/src/gallium/auxiliary/util/u_format.h
index ed942fb1658..e4b9c365c97 100644
--- a/src/gallium/auxiliary/util/u_format.h
+++ b/src/gallium/auxiliary/util/u_format.h
@@ -33,6 +33,9 @@
 #include "pipe/p_format.h"
 #include "util/u_debug.h"
 
+union pipe_color_union;
+
+
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -1117,6 +1120,15 @@ void util_format_compose_swizzles(const unsigned char swz1[4],
                                   const unsigned char swz2[4],
                                   unsigned char dst[4]);
 
+/* Apply the swizzle provided in \param swz (which is one of PIPE_SWIZZLE_x)
+ * to \param src and store the result in \param dst.
+ * \param is_integer determines the value written for PIPE_SWIZZLE_ONE.
+ */
+void util_format_apply_color_swizzle(union pipe_color_union *dst,
+                                     const union pipe_color_union *src,
+                                     const unsigned char swz[4],
+                                     const boolean is_integer);
+
 void util_format_swizzle_4f(float *dst, const float *src,
                             const unsigned char swz[4]);
 
diff --git a/src/gallium/docs/source/cso/sampler.rst b/src/gallium/docs/source/cso/sampler.rst
index 26ffc181031..9959793a332 100644
--- a/src/gallium/docs/source/cso/sampler.rst
+++ b/src/gallium/docs/source/cso/sampler.rst
@@ -101,7 +101,9 @@ max_lod
 border_color
     Color union used for texel coordinates that are outside the [0,width-1],
     [0, height-1] or [0, depth-1] ranges. Interpreted according to sampler
-    view format.
+    view format, unless the driver reports
+    PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK, in which case special care has to be
+    taken (see description of the cap).
 max_anisotropy
     Maximum anistropy ratio to use when sampling from textures.  For example,
     if max_anistropy=4, a region of up to 1 by 4 texels will be sampled.
@@ -111,4 +113,4 @@ max_anisotropy
 seamless_cube_map
     If set, the bilinear filter of a cube map may take samples from adjacent
     cube map faces when sampled near a texture border to produce a seamless
-    look.
\ No newline at end of file
+    look.
diff --git a/src/gallium/docs/source/screen.rst b/src/gallium/docs/source/screen.rst
index 4b01d77322e..3ab7e9e6906 100644
--- a/src/gallium/docs/source/screen.rst
+++ b/src/gallium/docs/source/screen.rst
@@ -151,6 +151,17 @@ The integer capabilities:
   dedicated memory should return 1 and all software rasterizers should return 0.
 * ``PIPE_CAP_QUERY_PIPELINE_STATISTICS``: Whether PIPE_QUERY_PIPELINE_STATISTICS
   is supported.
+* ``PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK``: Bitmask indicating whether special
+  considerations have to be given to the interaction between the border color
+  in the sampler object and the sampler view used with it.
+  If PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_R600 is set, the border color
+  may be affected in undefined ways for any kind of permutational swizzle
+  (any swizzle XYZW where X/Y/Z/W are not ZERO, ONE, or R/G/B/A respectively)
+  in the sampler view.
+  If PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50 is set, the border color
+  state should be swizzled manually according to the swizzle in the sampler
+  view it is intended to be used with, or herein undefined results may occur
+  for permutational swizzles.
 
 
 .. _pipe_capf:
diff --git a/src/gallium/drivers/freedreno/freedreno_screen.c b/src/gallium/drivers/freedreno/freedreno_screen.c
index 283d07f12e4..4a9a54e3aea 100644
--- a/src/gallium/drivers/freedreno/freedreno_screen.c
+++ b/src/gallium/drivers/freedreno/freedreno_screen.c
@@ -200,6 +200,7 @@ fd_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
 	case PIPE_CAP_USER_VERTEX_BUFFERS:
 	case PIPE_CAP_USER_INDEX_BUFFERS:
 	case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
+	case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
 		return 0;
 
