[llvm] Address base discriminator overflow in X86DiscriminateMemOps

Summary:
Macros are expanded on a single line. In case of large expansions,
with sufficiently many instructions with memory operands (and when
-fdebug-info-for-profiling is requested), we may be unable to generate
new base discriminator values - new values overflow (base
discriminators may not be larger than 2^12).

This CL warns instead of asserting in such a case. A subsequent CL
will add APIs to check for overflow before creating new debug info.

See https://bugs.llvm.org/show_bug.cgi?id=39890

Reviewers: davidxl, wmi, gbedwell

Reviewed By: davidxl

Subscribers: aprantl, llvm-commits

Differential Revision: https://reviews.llvm.org/D55643

llvm-svn: 349075
This commit is contained in:
Mircea Trofin 2018-12-13 19:40:59 +00:00
parent 4888c4aba5
commit 41c729e78e
1 changed files with 14 additions and 3 deletions

View File

@ -24,6 +24,8 @@
#include "llvm/Transforms/IPO/SampleProfile.h"
using namespace llvm;
#define DEBUG_TYPE "x86-discriminate-memops"
namespace {
using Location = std::pair<StringRef, unsigned>;
@ -114,9 +116,18 @@ bool X86DiscriminateMemOps::runOnMachineFunction(MachineFunction &MF) {
Changed = true;
const std::pair<DenseSet<unsigned>::iterator, bool> MustInsert =
Set.insert(DI->getBaseDiscriminator());
(void)MustInsert; // silence warning.
assert(MustInsert.second &&
"New discriminator shouldn't be present in set");
// FIXME (mtrofin): check if the to-be inserted base discriminator can
// be added. This requires a new API on DILocation.
// The assumption is that this scenario is infrequent/OK not to support.
// If evidence points otherwise, we can explore synthesize unique DIs by
// adding fake line numbers.
if (!MustInsert.second) {
LLVM_DEBUG(dbgs()
<< "Unable to create a unique discriminator in "
<< DI->getFilename() << " Line: " << DI->getLine()
<< " Column: " << DI->getColumn()
<< ". This is likely due to a large macro expansion.\n");
}
}
// Bump the reference DI to avoid cramming discriminators on line 0.