nouveau: Fix swizzling for copies to rectangular textures

nVidia hardware seems to swizzle rectangular texture (with width !=
height) coordinates by swizzling the lower bits and then adding the
higher bits from the larger dimension.
However, nv04_swizzle_bits ignores width and height and just
interleaves everything.
This causes problems with rectangular POT textures with height or
width 2048 or 4096 (but not 2048x1024 where it works by chance) since
the driver swizzles them in 1024x1024 chunks and gets the start
position for the non-first chunks wrong.
The following patch seems to fix those problems.

diff --git a/src/gallium/drivers/nv04/nv04_surface_2d.c b/src/gallium/drivers/nv04/nv04_surface_2d.c
index 819f45e96ad4a5813ace9f61b34296bc8a6088bf..40b538fd71b8bbc976846bbdb8bdcc2cf1284662 100644 (file)
--- a/src/gallium/drivers/nv04/nv04_surface_2d.c
+++ b/src/gallium/drivers/nv04/nv04_surface_2d.c
@@ -77,7 +77,7 @@ nv04_scaled_image_format(enum pipe_format format)
 }
 
 static INLINE unsigned
-nv04_swizzle_bits(unsigned x, unsigned y)
+nv04_swizzle_bits_square(unsigned x, unsigned y)
 {
        unsigned u = (x & 0x001) << 0 |
                     (x & 0x002) << 1 |
@@ -107,6 +107,15 @@ nv04_swizzle_bits(unsigned x, unsigned y)
        return v | u;
 }
 
+/* rectangular swizzled textures are linear concatenations of swizzled square tiles */
+static INLINE unsigned
+nv04_swizzle_bits(unsigned x, unsigned y, unsigned w, unsigned h)
+{
+       unsigned s = MIN2(w, h);
+       unsigned m = s - 1;
+       return (((x | y) & ~m) * s) | nv04_swizzle_bits_square(x & m, y & m);
+}
+
 static int
 nv04_surface_copy_swizzle(struct nv04_surface_2d *ctx,
                          struct pipe_surface *dst, int dx, int dy,
@@ -159,10 +168,10 @@ nv04_surface_copy_swizzle(struct nv04_surface_2d *ctx,
            sub_w = MIN2(sub_w, w - x);
 
            /* Must be 64-byte aligned */
-           assert(!((dst->offset + nv04_swizzle_bits(dx+x, dy+y) * util_format_get_blocksize(dst->texture->format)) & 63));
+           assert(!((dst->offset + nv04_swizzle_bits(dx+x, dy+y, w, h) * util_format_get_blocksize(dst->texture->format)) & 63));
 
            BEGIN_RING(chan, swzsurf, NV04_SWIZZLED_SURFACE_OFFSET, 1);
-           OUT_RELOCl(chan, dst_bo, dst->offset + nv04_swizzle_bits(dx+x, dy+y) * util_format_get_blocksize(dst->texture->format),
+           OUT_RELOCl(chan, dst_bo, dst->offset + nv04_swizzle_bits(dx+x, dy+y, w, h) * util_format_get_blocksize(dst->texture->format),
                              NOUVEAU_BO_GART | NOUVEAU_BO_VRAM | NOUVEAU_BO_WR);
 
            BEGIN_RING(chan, sifm, NV04_SCALED_IMAGE_FROM_MEMORY_COLOR_CONVERSION, 9);