1/*
2 * Copyright © 2017 Intel Corporation
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 shall be included
12 * in all copies or substantial portions of the Software.
13 *
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
15 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
17 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
18 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
19 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
20 * DEALINGS IN THE SOFTWARE.
21 */
22
23/**
24 * @file iris_pipe_control.c
25 *
26 * PIPE_CONTROL is the main flushing and synchronization primitive on Intel
27 * GPUs.  It can invalidate caches, stall until rendering reaches various
28 * stages of completion, write to memory, and other things.  In a way, it's
29 * a swiss army knife command - it has all kinds of capabilities, but some
30 * significant limitations as well.
31 *
32 * Unfortunately, it's notoriously complicated and difficult to use.  Many
33 * sub-commands can't be used together.  Some are meant to be used at the
34 * top of the pipeline (invalidating caches before drawing), while some are
35 * meant to be used at the end (stalling or flushing after drawing).
36 *
37 * Also, there's a list of restrictions a mile long, which vary by generation.
38 * Do this before doing that, or suffer the consequences (usually a GPU hang).
39 *
40 * This file contains helpers for emitting them safely.  You can simply call
41 * iris_emit_pipe_control_flush() with the desired operations (as logical
42 * PIPE_CONTROL_* bits), and it will take care of splitting it into multiple
43 * PIPE_CONTROL commands as necessary.  The per-generation workarounds are
44 * applied in iris_emit_raw_pipe_control() in iris_state.c.
45 */
46
47#include "iris_context.h"
48#include "util/hash_table.h"
49#include "util/set.h"
50
51/**
52 * Emit a PIPE_CONTROL with various flushing flags.
53 *
54 * The caller is responsible for deciding what flags are appropriate for the
55 * given generation.
56 */
57void
58iris_emit_pipe_control_flush(struct iris_batch *batch,
59                             const char *reason,
60                             uint32_t flags)
61{
62   if ((flags & PIPE_CONTROL_CACHE_FLUSH_BITS) &&
63       (flags & PIPE_CONTROL_CACHE_INVALIDATE_BITS)) {
64      /* A pipe control command with flush and invalidate bits set
65       * simultaneously is an inherently racy operation on Gfx6+ if the
66       * contents of the flushed caches were intended to become visible from
67       * any of the invalidated caches.  Split it in two PIPE_CONTROLs, the
68       * first one should stall the pipeline to make sure that the flushed R/W
69       * caches are coherent with memory once the specified R/O caches are
70       * invalidated.  On pre-Gfx6 hardware the (implicit) R/O cache
71       * invalidation seems to happen at the bottom of the pipeline together
72       * with any write cache flush, so this shouldn't be a concern.  In order
73       * to ensure a full stall, we do an end-of-pipe sync.
74       */
75      iris_emit_end_of_pipe_sync(batch, reason,
76                                 flags & PIPE_CONTROL_CACHE_FLUSH_BITS);
77      flags &= ~(PIPE_CONTROL_CACHE_FLUSH_BITS | PIPE_CONTROL_CS_STALL);
78   }
79
80   batch->screen->vtbl.emit_raw_pipe_control(batch, reason, flags, NULL, 0, 0);
81}
82
83/**
84 * Emit a PIPE_CONTROL that writes to a buffer object.
