intel/compiler: Get rid of the global compaction table pointers
[mesa.git] / src / intel / common / gen_clflush.h
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 (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
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 */
23
24 #ifndef GEN_CLFLUSH_H
25 #define GEN_CLFLUSH_H
26
27 #define CACHELINE_SIZE 64
28 #define CACHELINE_MASK 63
29
30 static inline void
31 gen_clflush_range(void *start, size_t size)
32 {
33 void *p = (void *) (((uintptr_t) start) & ~CACHELINE_MASK);
34 void *end = start + size;
35
36 while (p < end) {
37 __builtin_ia32_clflush(p);
38 p += CACHELINE_SIZE;
39 }
40 }
41
42 static inline void
43 gen_flush_range(void *start, size_t size)
44 {
45 __builtin_ia32_mfence();
46 gen_clflush_range(start, size);
47 }
48
49 static inline void
50 gen_invalidate_range(void *start, size_t size)
51 {
52 gen_clflush_range(start, size);
53
54 /* Modern Atom CPUs (Baytrail+) have issues with clflush serialization,
55 * where mfence is not a sufficient synchronization barrier. We must
56 * double clflush the last cacheline. This guarantees it will be ordered
57 * after the preceding clflushes, and then the mfence guards against
58 * prefetches crossing the clflush boundary.
59 *
60 * See kernel commit 396f5d62d1a5fd99421855a08ffdef8edb43c76e
61 * ("drm: Restore double clflush on the last partial cacheline")
62 * and https://bugs.freedesktop.org/show_bug.cgi?id=92845.
63 */
64 __builtin_ia32_clflush(start + size - 1);
65 __builtin_ia32_mfence();
66 }
67
68 #endif