ASDenysPetrov updated this revision to Diff 388552.
ASDenysPetrov added a comment.
Rebased.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D103096/new/
https://reviews.llvm.org/D103096
Files:
clang/include/clang/StaticAnalyzer/Checkers/SValExplainer.h
clang/include/clang/StaticAnalyzer/Core/PathSensitive/SymExpr.h
clang/lib/StaticAnalyzer/Checkers/ExprInspectionChecker.cpp
clang/lib/StaticAnalyzer/Core/RangeConstraintManager.cpp
clang/lib/StaticAnalyzer/Core/SimpleSValBuilder.cpp
clang/lib/StaticAnalyzer/Core/SymbolManager.cpp
clang/test/Analysis/symbol-integral-cast.cpp
Index: clang/test/Analysis/symbol-integral-cast.cpp
===================================================================
--- /dev/null
+++ clang/test/Analysis/symbol-integral-cast.cpp
@@ -0,0 +1,374 @@
+// RUN: %clang_analyze_cc1 -analyzer-checker=debug.ExprInspection -analyzer-config eagerly-assume=false -analyzer-config support-symbolic-integer-casts=true -verify %s
+
+template <typename T>
+void clang_analyzer_eval(T);
+void clang_analyzer_warnIfReached();
+
+typedef short int16_t;
+typedef int int32_t;
+typedef unsigned short uint16_t;
+typedef unsigned int uint32_t;
+
+void test1(int x) {
+ // Even if two lower bytes of `x` equal to zero, it doesn't mean that
+ // the entire `x` is zero. We are not able to know the exact value of x.
+ // It can be one of 65536 possible values like [0, 65536, 131072, ...]
+ // and so on. To avoid huge range sets we still assume `x` in the range
+ // [INT_MIN, INT_MAX].
+ if (!(short)x) {
+ if (!x)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ }
+}
+
+void test2(int x) {
+ // If two lower bytes of `x` equal to zero, and we know x to be 65537,
+ // which is not truncated to short as zero. Thus the branch is infisible.
+ short s = x;
+ if (!s) {
+ if (x == 65537)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ }
+}
+
+void test3(int x, short s) {
+ s = x;
+ if ((short)x > -10 && s < 10) {
+ if (x > 0 && x < 10) {
+ // If the range of the whole variable was constrained then reason again
+ // about truncated bytes to make the ranges more precise.
+ clang_analyzer_eval((short)x <= 0); // expected-warning {{FALSE}}
+ }
+ }
+}
+
+void test4(unsigned x) {
+ if ((char)x > 8) {
+ // Constraint the range of the lowest byte of `x` to [9, CHAR_MAX].
+ // The original range of `x` still remains [0, UINT_MAX].
+ clang_analyzer_eval((char)x < 42); // expected-warning {{UNKNOWN}}
+ if (x < 42) {
+ // Constraint the original range to [0, 42] and update (re-constraint)
+ // the range of the lowest byte of 'x' to [9, 42].
+ clang_analyzer_eval((char)x < 42); // expected-warning {{TRUE}}
+ }
+ }
+}
+
+void test5(unsigned x) {
+ if ((char)x > -10 && (char)x < 10) {
+ if ((short)x == 8) {
+ // If the range of higher bytes(short) was constrained then reason again
+ // about smaller truncated ranges(char) to make it more precise.
+ clang_analyzer_eval((char)x == 8); // expected-warning {{TRUE}}
+ clang_analyzer_eval((short)x == 8); // expected-warning {{TRUE}}
+ // We still assume full version of `x` in the range [INT_MIN, INT_MAX].
+ clang_analyzer_eval(x == 8); // expected-warning {{UNKNOWN}}
+ }
+ }
+}
+
+void test6(int x) {
+ // Even if two lower bytes of `x` less than zero, it doesn't mean that `x`
+ // can't be greater than zero. Thence we don't change the native range of
+ // `x` and this branch is feasible.
+ if (x > 0)
+ if ((short)x < 0)
+ clang_analyzer_eval(x > 0); // expected-warning {{TRUE}}
+}
+
+void test7(int x) {
+ // The range of two lower bytes of `x` [1, SHORT_MAX] is enough to cover
+ // all possible values of char [CHAR_MIN, CHAR_MAX]. So the lowest byte
+ // can be lower than zero.
