gallium: add PIPE_SHADER_CAP_MAX_OUTPUTS and use it in st/mesa

With 5 shader stages and various combinations of enabled and disabled shaders,
the maximum number of outputs in one shader doesn't have to be equal to
the maximum number of inputs in the following shader.

v2: return 32 for softpipe and llvmpipe

16 files changed, 36 insertions, 4 deletions

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_limits.h b/src/gallium/auxiliary/gallivm/lp_bld_limits.h
index a96ab2924d2..8c66f9d618e 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_limits.h
+++ b/src/gallium/auxiliary/gallivm/lp_bld_limits.h
@@ -97,6 +97,8 @@ gallivm_get_shader_param(enum pipe_shader_cap param)
       return LP_MAX_TGSI_NESTING;
    case PIPE_SHADER_CAP_MAX_INPUTS:
       return PIPE_MAX_SHADER_INPUTS;
+   case PIPE_SHADER_CAP_MAX_OUTPUTS:
+      return 32;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
       return sizeof(float[4]) * 4096;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/auxiliary/tgsi/tgsi_exec.h b/src/gallium/auxiliary/tgsi/tgsi_exec.h
index 4720ec673cf..cc5a9160c5c 100644
--- a/src/gallium/auxiliary/tgsi/tgsi_exec.h
+++ b/src/gallium/auxiliary/tgsi/tgsi_exec.h
@@ -426,6 +426,8 @@ tgsi_exec_get_shader_param(enum pipe_shader_cap param)
       return TGSI_EXEC_MAX_NESTING;
    case PIPE_SHADER_CAP_MAX_INPUTS:
       return TGSI_EXEC_MAX_INPUT_ATTRIBS;
+   case PIPE_SHADER_CAP_MAX_OUTPUTS:
+      return 32;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
       return TGSI_EXEC_MAX_CONST_BUFFER_SIZE;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/docs/source/screen.rst b/src/gallium/docs/source/screen.rst
index ba34ec8297a..88d7e4924f2 100644
--- a/src/gallium/docs/source/screen.rst
+++ b/src/gallium/docs/source/screen.rst
@@ -267,6 +267,8 @@ support different features.
 * ``PIPE_SHADER_CAP_MAX_TEX_INDIRECTIONS``: The maximum number of texture indirections.
 * ``PIPE_SHADER_CAP_MAX_CONTROL_FLOW_DEPTH``: The maximum nested control flow depth.
 * ``PIPE_SHADER_CAP_MAX_INPUTS``: The maximum number of input registers.
+* ``PIPE_SHADER_CAP_MAX_OUTPUTS``: The maximum number of output registers.
+  This is valid for all shaders except the fragment shader.
 * ``PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE``: The maximum size per constant buffer in bytes.
 * ``PIPE_SHADER_CAP_MAX_CONST_BUFFERS``: Maximum number of constant buffers that can be bound
   to any shader stage using ``set_constant_buffer``. If 0 or 1, the pipe will
diff --git a/src/gallium/drivers/freedreno/freedreno_screen.c b/src/gallium/drivers/freedreno/freedreno_screen.c
index ddc7302c5c8..90156b49cb6 100644
--- a/src/gallium/drivers/freedreno/freedreno_screen.c
+++ b/src/gallium/drivers/freedreno/freedreno_screen.c
@@ -351,6 +351,7 @@ fd_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
 	case PIPE_SHADER_CAP_MAX_CONTROL_FLOW_DEPTH:
 		return 8; /* XXX */
 	case PIPE_SHADER_CAP_MAX_INPUTS:
+        case PIPE_SHADER_CAP_MAX_OUTPUTS:
 		return 16;
 	case PIPE_SHADER_CAP_MAX_TEMPS:
 		return 64; /* Max native temporaries. */
diff --git a/src/gallium/drivers/i915/i915_screen.c b/src/gallium/drivers/i915/i915_screen.c
index 90067343fba..2a6e7518b0e 100644
--- a/src/gallium/drivers/i915/i915_screen.c
+++ b/src/gallium/drivers/i915/i915_screen.c
@@ -130,6 +130,8 @@ i915_get_shader_param(struct pipe_screen *screen, unsigned shader, enum pipe_sha
          return 0;
       case PIPE_SHADER_CAP_MAX_INPUTS:
          return 10;
+      case PIPE_SHADER_CAP_MAX_OUTPUTS:
+         return 1;
       case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
          return 32 * sizeof(float[4]);
       case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/ilo/ilo_screen.c b/src/gallium/drivers/ilo/ilo_screen.c
index bfd67dad622..48c3dea2d7e 100644
--- a/src/gallium/drivers/ilo/ilo_screen.c
+++ b/src/gallium/drivers/ilo/ilo_screen.c
@@ -121,6 +121,7 @@ ilo_get_shader_param(struct pipe_screen *screen, unsigned shader,
    case PIPE_SHADER_CAP_MAX_CONTROL_FLOW_DEPTH:
       return UINT_MAX;
    case PIPE_SHADER_CAP_MAX_INPUTS:
+   case PIPE_SHADER_CAP_MAX_OUTPUTS:
       /* this is limited by how many attributes SF can remap */
