1/*
2 * Copyright 2013 Advanced Micro Devices, Inc.
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 * SOFTWARE.
22 *
23 * Authors: Marek Olšák <maraeo@gmail.com>
24 *
25 */
26
27#include "r600_pipe_common.h"
28#include "r600_cs.h"
29#include "evergreen_compute.h"
30#include "tgsi/tgsi_parse.h"
31#include "util/list.h"
32#include "util/u_draw_quad.h"
33#include "util/u_memory.h"
34#include "util/format/u_format_s3tc.h"
35#include "util/u_upload_mgr.h"
36#include "util/os_time.h"
37#include "vl/vl_decoder.h"
38#include "vl/vl_video_buffer.h"
39#include "radeon_video.h"
40#include <inttypes.h>
41#include <sys/utsname.h>
42#include <stdlib.h>
43
44#ifdef LLVM_AVAILABLE
45#include <llvm-c/TargetMachine.h>
46#endif
47
48struct r600_multi_fence {
49	struct pipe_reference reference;
50	struct pipe_fence_handle *gfx;
51	struct pipe_fence_handle *sdma;
52
53	/* If the context wasn't flushed at fence creation, this is non-NULL. */
54	struct {
55		struct r600_common_context *ctx;
56		unsigned ib_index;
57	} gfx_unflushed;
58};
59
60/*
61 * pipe_context
62 */
63
64/**
65 * Write an EOP event.
66 *
67 * \param event		EVENT_TYPE_*
68 * \param event_flags	Optional cache flush flags (TC)
69 * \param data_sel	1 = fence, 3 = timestamp
70 * \param buf		Buffer
71 * \param va		GPU address
72 * \param old_value	Previous fence value (for a bug workaround)
73 * \param new_value	Fence value to write for this event.
74 */
75void r600_gfx_write_event_eop(struct r600_common_context *ctx,
76			      unsigned event, unsigned event_flags,
77			      unsigned data_sel,
78			      struct r600_resource *buf, uint64_t va,
79			      uint32_t new_fence, unsigned query_type)
80{
81	struct radeon_cmdbuf *cs = &ctx->gfx.cs;
82	unsigned op = EVENT_TYPE(event) |
83		      EVENT_INDEX(5) |
84		      event_flags;
85	unsigned sel = EOP_DATA_SEL(data_sel);
86
87	radeon_emit(cs, PKT3(PKT3_EVENT_WRITE_EOP, 4, 0));
88	radeon_emit(cs, op);
89	radeon_emit(cs, va);
90	radeon_emit(cs, ((va >> 32) & 0xffff) | sel);
91	radeon_emit(cs, new_fence); /* immediate data */
92	radeon_emit(cs, 0); /* unused */
93
94	if (buf)
95		r600_emit_reloc(ctx, &ctx->gfx, buf, RADEON_USAGE_WRITE |
96				RADEON_PRIO_QUERY);
97}
98
99unsigned r600_gfx_write_fence_dwords(struct r600_common_screen *screen)
100{
101	unsigned dwords = 6;
102
103	if (!screen->info.r600_has_virtual_memory)
104		dwords += 2;
105
106	return dwords;
107}
108
109void r600_gfx_wait_fence(struct r600_common_context *ctx,
110			 struct r600_resource *buf,
111			 uint64_t va, uint32_t ref, uint32_t mask)
112{
113	struct radeon_cmdbuf *cs = &ctx->gfx.cs;
114
115	radeon_emit(cs, PKT3(PKT3_WAIT_REG_MEM, 5, 0));
116	radeon_emit(cs, WAIT_REG_MEM_EQUAL | WAIT_REG_MEM_MEM_SPACE(1));
117	radeon_emit(cs, va);
118	radeon_emit(cs, va >> 32);
119	radeon_emit(cs, ref); /* reference value */
120	radeon_emit(cs, mask); /* mask */
121	radeon_emit(cs, 4); /* poll interval */
122
123	if (buf)
124		r600_emit_reloc(ctx, &ctx->gfx, buf, RADEON_USAGE_READ |
125				RADEON_PRIO_QUERY);
126}
127
128void r600_draw_rectangle(struct blitter_context *blitter,
129			 void *vertex_elements_cso,
130			 blitter_get_vs_func get_vs,
131			 int x1, int y1, int x2, int y2,
132			 float depth, unsigned num_instances,
133			 enum blitter_attrib_type type,
134			 const union blitter_attrib *attrib)
135{
136	struct r600_common_context *rctx =
137		(struct r600_common_context*)util_blitter_get_pipe(blitter);
138	struct pipe_viewport_state viewport;
139	struct pipe_resource *buf = NULL;
140	unsigned offset = 0;
141	float *vb;
142
143	rctx->b.bind_vertex_elements_state(&rctx->b, vertex_elements_cso);
144	rctx->b.bind_vs_state(&rctx->b, get_vs(blitter));
145
146	/* Some operations (like color resolve on r6xx) don't work
147	 * with the conventional primitive types.
148	 * One that works is PT_RECTLIST, which we use here. */
149
150	/* setup viewport */
151	viewport.scale[0] = 1.0f;
152	viewport.scale[1] = 1.0f;
153	viewport.scale[2] = 1.0f;
154	viewport.translate[0] = 0.0f;
155	viewport.translate[1] = 0.0f;
156	viewport.translate[2] = 0.0f;
157	rctx->b.set_viewport_states(&rctx->b, 0, 1, &viewport);
158
159	/* Upload vertices. The hw rectangle has only 3 vertices,
160	 * The 4th one is derived from the first 3.
161	 * The vertex specification should match u_blitter's vertex element state. */
162	u_upload_alloc(rctx->b.stream_uploader, 0, sizeof(float) * 24,
163		       rctx->screen->info.tcc_cache_line_size,
164                       &offset, &buf, (void**)&vb);
165	if (!buf)
166		return;
167
168	vb[0] = x1;
169	vb[1] = y1;
170	vb[2] = depth;
171	vb[3] = 1;
172
173	vb[8] = x1;
174	vb[9] = y2;
175	vb[10] = depth;
176	vb[11] = 1;
177
178	vb[16] = x2;
179	vb[17] = y1;
180	vb[18] = depth;
181	vb[19] = 1;
182
183	switch (type) {
184	case UTIL_BLITTER_ATTRIB_COLOR:
185		memcpy(vb+4, attrib->color, sizeof(float)*4);
186		memcpy(vb+12, attrib->color, sizeof(float)*4);
187		memcpy(vb+20, attrib->color, sizeof(float)*4);
188		break;
189	case UTIL_BLITTER_ATTRIB_TEXCOORD_XYZW:
190	case UTIL_BLITTER_ATTRIB_TEXCOORD_XY:
191		vb[6] = vb[14] = vb[22] = attrib->texcoord.z;
192		vb[7] = vb[15] = vb[23] = attrib->texcoord.w;
193		/* fall through */
194		vb[4] = attrib->texcoord.x1;
195		vb[5] = attrib->texcoord.y1;
196		vb[12] = attrib->texcoord.x1;
197		vb[13] = attrib->texcoord.y2;
198		vb[20] = attrib->texcoord.x2;
199		vb[21] = attrib->texcoord.y1;
200		break;
201	default:; /* Nothing to do. */
202	}
203
204	/* draw */
205	struct pipe_vertex_buffer vbuffer = {};
206	vbuffer.buffer.resource = buf;
207	vbuffer.stride = 2 * 4 * sizeof(float); /* vertex size */
208	vbuffer.buffer_offset = offset;
209
210	rctx->b.set_vertex_buffers(&rctx->b, blitter->vb_slot, 1, 0, false, &vbuffer);
211	util_draw_arrays_instanced(&rctx->b, R600_PRIM_RECTANGLE_LIST, 0, 3,
212				   0, num_instances);
213	pipe_resource_reference(&buf, NULL);
214}
215
216static void r600_dma_emit_wait_idle(struct r600_common_context *rctx)
217{
218	struct radeon_cmdbuf *cs = &rctx->dma.cs;
219
220	if (rctx->gfx_level >= EVERGREEN)
221		radeon_emit(cs, 0xf0000000); /* NOP */
222	else {
223		/* TODO: R600-R700 should use the FENCE packet.