+ if ((short)x > 0) {
+ if ((char)x < 0)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ }
+}
+
+void test8(int x) {
+ // Promotion from `signed int` to `signed long long` also reasoning about the
+ // original range, because we know the fact that even after promotion it
+ // remains in the range [INT_MIN, INT_MAX].
+ if ((long long)x < 0)
+ clang_analyzer_eval(x < 0); // expected-warning {{TRUE}}
+}
+
+void test9(signed int x) {
+ // Any cast `signed` to `unsigned` produces an unsigned range, which is
+ // [0, UNSIGNED_MAX] and can not be lower than zero.
+ if ((unsigned long long)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ if ((unsigned int)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ if ((unsigned short)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ if ((unsigned char)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+}
+
+void test10(unsigned int x, signed char sc) {
+ // Promotion from `unsigned` to `signed` produces a signed range,
+ // which is able to cover all the values of the original,
+ // so that such cast is not lower than zero.
+ if ((signed long long)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ // Any other cast(conversion or truncation) from `unsigned` to `signed`
+ // produces a signed range, which is [SIGNED_MIN, SIGNED_MAX]
+ // and can be lower than zero.
+ if ((signed int)x < 0) // explicit cast
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ signed short ss = x; // initialization
+ if (ss < 0)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ sc = x; // assignment
+ if (sc < 0)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+}
+
+void test11(unsigned int x) {
+ // Promotion from 'unsigned' to 'signed' entirely covers the original range.
+ // Thence such cast is not lower than zero and the `true` branch is
+ // infiseable. But it doesn't affect the original range, which still remains
+ // as [0, UNSIGNED_MAX].
+ if ((signed long long)x < 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_eval(x < 0); // expected-warning {{FALSE}}
+
+ // Any other cast(conversion or truncation) from `unsigned` to `signed`
+ // produces a signed range, which is [SIGNED_MIN, SIGNED_MAX]. But it doesn't
+ // affect the original range, which still remains as [0, UNSIGNED_MAX].
+ if ((signed int)x < 0)
+ clang_analyzer_eval(x < 0); // expected-warning {{FALSE}}
+
+ if ((signed short)x < 0)
+ clang_analyzer_eval(x < 0); // expected-warning {{FALSE}}
+
+ if ((signed char)x < 0)
+ clang_analyzer_eval(x < 0); // expected-warning {{FALSE}}
+}
+
+void test12(int x, char c) {
+ if (x >= 5308) {
+ if (x <= 5419) {
+ // Truncation on assignment: int[5308, 5419] -> char[-68, 43]
+ c = x;
+ clang_analyzer_eval(-68 <= c && c <= 43); // expected-warning {{TRUE}}
+
+ if (c < 50)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+
+ // Truncation on initializaion: int[5308, 5419] -> char[-68, 43]
+ char c1 = x;
+ clang_analyzer_eval(-68 <= c1 && c1 <= 43); // expected-warning {{TRUE}}
+ }
+ }
+}
+
+void test13(int x) {
+ if (x > 913440767 && x < 913440769) { // 0x36720000
+
+ if ((short)x) // Truncation: int[913440768] -> short[0]
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+
+ if ((short)x != 0)
+ clang_analyzer_warnIfReached(); // no-warning
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ }
+}
+
+void test14(int x) {
+ if (x >= -1569193983 && x <= 578290016) {
+ // The big range of `x` covers all possible values of short.
+ // Truncation: int[-1569193983, 578290016] -> short[-32768, 32767]
+ if ((short)x > 0) {
+ clang_analyzer_eval(-1569193983 <= x && x <= 578290016); // expected-warning {{TRUE}}
+ short s = x;
+ clang_analyzer_eval(-32768 <= s && s <= 32767); // expected-warning {{TRUE}}
+ }
+ }
+}
+
+void test15(int x) {
+ if (x >= -1569193983 && x <= -1569193871) { // [0xA2780001, 0xA2780071]
+ // The small range of `x` covers only several values of short.
