diff options
Diffstat (limited to 'src/gallium/drivers/nv40')
-rw-r--r-- | src/gallium/drivers/nv40/nv40_context.c | 6 | ||||
-rw-r--r-- | src/gallium/drivers/nv40/nv40_draw.c | 5 | ||||
-rw-r--r-- | src/gallium/drivers/nv40/nv40_fragprog.c | 46 | ||||
-rw-r--r-- | src/gallium/drivers/nv40/nv40_miptree.c | 22 | ||||
-rw-r--r-- | src/gallium/drivers/nv40/nv40_screen.c | 7 | ||||
-rw-r--r-- | src/gallium/drivers/nv40/nv40_transfer.c | 26 |
6 files changed, 87 insertions, 25 deletions
diff --git a/src/gallium/drivers/nv40/nv40_context.c b/src/gallium/drivers/nv40/nv40_context.c index eb9cce4c78..d56c7a6b49 100644 --- a/src/gallium/drivers/nv40/nv40_context.c +++ b/src/gallium/drivers/nv40/nv40_context.c @@ -25,6 +25,12 @@ static void nv40_destroy(struct pipe_context *pipe) { struct nv40_context *nv40 = nv40_context(pipe); + unsigned i; + + for (i = 0; i < NV40_STATE_MAX; i++) { + if (nv40->state.hw[i]) + so_ref(NULL, &nv40->state.hw[i]); + } if (nv40->draw) draw_destroy(nv40->draw); diff --git a/src/gallium/drivers/nv40/nv40_draw.c b/src/gallium/drivers/nv40/nv40_draw.c index b2f19ecb69..3875bc3545 100644 --- a/src/gallium/drivers/nv40/nv40_draw.c +++ b/src/gallium/drivers/nv40/nv40_draw.c @@ -261,7 +261,8 @@ nv40_draw_elements_swtnl(struct pipe_context *pipe, map = pipe_buffer_map(pscreen, nv40->constbuf[PIPE_SHADER_VERTEX], PIPE_BUFFER_USAGE_CPU_READ); - draw_set_mapped_constant_buffer(nv40->draw, map, nr); + draw_set_mapped_constant_buffer(nv40->draw, PIPE_SHADER_VERTEX, + map, nr); } draw_arrays(nv40->draw, mode, start, count); @@ -285,7 +286,7 @@ static INLINE void emit_attrib(struct nv40_context *nv40, unsigned hw, unsigned emit, unsigned semantic, unsigned index) { - unsigned draw_out = draw_find_vs_output(nv40->draw, semantic, index); + unsigned draw_out = draw_find_shader_output(nv40->draw, semantic, index); unsigned a = nv40->swtnl.nr_attribs++; nv40->swtnl.hw[a] = hw; diff --git a/src/gallium/drivers/nv40/nv40_fragprog.c b/src/gallium/drivers/nv40/nv40_fragprog.c index 1bf16726d1..bb9c85cc43 100644 --- a/src/gallium/drivers/nv40/nv40_fragprog.c +++ b/src/gallium/drivers/nv40/nv40_fragprog.c @@ -149,7 +149,7 @@ emit_src(struct nv40_fpc *fpc, int pos, struct nv40_sreg src) sizeof(uint32_t) * 4); } - sr |= (NV40_FP_REG_TYPE_CONST << NV40_FP_REG_TYPE_SHIFT); + sr |= (NV40_FP_REG_TYPE_CONST << NV40_FP_REG_TYPE_SHIFT); break; case NV40SR_NONE: sr |= (NV40_FP_REG_TYPE_INPUT << NV40_FP_REG_TYPE_SHIFT); @@ -445,10 +445,11 @@ nv40_fragprog_parse_instruction(struct nv40_fpc *fpc, arith(fpc, sat, ADD, dst, mask, src[0], src[1], none); break; case TGSI_OPCODE_CMP: - tmp = temp(fpc); - arith(fpc, sat, MOV, dst, mask, src[2], none, none); + tmp = nv40_sr(NV40SR_NONE, 0); tmp.cc_update = 1; arith(fpc, 0, MOV, tmp, 0xf, src[0], none, none); + dst.cc_test = NV40_VP_INST_COND_GE; + arith(fpc, sat, MOV, dst, mask, src[2], none, none); dst.cc_test = NV40_VP_INST_COND_LT; arith(fpc, sat, MOV, dst, mask, src[1], none, none); break; @@ -573,13 +574,28 @@ nv40_fragprog_parse_instruction(struct nv40_fpc *fpc, neg(swz(tmp, X, X, X, X)), none, none); break; case TGSI_OPCODE_SCS: - if (mask & MASK_X) { - arith(fpc, sat, COS, dst, MASK_X, - swz(src[0], X, X, X, X), none, none); + /* avoid overwriting the source */ + if(src[0].swz[SWZ_X] != SWZ_X) + { + if (mask & MASK_X) { + arith(fpc, sat, COS, dst, MASK_X, + swz(src[0], X, X, X, X), none, none); + } + if (mask & MASK_Y) { + arith(fpc, sat, SIN, dst, MASK_Y, + swz(src[0], X, X, X, X), none, none); + } } - if (mask & MASK_Y) { - arith(fpc, sat, SIN, dst, MASK_Y, - swz(src[0], X, X, X, X), none, none); + else + { + if (mask & MASK_Y) { + arith(fpc, sat, SIN, dst, MASK_Y, + swz(src[0], X, X, X, X), none, none); + } + if (mask & MASK_X) { + arith(fpc, sat, COS, dst, MASK_X, + swz(src[0], X, X, X, X), none, none); + } } break; case TGSI_OPCODE_SEQ: @@ -752,7 +768,7 @@ nv40_fragprog_prepare(struct nv40_fpc *fpc) { struct tgsi_full_immediate *imm; float vals[4]; - + imm = &p.FullToken.FullImmediate; assert(imm->Immediate.DataType == TGSI_IMM_FLOAT32); assert(fpc->nr_imm < MAX_IMM); @@ -836,7 +852,7 @@ nv40_fragprog_translate(struct nv40_context *nv40, fp->insn[fpc->inst_offset + 1] = 0x00000000; fp->insn[fpc->inst_offset + 2] = 0x00000000; fp->insn[fpc->inst_offset + 3] = 0x00000000; - + fp->translated = TRUE; out_err: tgsi_parse_free(&parse); @@ -917,7 +933,7 @@ nv40_fragprog_validate(struct nv40_context *nv40) update_constants: if (fp->nr_consts) { float *map; - + map = pipe_buffer_map(pscreen, constbuf, PIPE_BUFFER_USAGE_CPU_READ); for (i = 0; i < fp->nr_consts; i++) { @@ -948,6 +964,12 @@ void nv40_fragprog_destroy(struct nv40_context *nv40, struct nv40_fragment_program *fp) { + if (fp->buffer) + pipe_buffer_reference(&fp->buffer, NULL); + + if (fp->so) + so_ref(NULL, &fp->so); + if (fp->insn_len) FREE(fp->insn); } diff --git a/src/gallium/drivers/nv40/nv40_miptree.c b/src/gallium/drivers/nv40/nv40_miptree.c index b974e68a07..89bd155ff4 100644 --- a/src/gallium/drivers/nv40/nv40_miptree.c +++ b/src/gallium/drivers/nv40/nv40_miptree.c @@ -5,6 +5,7 @@ #include "util/u_math.h" #include "nv40_context.h" +#include "../nv04/nv04_surface_2d.h" @@ -105,6 +106,12 @@ nv40_miptree_create(struct pipe_screen *pscreen, const struct pipe_texture *pt) if (pt->tex_usage & PIPE_TEXTURE_USAGE_DYNAMIC) buf_usage |= PIPE_BUFFER_USAGE_CPU_READ_WRITE; + /* apparently we can't render to swizzled surfaces smaller than 64 bytes, so make them linear. + * If the user did not ask for a render target, they can still render to it, but it will cost them an extra copy. + * This also happens for small mipmaps of large textures. */ + if (pt->tex_usage & PIPE_TEXTURE_USAGE_RENDER_TARGET && util_format_get_stride(pt->format, pt->width0) < 64) + mt->base.tex_usage |= NOUVEAU_TEXTURE_USAGE_LINEAR; + nv40_miptree_layout(mt); mt->buffer = pscreen->buffer_create(pscreen, 256, buf_usage, mt->total_size); @@ -191,12 +198,27 @@ nv40_miptree_surface_new(struct pipe_screen *pscreen, struct pipe_texture *pt, ns->base.offset = mt->level[level].image_offset[0]; } + /* create a linear temporary that we can render into if necessary. + * Note that ns->pitch is always a multiple of 64 for linear surfaces and swizzled surfaces are POT, so + * ns->pitch & 63 is equivalent to (ns->pitch < 64 && swizzled)*/ + if((ns->pitch & 63) && (ns->base.usage & (PIPE_BUFFER_USAGE_GPU_WRITE | NOUVEAU_BUFFER_USAGE_NO_RENDER)) == PIPE_BUFFER_USAGE_GPU_WRITE) + return &nv04_surface_wrap_for_render(pscreen, ((struct nv40_screen*)pscreen)->eng2d, ns)->base; + return &ns->base; } static void nv40_miptree_surface_del(struct pipe_surface *ps) { + struct nv04_surface* ns = (struct nv04_surface*)ps; + if(ns->backing) + { + struct nv40_screen* screen = (struct nv40_screen*)ps->texture->screen; + if(ns->backing->base.usage & PIPE_BUFFER_USAGE_GPU_WRITE) + screen->eng2d->copy(screen->eng2d, &ns->backing->base, 0, 0, ps, 0, 0, ns->base.width, ns->base.height); + nv40_miptree_surface_del(&ns->backing->base); + } + pipe_texture_reference(&ps->texture, NULL); FREE(ps); } diff --git a/src/gallium/drivers/nv40/nv40_screen.c b/src/gallium/drivers/nv40/nv40_screen.c index bd13dfddd1..d01e712805 100644 --- a/src/gallium/drivers/nv40/nv40_screen.c +++ b/src/gallium/drivers/nv40/nv40_screen.c @@ -140,6 +140,12 @@ static void nv40_screen_destroy(struct pipe_screen *pscreen) { struct nv40_screen *screen = nv40_screen(pscreen); + unsigned i; + + for (i = 0; i < NV40_STATE_MAX; i++) { + if (screen->state[i]) + so_ref(NULL, &screen->state[i]); + } nouveau_resource_free(&screen->vp_exec_heap); nouveau_resource_free(&screen->vp_data_heap); @@ -147,6 +153,7 @@ nv40_screen_destroy(struct pipe_screen *pscreen) nouveau_notifier_free(&screen->query); nouveau_notifier_free(&screen->sync); nouveau_grobj_free(&screen->curie); + nv04_surface_2d_takedown(&screen->eng2d); nouveau_screen_fini(&screen->base); diff --git a/src/gallium/drivers/nv40/nv40_transfer.c b/src/gallium/drivers/nv40/nv40_transfer.c index b084a38b48..791ee6823d 100644 --- a/src/gallium/drivers/nv40/nv40_transfer.c +++ b/src/gallium/drivers/nv40/nv40_transfer.c @@ -16,14 +16,14 @@ struct nv40_transfer { }; static void -nv40_compatible_transfer_tex(struct pipe_texture *pt, unsigned level, +nv40_compatible_transfer_tex(struct pipe_texture *pt, unsigned width, unsigned height, struct pipe_texture *template) { memset(template, 0, sizeof(struct pipe_texture)); template->target = pt->target; template->format = pt->format; - template->width0 = u_minify(pt->width0, level); - template->height0 = u_minify(pt->height0, level); + template->width0 = width; + template->height0 = height; template->depth0 = 1; template->last_level = 0; template->nr_samples = pt->nr_samples; @@ -71,7 +71,7 @@ nv40_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt, tx->direct = false; - nv40_compatible_transfer_tex(pt, level, &tx_tex_template); + nv40_compatible_transfer_tex(pt, w, h, &tx_tex_template); tx_tex = pscreen->texture_create(pscreen, &tx_tex_template); if (!tx_tex) @@ -80,6 +80,8 @@ nv40_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt, return NULL; } + tx->base.stride = ((struct nv40_miptree*)tx_tex)->level[0].pitch; + tx->surface = pscreen->get_tex_surface(pscreen, tx_tex, 0, 0, 0, pipe_transfer_buffer_flags(&tx->base)); @@ -105,8 +107,8 @@ nv40_transfer_new(struct pipe_screen *pscreen, struct pipe_texture *pt, /* TODO: Check if SIFM can un-swizzle */ nvscreen->eng2d->copy(nvscreen->eng2d, tx->surface, 0, 0, - src, 0, 0, - src->width, src->height); + src, x, y, + w, h); pipe_surface_reference(&src, NULL); } @@ -126,13 +128,13 @@ nv40_transfer_del(struct pipe_transfer *ptx) dst = pscreen->get_tex_surface(pscreen, ptx->texture, ptx->face, ptx->level, ptx->zslice, - PIPE_BUFFER_USAGE_GPU_WRITE); + PIPE_BUFFER_USAGE_GPU_WRITE | NOUVEAU_BUFFER_USAGE_NO_RENDER); /* TODO: Check if SIFM can deal with x,y,w,h when swizzling */ nvscreen->eng2d->copy(nvscreen->eng2d, - dst, 0, 0, + dst, tx->base.x, tx->base.y, tx->surface, 0, 0, - dst->width, dst->height); + tx->base.width, tx->base.height); pipe_surface_reference(&dst, NULL); } @@ -151,8 +153,10 @@ nv40_transfer_map(struct pipe_screen *pscreen, struct pipe_transfer *ptx) void *map = pipe_buffer_map(pscreen, mt->buffer, pipe_transfer_buffer_flags(ptx)); - return map + ns->base.offset + - ptx->y * ns->pitch + ptx->x * util_format_get_blocksize(ptx->texture->format); + if(!tx->direct) + return map + ns->base.offset; + else + return map + ns->base.offset + ptx->y * ns->pitch + ptx->x * util_format_get_blocksize(ptx->texture->format); } static void |