224		 * CS checker support is required. */
225	}
226}
227
228void r600_need_dma_space(struct r600_common_context *ctx, unsigned num_dw,
229                         struct r600_resource *dst, struct r600_resource *src)
230{
231	uint64_t vram = (uint64_t)ctx->dma.cs.used_vram_kb * 1024;
232	uint64_t gtt = (uint64_t)ctx->dma.cs.used_gart_kb * 1024;
233
234	if (dst) {
235		vram += dst->vram_usage;
236		gtt += dst->gart_usage;
237	}
238	if (src) {
239		vram += src->vram_usage;
240		gtt += src->gart_usage;
241	}
242
243	/* Flush the GFX IB if DMA depends on it. */
244	if (radeon_emitted(&ctx->gfx.cs, ctx->initial_gfx_cs_size) &&
245	    ((dst &&
246	      ctx->ws->cs_is_buffer_referenced(&ctx->gfx.cs, dst->buf,
247					       RADEON_USAGE_READWRITE)) ||
248	     (src &&
249	      ctx->ws->cs_is_buffer_referenced(&ctx->gfx.cs, src->buf,
250					       RADEON_USAGE_WRITE))))
251		ctx->gfx.flush(ctx, PIPE_FLUSH_ASYNC, NULL);
252
253	/* Flush if there's not enough space, or if the memory usage per IB
254	 * is too large.
255	 *
256	 * IBs using too little memory are limited by the IB submission overhead.
257	 * IBs using too much memory are limited by the kernel/TTM overhead.
258	 * Too long IBs create CPU-GPU pipeline bubbles and add latency.
259	 *
260	 * This heuristic makes sure that DMA requests are executed
261	 * very soon after the call is made and lowers memory usage.
262	 * It improves texture upload performance by keeping the DMA
263	 * engine busy while uploads are being submitted.
264	 */
265	num_dw++; /* for emit_wait_idle below */
266	if (!ctx->ws->cs_check_space(&ctx->dma.cs, num_dw) ||
267	    ctx->dma.cs.used_vram_kb + ctx->dma.cs.used_gart_kb > 64 * 1024 ||
268	    !radeon_cs_memory_below_limit(ctx->screen, &ctx->dma.cs, vram, gtt)) {
269		ctx->dma.flush(ctx, PIPE_FLUSH_ASYNC, NULL);
270		assert((num_dw + ctx->dma.cs.current.cdw) <= ctx->dma.cs.current.max_dw);
271	}
272
273	/* Wait for idle if either buffer has been used in the IB before to
274	 * prevent read-after-write hazards.
275	 */
276	if ((dst &&
277	     ctx->ws->cs_is_buffer_referenced(&ctx->dma.cs, dst->buf,
278					      RADEON_USAGE_READWRITE)) ||
279	    (src &&
280	     ctx->ws->cs_is_buffer_referenced(&ctx->dma.cs, src->buf,
281					      RADEON_USAGE_WRITE)))
282		r600_dma_emit_wait_idle(ctx);
283
284	/* If GPUVM is not supported, the CS checker needs 2 entries
285	 * in the buffer list per packet, which has to be done manually.
286	 */
287	if (ctx->screen->info.r600_has_virtual_memory) {
288		if (dst)
289			radeon_add_to_buffer_list(ctx, &ctx->dma, dst,
290						  RADEON_USAGE_WRITE);
291		if (src)
292			radeon_add_to_buffer_list(ctx, &ctx->dma, src,
293						  RADEON_USAGE_READ);
294	}
295
296	/* this function is called before all DMA calls, so increment this. */
297	ctx->num_dma_calls++;
298}
299
300void r600_preflush_suspend_features(struct r600_common_context *ctx)
301{
302	/* suspend queries */
303	if (!list_is_empty(&ctx->active_queries))
304		r600_suspend_queries(ctx);
305
306	ctx->streamout.suspended = false;
307	if (ctx->streamout.begin_emitted) {
308		r600_emit_streamout_end(ctx);
309		ctx->streamout.suspended = true;
310	}
311}
312
313void r600_postflush_resume_features(struct r600_common_context *ctx)
314{
315	if (ctx->streamout.suspended) {
316		ctx->streamout.append_bitmask = ctx->streamout.enabled_mask;
317		r600_streamout_buffers_dirty(ctx);
318	}
319
320	/* resume queries */
321	if (!list_is_empty(&ctx->active_queries))
322		r600_resume_queries(ctx);
323}
324
325static void r600_fence_server_sync(struct pipe_context *ctx,
326				   struct pipe_fence_handle *fence)
327{
328	/* radeon synchronizes all rings by default and will not implement
329	 * fence imports.
330	 */
331}
332
333static void r600_flush_from_st(struct pipe_context *ctx,
334			       struct pipe_fence_handle **fence,
335			       unsigned flags)
336{
337	struct pipe_screen *screen = ctx->screen;
338	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
339	struct radeon_winsys *ws = rctx->ws;
340	struct pipe_fence_handle *gfx_fence = NULL;
341	struct pipe_fence_handle *sdma_fence = NULL;
342	bool deferred_fence = false;
343	unsigned rflags = PIPE_FLUSH_ASYNC;
344
345	if (flags & PIPE_FLUSH_END_OF_FRAME)
346		rflags |= PIPE_FLUSH_END_OF_FRAME;
347
348	/* DMA IBs are preambles to gfx IBs, therefore must be flushed first. */
349	if (rctx->dma.cs.priv)
350		rctx->dma.flush(rctx, rflags, fence ? &sdma_fence : NULL);
351
352	if (!radeon_emitted(&rctx->gfx.cs, rctx->initial_gfx_cs_size)) {
353		if (fence)
354			ws->fence_reference(&gfx_fence, rctx->last_gfx_fence);
355		if (!(flags & PIPE_FLUSH_DEFERRED))
356			ws->cs_sync_flush(&rctx->gfx.cs);
357	} else {
358		/* Instead of flushing, create a deferred fence. Constraints:
359		 * - the gallium frontend must allow a deferred flush.
360		 * - the gallium frontend must request a fence.
361		 * Thread safety in fence_finish must be ensured by the gallium frontend.
362		 */
363		if (flags & PIPE_FLUSH_DEFERRED && fence) {
364			gfx_fence = rctx->ws->cs_get_next_fence(&rctx->gfx.cs);
365			deferred_fence = true;
366		} else {
367			rctx->gfx.flush(rctx, rflags, fence ? &gfx_fence : NULL);
368		}
369	}
370
371	/* Both engines can signal out of order, so we need to keep both fences. */
372	if (fence) {
373		struct r600_multi_fence *multi_fence =
374			CALLOC_STRUCT(r600_multi_fence);
375		if (!multi_fence) {
376			ws->fence_reference(&sdma_fence, NULL);
377			ws->fence_reference(&gfx_fence, NULL);
378			goto finish;
379		}
380
381		multi_fence->reference.count = 1;
382		/* If both fences are NULL, fence_finish will always return true. */
383		multi_fence->gfx = gfx_fence;
384		multi_fence->sdma = sdma_fence;
385
386		if (deferred_fence) {
387			multi_fence->gfx_unflushed.ctx = rctx;
388			multi_fence->gfx_unflushed.ib_index = rctx->num_gfx_cs_flushes;
389		}
390
391		screen->fence_reference(screen, fence, NULL);
392		*fence = (struct pipe_fence_handle*)multi_fence;
393	}
394finish:
395	if (!(flags & PIPE_FLUSH_DEFERRED)) {
396		if (rctx->dma.cs.priv)
397			ws->cs_sync_flush(&rctx->dma.cs);
398		ws->cs_sync_flush(&rctx->gfx.cs);
399	}
400}
401
402static void r600_flush_dma_ring(void *ctx, unsigned flags,
403				struct pipe_fence_handle **fence)
404{
405	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
406	struct radeon_cmdbuf *cs = &rctx->dma.cs;
407	struct radeon_saved_cs saved;
408	bool check_vm =
409		(rctx->screen->debug_flags & DBG_CHECK_VM) &&
410		rctx->check_vm_faults;
411
412	if (!radeon_emitted(cs, 0)) {
413		if (fence)
414			rctx->ws->fence_reference(fence, rctx->last_sdma_fence);
415		return;
416	}
417
418	if (check_vm)
419		radeon_save_cs(rctx->ws, cs, &saved, true);
420
421	rctx->ws->cs_flush(cs, flags, &rctx->last_sdma_fence);
422	if (fence)
423		rctx->ws->fence_reference(fence, rctx->last_sdma_fence);
424
425	if (check_vm) {
426		/* Use conservative timeout 800ms, after which we won't wait any
427		 * longer and assume the GPU is hung.