+ // Truncation: int[-1569193983, -1569193871] -> short[1, 113]
+ if ((short)x)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+
+ if ((short)x > 0)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+
+ if ((short)x < 114)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+ }
+}
+
+void test16(char x) {
+ if (x < 0)
+ clang_analyzer_eval(-128 <= x && x < 0); // expected-warning {{TRUE}}
+ else
+ clang_analyzer_eval(0 <= x && x <= 127); // expected-warning {{TRUE}}
+}
+
+void test17(char x) {
+ if (-11 <= x && x <= -10) {
+ unsigned u = x;
+ // Conversion: char[-11, -10] -> unsigned int[4294967285, 4294967286]
+ clang_analyzer_eval(4294967285 <= u && u <= 4294967286); // expected-warning {{TRUE}}
+ unsigned short us = x;
+ // Conversion: char[-11, -10] -> unsigned short[65525, 65526]
+ clang_analyzer_eval(65525 <= us && us <= 65526); // expected-warning {{TRUE}}
+ unsigned char uc = x;
+ // Conversion: char[-11, -10] -> unsigned char[245, 246]
+ clang_analyzer_eval(245 <= uc && uc <= 246); // expected-warning {{TRUE}}
+ }
+}
+
+void test18(char c, short s, int i) {
+ // Any char value always is less then 1000.
+ int OneThousand = 1000;
+ c = i;
+ if (c < OneThousand)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+
+ // Any short value always is greater then 40000.
+ int MinusFourtyThousands = -40000;
+ s = i;
+ if (s > MinusFourtyThousands)
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // no-warning
+}
+
+void test19(char x, short y) {
+ if (-43 <= x && x <= -42) { // x[-42, -43]
+ y = 42;
+ clang_analyzer_eval(int16_t(x) < int16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int16_t(x) < int32_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < int16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < int32_t(y)); // expected-warning {{TRUE}}
+
+ clang_analyzer_eval(int16_t(x) < uint16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int16_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(int32_t(x) < uint16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+
+ clang_analyzer_eval(uint16_t(x) < int16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint16_t(x) < int32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < int16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < int32_t(y)); // expected-warning {{FALSE}}
+
+ clang_analyzer_eval(uint16_t(x) < uint16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint16_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < uint16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ }
+}
+
+void test20(char x, short y) {
+ if (42 <= y && y <= 43) { // y[42, 43]
+ x = -42;
+ clang_analyzer_eval(int16_t(x) < int16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int16_t(x) < int32_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < int16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < int32_t(y)); // expected-warning {{TRUE}}
+
+ clang_analyzer_eval(int16_t(x) < uint16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int16_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(int32_t(x) < uint16_t(y)); // expected-warning {{TRUE}}
+ clang_analyzer_eval(int32_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+
+ clang_analyzer_eval(uint16_t(x) < int16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint16_t(x) < int32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < int16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < int32_t(y)); // expected-warning {{FALSE}}
+
+ clang_analyzer_eval(uint16_t(x) < uint16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint16_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < uint16_t(y)); // expected-warning {{FALSE}}
+ clang_analyzer_eval(uint32_t(x) < uint32_t(y)); // expected-warning {{FALSE}}
+ }
+}
+
+void test21(unsigned x) {
+ if (x > 42) {
+ // Unsigned range can generate two signed ranges.
+ // Conversion: unsigned[43, 4294967295] -> int[-2147483648, -1]U[43, 2147483647]
+ int i = x; // initialization
+ clang_analyzer_eval(-1 < i && i < 43); // expected-warning {{FALSE}}
+ }
+}
+
+void test22(int x, unsigned u) {
+ if (x > -42) {
+ // Signed range can generate two unsigned ranges.
+ // Conversion: int[-41, 2147483647] -> unsigned[0, 2147483647]U[4294967255, 4294967295]
+ u = x; // assignment
+ clang_analyzer_eval(2147483647 < u && u < 4294967255); // expected-warning {{FALSE}}
+ }
+}
+
+// PR51036
+void test23(signed char c) {
+ if ((unsigned int)c <= 200) {
+ // Conversion: char[0, 127] -> unsigned int[0, 127]
+ clang_analyzer_eval(0 <= c && c <= 127); // expected-warning {{TRUE}}
+ }
+}
+
+void test24(int x, int y) {
+ if (x == y) {
+ short s = x;
+ if (!s) {
+ if (y == 65537)
+ // FIXME: This should not warn. Support EquivalenceClasses.
