[clang] [analyzer] Do not reason about locations passed as inline asm input (PR #103714)

[Pavel Skripkin via cfe-commits]

https://github.com/pskrgag created https://github.com/llvm/llvm-project/pull/103714

If pointer is passed as input operand for inline assembly, it's possible that asm block will change memory behind this pointer. So if pointer is passed inside inline asm block, it's better to not guess and assume memory has unknown state.

Without such change, we observed a lot of FP with hand-written `memcpy` and friends.

>From e528b0ded1a9815195e33d141a9e8ce05fb26cd1 Mon Sep 17 00:00:00 2001
From: Pavel Skripkin <paskripkin at gmail.com>
Date: Wed, 14 Aug 2024 10:50:24 +0300
Subject: [PATCH] clang/csa: stop reasoning about pointers passed inside inline
 assembly

---
 clang/lib/StaticAnalyzer/Core/ExprEngine.cpp |  8 +++++
 clang/test/Analysis/asm.cpp                  | 36 +++++++++++++++++++-
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/clang/lib/StaticAnalyzer/Core/ExprEngine.cpp b/clang/lib/StaticAnalyzer/Core/ExprEngine.cpp
index 686310d38ebd58..d64134102d96c7 100644
--- a/clang/lib/StaticAnalyzer/Core/ExprEngine.cpp
+++ b/clang/lib/StaticAnalyzer/Core/ExprEngine.cpp
@@ -3807,6 +3807,14 @@ void ExprEngine::VisitGCCAsmStmt(const GCCAsmStmt *A, ExplodedNode *Pred,
       state = state->bindLoc(*LV, UnknownVal(), Pred->getLocationContext());
   }
 
+  // Do not reason about locations passed inside inline assembly.
+  for (const Expr *O : A->inputs()) {
+    SVal X = state->getSVal(O, Pred->getLocationContext());
+
+    if (std::optional<Loc> LV = X.getAs<Loc>())
+      state = state->bindLoc(*LV, UnknownVal(), Pred->getLocationContext());
+  }
+
   Bldr.generateNode(A, Pred, state);
 }
 
diff --git a/clang/test/Analysis/asm.cpp b/clang/test/Analysis/asm.cpp
index 1180063502168f..5d158b62e7221f 100644
--- a/clang/test/Analysis/asm.cpp
+++ b/clang/test/Analysis/asm.cpp
@@ -1,4 +1,5 @@
-// RUN: %clang_analyze_cc1 -analyzer-checker debug.ExprInspection -fheinous-gnu-extensions -w %s -verify
+// RUN: %clang_analyze_cc1 -triple=x86_64-unknown-unknown \
+// RUN:      -analyzer-checker debug.ExprInspection,core -fheinous-gnu-extensions -w %s -verify
 
 int clang_analyzer_eval(int);
 
@@ -10,3 +11,36 @@ void testRValueOutput() {
   clang_analyzer_eval(global == 1); // expected-warning{{UNKNOWN}}
   clang_analyzer_eval(ref == 1);    // expected-warning{{UNKNOWN}}
 }
+
+void *MyMemcpy(void *d, const void *s, const int n) {
+  asm volatile (
+    "cld\n rep movsb\n"
+    :: "S" (s), "D" (d), "c" (n) : "memory"
+  );
+
+  return d;
+}
+
+void testInlineAsmMemcpy(void)
+{
+    int a, b = 10, c;
+
+    MyMemcpy(&a, &b, sizeof(b));
+    c = a; // no-warning
+}
+
+void testInlineAsmMemcpyArray(void)
+{
+    int a[10], b[10] = {}, c;
+
+    MyMemcpy(&a, &b, sizeof(b));
+    c = a[8]; // no-warning
+}
+
+void testInlineAsmMemcpyUninit(void)
+{
+    int a[10], b[10] = {}, c;
+
+    MyMemcpy(&a[1], &b[1], sizeof(b) - sizeof(b[1]));
+    c = a[0]; // expected-warning{{Assigned value is garbage or undefined}}
+}