428		 */
429		rctx->ws->fence_wait(rctx->ws, rctx->last_sdma_fence, 800*1000*1000);
430
431		rctx->check_vm_faults(rctx, &saved, AMD_IP_SDMA);
432		radeon_clear_saved_cs(&saved);
433	}
434}
435
436/**
437 * Store a linearized copy of all chunks of \p cs together with the buffer
438 * list in \p saved.
439 */
440void radeon_save_cs(struct radeon_winsys *ws, struct radeon_cmdbuf *cs,
441		    struct radeon_saved_cs *saved, bool get_buffer_list)
442{
443	uint32_t *buf;
444	unsigned i;
445
446	/* Save the IB chunks. */
447	saved->num_dw = cs->prev_dw + cs->current.cdw;
448	saved->ib = MALLOC(4 * saved->num_dw);
449	if (!saved->ib)
450		goto oom;
451
452	buf = saved->ib;
453	for (i = 0; i < cs->num_prev; ++i) {
454		memcpy(buf, cs->prev[i].buf, cs->prev[i].cdw * 4);
455		buf += cs->prev[i].cdw;
456	}
457	memcpy(buf, cs->current.buf, cs->current.cdw * 4);
458
459	if (!get_buffer_list)
460		return;
461
462	/* Save the buffer list. */
463	saved->bo_count = ws->cs_get_buffer_list(cs, NULL);
464	saved->bo_list = CALLOC(saved->bo_count,
465				sizeof(saved->bo_list[0]));
466	if (!saved->bo_list) {
467		FREE(saved->ib);
468		goto oom;
469	}
470	ws->cs_get_buffer_list(cs, saved->bo_list);
471
472	return;
473
474oom:
475	fprintf(stderr, "%s: out of memory\n", __func__);
476	memset(saved, 0, sizeof(*saved));
477}
478
479void radeon_clear_saved_cs(struct radeon_saved_cs *saved)
480{
481	FREE(saved->ib);
482	FREE(saved->bo_list);
483
484	memset(saved, 0, sizeof(*saved));
485}
486
487static enum pipe_reset_status r600_get_reset_status(struct pipe_context *ctx)
488{
489	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
490
491	return rctx->ws->ctx_query_reset_status(rctx->ctx, false, NULL);
492}
493
494static void r600_set_debug_callback(struct pipe_context *ctx,
495				    const struct util_debug_callback *cb)
496{
497	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
498
499	if (cb)
500		rctx->debug = *cb;
501	else
502		memset(&rctx->debug, 0, sizeof(rctx->debug));
503}
504
505static void r600_set_device_reset_callback(struct pipe_context *ctx,
506					   const struct pipe_device_reset_callback *cb)
507{
508	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
509
510	if (cb)
511		rctx->device_reset_callback = *cb;
512	else
513		memset(&rctx->device_reset_callback, 0,
514		       sizeof(rctx->device_reset_callback));
515}
516
517bool r600_check_device_reset(struct r600_common_context *rctx)
518{
519	enum pipe_reset_status status;
520
521	if (!rctx->device_reset_callback.reset)
522		return false;
523
524	if (!rctx->b.get_device_reset_status)
525		return false;
526
527	status = rctx->b.get_device_reset_status(&rctx->b);
528	if (status == PIPE_NO_RESET)
529		return false;
530
531	rctx->device_reset_callback.reset(rctx->device_reset_callback.data, status);
532	return true;
533}
534
535static void r600_dma_clear_buffer_fallback(struct pipe_context *ctx,
536					   struct pipe_resource *dst,
537					   uint64_t offset, uint64_t size,
538					   unsigned value)
539{
540	struct r600_common_context *rctx = (struct r600_common_context *)ctx;
541
542	rctx->clear_buffer(ctx, dst, offset, size, value, R600_COHERENCY_NONE);
543}
544
545static bool r600_resource_commit(struct pipe_context *pctx,
546				 struct pipe_resource *resource,
547				 unsigned level, struct pipe_box *box,
548				 bool commit)
549{
550	struct r600_common_context *ctx = (struct r600_common_context *)pctx;
551	struct r600_resource *res = r600_resource(resource);
552
553	/*
554	 * Since buffer commitment changes cannot be pipelined, we need to
555	 * (a) flush any pending commands that refer to the buffer we're about
556	 *     to change, and
557	 * (b) wait for threaded submit to finish, including those that were
558	 *     triggered by some other, earlier operation.
559	 */
560	if (radeon_emitted(&ctx->gfx.cs, ctx->initial_gfx_cs_size) &&
561	    ctx->ws->cs_is_buffer_referenced(&ctx->gfx.cs,
562					     res->buf, RADEON_USAGE_READWRITE)) {
563		ctx->gfx.flush(ctx, PIPE_FLUSH_ASYNC, NULL);
564	}
565	if (radeon_emitted(&ctx->dma.cs, 0) &&
566	    ctx->ws->cs_is_buffer_referenced(&ctx->dma.cs,
567					     res->buf, RADEON_USAGE_READWRITE)) {
568		ctx->dma.flush(ctx, PIPE_FLUSH_ASYNC, NULL);
569	}
570
571	ctx->ws->cs_sync_flush(&ctx->dma.cs);
572	ctx->ws->cs_sync_flush(&ctx->gfx.cs);
573
574	assert(resource->target == PIPE_BUFFER);
575
576	return ctx->ws->buffer_commit(ctx->ws, res->buf, box->x, box->width, commit);
577}
578
579bool r600_common_context_init(struct r600_common_context *rctx,
580			      struct r600_common_screen *rscreen,
581			      unsigned context_flags)
582{
583	slab_create_child(&rctx->pool_transfers, &rscreen->pool_transfers);
584	slab_create_child(&rctx->pool_transfers_unsync, &rscreen->pool_transfers);
585
586	rctx->screen = rscreen;
587	rctx->ws = rscreen->ws;
588	rctx->family = rscreen->family;
589	rctx->gfx_level = rscreen->gfx_level;
590
591	rctx->b.invalidate_resource = r600_invalidate_resource;
592	rctx->b.resource_commit = r600_resource_commit;
593	rctx->b.buffer_map = r600_buffer_transfer_map;
594        rctx->b.texture_map = r600_texture_transfer_map;
595	rctx->b.transfer_flush_region = r600_buffer_flush_region;
596	rctx->b.buffer_unmap = r600_buffer_transfer_unmap;
597        rctx->b.texture_unmap = r600_texture_transfer_unmap;
598	rctx->b.texture_subdata = u_default_texture_subdata;
599	rctx->b.flush = r600_flush_from_st;
600	rctx->b.set_debug_callback = r600_set_debug_callback;
601	rctx->b.fence_server_sync = r600_fence_server_sync;
602	rctx->dma_clear_buffer = r600_dma_clear_buffer_fallback;
603
604	/* evergreen_compute.c has a special codepath for global buffers.
605	 * Everything else can use the direct path.