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ else
+ clang_analyzer_warnIfReached(); // expected-warning {{REACHABLE}}
+ }
+ }
+}
Index: clang/lib/StaticAnalyzer/Core/SymbolManager.cpp
===================================================================
--- clang/lib/StaticAnalyzer/Core/SymbolManager.cpp
+++ clang/lib/StaticAnalyzer/Core/SymbolManager.cpp
@@ -543,3 +543,10 @@
return VarContext->isParentOf(CurrentContext);
}
+
+SymbolRef SymExpr::ignoreCasts() const {
+ SymbolRef Sym = this;
+ while (isa<SymbolCast>(Sym))
+ Sym = cast<SymbolCast>(Sym)->getOperand();
+ return Sym;
+}
Index: clang/lib/StaticAnalyzer/Core/SimpleSValBuilder.cpp
===================================================================
--- clang/lib/StaticAnalyzer/Core/SimpleSValBuilder.cpp
+++ clang/lib/StaticAnalyzer/Core/SimpleSValBuilder.cpp
@@ -532,8 +532,11 @@
// We only handle LHS as simple symbols or SymIntExprs.
SymbolRef Sym = lhs.castAs<nonloc::SymbolVal>().getSymbol();
+ // Unwrap SymbolCast trying to find SymIntExpr inside.
+ SymbolRef S = Sym->ignoreCasts();
+
// LHS is a symbolic expression.
- if (const SymIntExpr *symIntExpr = dyn_cast<SymIntExpr>(Sym)) {
+ if (const SymIntExpr *symIntExpr = dyn_cast<SymIntExpr>(S)) {
// Is this a logical not? (!x is represented as x == 0.)
if (op == BO_EQ && rhs.isZeroConstant()) {
Index: clang/lib/StaticAnalyzer/Core/RangeConstraintManager.cpp
===================================================================
--- clang/lib/StaticAnalyzer/Core/RangeConstraintManager.cpp
+++ clang/lib/StaticAnalyzer/Core/RangeConstraintManager.cpp
@@ -13,6 +13,7 @@
#include "clang/Basic/JsonSupport.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/APSIntType.h"
+#include "clang/StaticAnalyzer/Core/PathSensitive/AnalysisManager.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/ProgramState.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/ProgramStateTrait.h"
#include "clang/StaticAnalyzer/Core/PathSensitive/RangedConstraintManager.h"
@@ -20,8 +21,8 @@
#include "llvm/ADT/FoldingSet.h"
#include "llvm/ADT/ImmutableSet.h"
#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/StringExtras.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
@@ -1048,6 +1049,13 @@
return State->set<ConstraintRange>(Class, Constraint);
}
+LLVM_NODISCARD ProgramStateRef setConstraint(ProgramStateRef State,
+ SymbolRef Sym,
+ RangeSet Constraint) {
+ return State->set<ConstraintRange>(EquivalenceClass::find(State, Sym),
+ Constraint);
+}
+
LLVM_NODISCARD ProgramStateRef setConstraints(ProgramStateRef State,
ConstraintRangeTy Constraints) {
return State->set<ConstraintRange>(Constraints);
@@ -1179,6 +1187,60 @@
// Symbolic reasoning logic
//===----------------------------------------------------------------------===//
+/// This class is used for integral symbolic casts feature as a helper instance.
+///
+/// It represents a list of integral types of different sizes going in ascending
+/// order from 1 to 8 bytes. It aggregates several functions for convenience of
+/// usage. We can iterate through the types and find a type by size (bit width).
+///
+/// We use FOUR integer types: `int8`, `int16`, `int32`, `int64`, because we
+/// only support casts between types, which are lower or equal to 64-bit width.
+///
+/// We use these types for creating SymbolCast to find constraints in the
+/// constraint map. This allows to canonize a `key-value` to store and retrieve
+/// constraints instead of brute force.
+///
+/// We don't care about the type signedness. Signedness is just a way of bits
+/// representation. We just care about saving data. It's enough for us to store
+/// specific constraints for the type for a specific bit width. We never use
+/// retrieved constraint directly. We always use RangeSet::Factory::castTo to
+/// get ranges for a needed type (signed or unsigned) after retrieving.
