Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
//===-- LCSSA.cpp - Convert loops into loop-closed SSA form ---------------===//
//
// 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 pass transforms loops by placing phi nodes at the end of the loops for
// all values that are live across the loop boundary.  For example, it turns
// the left into the right code:
//
// for (...)                for (...)
//   if (c)                   if (c)
//     X1 = ...                 X1 = ...
//   else                     else
//     X2 = ...                 X2 = ...
//   X3 = phi(X1, X2)         X3 = phi(X1, X2)
// ... = X3 + 4             X4 = phi(X3)
//                          ... = X4 + 4
//
// This is still valid LLVM; the extra phi nodes are purely redundant, and will
// be trivially eliminated by InstCombine.  The major benefit of this
// transformation is that it makes many other loop optimizations, such as
// LoopUnswitching, simpler.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Utils/LCSSA.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionAliasAnalysis.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/PredIteratorCache.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Transforms/Utils.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/SSAUpdater.h"
using namespace llvm;

#define DEBUG_TYPE "lcssa"

STATISTIC(NumLCSSA, "Number of live out of a loop variables");

#ifdef EXPENSIVE_CHECKS
static bool VerifyLoopLCSSA = true;
#else
static bool VerifyLoopLCSSA = false;
#endif
static cl::opt<bool, true>
    VerifyLoopLCSSAFlag("verify-loop-lcssa", cl::location(VerifyLoopLCSSA),
                        cl::Hidden,
                        cl::desc("Verify loop lcssa form (time consuming)"));

/// Return true if the specified block is in the list.
static bool isExitBlock(BasicBlock *BB,
                        const SmallVectorImpl<BasicBlock *> &ExitBlocks) {
  return is_contained(ExitBlocks, BB);
}

/// For every instruction from the worklist, check to see if it has any uses
/// that are outside the current loop.  If so, insert LCSSA PHI nodes and
/// rewrite the uses.
bool llvm::formLCSSAForInstructions(SmallVectorImpl<Instruction *> &Worklist,
                                    const DominatorTree &DT, const LoopInfo &LI,
                                    ScalarEvolution *SE, IRBuilderBase &Builder,
                                    SmallVectorImpl<PHINode *> *PHIsToRemove) {
  SmallVector<Use *, 16> UsesToRewrite;
  SmallSetVector<PHINode *, 16> LocalPHIsToRemove;
  PredIteratorCache PredCache;
  bool Changed = false;

  IRBuilderBase::InsertPointGuard InsertPtGuard(Builder);

  // Cache the Loop ExitBlocks across this loop.  We expect to get a lot of
  // instructions within the same loops, computing the exit blocks is
  // expensive, and we're not mutating the loop structure.
  SmallDenseMap<Loop*, SmallVector<BasicBlock *,1>> LoopExitBlocks;

  while (!Worklist.empty()) {
    UsesToRewrite.clear();

    Instruction *I = Worklist.pop_back_val();
    assert(!I->getType()->isTokenTy() && "Tokens shouldn't be in the worklist");
    BasicBlock *InstBB = I->getParent();
    Loop *L = LI.getLoopFor(InstBB);
    assert(L && "Instruction belongs to a BB that's not part of a loop");
    if (!LoopExitBlocks.count(L))
      L->getExitBlocks(LoopExitBlocks[L]);
    assert(LoopExitBlocks.count(L));
    const SmallVectorImpl<BasicBlock *> &ExitBlocks = LoopExitBlocks[L];

    if (ExitBlocks.empty())
      continue;

    for (Use &U : I->uses()) {
      Instruction *User = cast<Instruction>(U.getUser());
      BasicBlock *UserBB = User->getParent();

      // For practical purposes, we consider that the use in a PHI
      // occurs in the respective predecessor block. For more info,
      // see the `phi` doc in LangRef and the LCSSA doc.
      if (auto *PN = dyn_cast<PHINode>(User))
        UserBB = PN->getIncomingBlock(U);

      if (InstBB != UserBB && !L->contains(UserBB))
        UsesToRewrite.push_back(&U);
    }

