[flang] [clang] [mlir] [clang-tools-extra] [libcxx] [libc] [compiler-rt] [llvm] [AsmWriter] Ensure getMnemonic doesn't return invalid pointers (PR #75783)

[Lucas Duarte Prates via cfe-commits]

https://github.com/pratlucas updated https://github.com/llvm/llvm-project/pull/75783

>From 62f4b5daeca0be5b463c5c42271a4b997f084523 Mon Sep 17 00:00:00 2001
From: Lucas Prates <lucas.prates at arm.com>
Date: Mon, 18 Dec 2023 10:49:25 +0000
Subject: [PATCH 1/2] [AsmWriter] Ensure getMnemonic doesn't return invalid
 pointers

For instructions that don't map to a mnemonic string, the implementation
of MCInstPrinter::getMnemonic would return an invalid pointer due to the
result of the calculation of the instruction's position in the `AsmStrs`
table. This patch fixes the issue by ensuring those cases return a
`nullptr` value instead.

Fixes #74177.
---
 llvm/lib/MC/MCAsmStreamer.cpp            | 5 ++++-
 llvm/utils/TableGen/AsmWriterEmitter.cpp | 4 ++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index 9e1d108ac14dc5..532ac89bf9ff76 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -154,7 +154,10 @@ class MCAsmStreamer final : public MCStreamer {
   void emitGNUAttribute(unsigned Tag, unsigned Value) override;
 
   StringRef getMnemonic(MCInst &MI) override {
-    return InstPrinter->getMnemonic(&MI).first;
+    std::pair<const char *, uint64_t> M = InstPrinter->getMnemonic(&MI);
+    assert((M.second != 0 || M.first == nullptr) &&
+           "Invalid char pointer for instruction with no mnemonic");
+    return M.first;
   }
 
   void emitLabel(MCSymbol *Symbol, SMLoc Loc = SMLoc()) override;
diff --git a/llvm/utils/TableGen/AsmWriterEmitter.cpp b/llvm/utils/TableGen/AsmWriterEmitter.cpp
index 0220927295cf78..e0cd5fad3254de 100644
--- a/llvm/utils/TableGen/AsmWriterEmitter.cpp
+++ b/llvm/utils/TableGen/AsmWriterEmitter.cpp
@@ -438,6 +438,10 @@ void AsmWriterEmitter::EmitGetMnemonic(
   O << "  // Emit the opcode for the instruction.\n";
   O << BitsString;
 
+  // Make sure we don't return an invalid pointer if bits is 0
+  O << "  if (Bits == 0)\n"
+       "    return {nullptr, Bits};\n";
+
   // Return mnemonic string and bits.
   O << "  return {AsmStrs+(Bits & " << (1 << AsmStrBits) - 1
     << ")-1, Bits};\n\n";

>From 1326609f665f6f202301bc6f7945d49e3cd1b72c Mon Sep 17 00:00:00 2001
From: Lucas Prates <lucas.prates at arm.com>
Date: Mon, 18 Dec 2023 11:59:26 +0000
Subject: [PATCH 2/2] fixup! [AsmWriter] Ensure getMnemonic doesn't return
 invalid pointers

---
 llvm/lib/MC/MCAsmStreamer.cpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index 532ac89bf9ff76..49668de27d67e7 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -154,10 +154,10 @@ class MCAsmStreamer final : public MCStreamer {
   void emitGNUAttribute(unsigned Tag, unsigned Value) override;
 
   StringRef getMnemonic(MCInst &MI) override {
-    std::pair<const char *, uint64_t> M = InstPrinter->getMnemonic(&MI);
-    assert((M.second != 0 || M.first == nullptr) &&
+    auto [Ptr, Bits] = InstPrinter->getMnemonic(&MI);
+    assert((Bits != 0 || Ptr == nullptr) &&
            "Invalid char pointer for instruction with no mnemonic");
-    return M.first;
+    return Ptr;
   }
 
   void emitLabel(MCSymbol *Symbol, SMLoc Loc = SMLoc()) override;