606	 */
607	if ((rscreen->gfx_level == EVERGREEN || rscreen->gfx_level == CAYMAN) &&
608	    (context_flags & PIPE_CONTEXT_COMPUTE_ONLY))
609		rctx->b.buffer_subdata = u_default_buffer_subdata;
610	else
611		rctx->b.buffer_subdata = r600_buffer_subdata;
612
613	rctx->b.get_device_reset_status = r600_get_reset_status;
614	rctx->b.set_device_reset_callback = r600_set_device_reset_callback;
615
616	r600_init_context_texture_functions(rctx);
617	r600_init_viewport_functions(rctx);
618	r600_streamout_init(rctx);
619	r600_query_init(rctx);
620	cayman_init_msaa(&rctx->b);
621
622	u_suballocator_init(&rctx->allocator_zeroed_memory, &rctx->b, rscreen->info.gart_page_size,
623			    0, PIPE_USAGE_DEFAULT, 0, true);
624
625	rctx->b.stream_uploader = u_upload_create(&rctx->b, 1024 * 1024,
626						  0, PIPE_USAGE_STREAM, 0);
627	if (!rctx->b.stream_uploader)
628		return false;
629
630	rctx->b.const_uploader = u_upload_create(&rctx->b, 128 * 1024,
631						 0, PIPE_USAGE_DEFAULT, 0);
632	if (!rctx->b.const_uploader)
633		return false;
634
635	rctx->ctx = rctx->ws->ctx_create(rctx->ws, RADEON_CTX_PRIORITY_MEDIUM);
636	if (!rctx->ctx)
637		return false;
638
639	if (rscreen->info.ip[AMD_IP_SDMA].num_queues && !(rscreen->debug_flags & DBG_NO_ASYNC_DMA)) {
640		rctx->ws->cs_create(&rctx->dma.cs, rctx->ctx, AMD_IP_SDMA,
641                                    r600_flush_dma_ring, rctx, false);
642		rctx->dma.flush = r600_flush_dma_ring;
643	}
644
645	return true;
646}
647
648void r600_common_context_cleanup(struct r600_common_context *rctx)
649{
650	if (rctx->query_result_shader)
651		rctx->b.delete_compute_state(&rctx->b, rctx->query_result_shader);
652
653	rctx->ws->cs_destroy(&rctx->gfx.cs);
654	rctx->ws->cs_destroy(&rctx->dma.cs);
655	if (rctx->ctx)
656		rctx->ws->ctx_destroy(rctx->ctx);
657
658	if (rctx->b.stream_uploader)
659		u_upload_destroy(rctx->b.stream_uploader);
660	if (rctx->b.const_uploader)
661		u_upload_destroy(rctx->b.const_uploader);
662
663	slab_destroy_child(&rctx->pool_transfers);
664	slab_destroy_child(&rctx->pool_transfers_unsync);
665
666	u_suballocator_destroy(&rctx->allocator_zeroed_memory);
667	rctx->ws->fence_reference(&rctx->last_gfx_fence, NULL);
668	rctx->ws->fence_reference(&rctx->last_sdma_fence, NULL);
669	r600_resource_reference(&rctx->eop_bug_scratch, NULL);
670}
671
672/*
673 * pipe_screen
674 */
675
676static const struct debug_named_value common_debug_options[] = {
677	/* logging */
678	{ "tex", DBG_TEX, "Print texture info" },
679	{ "nir", DBG_NIR, "Enable experimental NIR shaders" },
680	{ "compute", DBG_COMPUTE, "Print compute info" },
681	{ "vm", DBG_VM, "Print virtual addresses when creating resources" },
682	{ "info", DBG_INFO, "Print driver information" },
683
684	/* shaders */
685	{ "fs", DBG_FS, "Print fetch shaders" },
686	{ "vs", DBG_VS, "Print vertex shaders" },
687	{ "gs", DBG_GS, "Print geometry shaders" },
688	{ "ps", DBG_PS, "Print pixel shaders" },
689	{ "cs", DBG_CS, "Print compute shaders" },
690	{ "tcs", DBG_TCS, "Print tessellation control shaders" },
691	{ "tes", DBG_TES, "Print tessellation evaluation shaders" },
692	{ "preoptir", DBG_PREOPT_IR, "Print the LLVM IR before initial optimizations" },
693	{ "checkir", DBG_CHECK_IR, "Enable additional sanity checks on shader IR" },
694	{ "use_tgsi", DBG_USE_TGSI, "Take TGSI directly instead of using NIR-to-TGSI"},
695
696	{ "testdma", DBG_TEST_DMA, "Invoke SDMA tests and exit." },
697	{ "testvmfaultcp", DBG_TEST_VMFAULT_CP, "Invoke a CP VM fault test and exit." },
698	{ "testvmfaultsdma", DBG_TEST_VMFAULT_SDMA, "Invoke a SDMA VM fault test and exit." },
699	{ "testvmfaultshader", DBG_TEST_VMFAULT_SHADER, "Invoke a shader VM fault test and exit." },
700
701	/* features */
702	{ "nodma", DBG_NO_ASYNC_DMA, "Disable asynchronous DMA" },
703	{ "nohyperz", DBG_NO_HYPERZ, "Disable Hyper-Z" },
704	/* GL uses the word INVALIDATE, gallium uses the word DISCARD */
705	{ "noinvalrange", DBG_NO_DISCARD_RANGE, "Disable handling of INVALIDATE_RANGE map flags" },
706	{ "no2d", DBG_NO_2D_TILING, "Disable 2D tiling" },
707	{ "notiling", DBG_NO_TILING, "Disable tiling" },
708	{ "switch_on_eop", DBG_SWITCH_ON_EOP, "Program WD/IA to switch on end-of-packet." },
709	{ "forcedma", DBG_FORCE_DMA, "Use asynchronous DMA for all operations when possible." },
710	{ "nowc", DBG_NO_WC, "Disable GTT write combining" },
711	{ "check_vm", DBG_CHECK_VM, "Check VM faults and dump debug info." },
712
713	DEBUG_NAMED_VALUE_END /* must be last */
714};
715
716static const char* r600_get_vendor(struct pipe_screen* pscreen)
717{
718	return "X.Org";
719}
720
721static const char* r600_get_device_vendor(struct pipe_screen* pscreen)
722{
723	return "AMD";
724}
725
726static const char *r600_get_family_name(const struct r600_common_screen *rscreen)
727{
728	switch (rscreen->info.family) {
729	case CHIP_R600: return "AMD R600";
730	case CHIP_RV610: return "AMD RV610";
731	case CHIP_RV630: return "AMD RV630";
732	case CHIP_RV670: return "AMD RV670";
733	case CHIP_RV620: return "AMD RV620";
734	case CHIP_RV635: return "AMD RV635";
735	case CHIP_RS780: return "AMD RS780";
736	case CHIP_RS880: return "AMD RS880";
737	case CHIP_RV770: return "AMD RV770";
738	case CHIP_RV730: return "AMD RV730";
739	case CHIP_RV710: return "AMD RV710";
740	case CHIP_RV740: return "AMD RV740";
741	case CHIP_CEDAR: return "AMD CEDAR";
742	case CHIP_REDWOOD: return "AMD REDWOOD";
743	case CHIP_JUNIPER: return "AMD JUNIPER";
744	case CHIP_CYPRESS: return "AMD CYPRESS";
745	case CHIP_HEMLOCK: return "AMD HEMLOCK";
746	case CHIP_PALM: return "AMD PALM";
747	case CHIP_SUMO: return "AMD SUMO";
748	case CHIP_SUMO2: return "AMD SUMO2";
749	case CHIP_BARTS: return "AMD BARTS";
750	case CHIP_TURKS: return "AMD TURKS";
751	case CHIP_CAICOS: return "AMD CAICOS";
752	case CHIP_CAYMAN: return "AMD CAYMAN";
753	case CHIP_ARUBA: return "AMD ARUBA";
754	default: return "AMD unknown";
755	}
756}
757
758static void r600_disk_cache_create(struct r600_common_screen *rscreen)
759{
760	/* Don't use the cache if shader dumping is enabled. */
761	if (rscreen->debug_flags & DBG_ALL_SHADERS)
762		return;
763
764	struct mesa_sha1 ctx;
765	unsigned char sha1[20];
766	char cache_id[20 * 2 + 1];
767
768	_mesa_sha1_init(&ctx);