+class NominalTypeList {
+ CanQualType Types[4];
+
+public:
+ using Iterator = CanQualType *;
+
+ void init(ASTContext &C) {
+ Types[0] = C.Char8Ty;
+ Types[1] = C.Char16Ty;
+ Types[2] = C.Char32Ty;
+ Types[3] = C.LongLongTy;
+ }
+ Iterator findByWidth(uint32_t Width) {
+ int index = 4;
+ switch (Width) {
+ case 8:
+ index = 0;
+ break;
+ case 16:
+ index = 1;
+ break;
+ case 32:
+ index = 2;
+ break;
+ case 64:
+ index = 3;
+ };
+ return Types + index;
+ }
+ Iterator begin() { return std::begin(Types); }
+ Iterator end() { return std::end(Types); }
+};
+
+// We should initialize NTL with `init` method before use.
+static NominalTypeList NTL;
+
/// A little component aggregating all of the reasoning we have about
/// the ranges of symbolic expressions.
///
@@ -1194,6 +1256,69 @@
return Inferrer.infer(Origin);
}
+ RangeSet VisitSymbolCast(const SymbolCast *Sym) {
+ AnalyzerOptions &Opts = State->getAnalysisManager().getAnalyzerOptions();
+ if (!Opts.ShouldSupportSymbolicIntegerCasts)
+ return VisitSymExpr(Sym);
+
+ // Unwrap symbol to get an underlying(root) symbol.
+ // Store every next type except the inner(original) one.
+ SmallVector<QualType, 2> Types;
+ uint32_t MinBitWidth = UINT32_MAX;
+ SymbolRef RootSym = Sym;
+ ASTContext &C = ValueFactory.getContext();
+ do {
+ // We only handle integral cast, when all the types are integrals.
+ // Otherwise, pass the given symbol to VisitSymExpr.
+ QualType T = RootSym->getType();
+ if (!T->isIntegralOrEnumerationType())
+ return VisitSymExpr(Sym);
+
+ MinBitWidth = std::min(MinBitWidth, C.getIntWidth(T));
+ Types.push_back(T);
+ RootSym = cast<SymbolCast>(RootSym)->getOperand();
+ } while (isa<SymbolCast>(RootSym));
+
+ QualType RootTy = RootSym->getType();
+ const uint32_t RootBitWidth = C.getIntWidth(RootTy);
+
+ // Check if we have any known truncated ranges of the root symbol.
+ // Truncated ranges usually are more precise then the original one.
+ // The more truncated is the range the more precise it should be.
+ // Example: Consider the given SymbolCast is (int8)(int64)(int16){int32 x}.
+ // `int8` - is the smallest type. Than the range will fit in it.
+ // Traverse through NTL types, that are smaller then the root type:
+ // [int8, int32).
+ const RangeSet *RSPtr = nullptr;
+ auto It = NTL.findByWidth(MinBitWidth);
+ auto E = NTL.findByWidth(RootBitWidth);
+ for (; !RSPtr && It < E; ++It) {
+ // Produce canonical symbols with the nominal type.
+ SymbolRef S =
+ State->getSymbolManager().getCastSymbol(RootSym, RootTy, *It);
+ // Find the first constraint and exit the loop.
+ RSPtr = getConstraint(State, S);
+ }
+ // If we didn't find any truncated ranges, look for the constraint for
+ // the root type.
+ // Example (cont.): Use the root symbol `{int32 x}`.
+ if (!RSPtr)
+ RSPtr = getConstraint(State, RootSym);
+ // If there's no existing range, create it based on the root type.
+ // Example (cont.): Make range based on `int32`.
+ RangeSet RS = RSPtr ? *RSPtr : infer(RootTy);
+
+ // Cast the range to the cast types from inner to outer one by one.
+ // Example (cont.): Go through 3 types from `int16` to `int8`.
+ auto TypesReversedRange = llvm::make_range(Types.rbegin(), Types.rend());
+ for (const QualType T : TypesReversedRange)
+ RS = RangeFactory.castTo(RS, T);
+
+ // Finally we got a range of Sym->getType() type.
+ // Example (cont.): Type of range is `int8`.
+ return RS;
+ }
+
RangeSet VisitSymExpr(SymbolRef Sym) {
// If we got to this function, the actual type of the symbolic
// expression is not supported for advanced inference.