    // If there are no uses outside the loop, exit with no change.
    if (UsesToRewrite.empty())
      continue;

    ++NumLCSSA; // We are applying the transformation

    // Invoke instructions are special in that their result value is not
    // available along their unwind edge. The code below tests to see whether
    // DomBB dominates the value, so adjust DomBB to the normal destination
    // block, which is effectively where the value is first usable.
    BasicBlock *DomBB = InstBB;
    if (auto *Inv = dyn_cast<InvokeInst>(I))
      DomBB = Inv->getNormalDest();

    const DomTreeNode *DomNode = DT.getNode(DomBB);

    SmallVector<PHINode *, 16> AddedPHIs;
    SmallVector<PHINode *, 8> PostProcessPHIs;

    SmallVector<PHINode *, 4> InsertedPHIs;
    SSAUpdater SSAUpdate(&InsertedPHIs);
    SSAUpdate.Initialize(I->getType(), I->getName());

    // Force re-computation of I, as some users now need to use the new PHI
    // node.
    if (SE)
      SE->forgetValue(I);

    // Insert the LCSSA phi's into all of the exit blocks dominated by the
    // value, and add them to the Phi's map.
    for (BasicBlock *ExitBB : ExitBlocks) {
      if (!DT.dominates(DomNode, DT.getNode(ExitBB)))
        continue;

      // If we already inserted something for this BB, don't reprocess it.
      if (SSAUpdate.HasValueForBlock(ExitBB))
        continue;
      Builder.SetInsertPoint(&ExitBB->front());
      PHINode *PN = Builder.CreatePHI(I->getType(), PredCache.size(ExitBB),
                                      I->getName() + ".lcssa");
      // Get the debug location from the original instruction.
      PN->setDebugLoc(I->getDebugLoc());

      // Add inputs from inside the loop for this PHI. This is valid
      // because `I` dominates `ExitBB` (checked above).  This implies
      // that every incoming block/edge is dominated by `I` as well,
      // i.e. we can add uses of `I` to those incoming edges/append to the incoming
      // blocks without violating the SSA dominance property.
      for (BasicBlock *Pred : PredCache.get(ExitBB)) {
        PN->addIncoming(I, Pred);

        // If the exit block has a predecessor not within the loop, arrange for
        // the incoming value use corresponding to that predecessor to be
        // rewritten in terms of a different LCSSA PHI.
        if (!L->contains(Pred))
          UsesToRewrite.push_back(
              &PN->getOperandUse(PN->getOperandNumForIncomingValue(
                  PN->getNumIncomingValues() - 1)));
      }

      AddedPHIs.push_back(PN);

      // Remember that this phi makes the value alive in this block.
      SSAUpdate.AddAvailableValue(ExitBB, PN);

      // LoopSimplify might fail to simplify some loops (e.g. when indirect
      // branches are involved). In such situations, it might happen that an
      // exit for Loop L1 is the header of a disjoint Loop L2. Thus, when we
      // create PHIs in such an exit block, we are also inserting PHIs into L2's
      // header. This could break LCSSA form for L2 because these inserted PHIs
      // can also have uses outside of L2. Remember all PHIs in such situation
      // as to revisit than later on. FIXME: Remove this if indirectbr support
      // into LoopSimplify gets improved.
      if (auto *OtherLoop = LI.getLoopFor(ExitBB))
        if (!L->contains(OtherLoop))
          PostProcessPHIs.push_back(PN);
    }

    // Rewrite all uses outside the loop in terms of the new PHIs we just
    // inserted.
    for (Use *UseToRewrite : UsesToRewrite) {
      Instruction *User = cast<Instruction>(UseToRewrite->getUser());
      BasicBlock *UserBB = User->getParent();