 	/* Stream output. */
diff --git a/src/gallium/drivers/i915/i915_screen.c b/src/gallium/drivers/i915/i915_screen.c
index 54b21549ba5..dfb76b3e98c 100644
--- a/src/gallium/drivers/i915/i915_screen.c
+++ b/src/gallium/drivers/i915/i915_screen.c
@@ -213,6 +213,7 @@ i915_get_param(struct pipe_screen *screen, enum pipe_cap cap)
    case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
    case PIPE_CAP_TEXTURE_MULTISAMPLE:
    case PIPE_CAP_MIN_MAP_BUFFER_ALIGNMENT:
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
       return 0;
 
    case PIPE_CAP_CONSTANT_BUFFER_OFFSET_ALIGNMENT:
diff --git a/src/gallium/drivers/llvmpipe/lp_screen.c b/src/gallium/drivers/llvmpipe/lp_screen.c
index 7152c3e8bca..5535f8523a7 100644
--- a/src/gallium/drivers/llvmpipe/lp_screen.c
+++ b/src/gallium/drivers/llvmpipe/lp_screen.c
@@ -138,6 +138,8 @@ llvmpipe_get_param(struct pipe_screen *screen, enum pipe_cap param)
       return 1;
    case PIPE_CAP_TEXTURE_SWIZZLE:
       return 1;
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+      return 0;
    case PIPE_CAP_MAX_TEXTURE_2D_LEVELS:
       return LP_MAX_TEXTURE_2D_LEVELS;
    case PIPE_CAP_MAX_TEXTURE_3D_LEVELS:
diff --git a/src/gallium/drivers/nv30/nv30_screen.c b/src/gallium/drivers/nv30/nv30_screen.c
index e33710e71f7..5b3b470cc4e 100644
--- a/src/gallium/drivers/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nv30/nv30_screen.c
@@ -123,6 +123,7 @@ nv30_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
    case PIPE_CAP_TEXTURE_BUFFER_OBJECTS:
    case PIPE_CAP_TEXTURE_BUFFER_OFFSET_ALIGNMENT:
    case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
       return 0;
    case PIPE_CAP_VERTEX_BUFFER_OFFSET_4BYTE_ALIGNED_ONLY:
    case PIPE_CAP_VERTEX_BUFFER_STRIDE_4BYTE_ALIGNED_ONLY:
diff --git a/src/gallium/drivers/nv50/nv50_screen.c b/src/gallium/drivers/nv50/nv50_screen.c
index 55081beb300..5aa8ef32e65 100644
--- a/src/gallium/drivers/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nv50/nv50_screen.c
@@ -186,6 +186,8 @@ nv50_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
       return 1;
    case PIPE_CAP_QUERY_PIPELINE_STATISTICS:
       return 0;
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+      return PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50;
    default:
       NOUVEAU_ERR("unknown PIPE_CAP %d\n", param);
       return 0;
diff --git a/src/gallium/drivers/nvc0/nvc0_screen.c b/src/gallium/drivers/nvc0/nvc0_screen.c
index ccdf2cde84b..8dfd4d12a02 100644
--- a/src/gallium/drivers/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nvc0/nvc0_screen.c
@@ -176,6 +176,8 @@ nvc0_screen_get_param(struct pipe_screen *pscreen, enum pipe_cap param)
       return (class_3d >= NVE4_3D_CLASS) ? 1 : 0;
    case PIPE_CAP_PREFER_BLIT_BASED_TEXTURE_TRANSFER:
       return 1;
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+      return PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50;
    default:
       NOUVEAU_ERR("unknown PIPE_CAP %d\n", param);
       return 0;
diff --git a/src/gallium/drivers/r300/r300_screen.c b/src/gallium/drivers/r300/r300_screen.c
index 3175b3bdd40..a932be9b41d 100644
--- a/src/gallium/drivers/r300/r300_screen.c
+++ b/src/gallium/drivers/r300/r300_screen.c
@@ -162,6 +162,7 @@ static int r300_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
         case PIPE_CAP_CUBE_MAP_ARRAY:
         case PIPE_CAP_TEXTURE_BUFFER_OBJECTS:
         case PIPE_CAP_TEXTURE_BUFFER_OFFSET_ALIGNMENT:
+        case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
             return 0;
 