769	if (!disk_cache_get_function_identifier(r600_disk_cache_create,
770						&ctx))
771		return;
772
773	_mesa_sha1_final(&ctx, sha1);
774	disk_cache_format_hex_id(cache_id, sha1, 20 * 2);
775
776	/* These flags affect shader compilation. */
777	uint64_t shader_debug_flags =
778		rscreen->debug_flags &
779		(DBG_NIR |
780		 DBG_NIR_PREFERRED |
781		 DBG_USE_TGSI);
782
783	rscreen->disk_shader_cache =
784		disk_cache_create(r600_get_family_name(rscreen),
785				  cache_id,
786				  shader_debug_flags);
787}
788
789static struct disk_cache *r600_get_disk_shader_cache(struct pipe_screen *pscreen)
790{
791	struct r600_common_screen *rscreen = (struct r600_common_screen*)pscreen;
792	return rscreen->disk_shader_cache;
793}
794
795static const char* r600_get_name(struct pipe_screen* pscreen)
796{
797	struct r600_common_screen *rscreen = (struct r600_common_screen*)pscreen;
798
799	return rscreen->renderer_string;
800}
801
802static float r600_get_paramf(struct pipe_screen* pscreen,
803			     enum pipe_capf param)
804{
805	switch (param) {
806	case PIPE_CAPF_MIN_LINE_WIDTH:
807	case PIPE_CAPF_MIN_LINE_WIDTH_AA:
808	case PIPE_CAPF_MIN_POINT_SIZE:
809	case PIPE_CAPF_MIN_POINT_SIZE_AA:
810		return 1;
811
812	case PIPE_CAPF_POINT_SIZE_GRANULARITY:
813	case PIPE_CAPF_LINE_WIDTH_GRANULARITY:
814		return 0.1;
815
816	case PIPE_CAPF_MAX_LINE_WIDTH:
817	case PIPE_CAPF_MAX_LINE_WIDTH_AA:
818	case PIPE_CAPF_MAX_POINT_SIZE:
819	case PIPE_CAPF_MAX_POINT_SIZE_AA:
820         return 8191.0f;
821	case PIPE_CAPF_MAX_TEXTURE_ANISOTROPY:
822		return 16.0f;
823	case PIPE_CAPF_MAX_TEXTURE_LOD_BIAS:
824		return 16.0f;
825    case PIPE_CAPF_MIN_CONSERVATIVE_RASTER_DILATE:
826    case PIPE_CAPF_MAX_CONSERVATIVE_RASTER_DILATE:
827    case PIPE_CAPF_CONSERVATIVE_RASTER_DILATE_GRANULARITY:
828        return 0.0f;
829	}
830	return 0.0f;
831}
832
833static int r600_get_video_param(struct pipe_screen *screen,
834				enum pipe_video_profile profile,
835				enum pipe_video_entrypoint entrypoint,
836				enum pipe_video_cap param)
837{
838	switch (param) {
839	case PIPE_VIDEO_CAP_SUPPORTED:
840		return vl_profile_supported(screen, profile, entrypoint);
841	case PIPE_VIDEO_CAP_NPOT_TEXTURES:
842		return 1;
843	case PIPE_VIDEO_CAP_MAX_WIDTH:
844	case PIPE_VIDEO_CAP_MAX_HEIGHT:
845		return vl_video_buffer_max_size(screen);
846	case PIPE_VIDEO_CAP_PREFERED_FORMAT:
847		return PIPE_FORMAT_NV12;
848	case PIPE_VIDEO_CAP_PREFERS_INTERLACED:
849		return false;
850	case PIPE_VIDEO_CAP_SUPPORTS_INTERLACED:
851		return false;
852	case PIPE_VIDEO_CAP_SUPPORTS_PROGRESSIVE:
853		return true;
854	case PIPE_VIDEO_CAP_MAX_LEVEL:
855		return vl_level_supported(screen, profile);
856	default:
857		return 0;
858	}
859}
860
861const char *r600_get_llvm_processor_name(enum radeon_family family)
862{
863	switch (family) {
864	case CHIP_R600:
865	case CHIP_RV630:
866	case CHIP_RV635:
867	case CHIP_RV670:
868		return "r600";
869	case CHIP_RV610:
870	case CHIP_RV620:
871	case CHIP_RS780:
872	case CHIP_RS880:
873		return "rs880";
874	case CHIP_RV710:
875		return "rv710";
876	case CHIP_RV730:
877		return "rv730";
878	case CHIP_RV740:
879	case CHIP_RV770:
880		return "rv770";
881	case CHIP_PALM:
882	case CHIP_CEDAR:
883		return "cedar";
884	case CHIP_SUMO:
885	case CHIP_SUMO2:
886		return "sumo";
887	case CHIP_REDWOOD:
888		return "redwood";
889	case CHIP_JUNIPER:
890		return "juniper";
891	case CHIP_HEMLOCK:
892	case CHIP_CYPRESS:
893		return "cypress";
894	case CHIP_BARTS:
895		return "barts";
896	case CHIP_TURKS:
897		return "turks";
898	case CHIP_CAICOS:
899		return "caicos";
900	case CHIP_CAYMAN:
901        case CHIP_ARUBA:
902		return "cayman";
903
904	default:
905		return "";
906	}
907}
908
909static unsigned get_max_threads_per_block(struct r600_common_screen *screen,
910					  enum pipe_shader_ir ir_type)
911{
912	if (ir_type != PIPE_SHADER_IR_TGSI &&
913	    ir_type != PIPE_SHADER_IR_NIR)
914		return 256;
915	if (screen->gfx_level >= EVERGREEN)
916		return 1024;
917	return 256;
918}
919
920static int r600_get_compute_param(struct pipe_screen *screen,
921        enum pipe_shader_ir ir_type,
922        enum pipe_compute_cap param,
923        void *ret)
924{
925	struct r600_common_screen *rscreen = (struct r600_common_screen *)screen;
926
927	//TODO: select these params by asic
928	switch (param) {
929	case PIPE_COMPUTE_CAP_IR_TARGET: {
930		const char *gpu;
931		const char *triple = "r600--";
932		gpu = r600_get_llvm_processor_name(rscreen->family);
933		if (ret) {
934			sprintf(ret, "%s-%s", gpu, triple);
935		}
936		/* +2 for dash and terminating NIL byte */
937		return (strlen(triple) + strlen(gpu) + 2) * sizeof(char);
938	}
939	case PIPE_COMPUTE_CAP_GRID_DIMENSION:
940		if (ret) {
941			uint64_t *grid_dimension = ret;
942			grid_dimension[0] = 3;
943		}
944		return 1 * sizeof(uint64_t);
945
946	case PIPE_COMPUTE_CAP_MAX_GRID_SIZE:
947		if (ret) {
948			uint64_t *grid_size = ret;
949			grid_size[0] = 65535;
950			grid_size[1] = 65535;
951			grid_size[2] = 65535;
952		}
953		return 3 * sizeof(uint64_t) ;
954
955	case PIPE_COMPUTE_CAP_MAX_BLOCK_SIZE:
956		if (ret) {
957			uint64_t *block_size = ret;
958			unsigned threads_per_block = get_max_threads_per_block(rscreen, ir_type);
959			block_size[0] = threads_per_block;
960			block_size[1] = threads_per_block;
961			block_size[2] = threads_per_block;
962		}
963		return 3 * sizeof(uint64_t);
964
965	case PIPE_COMPUTE_CAP_MAX_THREADS_PER_BLOCK:
966		if (ret) {
967			uint64_t *max_threads_per_block = ret;
968			*max_threads_per_block = get_max_threads_per_block(rscreen, ir_type);
969		}
970		return sizeof(uint64_t);
971	case PIPE_COMPUTE_CAP_ADDRESS_BITS:
972		if (ret) {
973			uint32_t *address_bits = ret;
974			address_bits[0] = 32;
975		}
976		return 1 * sizeof(uint32_t);
977
978	case PIPE_COMPUTE_CAP_MAX_GLOBAL_SIZE:
979		if (ret) {
980			uint64_t *max_global_size = ret;
981			uint64_t max_mem_alloc_size;
982
983			r600_get_compute_param(screen, ir_type,
984				PIPE_COMPUTE_CAP_MAX_MEM_ALLOC_SIZE,
985				&max_mem_alloc_size);
986
987			/* In OpenCL, the MAX_MEM_ALLOC_SIZE must be at least
988			 * 1/4 of the MAX_GLOBAL_SIZE.  Since the
989			 * MAX_MEM_ALLOC_SIZE is fixed for older kernels,
990			 * make sure we never report more than
991			 * 4 * MAX_MEM_ALLOC_SIZE.