      // For practical purposes, we consider that the use in a PHI
      // occurs in the respective predecessor block. For more info,
      // see the `phi` doc in LangRef and the LCSSA doc.
      if (auto *PN = dyn_cast<PHINode>(User))
        UserBB = PN->getIncomingBlock(*UseToRewrite);

      // If this use is in an exit block, rewrite to use the newly inserted PHI.
      // This is required for correctness because SSAUpdate doesn't handle uses
      // in the same block.  It assumes the PHI we inserted is at the end of the
      // block.
      if (isa<PHINode>(UserBB->begin()) && isExitBlock(UserBB, ExitBlocks)) {
        UseToRewrite->set(&UserBB->front());
        continue;
      }

      // If we added a single PHI, it must dominate all uses and we can directly
      // rename it.
      if (AddedPHIs.size() == 1) {
        UseToRewrite->set(AddedPHIs[0]);
        continue;
      }

      // Otherwise, do full PHI insertion.
      SSAUpdate.RewriteUse(*UseToRewrite);
    }

    SmallVector<DbgValueInst *, 4> DbgValues;
    llvm::findDbgValues(DbgValues, I);

    // Update pre-existing debug value uses that reside outside the loop.
    for (auto DVI : DbgValues) {
      BasicBlock *UserBB = DVI->getParent();
      if (InstBB == UserBB || L->contains(UserBB))
        continue;
      // We currently only handle debug values residing in blocks that were
      // traversed while rewriting the uses. If we inserted just a single PHI,
      // we will handle all relevant debug values.
      Value *V = AddedPHIs.size() == 1 ? AddedPHIs[0]
                                       : SSAUpdate.FindValueForBlock(UserBB);
      if (V)
        DVI->replaceVariableLocationOp(I, V);
    }

    // SSAUpdater might have inserted phi-nodes inside other loops. We'll need
    // to post-process them to keep LCSSA form.
    for (PHINode *InsertedPN : InsertedPHIs) {
      if (auto *OtherLoop = LI.getLoopFor(InsertedPN->getParent()))
        if (!L->contains(OtherLoop))
          PostProcessPHIs.push_back(InsertedPN);
    }

    // Post process PHI instructions that were inserted into another disjoint
    // loop and update their exits properly.
    for (auto *PostProcessPN : PostProcessPHIs)
      if (!PostProcessPN->use_empty())
        Worklist.push_back(PostProcessPN);

    // Keep track of PHI nodes that we want to remove because they did not have
    // any uses rewritten.
    for (PHINode *PN : AddedPHIs)
      if (PN->use_empty())
        LocalPHIsToRemove.insert(PN);

    Changed = true;
  }

  // Remove PHI nodes that did not have any uses rewritten or add them to
  // PHIsToRemove, so the caller can remove them after some additional cleanup.
  // We need to redo the use_empty() check here, because even if the PHI node
  // wasn't used when added to LocalPHIsToRemove, later added PHI nodes can be
  // using it.  This cleanup is not guaranteed to handle trees/cycles of PHI
  // nodes that only are used by each other. Such situations has only been
  // noticed when the input IR contains unreachable code, and leaving some extra
  // redundant PHI nodes in such situations is considered a minor problem.
  if (PHIsToRemove) {
    PHIsToRemove->append(LocalPHIsToRemove.begin(), LocalPHIsToRemove.end());
  } else {
    for (PHINode *PN : LocalPHIsToRemove)
      if (PN->use_empty())
        PN->eraseFromParent();
  }
  return Changed;
}

// Compute the set of BasicBlocks in the loop `L` dominating at least one exit.
static void computeBlocksDominatingExits(
    Loop &L, const DominatorTree &DT, SmallVector<BasicBlock *, 8> &ExitBlocks,
    SmallSetVector<BasicBlock *, 8> &BlocksDominatingExits) {
  // We start from the exit blocks, as every block trivially dominates itself
  // (not strictly).
  SmallVector<BasicBlock *, 8> BBWorklist(ExitBlocks);

  while (!BBWorklist.empty()) {
    BasicBlock *BB = BBWorklist.pop_back_val();

