aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Support/Windows/Threading.inc
blob: 7b48ca8fb1fb956f047a4f4ccaf1a8ffc159ebd3 (plain) (blame)
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
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
//===- Windows/Threading.inc - Win32 Threading Implementation - -*- C++ -*-===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file provides the Win32 specific implementation of Threading functions.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/SmallString.h"
#include "llvm/ADT/Twine.h"

#include "llvm/Support/Windows/WindowsSupport.h"
#include <process.h>

#include <bitset>

// Windows will at times define MemoryFence.
#ifdef MemoryFence
#undef MemoryFence
#endif

namespace llvm {
HANDLE
llvm_execute_on_thread_impl(unsigned(__stdcall *ThreadFunc)(void *), void *Arg,
                            llvm::Optional<unsigned> StackSizeInBytes) {
  HANDLE hThread = (HANDLE)::_beginthreadex(
      NULL, StackSizeInBytes.getValueOr(0), ThreadFunc, Arg, 0, NULL);

  if (!hThread) {
    ReportLastErrorFatal("_beginthreadex failed");
  }

  return hThread;
}

void llvm_thread_join_impl(HANDLE hThread) {
  if (::WaitForSingleObject(hThread, INFINITE) == WAIT_FAILED) {
    ReportLastErrorFatal("WaitForSingleObject failed");
  }
}

void llvm_thread_detach_impl(HANDLE hThread) {
  if (::CloseHandle(hThread) == FALSE) {
    ReportLastErrorFatal("CloseHandle failed");
  }
}

DWORD llvm_thread_get_id_impl(HANDLE hThread) {
  return ::GetThreadId(hThread);
}

DWORD llvm_thread_get_current_id_impl() {
  return ::GetCurrentThreadId();
}

} // namespace llvm

uint64_t llvm::get_threadid() {
  return uint64_t(::GetCurrentThreadId());
}

uint32_t llvm::get_max_thread_name_length() { return 0; }

#if defined(_MSC_VER)
static void SetThreadName(DWORD Id, LPCSTR Name) {
  constexpr DWORD MS_VC_EXCEPTION = 0x406D1388;

#pragma pack(push, 8)
  struct THREADNAME_INFO {
    DWORD dwType;     // Must be 0x1000.
    LPCSTR szName;    // Pointer to thread name
    DWORD dwThreadId; // Thread ID (-1 == current thread)
    DWORD dwFlags;    // Reserved.  Do not use.
  };
#pragma pack(pop)

  THREADNAME_INFO info;
  info.dwType = 0x1000;
  info.szName = Name;
  info.dwThreadId = Id;
  info.dwFlags = 0;

  __try {
    ::RaiseException(MS_VC_EXCEPTION, 0, sizeof(info) / sizeof(ULONG_PTR),
      (ULONG_PTR *)&info);
  }
  __except (EXCEPTION_EXECUTE_HANDLER) {
  }
}
#endif

void llvm::set_thread_name(const Twine &Name) {
#if defined(_MSC_VER)
  // Make sure the input is null terminated.
  SmallString<64> Storage;
  StringRef NameStr = Name.toNullTerminatedStringRef(Storage);
  SetThreadName(::GetCurrentThreadId(), NameStr.data());
#endif
}

void llvm::get_thread_name(SmallVectorImpl<char> &Name) {
  // "Name" is not an inherent property of a thread on Windows.  In fact, when
  // you "set" the name, you are only firing a one-time message to a debugger
  // which it interprets as a program setting its threads' name.  We may be
  // able to get fancy by creating a TLS entry when someone calls
  // set_thread_name so that subsequent calls to get_thread_name return this
  // value.
  Name.clear();
}