       return 16;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
diff --git a/src/gallium/drivers/nouveau/nv30/nv30_screen.c b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
index a1373fdd9d5..700b9bbfe09 100644
--- a/src/gallium/drivers/nouveau/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nouveau/nv30/nv30_screen.c
@@ -222,6 +222,7 @@ nv30_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
       case PIPE_SHADER_CAP_MAX_CONTROL_FLOW_DEPTH:
          return 0;
       case PIPE_SHADER_CAP_MAX_INPUTS:
+      case PIPE_SHADER_CAP_MAX_OUTPUTS:
          return 16;
       case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
          return ((eng3d->oclass >= NV40_3D_CLASS) ? (468 - 6): (256 - 6)) * sizeof(float[4]);
@@ -258,6 +259,8 @@ nv30_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
          return 0;
       case PIPE_SHADER_CAP_MAX_INPUTS:
          return 8; /* should be possible to do 10 with nv4x */
+      case PIPE_SHADER_CAP_MAX_OUTPUTS:
+         return 4;
       case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
          return ((eng3d->oclass >= NV40_3D_CLASS) ? 224 : 32) * sizeof(float[4]);
       case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.c b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
index 3a46e72a0f7..d26a438378c 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
@@ -253,6 +253,8 @@ nv50_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
       if (shader == PIPE_SHADER_VERTEX)
          return 32;
       return 15;
+   case PIPE_SHADER_CAP_MAX_OUTPUTS:
+      return 16;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
       return 65536;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
index 3858981348c..a673eb92035 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_screen.c
@@ -259,6 +259,8 @@ nvc0_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
        * and excludes 0x60 per-patch inputs.
        */
       return 0x200 / 16;
+   case PIPE_SHADER_CAP_MAX_OUTPUTS:
+      return 32;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
       return 65536;
    case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/r300/r300_screen.c b/src/gallium/drivers/r300/r300_screen.c
index c35559f5e73..db9ad15983c 100644
--- a/src/gallium/drivers/r300/r300_screen.c
+++ b/src/gallium/drivers/r300/r300_screen.c
@@ -258,6 +258,8 @@ static int r300_get_shader_param(struct pipe_screen *pscreen, unsigned shader, e
              * additional texcoords but there is no two-sided color
              * selection then. However the facing bit can be used instead. */
             return 10;
+        case PIPE_SHADER_CAP_MAX_OUTPUTS:
+            return 4;
         case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
             return (is_r500 ? 256 : 32) * sizeof(float[4]);
         case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
@@ -306,6 +308,8 @@ static int r300_get_shader_param(struct pipe_screen *pscreen, unsigned shader, e
             return is_r500 ? 4 : 0; /* For loops; not sure about conditionals. */
         case PIPE_SHADER_CAP_MAX_INPUTS:
             return 16;
+        case PIPE_SHADER_CAP_MAX_OUTPUTS:
+            return 10;
         case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
             return 256 * sizeof(float[4]);
         case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 3962fee4a43..c7945305182 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -434,6 +434,8 @@ static int r600_get_shader_param(struct pipe_screen* pscreen, unsigned shader, e
 		return 32;
 	case PIPE_SHADER_CAP_MAX_INPUTS:
 		return shader == PIPE_SHADER_VERTEX ? 16 : 32;
+	case PIPE_SHADER_CAP_MAX_OUTPUTS:
+		return shader == PIPE_SHADER_FRAGMENT ? 8 : 32;
 	case PIPE_SHADER_CAP_MAX_TEMPS:
 		return 256; /* Max native temporaries. */
 	case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index cba6d98f29c..839711504e5 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -364,6 +364,8 @@ static int si_get_shader_param(struct pipe_screen* pscreen, unsigned shader, enu
 		return 32;
 	case PIPE_SHADER_CAP_MAX_INPUTS:
 		return shader == PIPE_SHADER_VERTEX ? SI_NUM_VERTEX_BUFFERS : 32;
+	case PIPE_SHADER_CAP_MAX_OUTPUTS:
+		return shader == PIPE_SHADER_FRAGMENT ? 8 : 32;
 	case PIPE_SHADER_CAP_MAX_TEMPS:
 		return 256; /* Max native temporaries. */
 	case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
diff --git a/src/gallium/drivers/svga/svga_screen.c b/src/gallium/drivers/svga/svga_screen.c
index 004b4b4306d..587eaad07c8 100644
--- a/src/gallium/drivers/svga/svga_screen.c
+++ b/src/gallium/drivers/svga/svga_screen.c
@@ -330,6 +330,8 @@ static int svga_get_shader_param(struct pipe_screen *screen, unsigned shader, en
          return SVGA3D_MAX_NESTING_LEVEL;
       case PIPE_SHADER_CAP_MAX_INPUTS:
          return 10;
+      case PIPE_SHADER_CAP_MAX_OUTPUTS:
+         return svgascreen->max_color_buffers;
       case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
          return 224 * sizeof(float[4]);
       case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
@@ -387,6 +389,8 @@ static int svga_get_shader_param(struct pipe_screen *screen, unsigned shader, en
          return SVGA3D_MAX_NESTING_LEVEL;
       case PIPE_SHADER_CAP_MAX_INPUTS:
          return 16;
+      case PIPE_SHADER_CAP_MAX_OUTPUTS:
+         return 10;
       case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
          return 256 * sizeof(float[4]);
       case PIPE_SHADER_CAP_MAX_CONST_BUFFERS:
diff --git a/src/gallium/drivers/vc4/vc4_screen.c b/src/gallium/drivers/vc4/vc4_screen.c
index a327c7f26b4..4c0455da0c0 100644
--- a/src/gallium/drivers/vc4/vc4_screen.c
+++ b/src/gallium/drivers/vc4/vc4_screen.c
@@ -283,6 +283,8 @@ vc4_screen_get_shader_param(struct pipe_screen *pscreen, unsigned shader,
                         return 8;
                 else
                         return 16;
+	case PIPE_SHADER_CAP_MAX_OUTPUTS:
+		return shader == PIPE_SHADER_FRAGMENT ? 1 : 8;
         case PIPE_SHADER_CAP_MAX_TEMPS:
                 return 256; /* GL_MAX_PROGRAM_TEMPORARIES_ARB */
         case PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE:
diff --git a/src/gallium/include/pipe/p_defines.h b/src/gallium/include/pipe/p_defines.h
index d9b1547b1e2..42b6f3755e4 100644
--- a/src/gallium/include/pipe/p_defines.h
+++ b/src/gallium/include/pipe/p_defines.h
@@ -613,6 +613,7 @@ enum pipe_shader_cap
    PIPE_SHADER_CAP_MAX_TEX_INDIRECTIONS,
    PIPE_SHADER_CAP_MAX_CONTROL_FLOW_DEPTH,
    PIPE_SHADER_CAP_MAX_INPUTS,
+   PIPE_SHADER_CAP_MAX_OUTPUTS,
    PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE,
    PIPE_SHADER_CAP_MAX_CONST_BUFFERS,
    PIPE_SHADER_CAP_MAX_TEMPS,
diff --git a/src/mesa/state_tracker/st_extensions.c b/src/mesa/state_tracker/st_extensions.c
index 5dd8278007e..78bfe30735f 100644
--- a/src/mesa/state_tracker/st_extensions.c
+++ b/src/mesa/state_tracker/st_extensions.c
@@ -192,6 +192,10 @@ void st_init_limits(struct pipe_screen *screen,
       pc->MaxParameters      = pc->MaxNativeParameters      =
          screen->get_shader_param(screen, sh,
                    PIPE_SHADER_CAP_MAX_CONST_BUFFER_SIZE) / sizeof(float[4]);
+      pc->MaxInputComponents =
+         screen->get_shader_param(screen, sh, PIPE_SHADER_CAP_MAX_INPUTS) * 4;
+      pc->MaxOutputComponents =
+         screen->get_shader_param(screen, sh, PIPE_SHADER_CAP_MAX_OUTPUTS) * 4;
 
       pc->MaxUniformComponents = 4 * MIN2(pc->MaxNativeParameters, MAX_UNIFORMS);
 
@@ -261,10 +265,6 @@ void st_init_limits(struct pipe_screen *screen,
    c->MaxVarying = screen->get_shader_param(screen, PIPE_SHADER_FRAGMENT,
                                             PIPE_SHADER_CAP_MAX_INPUTS);
    c->MaxVarying = MIN2(c->MaxVarying, MAX_VARYING);
-   c->Program[MESA_SHADER_FRAGMENT].MaxInputComponents = c->MaxVarying * 4;
-   c->Program[MESA_SHADER_VERTEX].MaxOutputComponents = c->MaxVarying * 4;
-   c->Program[MESA_SHADER_GEOMETRY].MaxInputComponents = c->MaxVarying * 4;
-   c->Program[MESA_SHADER_GEOMETRY].MaxOutputComponents = c->MaxVarying * 4;
    c->MaxGeometryOutputVertices = screen->get_param(screen, PIPE_CAP_MAX_GEOMETRY_OUTPUT_VERTICES);
    c->MaxGeometryTotalOutputComponents = screen->get_param(screen, PIPE_CAP_MAX_GEOMETRY_TOTAL_OUTPUT_COMPONENTS);