    // Check if this is a loop header. If this is the case, we're done.
    if (L.getHeader() == BB)
      continue;

    // Otherwise, add its immediate predecessor in the dominator tree to the
    // worklist, unless we visited it already.
    BasicBlock *IDomBB = DT.getNode(BB)->getIDom()->getBlock();

    // Exit blocks can have an immediate dominator not beloinging to the
    // loop. For an exit block to be immediately dominated by another block
    // outside the loop, it implies not all paths from that dominator, to the
    // exit block, go through the loop.
    // Example:
    //
    // |---- A
    // |     |
    // |     B<--
    // |     |  |
    // |---> C --
    //       |
    //       D
    //
    // C is the exit block of the loop and it's immediately dominated by A,
    // which doesn't belong to the loop.
    if (!L.contains(IDomBB))
      continue;

    if (BlocksDominatingExits.insert(IDomBB))
      BBWorklist.push_back(IDomBB);
  }
}

bool llvm::formLCSSA(Loop &L, const DominatorTree &DT, const LoopInfo *LI,
                     ScalarEvolution *SE) {
  bool Changed = false;

#ifdef EXPENSIVE_CHECKS
  // Verify all sub-loops are in LCSSA form already.
  for (Loop *SubLoop: L)
    assert(SubLoop->isRecursivelyLCSSAForm(DT, *LI) && "Subloop not in LCSSA!");
#endif

  SmallVector<BasicBlock *, 8> ExitBlocks;
  L.getExitBlocks(ExitBlocks);
  if (ExitBlocks.empty())
    return false;

  SmallSetVector<BasicBlock *, 8> BlocksDominatingExits;

  // We want to avoid use-scanning leveraging dominance informations.
  // If a block doesn't dominate any of the loop exits, the none of the values
  // defined in the loop can be used outside.
  // We compute the set of blocks fullfilling the conditions in advance
  // walking the dominator tree upwards until we hit a loop header.
  computeBlocksDominatingExits(L, DT, ExitBlocks, BlocksDominatingExits);

  SmallVector<Instruction *, 8> Worklist;

  // Look at all the instructions in the loop, checking to see if they have uses
  // outside the loop.  If so, put them into the worklist to rewrite those uses.
  for (BasicBlock *BB : BlocksDominatingExits) {
    // Skip blocks that are part of any sub-loops, they must be in LCSSA
    // already.
    if (LI->getLoopFor(BB) != &L)
      continue;
    for (Instruction &I : *BB) {
      // Reject two common cases fast: instructions with no uses (like stores)
      // and instructions with one use that is in the same block as this.
      if (I.use_empty() ||
          (I.hasOneUse() && I.user_back()->getParent() == BB &&
           !isa<PHINode>(I.user_back())))
        continue;

      // Tokens cannot be used in PHI nodes, so we skip over them.
      // We can run into tokens which are live out of a loop with catchswitch
      // instructions in Windows EH if the catchswitch has one catchpad which
      // is inside the loop and another which is not.
      if (I.getType()->isTokenTy())
        continue;

      Worklist.push_back(&I);
    }
  }

  IRBuilder<> Builder(L.getHeader()->getContext());
  Changed = formLCSSAForInstructions(Worklist, DT, *LI, SE, Builder);

  // If we modified the code, remove any caches about the loop from SCEV to
  // avoid dangling entries.
  // FIXME: This is a big hammer, can we clear the cache more selectively?
  if (SE && Changed)
    SE->forgetLoop(&L);

  assert(L.isLCSSAForm(DT));

  return Changed;
}

/// Process a loop nest depth first.
bool llvm::formLCSSARecursively(Loop &L, const DominatorTree &DT,
                                const LoopInfo *LI, ScalarEvolution *SE) {
  bool Changed = false;

  // Recurse depth-first through inner loops.
  for (Loop *SubLoop : L.getSubLoops())
    Changed |= formLCSSARecursively(*SubLoop, DT, LI, SE);

