george.burgess.iv created this revision.
george.burgess.iv added a reviewer: rsmith.
george.burgess.iv added a subscriber: cfe-commits.
This is the first in a two patch series aimed at adding the alloc_size
attribute to clang. This patch adds the alloc_size attribute, docs, and all of
the logic needed to handle it in ExprConstant. The only thing that's _really_
missing is our ability to handle non-const locals, because that's proving to be
a moderately interesting challenge. (Spoiler alert: that's basically the only
thing in patch #2)
There's also a restructuring of TryEvaluateBuiltinObjectSize thrown in, because
I felt like it was getting overly subtle. Hopefully the new version is
considerably easier to reason about. :)
— Implementation notes —
- With the restructuring of TryEvaluateBuiltinObjectSize, I was able to make
EM_DesignatorFold (now EM_OffsetFold) the only EvalMode we use in evaluating
__builtin_object_size.
- The InvalidBase functionality of LValues was further (ab)used to get
information to TryEvaluateBuiltinObjectSize. We know an LValue has been
initialized by an alloc_size function if the base is invalid and the base
itself is a CallExpr. This won’t conflict with current behavior, because (prior
to this patch) all invalid bases were MemberExprs.
- As said in the ExprConstant code, I’d love a less hand-wavy approach to
writing tryEvaluateLValueAsAllocSize.
http://reviews.llvm.org/D14274
Files:
include/clang/Basic/Attr.td
include/clang/Basic/AttrDocs.td
include/clang/Basic/DiagnosticSemaKinds.td
lib/AST/ExprConstant.cpp
lib/Sema/SemaDeclAttr.cpp
test/CodeGen/alloc-size.c
test/Sema/alloc-size.c
Index: test/Sema/alloc-size.c
===================================================================
--- /dev/null
+++ test/Sema/alloc-size.c
@@ -0,0 +1,23 @@
+// RUN: %clang_cc1 %s -verify
+
+void *fail1(int a) __attribute__((alloc_size)); //expected-error{{'alloc_size' attribute takes at least 1 argument}}
+void *fail2(int a) __attribute__((alloc_size())); //expected-error{{'alloc_size' attribute takes at least 1 argument}}
+
+void *fail3(int a) __attribute__((alloc_size(0))); //expected-error{{'alloc_size' attribute parameter 1 is out of bounds: can only be 1, since there is one parameter}}
+void *fail4(int a) __attribute__((alloc_size(2))); //expected-error{{'alloc_size' attribute parameter 1 is out of bounds: can only be 1, since there is one parameter}}
+
+void *fail5(int a, int b) __attribute__((alloc_size(0, 1))); //expected-error{{'alloc_size' attribute parameter 1 is out of bounds: must be between 1 and 2}}
+void *fail6(int a, int b) __attribute__((alloc_size(3, 1))); //expected-error{{'alloc_size' attribute parameter 1 is out of bounds: must be between 1 and 2}}
+
+void *fail7(int a, int b) __attribute__((alloc_size(1, 0))); //expected-error{{'alloc_size' attribute parameter 2 is out of bounds: must be between 1 and 2}}
+void *fail8(int a, int b) __attribute__((alloc_size(1, 3))); //expected-error{{'alloc_size' attribute parameter 2 is out of bounds: must be between 1 and 2}}
+
+int fail9(int a) __attribute__((alloc_size(1))); //expected-warning{{'alloc_size' attribute only applies to return values that are pointers}}
+
+int fail10 __attribute__((alloc_size(1))); //expected-warning{{'alloc_size' attribute only applies to functions}}
+
+void *fail11(void *a) __attribute__((alloc_size(1))); //expected-error{{'alloc_size' attribute only applies to integer arguments}}
+
+void *fail12(int a) __attribute__((alloc_size("abc"))); //expected-error{{'alloc_size' attribute requires parameter 1 to be an integer constant}}
+void *fail12(int a) __attribute__((alloc_size(1, "abc"))); //expected-error{{'alloc_size' attribute requires parameter 2 to be an integer constant}}
+void *fail13(int a) __attribute__((alloc_size(1U<<31))); //expected-error{{integer constant expression evaluates to value 2147483648 that cannot be represented in a 32-bit signed integer type}}
Index: test/CodeGen/alloc-size.c
===================================================================
--- /dev/null
+++ test/CodeGen/alloc-size.c
@@ -0,0 +1,263 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -emit-llvm %s -o - 2>&1 | FileCheck %s
+
+#define NULL ((void *)0)
+
+int gi;
+
+void *my_malloc(int size) __attribute__((alloc_size(1)));
+void *my_calloc(int elem_size, int num_elems) __attribute__((alloc_size(1, 2)));
+
+// CHECK-LABEL: @test1
+void test1() {
+ void *const vp = my_malloc(100);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(vp, 0);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(vp, 1);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(vp, 2);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(vp, 3);
+
+ void *const arr = my_calloc(100, 5);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(arr, 0);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(arr, 1);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(arr, 2);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(arr, 3);
+
+ // CHECK: store i32 100