85 *
86 * \p flags should contain one of the following items:
87 *  - PIPE_CONTROL_WRITE_IMMEDIATE
88 *  - PIPE_CONTROL_WRITE_TIMESTAMP
89 *  - PIPE_CONTROL_WRITE_DEPTH_COUNT
90 */
91void
92iris_emit_pipe_control_write(struct iris_batch *batch,
93                             const char *reason, uint32_t flags,
94                             struct iris_bo *bo, uint32_t offset,
95                             uint64_t imm)
96{
97   batch->screen->vtbl.emit_raw_pipe_control(batch, reason, flags, bo, offset, imm);
98}
99
100/*
101 * From Sandybridge PRM, volume 2, "1.7.2 End-of-Pipe Synchronization":
102 *
103 *  Write synchronization is a special case of end-of-pipe
104 *  synchronization that requires that the render cache and/or depth
105 *  related caches are flushed to memory, where the data will become
106 *  globally visible. This type of synchronization is required prior to
107 *  SW (CPU) actually reading the result data from memory, or initiating
108 *  an operation that will use as a read surface (such as a texture
109 *  surface) a previous render target and/or depth/stencil buffer
110 *
111 * From Haswell PRM, volume 2, part 1, "End-of-Pipe Synchronization":
112 *
113 *  Exercising the write cache flush bits (Render Target Cache Flush
114 *  Enable, Depth Cache Flush Enable, DC Flush) in PIPE_CONTROL only
115 *  ensures the write caches are flushed and doesn't guarantee the data
116 *  is globally visible.
117 *
118 *  SW can track the completion of the end-of-pipe-synchronization by
119 *  using "Notify Enable" and "PostSync Operation - Write Immediate
120 *  Data" in the PIPE_CONTROL command.
121 */
122void
123iris_emit_end_of_pipe_sync(struct iris_batch *batch,
124                           const char *reason, uint32_t flags)
125{
126   /* From Sandybridge PRM, volume 2, "1.7.3.1 Writing a Value to Memory":
127    *
128    *    "The most common action to perform upon reaching a synchronization
129    *    point is to write a value out to memory. An immediate value
130    *    (included with the synchronization command) may be written."
131    *
132    * From Broadwell PRM, volume 7, "End-of-Pipe Synchronization":
133    *
134    *    "In case the data flushed out by the render engine is to be read
135    *    back in to the render engine in coherent manner, then the render
136    *    engine has to wait for the fence completion before accessing the
137    *    flushed data. This can be achieved by following means on various
138    *    products: PIPE_CONTROL command with CS Stall and the required
139    *    write caches flushed with Post-Sync-Operation as Write Immediate
140    *    Data.
141    *
142    *    Example:
143    *       - Workload-1 (3D/GPGPU/MEDIA)
144    *       - PIPE_CONTROL (CS Stall, Post-Sync-Operation Write Immediate
145    *         Data, Required Write Cache Flush bits set)
146    *       - Workload-2 (Can use the data produce or output by Workload-1)
147    */
148   iris_emit_pipe_control_write(batch, reason,
149                                flags | PIPE_CONTROL_CS_STALL |
150                                PIPE_CONTROL_WRITE_IMMEDIATE,
151                                batch->screen->workaround_address.bo,
152                                batch->screen->workaround_address.offset, 0);
153}
154
155/**
156 * Emits appropriate flushes and invalidations for any previous memory
157 * operations on \p bo to be strictly ordered relative to any subsequent
158 * memory operations performed from the caching domain \p access.
159 *
160 * This is useful because the GPU has separate incoherent caches for the
161 * render target, sampler, etc., which need to be explicitly invalidated or
162 * flushed in order to obtain the expected memory ordering in cases where the
163 * same surface is accessed through multiple caches (e.g. due to
164 * render-to-texture).
165 *
166 * This provides the expected memory ordering guarantees whether or not the
167 * previous access was performed from the same batch or a different one, but
168 * only the former case needs to be handled explicitly here, since the kernel
169 * already inserts implicit flushes and synchronization in order to guarantee
170 * that any data dependencies between batches are satisfied.
171 *
172 * Even though no flushing nor invalidation is required in order to account
173 * for concurrent updates from other batches, we provide the guarantee that a
174 * required synchronization operation due to a previous batch-local update
175 * will never be omitted due to the influence of another thread accessing the
176 * same buffer concurrently from the same caching domain: Such a concurrent
177 * update will only ever change the seqno of the last update to a value
178 * greater than the local value (see iris_bo_bump_seqno()), which means that
179 * we will always emit at least as much flushing and invalidation as we would
180 * have for the local seqno (see the coherent_seqnos comparisons below).
