Pull in r223171 from upstream llvm trunk (by Michael Zolotukhin): PR21302. Vectorize only bottom-tested loops. rdar://problem/18886083 This fixes a bug in the llvm vectorizer, which could sometimes cause vectorized loops to perform an additional iteration, leading to possible buffer overruns. Symptoms of this, which are usually segfaults, were first noticed when building gcc ports, here: https://lists.freebsd.org/pipermail/freebsd-ports/2014-September/095466.html https://lists.freebsd.org/pipermail/freebsd-toolchain/2014-September/001211.html Note: because this is applied on top of llvm/clang 3.5.0, this fix is slightly different from the one just checked into head in r275633. Introduced here: http://svnweb.freebsd.org/changeset/base/275635 Index: lib/Transforms/Vectorize/LoopVectorize.cpp =================================================================== --- lib/Transforms/Vectorize/LoopVectorize.cpp +++ lib/Transforms/Vectorize/LoopVectorize.cpp @@ -3466,6 +3466,15 @@ bool LoopVectorizationLegality::canVectorize() { return false; } + // We only handle bottom-tested loops, i.e. loop in which the condition is + // checked at the end of each iteration. With that we can assume that all + // instructions in the loop are executed the same number of times. + if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch()) { + emitAnalysis( + Report() << "loop control flow is not understood by vectorizer"); + return false; + } + // We need to have a loop header. DEBUG(dbgs() << "LV: Found a loop: " << TheLoop->getHeader()->getName() << '\n'); Index: test/Transforms/LoopVectorize/loop-form.ll =================================================================== --- test/Transforms/LoopVectorize/loop-form.ll +++ test/Transforms/LoopVectorize/loop-form.ll @@ -0,0 +1,31 @@ +; RUN: opt -S -loop-vectorize < %s | FileCheck %s +target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" + +; Check that we vectorize only bottom-tested loops. +; This is a reduced testcase from PR21302. +; +; rdar://problem/18886083 + +%struct.X = type { i32, i16 } +; CHECK-LABEL: @foo( +; CHECK-NOT: vector.body + +define void @foo(i32 %n) { +entry: + br label %for.cond + +for.cond: + %i = phi i32 [ 0, %entry ], [ %inc, %for.body ] + %cmp = icmp slt i32 %i, %n + br i1 %cmp, label %for.body, label %if.end + +for.body: + %iprom = sext i32 %i to i64 + %b = getelementptr inbounds %struct.X* undef, i64 %iprom, i32 1 + store i16 0, i16* %b, align 4 + %inc = add nsw i32 %i, 1 + br label %for.cond + +if.end: + ret void +}