  Changed |= formLCSSA(L, DT, LI, SE);
  return Changed;
}

/// Process all loops in the function, inner-most out.
static bool formLCSSAOnAllLoops(const LoopInfo *LI, const DominatorTree &DT,
                                ScalarEvolution *SE) {
  bool Changed = false;
  for (auto &L : *LI)
    Changed |= formLCSSARecursively(*L, DT, LI, SE);
  return Changed;
}

namespace {
struct LCSSAWrapperPass : public FunctionPass {
  static char ID; // Pass identification, replacement for typeid
  LCSSAWrapperPass() : FunctionPass(ID) {
    initializeLCSSAWrapperPassPass(*PassRegistry::getPassRegistry());
  }

  // Cached analysis information for the current function.
  DominatorTree *DT;
  LoopInfo *LI;
  ScalarEvolution *SE;

  bool runOnFunction(Function &F) override;
  void verifyAnalysis() const override {
    // This check is very expensive. On the loop intensive compiles it may cause
    // up to 10x slowdown. Currently it's disabled by default. LPPassManager
    // always does limited form of the LCSSA verification. Similar reasoning
    // was used for the LoopInfo verifier.
    if (VerifyLoopLCSSA) {
      assert(all_of(*LI,
                    [&](Loop *L) {
                      return L->isRecursivelyLCSSAForm(*DT, *LI);
                    }) &&
             "LCSSA form is broken!");
    }
  };

  /// This transformation requires natural loop information & requires that
  /// loop preheaders be inserted into the CFG.  It maintains both of these,
  /// as well as the CFG.  It also requires dominator information.
  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.setPreservesCFG();

    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<LoopInfoWrapperPass>();
    AU.addPreservedID(LoopSimplifyID);
    AU.addPreserved<AAResultsWrapperPass>();
    AU.addPreserved<BasicAAWrapperPass>();
    AU.addPreserved<GlobalsAAWrapperPass>();
    AU.addPreserved<ScalarEvolutionWrapperPass>();
    AU.addPreserved<SCEVAAWrapperPass>();
    AU.addPreserved<BranchProbabilityInfoWrapperPass>();
    AU.addPreserved<MemorySSAWrapperPass>();

    // This is needed to perform LCSSA verification inside LPPassManager
    AU.addRequired<LCSSAVerificationPass>();
    AU.addPreserved<LCSSAVerificationPass>();
  }
};
}

char LCSSAWrapperPass::ID = 0;
INITIALIZE_PASS_BEGIN(LCSSAWrapperPass, "lcssa", "Loop-Closed SSA Form Pass",
                      false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LCSSAVerificationPass)
INITIALIZE_PASS_END(LCSSAWrapperPass, "lcssa", "Loop-Closed SSA Form Pass",
                    false, false)

Pass *llvm::createLCSSAPass() { return new LCSSAWrapperPass(); }
char &llvm::LCSSAID = LCSSAWrapperPass::ID;

/// Transform \p F into loop-closed SSA form.
bool LCSSAWrapperPass::runOnFunction(Function &F) {
  LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>();
  SE = SEWP ? &SEWP->getSE() : nullptr;

  return formLCSSAOnAllLoops(LI, *DT, SE);
}

PreservedAnalyses LCSSAPass::run(Function &F, FunctionAnalysisManager &AM) {
  auto &LI = AM.getResult<LoopAnalysis>(F);
  auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
  auto *SE = AM.getCachedResult<ScalarEvolutionAnalysis>(F);
  if (!formLCSSAOnAllLoops(&LI, DT, SE))
    return PreservedAnalyses::all();

  PreservedAnalyses PA;
  PA.preserveSet<CFGAnalyses>();
  PA.preserve<ScalarEvolutionAnalysis>();
  // BPI maps terminators to probabilities, since we don't modify the CFG, no
  // updates are needed to preserve it.
  PA.preserve<BranchProbabilityAnalysis>();
  PA.preserve<MemorySSAAnalysis>();
  return PA;
}