181 */
182void
183iris_emit_buffer_barrier_for(struct iris_batch *batch,
184                             struct iris_bo *bo,
185                             enum iris_domain access)
186{
187   const struct intel_device_info *devinfo = &batch->screen->devinfo;
188   const struct brw_compiler *compiler = batch->screen->compiler;
189
190   const bool access_via_l3 = iris_domain_is_l3_coherent(devinfo, access);
191
192   const uint32_t all_flush_bits = (PIPE_CONTROL_CACHE_FLUSH_BITS |
193                                    PIPE_CONTROL_STALL_AT_SCOREBOARD |
194                                    PIPE_CONTROL_FLUSH_ENABLE);
195   const uint32_t flush_bits[NUM_IRIS_DOMAINS] = {
196      [IRIS_DOMAIN_RENDER_WRITE] = PIPE_CONTROL_RENDER_TARGET_FLUSH,
197      [IRIS_DOMAIN_DEPTH_WRITE] = PIPE_CONTROL_DEPTH_CACHE_FLUSH,
198      [IRIS_DOMAIN_DATA_WRITE] = PIPE_CONTROL_FLUSH_HDC,
199      /* OTHER_WRITE includes "VF Cache Invalidate" to make sure that any
200       * stream output writes are finished.  CS stall is added implicitly.
201       */
202      [IRIS_DOMAIN_OTHER_WRITE] = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_VF_CACHE_INVALIDATE,
203      [IRIS_DOMAIN_VF_READ] = PIPE_CONTROL_STALL_AT_SCOREBOARD,
204      [IRIS_DOMAIN_SAMPLER_READ] = PIPE_CONTROL_STALL_AT_SCOREBOARD,
205      [IRIS_DOMAIN_PULL_CONSTANT_READ] = PIPE_CONTROL_STALL_AT_SCOREBOARD,
206      [IRIS_DOMAIN_OTHER_READ] = PIPE_CONTROL_STALL_AT_SCOREBOARD,
207   };
208   const uint32_t invalidate_bits[NUM_IRIS_DOMAINS] = {
209      [IRIS_DOMAIN_RENDER_WRITE] = PIPE_CONTROL_RENDER_TARGET_FLUSH,
210      [IRIS_DOMAIN_DEPTH_WRITE] = PIPE_CONTROL_DEPTH_CACHE_FLUSH,
211      [IRIS_DOMAIN_DATA_WRITE] = PIPE_CONTROL_FLUSH_HDC,
212      [IRIS_DOMAIN_OTHER_WRITE] = PIPE_CONTROL_FLUSH_ENABLE,
213      [IRIS_DOMAIN_VF_READ] = PIPE_CONTROL_VF_CACHE_INVALIDATE,
214      [IRIS_DOMAIN_SAMPLER_READ] = PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE,
215      [IRIS_DOMAIN_PULL_CONSTANT_READ] = PIPE_CONTROL_CONST_CACHE_INVALIDATE |
216         (compiler->indirect_ubos_use_sampler ?
217          PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE :
218          PIPE_CONTROL_DATA_CACHE_FLUSH),
219   };
220   const uint32_t l3_flush_bits[NUM_IRIS_DOMAINS] = {
221      [IRIS_DOMAIN_RENDER_WRITE] = PIPE_CONTROL_TILE_CACHE_FLUSH,
222      [IRIS_DOMAIN_DEPTH_WRITE] = PIPE_CONTROL_TILE_CACHE_FLUSH,
223      [IRIS_DOMAIN_DATA_WRITE] = PIPE_CONTROL_DATA_CACHE_FLUSH,
224   };
225   uint32_t bits = 0;
226
227   /* Iterate over all read/write domains first in order to handle RaW
228    * and WaW dependencies, which might involve flushing the domain of
229    * the previous access and invalidating the specified domain.