992			 */
993			*max_global_size = MIN2(4 * max_mem_alloc_size,
994						rscreen->info.max_heap_size_kb * 1024ull);
995		}
996		return sizeof(uint64_t);
997
998	case PIPE_COMPUTE_CAP_MAX_LOCAL_SIZE:
999		if (ret) {
1000			uint64_t *max_local_size = ret;
1001			/* Value reported by the closed source driver. */
1002			*max_local_size = 32768;
1003		}
1004		return sizeof(uint64_t);
1005
1006	case PIPE_COMPUTE_CAP_MAX_INPUT_SIZE:
1007		if (ret) {
1008			uint64_t *max_input_size = ret;
1009			/* Value reported by the closed source driver. */
1010			*max_input_size = 1024;
1011		}
1012		return sizeof(uint64_t);
1013
1014	case PIPE_COMPUTE_CAP_MAX_MEM_ALLOC_SIZE:
1015		if (ret) {
1016			uint64_t *max_mem_alloc_size = ret;
1017
1018			*max_mem_alloc_size = (rscreen->info.max_heap_size_kb / 4) * 1024ull;
1019		}
1020		return sizeof(uint64_t);
1021
1022	case PIPE_COMPUTE_CAP_MAX_CLOCK_FREQUENCY:
1023		if (ret) {
1024			uint32_t *max_clock_frequency = ret;
1025			*max_clock_frequency = rscreen->info.max_gpu_freq_mhz;
1026		}
1027		return sizeof(uint32_t);
1028
1029	case PIPE_COMPUTE_CAP_MAX_COMPUTE_UNITS:
1030		if (ret) {
1031			uint32_t *max_compute_units = ret;
1032			*max_compute_units = rscreen->info.num_cu;
1033		}
1034		return sizeof(uint32_t);
1035
1036	case PIPE_COMPUTE_CAP_IMAGES_SUPPORTED:
1037		if (ret) {
1038			uint32_t *images_supported = ret;
1039			*images_supported = 0;
1040		}
1041		return sizeof(uint32_t);
1042	case PIPE_COMPUTE_CAP_MAX_PRIVATE_SIZE:
1043		break; /* unused */
1044	case PIPE_COMPUTE_CAP_SUBGROUP_SIZE:
1045		if (ret) {
1046			uint32_t *subgroup_size = ret;
1047			*subgroup_size = r600_wavefront_size(rscreen->family);
1048		}
1049		return sizeof(uint32_t);
1050	case PIPE_COMPUTE_CAP_MAX_VARIABLE_THREADS_PER_BLOCK:
1051		if (ret) {
1052			uint64_t *max_variable_threads_per_block = ret;
1053			*max_variable_threads_per_block = 0;
1054		}
1055		return sizeof(uint64_t);
1056	}
1057
1058        fprintf(stderr, "unknown PIPE_COMPUTE_CAP %d\n", param);
1059        return 0;
1060}
1061
1062static uint64_t r600_get_timestamp(struct pipe_screen *screen)
1063{
1064	struct r600_common_screen *rscreen = (struct r600_common_screen*)screen;
1065
1066	return 1000000 * rscreen->ws->query_value(rscreen->ws, RADEON_TIMESTAMP) /
1067			rscreen->info.clock_crystal_freq;
1068}
1069
1070static void r600_fence_reference(struct pipe_screen *screen,
1071				 struct pipe_fence_handle **dst,
1072				 struct pipe_fence_handle *src)
1073{
1074	struct radeon_winsys *ws = ((struct r600_common_screen*)screen)->ws;
1075	struct r600_multi_fence **rdst = (struct r600_multi_fence **)dst;
1076	struct r600_multi_fence *rsrc = (struct r600_multi_fence *)src;
1077
1078	if (pipe_reference(&(*rdst)->reference, &rsrc->reference)) {
1079		ws->fence_reference(&(*rdst)->gfx, NULL);
1080		ws->fence_reference(&(*rdst)->sdma, NULL);
1081		FREE(*rdst);
1082	}
1083        *rdst = rsrc;
1084}
1085
1086static bool r600_fence_finish(struct pipe_screen *screen,
1087			      struct pipe_context *ctx,
1088			      struct pipe_fence_handle *fence,
1089			      uint64_t timeout)
1090{
1091	struct radeon_winsys *rws = ((struct r600_common_screen*)screen)->ws;
1092	struct r600_multi_fence *rfence = (struct r600_multi_fence *)fence;
1093	struct r600_common_context *rctx;
1094	int64_t abs_timeout = os_time_get_absolute_timeout(timeout);
1095
1096	ctx = threaded_context_unwrap_sync(ctx);
1097	rctx = ctx ? (struct r600_common_context*)ctx : NULL;
1098
1099	if (rfence->sdma) {
1100		if (!rws->fence_wait(rws, rfence->sdma, timeout))
1101			return false;
1102
1103		/* Recompute the timeout after waiting. */
1104		if (timeout && timeout != PIPE_TIMEOUT_INFINITE) {
1105			int64_t time = os_time_get_nano();
1106			timeout = abs_timeout > time ? abs_timeout - time : 0;
1107		}
1108	}
1109
1110	if (!rfence->gfx)
1111		return true;
1112
1113	/* Flush the gfx IB if it hasn't been flushed yet. */
1114	if (rctx &&
1115	    rfence->gfx_unflushed.ctx == rctx &&
1116	    rfence->gfx_unflushed.ib_index == rctx->num_gfx_cs_flushes) {
1117		rctx->gfx.flush(rctx, timeout ? 0 : PIPE_FLUSH_ASYNC, NULL);
1118		rfence->gfx_unflushed.ctx = NULL;
1119
1120		if (!timeout)
1121			return false;
1122
1123		/* Recompute the timeout after all that. */
1124		if (timeout && timeout != PIPE_TIMEOUT_INFINITE) {
1125			int64_t time = os_time_get_nano();
1126			timeout = abs_timeout > time ? abs_timeout - time : 0;
1127		}
1128	}
1129
1130	return rws->fence_wait(rws, rfence->gfx, timeout);
1131}
1132
1133static void r600_query_memory_info(struct pipe_screen *screen,
1134				   struct pipe_memory_info *info)
1135{
1136	struct r600_common_screen *rscreen = (struct r600_common_screen*)screen;
1137	struct radeon_winsys *ws = rscreen->ws;
1138	unsigned vram_usage, gtt_usage;
1139
1140	info->total_device_memory = rscreen->info.vram_size_kb;
1141	info->total_staging_memory = rscreen->info.gart_size_kb;
1142
1143	/* The real TTM memory usage is somewhat random, because:
1144	 *
1145	 * 1) TTM delays freeing memory, because it can only free it after
1146	 *    fences expire.
1147	 *
1148	 * 2) The memory usage can be really low if big VRAM evictions are
1149	 *    taking place, but the real usage is well above the size of VRAM.
1150	 *
1151	 * Instead, return statistics of this process.