SetThreadPriorityResult llvm::set_thread_priority(ThreadPriority Priority) {
  // https://docs.microsoft.com/en-us/windows/desktop/api/processthreadsapi/nf-processthreadsapi-setthreadpriority
  // Begin background processing mode. The system lowers the resource scheduling
  // priorities of the thread so that it can perform background work without
  // significantly affecting activity in the foreground.
  // End background processing mode. The system restores the resource scheduling
  // priorities of the thread as they were before the thread entered background
  // processing mode.
  return SetThreadPriority(GetCurrentThread(),
                           Priority == ThreadPriority::Background
                               ? THREAD_MODE_BACKGROUND_BEGIN
                               : THREAD_MODE_BACKGROUND_END)
             ? SetThreadPriorityResult::SUCCESS
             : SetThreadPriorityResult::FAILURE;
}

struct ProcessorGroup {
  unsigned ID;
  unsigned AllThreads;
  unsigned UsableThreads;
  unsigned ThreadsPerCore;
  uint64_t Affinity;

  unsigned useableCores() const {
    return std::max(1U, UsableThreads / ThreadsPerCore);
  }
};

template <typename F>
static bool IterateProcInfo(LOGICAL_PROCESSOR_RELATIONSHIP Relationship, F Fn) {
  DWORD Len = 0;
  BOOL R = ::GetLogicalProcessorInformationEx(Relationship, NULL, &Len);
  if (R || GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
    return false;
  }
  auto *Info = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)calloc(1, Len);
  R = ::GetLogicalProcessorInformationEx(Relationship, Info, &Len);
  if (R) {
    auto *End =
        (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)((uint8_t *)Info + Len);
    for (auto *Curr = Info; Curr < End;
         Curr = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)((uint8_t *)Curr +
                                                            Curr->Size)) {
      if (Curr->Relationship != Relationship)
        continue;
      Fn(Curr);
    }
  }
  free(Info);
  return true;
}

static ArrayRef<ProcessorGroup> getProcessorGroups() {
  auto computeGroups = []() {
    SmallVector<ProcessorGroup, 4> Groups;

    auto HandleGroup = [&](SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *ProcInfo) {
      GROUP_RELATIONSHIP &El = ProcInfo->Group;
      for (unsigned J = 0; J < El.ActiveGroupCount; ++J) {
        ProcessorGroup G;
        G.ID = Groups.size();
        G.AllThreads = El.GroupInfo[J].MaximumProcessorCount;
        G.UsableThreads = El.GroupInfo[J].ActiveProcessorCount;
        assert(G.UsableThreads <= 64);
        G.Affinity = El.GroupInfo[J].ActiveProcessorMask;
        Groups.push_back(G);
      }
    };

    if (!IterateProcInfo(RelationGroup, HandleGroup))
      return std::vector<ProcessorGroup>();

    auto HandleProc = [&](SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *ProcInfo) {
      PROCESSOR_RELATIONSHIP &El = ProcInfo->Processor;
      assert(El.GroupCount == 1);
      unsigned NumHyperThreads = 1;
      // If the flag is set, each core supports more than one hyper-thread.
      if (El.Flags & LTP_PC_SMT)
        NumHyperThreads = std::bitset<64>(El.GroupMask[0].Mask).count();
      unsigned I = El.GroupMask[0].Group;
      Groups[I].ThreadsPerCore = NumHyperThreads;
    };

    if (!IterateProcInfo(RelationProcessorCore, HandleProc))
      return std::vector<ProcessorGroup>();

    // If there's an affinity mask set, assume the user wants to constrain the
    // current process to only a single CPU group. On Windows, it is not
    // possible for affinity masks to cross CPU group boundaries.
    DWORD_PTR ProcessAffinityMask = 0, SystemAffinityMask = 0;
    if (::GetProcessAffinityMask(GetCurrentProcess(), &ProcessAffinityMask,
                                 &SystemAffinityMask) &&
        ProcessAffinityMask != SystemAffinityMask) {
      // We don't expect more that 4 CPU groups on Windows (256 processors).
      USHORT GroupCount = 4;
      USHORT GroupArray[4]{};
      if (::GetProcessGroupAffinity(GetCurrentProcess(), &GroupCount,
                                    GroupArray)) {
        assert(GroupCount == 1 &&
               "On startup, a program is expected to be assigned only to "
               "one processor group!");
        unsigned CurrentGroupID = GroupArray[0];
        ProcessorGroup NewG{Groups[CurrentGroupID]};
        NewG.Affinity = ProcessAffinityMask;
        NewG.UsableThreads = countPopulation(ProcessAffinityMask);
        Groups.clear();
        Groups.push_back(NewG);
      }
    }

