From: NagyDonat <donat.nagy@ericsson.com>
Date: Tue, 23 Apr 2024 08:20:34 +0000 (+0200)
Subject: [analyzer] Fix performance of getTaintedSymbolsImpl() (#89606)
X-Git-Tag: upstream/18.1.6~66
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=3b4ba7277bd735ebea489d94c4ae771427283e6e;p=platform%2Fupstream%2Fllvm.git

[analyzer] Fix performance of getTaintedSymbolsImpl() (#89606)

Previously the function
```
std::vector<SymbolRef> taint::getTaintedSymbolsImpl(ProgramStateRef State,
                                                    const MemRegion *Reg,
                                                    TaintTagType K,
                                                    bool returnFirstOnly)
```
(one of the 4 overloaded variants under this name) was handling element
regions in a highly inefficient manner: it performed the "also examine
the super-region" step twice. (Once in the branch for element regions,
and once in the more general branch for all `SubRegion`s -- note that
`ElementRegion` is a subclass of `SubRegion`.)

As pointer arithmetic produces `ElementRegion`s, it's not too difficult
to get a chain of N nested element regions where this inefficient
recursion would produce 2^N calls.

This commit is essentially NFC, apart from the performance improvements
and the removal of (probably irrelevant) duplicate entries from the
return value of `getTaintedSymbols()` calls.

Fixes #89045

(cherry picked from commit ce763bff081f8e97c7c3610ed0f15f14d60e875f)
---

diff --git a/clang/lib/StaticAnalyzer/Checkers/Taint.cpp b/clang/lib/StaticAnalyzer/Checkers/Taint.cpp
index 4edb671753bf..6362c82b009d 100644
--- a/clang/lib/StaticAnalyzer/Checkers/Taint.cpp
+++ b/clang/lib/StaticAnalyzer/Checkers/Taint.cpp
@@ -216,21 +216,17 @@ std::vector<SymbolRef> taint::getTaintedSymbolsImpl(ProgramStateRef State,
   std::vector<SymbolRef> TaintedSymbols;
   if (!Reg)
     return TaintedSymbols;
-  // Element region (array element) is tainted if either the base or the offset
-  // are tainted.
+
+  // Element region (array element) is tainted if the offset is tainted.
   if (const ElementRegion *ER = dyn_cast<ElementRegion>(Reg)) {
     std::vector<SymbolRef> TaintedIndex =
         getTaintedSymbolsImpl(State, ER->getIndex(), K, returnFirstOnly);
     llvm::append_range(TaintedSymbols, TaintedIndex);
     if (returnFirstOnly && !TaintedSymbols.empty())
       return TaintedSymbols; // return early if needed
-    std::vector<SymbolRef> TaintedSuperRegion =
-        getTaintedSymbolsImpl(State, ER->getSuperRegion(), K, returnFirstOnly);
-    llvm::append_range(TaintedSymbols, TaintedSuperRegion);
-    if (returnFirstOnly && !TaintedSymbols.empty())
-      return TaintedSymbols; // return early if needed
   }
 
+  // Symbolic region is tainted if the corresponding symbol is tainted.
   if (const SymbolicRegion *SR = dyn_cast<SymbolicRegion>(Reg)) {
     std::vector<SymbolRef> TaintedRegions =
         getTaintedSymbolsImpl(State, SR->getSymbol(), K, returnFirstOnly);
@@ -239,6 +235,8 @@ std::vector<SymbolRef> taint::getTaintedSymbolsImpl(ProgramStateRef State,
       return TaintedSymbols; // return early if needed
   }
 
+  // Any subregion (including Element and Symbolic regions) is tainted if its
+  // super-region is tainted.
   if (const SubRegion *ER = dyn_cast<SubRegion>(Reg)) {
     std::vector<SymbolRef> TaintedSubRegions =
         getTaintedSymbolsImpl(State, ER->getSuperRegion(), K, returnFirstOnly);
@@ -318,4 +316,4 @@ std::vector<SymbolRef> taint::getTaintedSymbolsImpl(ProgramStateRef State,
     }
   }
   return TaintedSymbols;
-}
\ No newline at end of file
+}