1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
|
//===-- clear_cache.c - Implement __clear_cache ---------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#if defined(__linux__) && defined(__mips__)
// Otherwise, the build fails as it cannot find syscall
#define _GNU_SOURCE
#endif
#include "int_lib.h"
#if defined(__linux__)
#include <assert.h>
#endif
#include <stddef.h>
#if __APPLE__
#include <libkern/OSCacheControl.h>
#endif
#if defined(_WIN32)
// Forward declare Win32 APIs since the GCC mode driver does not handle the
// newer SDKs as well as needed.
uint32_t FlushInstructionCache(uintptr_t hProcess, void *lpBaseAddress,
uintptr_t dwSize);
uintptr_t GetCurrentProcess(void);
#endif
#if defined(__FreeBSD__) && defined(__arm__)
// clang-format off
#include <sys/types.h>
#include <machine/sysarch.h>
// clang-format on
#endif
#if defined(__NetBSD__) && defined(__arm__)
#include <machine/sysarch.h>
#endif
#if defined(__OpenBSD__) && (defined(__arm__) || defined(__mips__) || defined(__riscv))
// clang-format off
#include <sys/types.h>
#include <machine/sysarch.h>
// clang-format on
#endif
#if defined(__linux__) && defined(__mips__)
#include <sys/cachectl.h>
#include <sys/syscall.h>
#include <unistd.h>
#endif
#if defined(__linux__) && defined(__riscv)
// to get platform-specific syscall definitions
#include <linux/unistd.h>
#endif
// The compiler generates calls to __clear_cache() when creating
// trampoline functions on the stack for use with nested functions.
// It is expected to invalidate the instruction cache for the
// specified range.
void __clear_cache(void *start, void *end) {
#if __i386__ || __x86_64__ || defined(_M_IX86) || defined(_M_X64)
// Intel processors have a unified instruction and data cache
// so there is nothing to do
#elif defined(_WIN32) && (defined(__arm__) || defined(__aarch64__))
FlushInstructionCache(GetCurrentProcess(), start, end - start);
#elif defined(__arm__) && !defined(__APPLE__)
#if defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__)
struct arm_sync_icache_args arg;
arg.addr = (uintptr_t)start;
arg.len = (uintptr_t)end - (uintptr_t)start;
sysarch(ARM_SYNC_ICACHE, &arg);
#elif defined(__linux__)
// We used to include asm/unistd.h for the __ARM_NR_cacheflush define, but
// it also brought many other unused defines, as well as a dependency on
// kernel headers to be installed.
//
// This value is stable at least since Linux 3.13 and should remain so for
// compatibility reasons, warranting it's re-definition here.
#define __ARM_NR_cacheflush 0x0f0002
register int start_reg __asm("r0") = (int)(intptr_t)start;
const register int end_reg __asm("r1") = (int)(intptr_t)end;
const register int flags __asm("r2") = 0;
const register int syscall_nr __asm("r7") = __ARM_NR_cacheflush;
__asm __volatile("svc 0x0"
: "=r"(start_reg)
: "r"(syscall_nr), "r"(start_reg), "r"(end_reg), "r"(flags));
assert(start_reg == 0 && "Cache flush syscall failed.");
#else
compilerrt_abort();
#endif
#elif defined(__linux__) && defined(__mips__)
const uintptr_t start_int = (uintptr_t)start;
const uintptr_t end_int = (uintptr_t)end;
syscall(__NR_cacheflush, start, (end_int - start_int), BCACHE);
#elif defined(__mips__) && defined(__OpenBSD__)
cacheflush(start, (uintptr_t)end - (uintptr_t)start, BCACHE);
#elif defined(__aarch64__) && !defined(__APPLE__)
uint64_t xstart = (uint64_t)(uintptr_t)start;
uint64_t xend = (uint64_t)(uintptr_t)end;
// Get Cache Type Info.