@@ -1751,7 +1876,9 @@
class RangeConstraintManager : public RangedConstraintManager {
public:
RangeConstraintManager(ExprEngine *EE, SValBuilder &SVB)
- : RangedConstraintManager(EE, SVB), F(getBasicVals()) {}
+ : RangedConstraintManager(EE, SVB), F(getBasicVals()) {
+ NTL.init(SVB.getContext());
+ }
//===------------------------------------------------------------------===//
// Implementation for interface from ConstraintManager.
@@ -1862,7 +1989,7 @@
/// Derived class can control which types we handle by defining methods of the
/// following form:
///
-/// bool handle${SYMBOL}To${CONSTRAINT}(const SYMBOL *Sym,
+/// bool assign${SYMBOL}To${CONSTRAINT}(const SYMBOL *Sym,
/// CONSTRAINT Constraint);
///
/// where SYMBOL is the type of the symbol (e.g. SymSymExpr, SymbolCast, etc.)
@@ -1980,12 +2107,15 @@
}
inline bool assignSymExprToConst(const SymExpr *Sym, Const Constraint);
+ inline bool assignSymExprToRangeSet(const SymExpr *Sym, RangeSet Constraint);
inline bool assignSymIntExprToRangeSet(const SymIntExpr *Sym,
RangeSet Constraint) {
return handleRemainderOp(Sym, Constraint);
}
inline bool assignSymSymExprToRangeSet(const SymSymExpr *Sym,
RangeSet Constraint);
+ inline bool assignSymbolCastToRangeSet(const SymbolCast *Sym,
+ RangeSet Constraint);
private:
ConstraintAssignor(ProgramStateRef State, SValBuilder &Builder,
@@ -2058,8 +2188,8 @@
LLVM_NODISCARD Optional<bool> interpreteAsBool(RangeSet Constraint) {
assert(!Constraint.isEmpty() && "Empty ranges shouldn't get here");
- if (Constraint.getConcreteValue())
- return !Constraint.getConcreteValue()->isZero();
+ if (const llvm::APSInt *Int = Constraint.getConcreteValue())
+ return !Int->isZero();
if (!Constraint.containsZero())
return true;
@@ -2067,11 +2197,192 @@
return llvm::None;
}
+ void updateExistingConstraints(SymbolRef Sym, RangeSet R);
+ SymbolRef getProperSymbol(SymbolRef Sym);
+
ProgramStateRef State;
SValBuilder &Builder;
RangeSet::Factory &RangeFactory;
};
+//===----------------------------------------------------------------------===//
+// ConstraintAssignor implementation details
+//===----------------------------------------------------------------------===//
+
+bool ConstraintAssignor::assignSymExprToRangeSet(const SymExpr *Sym,
+ RangeSet Constraint) {
+ AnalyzerOptions &Opts = State->getAnalysisManager().getAnalyzerOptions();
+ if (Opts.ShouldSupportSymbolicIntegerCasts ||
+ !Sym->getType()->isIntegralOrEnumerationType()) {
+ updateExistingConstraints(Sym, Constraint);
+ if (!State)
+ return false;
+ }
+
+ // Next assignments is based on the fact that Constraint is a concrete value.
+ // Make sure of this.
+ if (!Constraint.getConcreteValue())
+ return true;
+
+ llvm::SmallSet<EquivalenceClass, 4> SimplifiedClasses;
+ // Iterate over all equivalence classes and try to simplify them.
+ ClassMembersTy Members = State->get<ClassMembers>();
+ for (std::pair<EquivalenceClass, SymbolSet> ClassToSymbolSet : Members) {
+ EquivalenceClass Class = ClassToSymbolSet.first;
+ State = EquivalenceClass::simplify(Builder, RangeFactory, State, Class);
+ if (!State)
+ return false;
+ SimplifiedClasses.insert(Class);
+ }
+
+ // Trivial equivalence classes (those that have only one symbol member) are
+ // not stored in the State. Thus, we must skim through the constraints as
+ // well. And we try to simplify symbols in the constraints.
+ ConstraintRangeTy Constraints = State->get<ConstraintRange>();
+ for (std::pair<EquivalenceClass, RangeSet> ClassConstraint : Constraints) {
+ EquivalenceClass Class = ClassConstraint.first;
+ if (SimplifiedClasses.count(Class)) // Already simplified.