         /* SWTCL-only features. */
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 9b43cef2737..4948dddae74 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -654,6 +654,9 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
 
 	case PIPE_CAP_MAX_TEXEL_OFFSET:
 		return 7;
+
+	case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+		return PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_R600;
 	}
 	return 0;
 }
diff --git a/src/gallium/drivers/radeonsi/radeonsi_pipe.c b/src/gallium/drivers/radeonsi/radeonsi_pipe.c
index 5c25b2f98b3..4e97f51dbdc 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_pipe.c
+++ b/src/gallium/drivers/radeonsi/radeonsi_pipe.c
@@ -380,6 +380,7 @@ static int r600_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
 	case PIPE_CAP_CUBE_MAP_ARRAY:
 	case PIPE_CAP_TEXTURE_BUFFER_OBJECTS:
 	case PIPE_CAP_TEXTURE_BUFFER_OFFSET_ALIGNMENT:
+	case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
 		return 0;
 
 	/* Stream output. */
diff --git a/src/gallium/drivers/softpipe/sp_screen.c b/src/gallium/drivers/softpipe/sp_screen.c
index b2b7f2e3208..53ee7d31cab 100644
--- a/src/gallium/drivers/softpipe/sp_screen.c
+++ b/src/gallium/drivers/softpipe/sp_screen.c
@@ -94,6 +94,8 @@ softpipe_get_param(struct pipe_screen *screen, enum pipe_cap param)
       return 1;
    case PIPE_CAP_TEXTURE_SWIZZLE:
       return 1;
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+      return 0;
    case PIPE_CAP_MAX_TEXTURE_2D_LEVELS:
       return SP_MAX_TEXTURE_2D_LEVELS;
    case PIPE_CAP_MAX_TEXTURE_3D_LEVELS:
diff --git a/src/gallium/drivers/svga/svga_screen.c b/src/gallium/drivers/svga/svga_screen.c
index 6213535a23e..60e0442944b 100644
--- a/src/gallium/drivers/svga/svga_screen.c
+++ b/src/gallium/drivers/svga/svga_screen.c
@@ -166,6 +166,8 @@ svga_get_param(struct pipe_screen *screen, enum pipe_cap param)
       return 1;
    case PIPE_CAP_TEXTURE_SWIZZLE:
       return 1;
+   case PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK:
+      return 0;
    case PIPE_CAP_USER_VERTEX_BUFFERS:
    case PIPE_CAP_USER_INDEX_BUFFERS:
       return 0;
diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h
index 5b00acc7418..2d38ce1a8c4 100644
--- a/src/gallium/include/pipe/p_defines.h
+++ b/src/gallium/include/pipe/p_defines.h
@@ -505,9 +505,14 @@ enum pipe_cap {
    PIPE_CAP_TEXTURE_BUFFER_OFFSET_ALIGNMENT = 78,
    PIPE_CAP_TGSI_TEXCOORD = 79,
    PIPE_CAP_PREFER_BLIT_BASED_TEXTURE_TRANSFER = 80,
-   PIPE_CAP_QUERY_PIPELINE_STATISTICS = 81
+   PIPE_CAP_QUERY_PIPELINE_STATISTICS = 81,
+   PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK = 82
 };
 
+#define PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50 (1 << 0)
+#define PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_R600 (1 << 1)
+
+
 /**
  * Implementation limits which are queried through
  * pipe_screen::get_paramf()
diff --git a/src/mesa/state_tracker/st_atom.c b/src/mesa/state_tracker/st_atom.c
index 32bcc266a34..7d383924300 100644
--- a/src/mesa/state_tracker/st_atom.c
+++ b/src/mesa/state_tracker/st_atom.c
@@ -55,10 +55,10 @@ static const struct st_tracked_state *atoms[] =
    &st_update_viewport,
    &st_update_scissor,
    &st_update_blend,
-   &st_update_sampler,
    &st_update_vertex_texture,
    &st_update_fragment_texture,
    &st_update_geometry_texture,
+   &st_update_sampler, /* depends on update_*_texture for swizzle */
    &st_update_framebuffer,
    &st_update_msaa,
    &st_update_vs_constants,
diff --git a/src/mesa/state_tracker/st_atom_sampler.c b/src/mesa/state_tracker/st_atom_sampler.c
index 3eba5b13cae..db51eead16b 100644
--- a/src/mesa/state_tracker/st_atom_sampler.c
+++ b/src/mesa/state_tracker/st_atom_sampler.c
@@ -48,6 +48,8 @@
 