static uint64_t ctr_el0 = 0;
if (ctr_el0 == 0)
__asm __volatile("mrs %0, ctr_el0" : "=r"(ctr_el0));
// The DC and IC instructions must use 64-bit registers so we don't use
// uintptr_t in case this runs in an IPL32 environment.
uint64_t addr;
// If CTR_EL0.IDC is set, data cache cleaning to the point of unification
// is not required for instruction to data coherence.
if (((ctr_el0 >> 28) & 0x1) == 0x0) {
const size_t dcache_line_size = 4 << ((ctr_el0 >> 16) & 15);
for (addr = xstart & ~(dcache_line_size - 1); addr < xend;
addr += dcache_line_size)
__asm __volatile("dc cvau, %0" ::"r"(addr));
}
__asm __volatile("dsb ish");
// If CTR_EL0.DIC is set, instruction cache invalidation to the point of
// unification is not required for instruction to data coherence.
if (((ctr_el0 >> 29) & 0x1) == 0x0) {
const size_t icache_line_size = 4 << ((ctr_el0 >> 0) & 15);
for (addr = xstart & ~(icache_line_size - 1); addr < xend;
addr += icache_line_size)
__asm __volatile("ic ivau, %0" ::"r"(addr));
__asm __volatile("dsb ish");
}
__asm __volatile("isb sy");
#elif defined(__powerpc__)
// Newer CPUs have a bigger line size made of multiple blocks, so the
// following value is a minimal common denominator for what used to be
// a single block cache line and is therefore inneficient.
const size_t line_size = 32;
const size_t len = (uintptr_t)end - (uintptr_t)start;
const uintptr_t mask = ~(line_size - 1);
const uintptr_t start_line = ((uintptr_t)start) & mask;
const uintptr_t end_line = ((uintptr_t)start + len + line_size - 1) & mask;
for (uintptr_t line = start_line; line < end_line; line += line_size)
__asm__ volatile("dcbf 0, %0" : : "r"(line));
__asm__ volatile("sync");
for (uintptr_t line = start_line; line < end_line; line += line_size)
__asm__ volatile("icbi 0, %0" : : "r"(line));
__asm__ volatile("isync");
#elif defined(__sparc__)
const size_t dword_size = 8;
const size_t len = (uintptr_t)end - (uintptr_t)start;
const uintptr_t mask = ~(dword_size - 1);
const uintptr_t start_dword = ((uintptr_t)start) & mask;
const uintptr_t end_dword = ((uintptr_t)start + len + dword_size - 1) & mask;
for (uintptr_t dword = start_dword; dword < end_dword; dword += dword_size)
__asm__ volatile("flush %0" : : "r"(dword));
#elif defined(__riscv) && defined(__linux__)
// See: arch/riscv/include/asm/cacheflush.h, arch/riscv/kernel/sys_riscv.c
register void *start_reg __asm("a0") = start;
const register void *end_reg __asm("a1") = end;
// "0" means that we clear cache for all threads (SYS_RISCV_FLUSH_ICACHE_ALL)
const register long flags __asm("a2") = 0;
const register long syscall_nr __asm("a7") = __NR_riscv_flush_icache;
__asm __volatile("ecall"
: "=r"(start_reg)
: "r"(start_reg), "r"(end_reg), "r"(flags), "r"(syscall_nr));
assert(start_reg == 0 && "Cache flush syscall failed.");
#elif defined(__riscv) && defined(__OpenBSD__)
struct riscv_sync_icache_args arg;
arg.addr = (uintptr_t)start;
arg.len = (uintptr_t)end - (uintptr_t)start;
sysarch(RISCV_SYNC_ICACHE, &arg);
#elif defined(__ve__)
__asm__ volatile("fencec 2");
#else
#if __APPLE__
// On Darwin, sys_icache_invalidate() provides this functionality
sys_icache_invalidate(start, end - start);
#else
compilerrt_abort();
#endif
#endif
}
|