1152	 */
1153	vram_usage = ws->query_value(ws, RADEON_REQUESTED_VRAM_MEMORY) / 1024;
1154	gtt_usage =  ws->query_value(ws, RADEON_REQUESTED_GTT_MEMORY) / 1024;
1155
1156	info->avail_device_memory =
1157		vram_usage <= info->total_device_memory ?
1158				info->total_device_memory - vram_usage : 0;
1159	info->avail_staging_memory =
1160		gtt_usage <= info->total_staging_memory ?
1161				info->total_staging_memory - gtt_usage : 0;
1162
1163	info->device_memory_evicted =
1164		ws->query_value(ws, RADEON_NUM_BYTES_MOVED) / 1024;
1165
1166	/* Just return the number of evicted 64KB pages. */
1167	info->nr_device_memory_evictions = info->device_memory_evicted / 64;
1168}
1169
1170struct pipe_resource *r600_resource_create_common(struct pipe_screen *screen,
1171						  const struct pipe_resource *templ)
1172{
1173	if (templ->target == PIPE_BUFFER) {
1174		return r600_buffer_create(screen, templ, 256);
1175	} else {
1176		return r600_texture_create(screen, templ);
1177	}
1178}
1179
1180static const void *
1181r600_get_compiler_options(struct pipe_screen *screen,
1182			  enum pipe_shader_ir ir,
1183			  enum pipe_shader_type shader)
1184{
1185       assert(ir == PIPE_SHADER_IR_NIR);
1186
1187       struct r600_common_screen *rscreen = (struct r600_common_screen *)screen;
1188
1189       if (shader != PIPE_SHADER_FRAGMENT)
1190          return &rscreen->nir_options;
1191       else
1192          return &rscreen->nir_options_fs;
1193}
1194
1195extern bool r600_lower_to_scalar_instr_filter(const nir_instr *instr, const void *);
1196
1197static void r600_resource_destroy(struct pipe_screen *screen,
1198				  struct pipe_resource *res)
1199{
1200	if (res->target == PIPE_BUFFER) {
1201		if (r600_resource(res)->compute_global_bo)
1202			r600_compute_global_buffer_destroy(screen, res);
1203		else
1204			r600_buffer_destroy(screen, res);
1205	} else {
1206		r600_texture_destroy(screen, res);
1207	}
1208}
1209
1210bool r600_common_screen_init(struct r600_common_screen *rscreen,
1211			     struct radeon_winsys *ws)
1212{
1213	char family_name[32] = {}, kernel_version[128] = {};
1214	struct utsname uname_data;
1215	const char *chip_name;
1216
1217	ws->query_info(ws, &rscreen->info, false, false);
1218	rscreen->ws = ws;
1219
1220	chip_name = r600_get_family_name(rscreen);
1221
1222	if (uname(&uname_data) == 0)
1223		snprintf(kernel_version, sizeof(kernel_version),
1224			 " / %s", uname_data.release);
1225
1226	snprintf(rscreen->renderer_string, sizeof(rscreen->renderer_string),
1227		 "%s (%sDRM %i.%i.%i%s"
1228#ifdef LLVM_AVAILABLE
1229		 ", LLVM " MESA_LLVM_VERSION_STRING
1230#endif
1231		 ")",
1232		 chip_name, family_name, rscreen->info.drm_major,
1233		 rscreen->info.drm_minor, rscreen->info.drm_patchlevel,
1234		 kernel_version);
1235
1236	rscreen->b.get_name = r600_get_name;
1237	rscreen->b.get_vendor = r600_get_vendor;
1238	rscreen->b.get_device_vendor = r600_get_device_vendor;
1239	rscreen->b.get_disk_shader_cache = r600_get_disk_shader_cache;
1240	rscreen->b.get_compute_param = r600_get_compute_param;
1241	rscreen->b.get_paramf = r600_get_paramf;
1242	rscreen->b.get_timestamp = r600_get_timestamp;
1243	rscreen->b.get_compiler_options = r600_get_compiler_options;
1244	rscreen->b.fence_finish = r600_fence_finish;
1245	rscreen->b.fence_reference = r600_fence_reference;
1246	rscreen->b.resource_destroy = r600_resource_destroy;
1247	rscreen->b.resource_from_user_memory = r600_buffer_from_user_memory;
1248	rscreen->b.query_memory_info = r600_query_memory_info;
1249
1250	if (rscreen->info.ip[AMD_IP_UVD].num_queues) {
1251		rscreen->b.get_video_param = rvid_get_video_param;
1252		rscreen->b.is_video_format_supported = rvid_is_format_supported;
1253	} else {
1254		rscreen->b.get_video_param = r600_get_video_param;
1255		rscreen->b.is_video_format_supported = vl_video_buffer_is_format_supported;
1256	}
1257
1258	r600_init_screen_texture_functions(rscreen);
1259	r600_init_screen_query_functions(rscreen);
1260
1261	rscreen->family = rscreen->info.family;
1262	rscreen->gfx_level = rscreen->info.gfx_level;
1263	rscreen->debug_flags |= debug_get_flags_option("R600_DEBUG", common_debug_options, 0);
1264
1265	r600_disk_cache_create(rscreen);
1266
1267	slab_create_parent(&rscreen->pool_transfers, sizeof(struct r600_transfer), 64);
1268
1269	rscreen->force_aniso = MIN2(16, debug_get_num_option("R600_TEX_ANISO", -1));
1270	if (rscreen->force_aniso >= 0) {
1271		printf("radeon: Forcing anisotropy filter to %ix\n",
1272		       /* round down to a power of two */
1273		       1 << util_logbase2(rscreen->force_aniso));
1274	}
1275
1276	(void) mtx_init(&rscreen->aux_context_lock, mtx_plain);
1277	(void) mtx_init(&rscreen->gpu_load_mutex, mtx_plain);
1278
1279	if (rscreen->debug_flags & DBG_INFO) {
1280		printf("pci (domain:bus:dev.func): %04x:%02x:%02x.%x\n",
1281		       rscreen->info.pci_domain, rscreen->info.pci_bus,
1282		       rscreen->info.pci_dev, rscreen->info.pci_func);
1283		printf("pci_id = 0x%x\n", rscreen->info.pci_id);
1284		printf("family = %i (%s)\n", rscreen->info.family,
1285		       r600_get_family_name(rscreen));
1286		printf("gfx_level = %i\n", rscreen->info.gfx_level);
1287		printf("pte_fragment_size = %u\n", rscreen->info.pte_fragment_size);
1288		printf("gart_page_size = %u\n", rscreen->info.gart_page_size);
1289		printf("gart_size = %i MB\n", (int)DIV_ROUND_UP(rscreen->info.gart_size_kb, 1024));
1290		printf("vram_size = %i MB\n", (int)DIV_ROUND_UP(rscreen->info.vram_size_kb, 1024));
1291		printf("vram_vis_size = %i MB\n", (int)DIV_ROUND_UP(rscreen->info.vram_vis_size_kb, 1024));
1292		printf("max_heap_size = %i MB\n",
1293		       (int)DIV_ROUND_UP(rscreen->info.max_heap_size_kb, 1024));
1294		printf("min_alloc_size = %u\n", rscreen->info.min_alloc_size);
1295		printf("has_dedicated_vram = %u\n", rscreen->info.has_dedicated_vram);
1296		printf("r600_has_virtual_memory = %i\n", rscreen->info.r600_has_virtual_memory);
1297		printf("gfx_ib_pad_with_type2 = %i\n", rscreen->info.gfx_ib_pad_with_type2);
1298		printf("ip[AMD_IP_UVD] = %u\n", rscreen->info.ip[AMD_IP_UVD].num_queues);
1299		printf("ip[AMD_IP_SDMA] = %i\n", rscreen->info.ip[AMD_IP_SDMA].num_queues);
1300		printf("ip[AMD_IP_COMPUTE] = %u\n", rscreen->info.ip[AMD_IP_COMPUTE].num_queues);
1301		printf("uvd_fw_version = %u\n", rscreen->info.uvd_fw_version);
