nvc0: fix 3d images on kepler

Looks like SUBFM.3D and SUEAU are perfectly capable of dealing with 3d
tiling, they just need the correct inputs. Supply them.

We also have to deal with the case where a 2d "layer" of a 3d image is
bound. In this case, we supply the z coordinate separately to the
shader, which has to optionally treat every 2d case as if it could be a
slice of a 3d texture.

Signed-off-by: Ilia Mirkin <[email protected]>
Cc: 19.0 <[email protected]>

2 files changed, 34 insertions, 35 deletions

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
index 45474f07547..34cb7dc3e4b 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
@@ -1934,7 +1934,8 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
       su->op == OP_SULDB || su->op == OP_SUSTB || su->op == OP_SUREDB;
    const int slot = su->tex.r;
    const int dim = su->tex.target.getDim();
-   const int arg = dim + (su->tex.target.isArray() || su->tex.target.isCube());
+   const bool array = su->tex.target.isArray() || su->tex.target.isCube();
+   const int arg = dim + array;
    int c;
    Value *zero = bld.mkImm(0);
    Value *p1 = NULL;
@@ -1943,6 +1944,7 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
    Value *bf, *eau, *off;
    Value *addr, *pred;
    Value *ind = su->getIndirectR();
+   Value *y, *z;
 
    off = bld.getScratch(4);
    bf = bld.getScratch(4);
@@ -1973,34 +1975,42 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
    for (; c < 3; ++c)
       src[c] = zero;
 
+   if (dim == 2 && !array) {
+      v = loadSuInfo32(ind, slot, NVC0_SU_INFO_UNK1C, su->tex.bindless);
+      src[2] = bld.mkOp2v(OP_SHR, TYPE_U32, bld.getSSA(),
+                          v, bld.loadImm(NULL, 16));
+
+      v = loadSuInfo32(ind, slot, NVC0_SU_INFO_DIM(2), su->tex.bindless);
+      bld.mkOp3(OP_SUCLAMP, TYPE_S32, src[2], src[2], v, zero)
+         ->subOp = NV50_IR_SUBOP_SUCLAMP_SD(0, 2);
+   }
+
    // set predicate output
    if (su->tex.target == TEX_TARGET_BUFFER) {
       src[0]->getInsn()->setFlagsDef(1, pred);
    } else
-   if (su->tex.target.isArray() || su->tex.target.isCube()) {
+   if (array) {
       p1 = bld.getSSA(1, FILE_PREDICATE);
       src[dim]->getInsn()->setFlagsDef(1, p1);
    }
 
    // calculate pixel offset
    if (dim == 1) {
+      y = z = zero;
       if (su->tex.target != TEX_TARGET_BUFFER)
          bld.mkOp2(OP_AND, TYPE_U32, off, src[0], bld.loadImm(NULL, 0xffff));
-   } else
-   if (dim == 3) {
+   } else {
+      y = src[1];
+      z = src[2];
+
       v = loadSuInfo32(ind, slot, NVC0_SU_INFO_UNK1C, su->tex.bindless);
       bld.mkOp3(OP_MADSP, TYPE_U32, off, src[2], v, src[1])
-         ->subOp = NV50_IR_SUBOP_MADSP(4,2,8); // u16l u16l u16l
+         ->subOp = NV50_IR_SUBOP_MADSP(4,4,8); // u16l u16l u16l
 
       v = loadSuInfo32(ind, slot, NVC0_SU_INFO_PITCH, su->tex.bindless);
       bld.mkOp3(OP_MADSP, TYPE_U32, off, off, v, src[0])
-         ->subOp = NV50_IR_SUBOP_MADSP(0,2,8); // u32 u16l u16l
-   } else {
-      assert(dim == 2);
-      v = loadSuInfo32(ind, slot, NVC0_SU_INFO_PITCH, su->tex.bindless);
-      bld.mkOp3(OP_MADSP, TYPE_U32, off, src[1], v, src[0])
-         ->subOp = (su->tex.target.isArray() || su->tex.target.isCube()) ?
-         NV50_IR_SUBOP_MADSP_SD : NV50_IR_SUBOP_MADSP(4,2,8); // u16l u16l u16l
+         ->subOp = array ?
+         NV50_IR_SUBOP_MADSP_SD : NV50_IR_SUBOP_MADSP(0,2,8); // u32 u16l u16l
    }
 
    // calculate effective address part 1
@@ -2013,19 +2023,15 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
             ->subOp = NV50_IR_SUBOP_V1(7,6,8|2);
       }
    } else {
-      Value *y = src[1];
-      Value *z = src[2];
       uint16_t subOp = 0;
 
       switch (dim) {
       case 1:
-         y = zero;
-         z = zero;
          break;
       case 2:
-         z = off;
-         if (!su->tex.target.isArray() && !su->tex.target.isCube()) {
-            z = loadSuInfo32(ind, slot, NVC0_SU_INFO_UNK1C, su->tex.bindless);
+         if (array) {
+            z = off;
+         } else {
             subOp = NV50_IR_SUBOP_SUBFM_3D;
          }
          break;
@@ -2048,7 +2054,7 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
       eau = bld.mkOp3v(OP_SUEAU, TYPE_U32, bld.getScratch(4), off, bf, v);
    }
    // add array layer offset
-   if (su->tex.target.isArray() || su->tex.target.isCube()) {
+   if (array) {
       v = loadSuInfo32(ind, slot, NVC0_SU_INFO_ARRAY, su->tex.bindless);
       if (dim == 1)
          bld.mkOp3(OP_MADSP, TYPE_U32, eau, src[1], v, eau)
diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_tex.c b/src/gallium/drivers/nouveau/nvc0/nvc0_tex.c
index 04f0a0d55da..8820b5aac66 100644
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_tex.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_tex.c
@@ -1051,21 +1051,13 @@ nve4_set_surface_info(struct nouveau_pushbuf *push,
    } else {
       struct nv50_miptree *mt = nv50_miptree(&res->base);
       struct nv50_miptree_level *lvl = &mt->level[view->u.tex.level];
-      const unsigned z = view->u.tex.first_layer;
-
-      if (z) {
-         if (mt->layout_3d) {
-            address += nvc0_mt_zslice_offset(mt, view->u.tex.level, z);
-            /* doesn't work if z passes z-tile boundary */
-            if (depth > 1) {
-               pipe_debug_message(&nvc0->base.debug, CONFORMANCE,
-                                  "3D images are not really supported!");
-               debug_printf("3D images are not really supported!\n");
-            }
-         } else {
-            address += mt->layer_stride * z;
-         }
+      unsigned z = view->u.tex.first_layer;
+
+      if (!mt->layout_3d) {
+         address += mt->layer_stride * z;
+         z = 0;
       }
+
       address += lvl->offset;
 
       info[0]  = address >> 8;
@@ -1080,7 +1072,8 @@ nve4_set_surface_info(struct nouveau_pushbuf *push,
       info[6]  = depth - 1;
       info[6] |= (lvl->tile_mode & 0xf00) << 21;
       info[6] |= NVC0_TILE_SHIFT_Z(lvl->tile_mode) << 22;
-      info[7]  = 0;
+      info[7]  = mt->layout_3d ? 1 : 0;
+      info[7] |= z << 16;
       info[14] = mt->ms_x;
       info[15] = mt->ms_y;
    }