+ continue;
+ State = EquivalenceClass::simplify(Builder, RangeFactory, State, Class);
+ if (!State)
+ return false;
+ }
+
+ return true;
+}
+
+bool ConstraintAssignor::assignSymbolCastToRangeSet(const SymbolCast *Sym,
+ RangeSet R) {
+ AnalyzerOptions &Opts = State->getAnalysisManager().getAnalyzerOptions();
+ // If symbol is not integral or the option is off, we need another handler.
+ if (!Opts.ShouldSupportSymbolicIntegerCasts ||
+ !Sym->getType()->isIntegralOrEnumerationType())
+ return false;
+
+ // If range is empty, the branch is infeasible.
+ if (R.isEmpty()) {
+ State = nullptr;
+ return false;
+ }
+
+ SymbolRef S = getProperSymbol(Sym);
+ // If symbol is not integral, we need another handler.
+ if (!S)
+ return true;
+
+ R = RangeFactory.castTo(R, S->getType());
+ updateExistingConstraints(S, R);
+ State = setConstraint(State, S, R);
+
+ return false;
+}
+
+/// Return a symbol which is the best canidate to save it in the constraint
+/// map. We should correct symbol because in case of truncation cast we can
+/// only reason about truncated bytes but not the whole value. E.g. (char)(int
+/// x), we can store constraints for the first lower byte but we still don't
+/// know the root value. Also in case of promotion or converion we should
+/// store the root value instead of cast symbol, because we can always get
+/// a correct range using `castTo` metho. And we are not intrested in any
+/// constraints of cast symbol but the root symbol in `if` expression
+/// or any bifurcation. We can return:
+/// - a new symbol based on the root, in case of a truncation,
+/// - a root symbol if it is not a truncation.
+///
+/// \param Sym -- a given symbol.
+/// \returns a corrected symbol based on a given one. Symbol is null if the
+/// given symbol is unsupported. We support only integral casts.
+SymbolRef ConstraintAssignor::getProperSymbol(SymbolRef Sym) {
+ // We don't need to do any extra work for non-SymbolCast's.
+ if (!isa<SymbolCast>(Sym))
+ return Sym;
+
+ // Extract a root symbol and compare it to outer types.
+ ASTContext &C = Builder.getContext();
+ SymbolRef RootSym = Sym;
+ // Get the root symbol.
+ uint32_t MinBitWidth = UINT32_MAX;
+ do {
+ // We only handle integral cast, when all the types are integrals.
+ // Return `None` in this particular case to notify user that we can not
+ // handle non-integral SymbolCast.
+ QualType T = RootSym->getType();
+ if (!T->isIntegralOrEnumerationType())
+ return nullptr;
+ MinBitWidth = std::min(MinBitWidth, C.getIntWidth(T));
+ RootSym = cast<SymbolCast>(RootSym)->getOperand();
+ } while (isa<SymbolCast>(RootSym));
+
+ // Check for trunation.
+ QualType RootTy = RootSym->getType();
+ uint32_t RootBitWidth = C.getIntWidth(RootTy);
+
+ const bool IsTruncated = (MinBitWidth < RootBitWidth);
+ if (IsTruncated) {
+ // Trancation occurred. High bits lost. We can't reason about ranges of
+ // the original(root) operand in this case, so we should not add it to the
+ // constraint map. Canonize Sym instead.
+ // We produce a new symbol using a NTL type equals to the smallest type of
+ // Sym. For instance:
+ // - (int)(uchar)x -> (char8)x
+ // - (long)(ushort)(short)x -> (char16)x
+
+ // Produce a new SymbolCast.
+ CanQualType Ty = *NTL.findByWidth(MinBitWidth);
+ RootSym = State->getSymbolManager().getCastSymbol(RootSym, RootTy, Ty);
+ }
+
+ return RootSym;
+}
+
+/// Update exsiting constraints for all truncated SymbolCasts based on the
+/// given symbol which types are less than the current one.
+/// For instance, for Sym:
+/// - {int8 x} update nothing;
+/// - {int16 x} update (int8)x;
+/// - {int32 x} update (int8)x, (int16)x;
+/// - {int64 x} update (int8)x, (int16)x, (int32)x.