1302		printf("vce_fw_version = %u\n", rscreen->info.vce_fw_version);
1303		printf("me_fw_version = %i\n", rscreen->info.me_fw_version);
1304		printf("pfp_fw_version = %i\n", rscreen->info.pfp_fw_version);
1305		printf("vce_harvest_config = %i\n", rscreen->info.vce_harvest_config);
1306		printf("clock_crystal_freq = %i\n", rscreen->info.clock_crystal_freq);
1307		printf("tcc_cache_line_size = %u\n", rscreen->info.tcc_cache_line_size);
1308		printf("drm = %i.%i.%i\n", rscreen->info.drm_major,
1309		       rscreen->info.drm_minor, rscreen->info.drm_patchlevel);
1310		printf("has_userptr = %i\n", rscreen->info.has_userptr);
1311		printf("has_syncobj = %u\n", rscreen->info.has_syncobj);
1312
1313		printf("r600_max_quad_pipes = %i\n", rscreen->info.r600_max_quad_pipes);
1314		printf("max_gpu_freq_mhz = %i\n", rscreen->info.max_gpu_freq_mhz);
1315		printf("num_cu = %i\n", rscreen->info.num_cu);
1316		printf("max_se = %i\n", rscreen->info.max_se);
1317		printf("max_sh_per_se = %i\n", rscreen->info.max_sa_per_se);
1318
1319		printf("r600_gb_backend_map = %i\n", rscreen->info.r600_gb_backend_map);
1320		printf("r600_gb_backend_map_valid = %i\n", rscreen->info.r600_gb_backend_map_valid);
1321		printf("r600_num_banks = %i\n", rscreen->info.r600_num_banks);
1322		printf("num_render_backends = %i\n", rscreen->info.max_render_backends);
1323		printf("num_tile_pipes = %i\n", rscreen->info.num_tile_pipes);
1324		printf("pipe_interleave_bytes = %i\n", rscreen->info.pipe_interleave_bytes);
1325		printf("enabled_rb_mask = 0x%x\n", rscreen->info.enabled_rb_mask);
1326		printf("max_alignment = %u\n", (unsigned)rscreen->info.max_alignment);
1327	}
1328
1329	const struct nir_shader_compiler_options nir_options = {
1330		.fuse_ffma16 = true,
1331		.fuse_ffma32 = true,
1332		.fuse_ffma64 = true,
1333		.lower_flrp32 = true,
1334		.lower_flrp64 = true,
1335		.lower_fdiv = true,
1336		.lower_isign = true,
1337		.lower_fsign = true,
1338		.lower_fmod = true,
1339		.lower_extract_byte = true,
1340		.lower_extract_word = true,
1341		.lower_insert_byte = true,
1342		.lower_insert_word = true,
1343		.lower_rotate = true,
1344		/* due to a bug in the shader compiler, some loops hang
1345		 * if they are not unrolled, see:
1346		 *    https://bugs.freedesktop.org/show_bug.cgi?id=86720
1347		 */
1348		.max_unroll_iterations = 255,
1349		.lower_interpolate_at = true,
1350		.vectorize_io = true,
1351		.has_umad24 = true,
1352		.has_umul24 = true,
1353		.has_fmulz = true,
1354		.use_interpolated_input_intrinsics = true,
1355		.has_fsub = true,
1356		.has_isub = true,
1357		.lower_iabs = true,
1358		.lower_uadd_sat = true,
1359		.lower_usub_sat = true,
1360		.lower_bitfield_extract = true,
1361		.lower_bitfield_insert_to_bitfield_select = true,
1362		.has_fused_comp_and_csel = true,
1363		.lower_find_msb_to_reverse = true,
1364		.lower_to_scalar = true,
1365		.lower_to_scalar_filter = r600_lower_to_scalar_instr_filter,
1366		.linker_ignore_precision = true,
1367		.lower_fpow = true,
1368		.lower_int64_options = ~0
1369	};
1370
1371	rscreen->nir_options = nir_options;
1372
1373	if (rscreen->info.family < CHIP_CEDAR)
1374		rscreen->nir_options.force_indirect_unrolling_sampler = true;
1375
1376	if (rscreen->info.gfx_level < EVERGREEN) {
1377		/* Pre-EG doesn't have these ALU ops */
1378		rscreen->nir_options.lower_bit_count = true;
1379		rscreen->nir_options.lower_bitfield_reverse = true;
1380	}
1381
1382	if (rscreen->info.gfx_level < CAYMAN) {
1383		rscreen->nir_options.lower_doubles_options = nir_lower_fp64_full_software;
1384	} else {
1385		rscreen->nir_options.lower_doubles_options =
1386			nir_lower_ddiv |
1387			nir_lower_dfloor |
1388			nir_lower_dceil |
1389			nir_lower_dmod |
1390			nir_lower_dsub |
1391			nir_lower_dtrunc;
1392	}
1393
1394	if (!(rscreen->debug_flags & DBG_NIR_PREFERRED)) {
1395
1396		rscreen->nir_options.lower_fpow = false;
1397		/* TGSI is vector, and NIR-to-TGSI doesn't like it when the
1398		 * input vars have been scalarized.
1399		 */
1400		rscreen->nir_options.lower_to_scalar = false;
1401
1402		/* NIR-to-TGSI can't do fused integer csel, and it can't just
1403		 * override the flag and get the code lowered back when we ask
1404		 * it to handle it.
1405		 */
1406		rscreen->nir_options.has_fused_comp_and_csel = false;
1407
1408		/* r600 has a bitfield_select and bitfield_extract opcode
1409		 * (called bfi/bfe), but TGSI's BFI/BFE isn't that.
1410		 */
1411		rscreen->nir_options.lower_bitfield_extract = false;
1412		rscreen->nir_options.lower_bitfield_insert_to_bitfield_select = false;
1413
1414		/* TGSI's ifind is reversed from ours, keep it the TGSI way. */
1415		rscreen->nir_options.lower_find_msb_to_reverse = false;
1416	} else {
1417      rscreen->nir_options.has_fmulz = true;
1418   }
1419
1420	rscreen->nir_options_fs = rscreen->nir_options;
1421	rscreen->nir_options_fs.lower_all_io_to_temps = true;
1422
1423	return true;
1424}
1425
1426void r600_destroy_common_screen(struct r600_common_screen *rscreen)
1427{
1428	r600_perfcounters_destroy(rscreen);
1429	r600_gpu_load_kill_thread(rscreen);
1430
1431	mtx_destroy(&rscreen->gpu_load_mutex);
1432	mtx_destroy(&rscreen->aux_context_lock);
1433	rscreen->aux_context->destroy(rscreen->aux_context);
1434
1435	slab_destroy_parent(&rscreen->pool_transfers);
1436
1437	disk_cache_destroy(rscreen->disk_shader_cache);
1438	rscreen->ws->destroy(rscreen->ws);
1439	FREE(rscreen);
1440}
1441
1442bool r600_can_dump_shader(struct r600_common_screen *rscreen,
1443			  unsigned processor)
1444{
1445	return rscreen->debug_flags & (1 << processor);
1446}
1447
1448bool r600_extra_shader_checks(struct r600_common_screen *rscreen, unsigned processor)
1449{
1450	return (rscreen->debug_flags & DBG_CHECK_IR) ||
1451	       r600_can_dump_shader(rscreen, processor);
1452}
1453
1454void r600_screen_clear_buffer(struct r600_common_screen *rscreen, struct pipe_resource *dst,
1455			      uint64_t offset, uint64_t size, unsigned value)
1456{
1457	struct r600_common_context *rctx = (struct r600_common_context*)rscreen->aux_context;
1458
1459	mtx_lock(&rscreen->aux_context_lock);
1460	rctx->dma_clear_buffer(&rctx->b, dst, offset, size, value);
1461	rscreen->aux_context->flush(rscreen->aux_context, NULL, 0);
1462	mtx_unlock(&rscreen->aux_context_lock);
1463}
1464