    return std::vector<ProcessorGroup>(Groups.begin(), Groups.end());
  };
  static auto Groups = computeGroups();
  return ArrayRef<ProcessorGroup>(Groups);
}

template <typename R, typename UnaryPredicate>
static unsigned aggregate(R &&Range, UnaryPredicate P) {
  unsigned I{};
  for (const auto &It : Range)
    I += P(It);
  return I;
}

// for sys::getHostNumPhysicalCores
int computeHostNumPhysicalCores() {
  static unsigned Cores =
      aggregate(getProcessorGroups(), [](const ProcessorGroup &G) {
        return G.UsableThreads / G.ThreadsPerCore;
      });
  return Cores;
}

int computeHostNumHardwareThreads() {
  static unsigned Threads =
      aggregate(getProcessorGroups(),
                [](const ProcessorGroup &G) { return G.UsableThreads; });
  return Threads;
}

// Finds the proper CPU socket where a thread number should go. Returns 'None'
// if the thread shall remain on the actual CPU socket.
Optional<unsigned>
llvm::ThreadPoolStrategy::compute_cpu_socket(unsigned ThreadPoolNum) const {
  ArrayRef<ProcessorGroup> Groups = getProcessorGroups();
  // Only one CPU socket in the system or process affinity was set, no need to
  // move the thread(s) to another CPU socket.
  if (Groups.size() <= 1)
    return None;

  // We ask for less threads than there are hardware threads per CPU socket, no
  // need to dispatch threads to other CPU sockets.
  unsigned MaxThreadsPerSocket =
      UseHyperThreads ? Groups[0].UsableThreads : Groups[0].useableCores();
  if (compute_thread_count() <= MaxThreadsPerSocket)
    return None;

  assert(ThreadPoolNum < compute_thread_count() &&
         "The thread index is not within thread strategy's range!");

  // Assumes the same number of hardware threads per CPU socket.
  return (ThreadPoolNum * Groups.size()) / compute_thread_count();
}

// Assign the current thread to a more appropriate CPU socket or CPU group
void llvm::ThreadPoolStrategy::apply_thread_strategy(
    unsigned ThreadPoolNum) const {
  Optional<unsigned> Socket = compute_cpu_socket(ThreadPoolNum);
  if (!Socket)
    return;
  ArrayRef<ProcessorGroup> Groups = getProcessorGroups();
  GROUP_AFFINITY Affinity{};
  Affinity.Group = Groups[*Socket].ID;
  Affinity.Mask = Groups[*Socket].Affinity;
  SetThreadGroupAffinity(GetCurrentThread(), &Affinity, nullptr);
}

llvm::BitVector llvm::get_thread_affinity_mask() {
  GROUP_AFFINITY Affinity{};
  GetThreadGroupAffinity(GetCurrentThread(), &Affinity);

  static unsigned All =
      aggregate(getProcessorGroups(),
                [](const ProcessorGroup &G) { return G.AllThreads; });

  unsigned StartOffset =
      aggregate(getProcessorGroups(), [&](const ProcessorGroup &G) {
        return G.ID < Affinity.Group ? G.AllThreads : 0;
      });

  llvm::BitVector V;
  V.resize(All);
  for (unsigned I = 0; I < sizeof(KAFFINITY) * 8; ++I) {
    if ((Affinity.Mask >> I) & 1)
      V.set(StartOffset + I);
  }
  return V;
}

unsigned llvm::get_cpus() { return getProcessorGroups().size(); }