 #include "cso_cache/cso_context.h"
 
+#include "util/u_format.h"
+
 
 /**
  * Convert GLenum texcoord wrap tokens to pipe tokens.
@@ -172,8 +174,10 @@ convert_sampler(struct st_context *st,
        msamp->BorderColor.ui[1] ||
        msamp->BorderColor.ui[2] ||
        msamp->BorderColor.ui[3]) {
+      struct st_texture_object *stobj = st_texture_object(texobj);
       struct gl_texture_image *teximg;
       GLboolean is_integer = GL_FALSE;
+      union pipe_color_union border_color;
 
       teximg = texobj->Image[0][texobj->BaseLevel];
 
@@ -181,9 +185,26 @@ convert_sampler(struct st_context *st,
          is_integer = _mesa_is_enum_format_integer(teximg->InternalFormat);
       }
 
-      st_translate_color(&msamp->BorderColor,
-                         &sampler->border_color,
-                         teximg ? teximg->_BaseFormat : GL_RGBA, is_integer);
+      if (st->apply_texture_swizzle_to_border_color && stobj->sampler_view) {
+         const unsigned char swz[4] =
+         {
+            stobj->sampler_view->swizzle_r,
+            stobj->sampler_view->swizzle_g,
+            stobj->sampler_view->swizzle_b,
+            stobj->sampler_view->swizzle_a,
+         };
+
+         st_translate_color(&msamp->BorderColor,
+                            &border_color,
+                            teximg ? teximg->_BaseFormat : GL_RGBA, is_integer);
+
+         util_format_apply_color_swizzle(&sampler->border_color,
+                                         &border_color, swz, is_integer);
+      } else {
+         st_translate_color(&msamp->BorderColor,
+                            &sampler->border_color,
+                            teximg ? teximg->_BaseFormat : GL_RGBA, is_integer);
+      }
    }
 
    sampler->max_anisotropy = (msamp->MaxAnisotropy == 1.0 ?
diff --git a/src/mesa/state_tracker/st_context.c b/src/mesa/state_tracker/st_context.c
index 2042be36bd3..ed1bf26a260 100644
--- a/src/mesa/state_tracker/st_context.c
+++ b/src/mesa/state_tracker/st_context.c
@@ -188,6 +188,10 @@ st_create_context_priv( struct gl_context *ctx, struct pipe_context *pipe,
 
    st->needs_texcoord_semantic =
       screen->get_param(screen, PIPE_CAP_TGSI_TEXCOORD);
+   st->apply_texture_swizzle_to_border_color =
+      !!(screen->get_param(screen, PIPE_CAP_TEXTURE_BORDER_COLOR_QUIRK) &
+         (PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_NV50 |
+          PIPE_QUIRK_TEXTURE_BORDER_COLOR_SWIZZLE_R600));
 
    /* GL limits and extensions */
    st_init_limits(st);
diff --git a/src/mesa/state_tracker/st_context.h b/src/mesa/state_tracker/st_context.h
index 8786a036ff4..807453e9974 100644
--- a/src/mesa/state_tracker/st_context.h
+++ b/src/mesa/state_tracker/st_context.h
@@ -87,6 +87,7 @@ struct st_context
    boolean prefer_blit_based_texture_transfer;
 
    boolean needs_texcoord_semantic;
+   boolean apply_texture_swizzle_to_border_color;
 
    /* On old libGL's for linux we need to invalidate the drawables
     * on glViewpport calls, this is set via a option.