230    */
231   for (unsigned i = 0; i < IRIS_DOMAIN_OTHER_WRITE; i++) {
232      assert(!iris_domain_is_read_only(i));
233      assert(iris_domain_is_l3_coherent(devinfo, i));
234
235      if (i != access) {
236         const uint64_t seqno = READ_ONCE(bo->last_seqnos[i]);
237
238         /* Invalidate unless the most recent read/write access from
239          * this domain is already guaranteed to be visible to the
240          * specified domain.  Flush if the most recent access from
241          * this domain occurred after its most recent flush.
242          */
243         if (seqno > batch->coherent_seqnos[access][i]) {
244            bits |= invalidate_bits[access];
245
246            if (access_via_l3) {
247               /* Both domains share L3.  If the most recent read/write access
248                * in domain `i' isn't visible to L3, then flush it to L3.
249                */
250               if (seqno > batch->l3_coherent_seqnos[i])
251                  bits |= flush_bits[i];
252            } else {
253               /* Domain `i` is L3 coherent but the specified domain is not.
254                * Flush both this cache and L3 out to memory.
255                */
256               if (seqno > batch->coherent_seqnos[i][i])
257                  bits |= flush_bits[i] | l3_flush_bits[i];
258            }
259         }
260      }
261   }
262
263   /* All read-only domains can be considered mutually coherent since
264    * the order of read-only memory operations is immaterial.  If the
265    * specified domain is read/write we need to iterate over them too,
266    * in order to handle any WaR dependencies.
267    */
268   if (!iris_domain_is_read_only(access)) {
269      for (unsigned i = IRIS_DOMAIN_VF_READ; i < NUM_IRIS_DOMAINS; i++) {
270         assert(iris_domain_is_read_only(i));
271         const uint64_t seqno = READ_ONCE(bo->last_seqnos[i]);
272
273         const uint64_t last_visible_seqno =
274            iris_domain_is_l3_coherent(devinfo, i) ?
275            batch->l3_coherent_seqnos[i] : batch->coherent_seqnos[i][i];
276
277         /* Flush if the most recent access from this domain occurred
278          * after its most recent flush.
279          */
280         if (seqno > last_visible_seqno)
281            bits |= flush_bits[i];
282      }
283   }
284
285   /* The IRIS_DOMAIN_OTHER_WRITE kitchen-sink domain cannot be
286    * considered coherent with itself since it's really a collection
287    * of multiple incoherent read/write domains, so we special-case it
288    * here.
289    */
290   const unsigned i = IRIS_DOMAIN_OTHER_WRITE;
291   const uint64_t seqno = READ_ONCE(bo->last_seqnos[i]);
292
293   assert(!iris_domain_is_l3_coherent(devinfo, i));
294
295   /* Invalidate unless the most recent read/write access from this
296    * domain is already guaranteed to be visible to the specified
297    * domain.  Flush if the most recent access from this domain
298    * occurred after its most recent flush.
299    */
300   if (seqno > batch->coherent_seqnos[access][i]) {
301      bits |= invalidate_bits[access];
302
303      /* There is a non-L3-coherent write that isn't visible to the
304       * specified domain.  If the access is via L3, then it might see
305       * stale L3 data that was loaded before that write.  In this case,
306       * we try to invalidate all read-only sections of the L3 cache.
307       */
308      if (access_via_l3 && seqno > batch->l3_coherent_seqnos[i])
309         bits |= PIPE_CONTROL_L3_RO_INVALIDATE_BITS;
310
311      if (seqno > batch->coherent_seqnos[i][i])
312         bits |= flush_bits[i];
313   }
314
315   if (bits) {
316      /* Stall-at-scoreboard is not expected to work in combination with other
317       * flush bits.
318       */
319      if (bits & PIPE_CONTROL_CACHE_FLUSH_BITS)
320         bits &= ~PIPE_CONTROL_STALL_AT_SCOREBOARD;
321
322      /* Emit any required flushes and invalidations. */
323      if (bits & all_flush_bits)
324         iris_emit_end_of_pipe_sync(batch, "cache tracker: flush",
325                                    bits & all_flush_bits);
326
327      if (bits & ~all_flush_bits)
328         iris_emit_pipe_control_flush(batch, "cache tracker: invalidate",
329                                      bits & ~all_flush_bits);
330   }
331}
332
333/**
334 * Flush and invalidate all caches (for debugging purposes).
