From fb3d9e97e1ad5f2c19b68fe5a0c6a95bf57c65c3 Mon Sep 17 00:00:00 2001 From: Ilija Hadzic Date: Wed, 12 Oct 2011 23:29:41 -0400 Subject: [PATCH] drm/radeon/kms: blit code commoning factor out most of evergreen blit code and use the refactored code from r600 that is now common for both r600 and evergreen Signed-off-by: Ilija Hadzic Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/evergreen.c | 25 +-- drivers/gpu/drm/radeon/evergreen_blit_kms.c | 260 ++-------------------------- drivers/gpu/drm/radeon/ni.c | 4 +- drivers/gpu/drm/radeon/radeon_asic.c | 16 +- drivers/gpu/drm/radeon/radeon_asic.h | 10 -- 5 files changed, 30 insertions(+), 285 deletions(-) diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 7cd40241205..b37b6a0bbec 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -3087,7 +3087,7 @@ static int evergreen_startup(struct radeon_device *rdev) r = evergreen_blit_init(rdev); if (r) { - evergreen_blit_fini(rdev); + r600_blit_fini(rdev); rdev->asic->copy = NULL; dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r); } @@ -3172,27 +3172,6 @@ int evergreen_suspend(struct radeon_device *rdev) return 0; } -int evergreen_copy_blit(struct radeon_device *rdev, - uint64_t src_offset, uint64_t dst_offset, - unsigned num_pages, struct radeon_fence *fence) -{ - int r; - - mutex_lock(&rdev->r600_blit.mutex); - rdev->r600_blit.vb_ib = NULL; - r = evergreen_blit_prepare_copy(rdev, num_pages); - if (r) { - if (rdev->r600_blit.vb_ib) - radeon_ib_free(rdev, &rdev->r600_blit.vb_ib); - mutex_unlock(&rdev->r600_blit.mutex); - return r; - } - evergreen_kms_blit_copy(rdev, src_offset, dst_offset, num_pages); - evergreen_blit_done_copy(rdev, fence); - mutex_unlock(&rdev->r600_blit.mutex); - return 0; -} - /* Plan is to move initialization in that function and use * helper function so that radeon_device_init pretty much * do nothing more than calling asic specific function. This @@ -3301,7 +3280,7 @@ int evergreen_init(struct radeon_device *rdev) void evergreen_fini(struct radeon_device *rdev) { - evergreen_blit_fini(rdev); + r600_blit_fini(rdev); r700_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c index 5befd513900..dcf11bbc06d 100644 --- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c +++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c @@ -44,10 +44,6 @@ #define COLOR_5_6_5 0x8 #define COLOR_8_8_8_8 0x1a -#define RECT_UNIT_H 32 -#define RECT_UNIT_W (RADEON_GPU_PAGE_SIZE / 4 / RECT_UNIT_H) -#define MAX_RECT_DIM 16384 - /* emits 17 */ static void set_render_target(struct radeon_device *rdev, int format, @@ -599,31 +595,6 @@ set_default_state(struct radeon_device *rdev) } -static uint32_t i2f(uint32_t input) -{ - u32 result, i, exponent, fraction; - - if ((input & 0x3fff) == 0) - result = 0; /* 0 is a special case */ - else { - exponent = 140; /* exponent biased by 127; */ - fraction = (input & 0x3fff) << 10; /* cheat and only - handle numbers below 2^^15 */ - for (i = 0; i < 14; i++) { - if (fraction & 0x800000) - break; - else { - fraction = fraction << 1; /* keep - shifting left until top bit = 1 */ - exponent = exponent - 1; - } - } - result = exponent << 23 | (fraction & 0x7fffff); /* mask - off top bit; assumed 1 */ - } - return result; -} - int evergreen_blit_init(struct radeon_device *rdev) { u32 obj_size; @@ -632,6 +603,24 @@ int evergreen_blit_init(struct radeon_device *rdev) u32 packet2s[16]; int num_packet2s = 0; + rdev->r600_blit.primitives.set_render_target = set_render_target; + rdev->r600_blit.primitives.cp_set_surface_sync = cp_set_surface_sync; + rdev->r600_blit.primitives.set_shaders = set_shaders; + rdev->r600_blit.primitives.set_vtx_resource = set_vtx_resource; + rdev->r600_blit.primitives.set_tex_resource = set_tex_resource; + rdev->r600_blit.primitives.set_scissors = set_scissors; + rdev->r600_blit.primitives.draw_auto = draw_auto; + rdev->r600_blit.primitives.set_default_state = set_default_state; + + rdev->r600_blit.ring_size_common = 55; /* shaders + def state */ + rdev->r600_blit.ring_size_common += 10; /* fence emit for VB IB */ + rdev->r600_blit.ring_size_common += 5; /* done copy */ + rdev->r600_blit.ring_size_common += 10; /* fence emit for done copy */ + + rdev->r600_blit.ring_size_per_loop = 74; + + rdev->r600_blit.max_dim = 16384; + /* pin copy shader into vram if already initialized */ if (rdev->r600_blit.shader_obj) goto done; @@ -727,216 +716,3 @@ done: radeon_ttm_set_active_vram_size(rdev, rdev->mc.real_vram_size); return 0; } - -void evergreen_blit_fini(struct radeon_device *rdev) -{ - int r; - - radeon_ttm_set_active_vram_size(rdev, rdev->mc.visible_vram_size); - if (rdev->r600_blit.shader_obj == NULL) - return; - /* If we can't reserve the bo, unref should be enough to destroy - * it when it becomes idle. - */ - r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false); - if (!r) { - radeon_bo_unpin(rdev->r600_blit.shader_obj); - radeon_bo_unreserve(rdev->r600_blit.shader_obj); - } - radeon_bo_unref(&rdev->r600_blit.shader_obj); -} - -static int evergreen_vb_ib_get(struct radeon_device *rdev) -{ - int r; - r = radeon_ib_get(rdev, &rdev->r600_blit.vb_ib); - if (r) { - DRM_ERROR("failed to get IB for vertex buffer\n"); - return r; - } - - rdev->r600_blit.vb_total = 64*1024; - rdev->r600_blit.vb_used = 0; - return 0; -} - -static void evergreen_vb_ib_put(struct radeon_device *rdev) -{ - radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence); - radeon_ib_free(rdev, &rdev->r600_blit.vb_ib); -} - - -/* maps the rectangle to the buffer so that satisfies the following properties: - * - dimensions are less or equal to the hardware limit (MAX_RECT_DIM) - * - rectangle consists of integer number of pages - * - height is an integer multiple of RECT_UNIT_H - * - width is an integer multiple of RECT_UNIT_W - * - (the above three conditions also guarantee tile-aligned size) - * - it is as square as possible (sides ratio never greater than 2:1) - * - uses maximum number of pages that fit the above constraints - * - * input: buffer size, pointers to width/height variables - * return: number of pages that were successfully mapped to the rectangle - * width/height of the rectangle - */ -static unsigned evergreen_blit_create_rect(unsigned num_pages, int *width, int *height) -{ - unsigned max_pages; - unsigned pages = num_pages; - int w, h; - - if (num_pages == 0) { - /* not supposed to be called with no pages, but just in case */ - h = 0; - w = 0; - pages = 0; - WARN_ON(1); - } else { - int rect_order = 2; - h = RECT_UNIT_H; - while (num_pages / rect_order) { - h *= 2; - rect_order *= 4; - if (h >= MAX_RECT_DIM) { - h = MAX_RECT_DIM; - break; - } - } - max_pages = (MAX_RECT_DIM * h) / (RECT_UNIT_W * RECT_UNIT_H); - if (pages > max_pages) - pages = max_pages; - w = (pages * RECT_UNIT_W * RECT_UNIT_H) / h; - w = (w / RECT_UNIT_W) * RECT_UNIT_W; - pages = (w * h) / (RECT_UNIT_W * RECT_UNIT_H); - BUG_ON(pages == 0); - } - - - DRM_DEBUG("blit_rectangle: h=%d, w=%d, pages=%d\n", h, w, pages); - - /* return width and height only of the caller wants it */ - if (height) - *height = h; - if (width) - *width = w; - - return pages; -} - -int evergreen_blit_prepare_copy(struct radeon_device *rdev, unsigned num_pages) -{ - int r; - int ring_size; - /* loops of emits + fence emit possible */ - int dwords_per_loop = 74, num_loops = 0; - - r = evergreen_vb_ib_get(rdev); - if (r) - return r; - - /* num loops */ - while (num_pages) { - num_pages -= evergreen_blit_create_rect(num_pages, NULL, NULL); - num_loops++; - } - /* calculate number of loops correctly */ - ring_size = num_loops * dwords_per_loop; - /* set default + shaders */ - ring_size += 55; /* shaders + def state */ - ring_size += 10; /* fence emit for VB IB */ - ring_size += 5; /* done copy */ - ring_size += 10; /* fence emit for done copy */ - r = radeon_ring_lock(rdev, ring_size); - if (r) - return r; - - set_default_state(rdev); /* 36 */ - set_shaders(rdev); /* 16 */ - return 0; -} - -void evergreen_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence) -{ - int r; - - if (rdev->r600_blit.vb_ib) - evergreen_vb_ib_put(rdev); - - if (fence) - r = radeon_fence_emit(rdev, fence); - - radeon_ring_unlock_commit(rdev); -} - -void evergreen_kms_blit_copy(struct radeon_device *rdev, - u64 src_gpu_addr, u64 dst_gpu_addr, - unsigned num_pages) -{ - u64 vb_gpu_addr; - u32 *vb; - - DRM_DEBUG("emitting copy %16llx %16llx %d %d\n", src_gpu_addr, dst_gpu_addr, - num_pages, rdev->r600_blit.vb_used); - vb = (u32 *)(rdev->r600_blit.vb_ib->ptr + rdev->r600_blit.vb_used); - - while (num_pages) { - int w, h; - unsigned size_in_bytes; - unsigned pages_per_loop = evergreen_blit_create_rect(num_pages, &w, &h); - - size_in_bytes = pages_per_loop * RADEON_GPU_PAGE_SIZE; - DRM_DEBUG("rectangle w=%d h=%d\n", w, h); - - if ((rdev->r600_blit.vb_used + 48) > rdev->r600_blit.vb_total) { - WARN_ON(1); - } - - vb[0] = 0; - vb[1] = 0; - vb[2] = 0; - vb[3] = 0; - - vb[4] = 0; - vb[5] = i2f(h); - vb[6] = 0; - vb[7] = i2f(h); - - vb[8] = i2f(w); - vb[9] = i2f(h); - vb[10] = i2f(w); - vb[11] = i2f(h); - - /* src 10 */ - set_tex_resource(rdev, FMT_8_8_8_8, w, h, w, src_gpu_addr); - - /* 5 */ - cp_set_surface_sync(rdev, - PACKET3_TC_ACTION_ENA, size_in_bytes, src_gpu_addr); - - /* dst 17 */ - set_render_target(rdev, COLOR_8_8_8_8, w, h, dst_gpu_addr); - - /* scissors 12 */ - set_scissors(rdev, 0, 0, w, h); - - /* Vertex buffer setup 15 */ - vb_gpu_addr = rdev->r600_blit.vb_ib->gpu_addr + rdev->r600_blit.vb_used; - set_vtx_resource(rdev, vb_gpu_addr); - - /* draw 10 */ - draw_auto(rdev); - - /* 5 */ - cp_set_surface_sync(rdev, - PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA, - size_in_bytes, dst_gpu_addr); - - /* 74 ring dwords per loop */ - vb += 12; - rdev->r600_blit.vb_used += 4*12; - src_gpu_addr += size_in_bytes; - dst_gpu_addr += size_in_bytes; - num_pages -= pages_per_loop; - } -} diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index b6c8a4880a8..b5da6dab568 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1401,7 +1401,7 @@ static int cayman_startup(struct radeon_device *rdev) r = evergreen_blit_init(rdev); if (r) { - evergreen_blit_fini(rdev); + r600_blit_fini(rdev); rdev->asic->copy = NULL; dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r); } @@ -1589,7 +1589,7 @@ int cayman_init(struct radeon_device *rdev) void cayman_fini(struct radeon_device *rdev) { - evergreen_blit_fini(rdev); + r600_blit_fini(rdev); cayman_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index df8218bb83a..e2944566ffe 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -765,9 +765,9 @@ static struct radeon_asic evergreen_asic = { .get_vblank_counter = &evergreen_get_vblank_counter, .fence_ring_emit = &r600_fence_ring_emit, .cs_parse = &evergreen_cs_parse, - .copy_blit = &evergreen_copy_blit, + .copy_blit = &r600_copy_blit, .copy_dma = NULL, - .copy = &evergreen_copy_blit, + .copy = &r600_copy_blit, .get_engine_clock = &radeon_atom_get_engine_clock, .set_engine_clock = &radeon_atom_set_engine_clock, .get_memory_clock = &radeon_atom_get_memory_clock, @@ -812,9 +812,9 @@ static struct radeon_asic sumo_asic = { .get_vblank_counter = &evergreen_get_vblank_counter, .fence_ring_emit = &r600_fence_ring_emit, .cs_parse = &evergreen_cs_parse, - .copy_blit = &evergreen_copy_blit, + .copy_blit = &r600_copy_blit, .copy_dma = NULL, - .copy = &evergreen_copy_blit, + .copy = &r600_copy_blit, .get_engine_clock = &radeon_atom_get_engine_clock, .set_engine_clock = &radeon_atom_set_engine_clock, .get_memory_clock = NULL, @@ -859,9 +859,9 @@ static struct radeon_asic btc_asic = { .get_vblank_counter = &evergreen_get_vblank_counter, .fence_ring_emit = &r600_fence_ring_emit, .cs_parse = &evergreen_cs_parse, - .copy_blit = &evergreen_copy_blit, + .copy_blit = &r600_copy_blit, .copy_dma = NULL, - .copy = &evergreen_copy_blit, + .copy = &r600_copy_blit, .get_engine_clock = &radeon_atom_get_engine_clock, .set_engine_clock = &radeon_atom_set_engine_clock, .get_memory_clock = &radeon_atom_get_memory_clock, @@ -906,9 +906,9 @@ static struct radeon_asic cayman_asic = { .get_vblank_counter = &evergreen_get_vblank_counter, .fence_ring_emit = &r600_fence_ring_emit, .cs_parse = &evergreen_cs_parse, - .copy_blit = &evergreen_copy_blit, + .copy_blit = &r600_copy_blit, .copy_dma = NULL, - .copy = &evergreen_copy_blit, + .copy = &r600_copy_blit, .get_engine_clock = &radeon_atom_get_engine_clock, .set_engine_clock = &radeon_atom_set_engine_clock, .get_memory_clock = &radeon_atom_get_memory_clock, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index cd60da562ec..e040de3e8cc 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -401,9 +401,6 @@ bool evergreen_gpu_is_lockup(struct radeon_device *rdev); int evergreen_asic_reset(struct radeon_device *rdev); void evergreen_bandwidth_update(struct radeon_device *rdev); void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib); -int evergreen_copy_blit(struct radeon_device *rdev, - uint64_t src_offset, uint64_t dst_offset, - unsigned num_pages, struct radeon_fence *fence); void evergreen_hpd_init(struct radeon_device *rdev); void evergreen_hpd_fini(struct radeon_device *rdev); bool evergreen_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd); @@ -421,13 +418,6 @@ extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_ba extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc); void evergreen_disable_interrupt_state(struct radeon_device *rdev); int evergreen_blit_init(struct radeon_device *rdev); -void evergreen_blit_fini(struct radeon_device *rdev); -/* evergreen blit */ -int evergreen_blit_prepare_copy(struct radeon_device *rdev, unsigned num_pages); -void evergreen_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence); -void evergreen_kms_blit_copy(struct radeon_device *rdev, - u64 src_gpu_addr, u64 dst_gpu_addr, - unsigned num_pages); /* * cayman -- 2.11.4.GIT