+///
+/// FIXME: Update bigger casts. We only can reason about ranges of smaller
+/// types, because it would be too complicated to update, say, the entire
+/// `int` range if you only have knowledge that its lowest byte has been
+/// changed. So we don't touch bigger casts and they may be potentially
+/// invalid. For future, for:
+/// - {int8 x} update (int16)x, (int32)x, (int64)x;
+/// - {int16 x} update (int32)x, (int64)x;
+/// - {int32 x} update (int64)x;
+/// - {int64 x} update nothing.
+///
+/// \param State -- current program state.
+/// \param Sym -- a considered symbol.
+/// \param R -- a known range for the given symbol.
+/// \note: needs check of null state after use.
+void ConstraintAssignor::updateExistingConstraints(SymbolRef Sym, RangeSet R) {
+ unsigned SymBitWidth = Builder.getContext().getIntWidth(Sym->getType());
+ // Get a root symbol in case of SymbolCast.
+ Sym = Sym->ignoreCasts();
+ QualType SymTy = Sym->getType();
+ auto SmallerNTLTypes =
+ llvm::make_range(NTL.begin(), NTL.findByWidth(SymBitWidth));
+ SymbolManager &SM = State->getSymbolManager();
+ for (const QualType T : SmallerNTLTypes) {
+ // Use NTL typr to create canonical SymbolCast to find an existing
+ // constraint.
+ SymbolRef S = SM.getCastSymbol(Sym, SymTy, T);
+ // If such constraint is found, update it by intersecting.
+ if (const RangeSet *RS = getConstraint(State, S)) {
+ RangeSet TruncR = RangeFactory.castTo(R, T);
+ TruncR = RangeFactory.intersect(*RS, TruncR);
+ // If intersection is empty, then the branch is infisible.
+ if (TruncR.isEmpty()) {
+ State = nullptr;
+ break;
+ }
+ // Update the constraint.
+ State = setConstraint(State, S, TruncR);
+ }
+ }
+}
bool ConstraintAssignor::assignSymExprToConst(const SymExpr *Sym,
const llvm::APSInt &Constraint) {
Index: clang/lib/StaticAnalyzer/Checkers/ExprInspectionChecker.cpp
===================================================================
--- clang/lib/StaticAnalyzer/Checkers/ExprInspectionChecker.cpp
+++ clang/lib/StaticAnalyzer/Checkers/ExprInspectionChecker.cpp
@@ -418,6 +418,12 @@
ProgramStateRef State = C.getState();
+ // Unwrap symbolic expression to skip argument casts on function call.
+ // This is useful when there is no way for overloading function in C
+ // but we need to pass different types of arguments and
+ // implicit cast occures.
+ Sym = Sym->ignoreCasts();
+
C.addTransition(C.getState()->set<DenotedSymbols>(Sym, E));
}
Index: clang/include/clang/StaticAnalyzer/Core/PathSensitive/SymExpr.h
===================================================================
--- clang/include/clang/StaticAnalyzer/Core/PathSensitive/SymExpr.h
+++ clang/include/clang/StaticAnalyzer/Core/PathSensitive/SymExpr.h
@@ -62,6 +62,8 @@
virtual QualType getType() const = 0;
virtual void Profile(llvm::FoldingSetNodeID &profile) = 0;
+ const SymExpr *ignoreCasts() const;
+
/// Iterator over symbols that the current symbol depends on.
///
/// For SymbolData, it's the symbol itself; for expressions, it's the
Index: clang/include/clang/StaticAnalyzer/Checkers/SValExplainer.h
===================================================================
--- clang/include/clang/StaticAnalyzer/Checkers/SValExplainer.h
+++ clang/include/clang/StaticAnalyzer/Checkers/SValExplainer.h
@@ -135,8 +135,9 @@
" (" + Visit(S->getRHS()) + ")";
}
- // TODO: SymbolCast doesn't appear in practice.
- // Add the relevant code once it does.
+ std::string VisitSymbolCast(const SymbolCast *S) {
+ return "(" + S->getType().getAsString() + ")" + Visit(S->getOperand());
+ }
std::string VisitSymbolicRegion(const SymbolicRegion *R) {
// Explain 'this' object here.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