335 */
336void
337iris_flush_all_caches(struct iris_batch *batch)
338{
339   iris_emit_pipe_control_flush(batch, "debug: flush all caches",
340                                PIPE_CONTROL_CS_STALL |
341                                PIPE_CONTROL_DATA_CACHE_FLUSH |
342                                PIPE_CONTROL_DEPTH_CACHE_FLUSH |
343                                PIPE_CONTROL_RENDER_TARGET_FLUSH |
344                                PIPE_CONTROL_TILE_CACHE_FLUSH |
345                                PIPE_CONTROL_VF_CACHE_INVALIDATE |
346                                PIPE_CONTROL_INSTRUCTION_INVALIDATE |
347                                PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
348                                PIPE_CONTROL_CONST_CACHE_INVALIDATE |
349                                PIPE_CONTROL_STATE_CACHE_INVALIDATE);
350}
351
352static void
353iris_texture_barrier(struct pipe_context *ctx, unsigned flags)
354{
355   struct iris_context *ice = (void *) ctx;
356   struct iris_batch *render_batch = &ice->batches[IRIS_BATCH_RENDER];
357   struct iris_batch *compute_batch = &ice->batches[IRIS_BATCH_COMPUTE];
358
359   if (render_batch->contains_draw) {
360      iris_batch_maybe_flush(render_batch, 48);
361      iris_emit_pipe_control_flush(render_batch,
362                                   "API: texture barrier (1/2)",
363                                   PIPE_CONTROL_DEPTH_CACHE_FLUSH |
364                                   PIPE_CONTROL_RENDER_TARGET_FLUSH |
365                                   PIPE_CONTROL_CS_STALL);
366      iris_emit_pipe_control_flush(render_batch,
367                                   "API: texture barrier (2/2)",
368                                   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
369   }
370
371   if (compute_batch->contains_draw) {
372      iris_batch_maybe_flush(compute_batch, 48);
373      iris_emit_pipe_control_flush(compute_batch,
374                                   "API: texture barrier (1/2)",
375                                   PIPE_CONTROL_CS_STALL);
376      iris_emit_pipe_control_flush(compute_batch,
377                                   "API: texture barrier (2/2)",
378                                   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
379   }
380}
381
382static void
383iris_memory_barrier(struct pipe_context *ctx, unsigned flags)
384{
385   struct iris_context *ice = (void *) ctx;
386   unsigned bits = PIPE_CONTROL_DATA_CACHE_FLUSH | PIPE_CONTROL_CS_STALL;
387
388   if (flags & (PIPE_BARRIER_VERTEX_BUFFER |
389                PIPE_BARRIER_INDEX_BUFFER |
390                PIPE_BARRIER_INDIRECT_BUFFER)) {
391      bits |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
392   }
393
394   if (flags & PIPE_BARRIER_CONSTANT_BUFFER) {
395      bits |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
396              PIPE_CONTROL_CONST_CACHE_INVALIDATE;
397   }
398
399   if (flags & (PIPE_BARRIER_TEXTURE | PIPE_BARRIER_FRAMEBUFFER)) {
400      bits |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE |
401              PIPE_CONTROL_RENDER_TARGET_FLUSH |
402              PIPE_CONTROL_TILE_CACHE_FLUSH;
403   }
404
405   iris_foreach_batch(ice, batch) {
406      if (batch->contains_draw) {
407         iris_batch_maybe_flush(batch, 24);
408         iris_emit_pipe_control_flush(batch, "API: memory barrier", bits);
409      }
410   }
411}
412
413void
414iris_init_flush_functions(struct pipe_context *ctx)
415{
416   ctx->memory_barrier = iris_memory_barrier;
417   ctx->texture_barrier = iris_texture_barrier;
418}
419