+ gi = __builtin_object_size(my_malloc(100), 0);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(my_malloc(100), 1);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(my_malloc(100), 2);
+ // CHECK: store i32 100
+ gi = __builtin_object_size(my_malloc(100), 3);
+
+ // CHECK: store i32 500
+ gi = __builtin_object_size(my_calloc(100, 5), 0);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(my_calloc(100, 5), 1);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(my_calloc(100, 5), 2);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(my_calloc(100, 5), 3);
+}
+
+// CHECK-LABEL: @test2
+void test2() {
+ void *const vp = my_malloc(gi);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 false)
+ gi = __builtin_object_size(vp, 0);
+
+ void *const arr1 = my_calloc(gi, 1);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 false)
+ gi = __builtin_object_size(arr1, 0);
+
+ void *const arr2 = my_calloc(1, gi);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 false)
+ gi = __builtin_object_size(arr2, 0);
+}
+
+// CHECK-LABEL: @test3
+void test3() {
+ char *const buf = (char *)my_calloc(100, 5);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(buf, 0);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(buf, 1);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(buf, 2);
+ // CHECK: store i32 500
+ gi = __builtin_object_size(buf, 3);
+}
+
+struct Data {
+ int a;
+ int t[10];
+ char pad[3];
+ char end[1];
+};
+
+// CHECK-LABEL: @test5
+void test5() {
+ struct Data *const data = my_malloc(sizeof(*data));
+ // CHECK: store i32 48
+ gi = __builtin_object_size(data, 0);
+ // CHECK: store i32 48
+ gi = __builtin_object_size(data, 1);
+ // CHECK: store i32 48
+ gi = __builtin_object_size(data, 2);
+ // CHECK: store i32 48
+ gi = __builtin_object_size(data, 3);
+
+ // CHECK: store i32 40
+ gi = __builtin_object_size(&data->t[1], 0);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&data->t[1], 1);
+ // CHECK: store i32 40
+ gi = __builtin_object_size(&data->t[1], 2);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&data->t[1], 3);
+
+ struct Data *const arr = my_calloc(sizeof(*data), 2);
+ // CHECK: store i32 96
+ gi = __builtin_object_size(arr, 0);
+ // CHECK: store i32 96
+ gi = __builtin_object_size(arr, 1);
+ // CHECK: store i32 96
+ gi = __builtin_object_size(arr, 2);
+ // CHECK: store i32 96
+ gi = __builtin_object_size(arr, 3);
+
+ // CHECK: store i32 88
+ gi = __builtin_object_size(&arr->t[1], 0);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&arr->t[1], 1);
+ // CHECK: store i32 88
+ gi = __builtin_object_size(&arr->t[1], 2);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&arr->t[1], 3);
+}
+
+// CHECK-LABEL: @test6
+void test6() {
+ // Things that would normally trigger conservative estimates don't need to do
+ // so when we know the source of the allocation.
+ struct Data *const data = my_malloc(sizeof(*data) + 10);
+ // CHECK: store i32 11
+ gi = __builtin_object_size(data->end, 0);
+ // CHECK: store i32 11
+ gi = __builtin_object_size(data->end, 1);
+ // CHECK: store i32 11
+ gi = __builtin_object_size(data->end, 2);
+ // CHECK: store i32 11
+ gi = __builtin_object_size(data->end, 3);
+
+ struct Data *const arr = my_calloc(sizeof(*arr) + 5, 3);
+ // It's unclear what the best path is here.
+ //
+ // First, if we're writing off the end and we're in an array, then the user's
+ // intent gets a lot less clear. Consider:
+ // struct Data { char end[1]; };
+ // struct Data *D = calloc(sizeof(*D) + 10, 2);
+ // __builtin_object_size(D[0]->end, 1);
+ // We can't reasonably determine whether the user will consider the 0th
+ // element of D to be at ((char*)D + sizeof(*D)), or ((char*)D + sizeof(*D)
+ // + 10).
+ //
+ // Next, many C users see this:
+ // struct Foo { /* [snip] */ };
+ // void *p = malloc(sizeof(struct Foo) * 100);
+ // memset(p, '\0', sizeof(struct Foo) * 100);
+ //
+ // ...As identical to this:
+ // struct Foo { /* [snip] */ };
+ // void *p = calloc(sizeof(struct Foo), 100);
+ //
+ // ...So acting differently in these cases may be confusing.
+ //
+ // Therefore, I think the best path is to treat them as identical, since we're
+ // guaranteed that the bytes, at the very least, exist, and there's no clear
+ // object boundaries to speak of. Note that all of this only applies if we've
+ // hit the special "we're trying to write off the end of an object" logic.
+
+ // CHECK: store i32 112
+ gi = __builtin_object_size(arr[0].end, 0);
+ // CHECK: store i32 112
+ gi = __builtin_object_size(arr[0].end, 1);
+ // CHECK: store i32 112
+ gi = __builtin_object_size(arr[0].end, 2);
+ // CHECK: store i32 112
+ gi = __builtin_object_size(arr[0].end, 3);
+
+ // CHECK: store i32 64
+ gi = __builtin_object_size(arr[1].end, 0);
+ // CHECK: store i32 64
+ gi = __builtin_object_size(arr[1].end, 1);
+ // CHECK: store i32 64
+ gi = __builtin_object_size(arr[1].end, 2);
+ // CHECK: store i32 64
+ gi = __builtin_object_size(arr[1].end, 3);
+
+ // CHECK: store i32 16
+ gi = __builtin_object_size(arr[2].end, 0);
+ // CHECK: store i32 16
+ gi = __builtin_object_size(arr[2].end, 1);
+ // CHECK: store i32 16
+ gi = __builtin_object_size(arr[2].end, 2);
+ // CHECK: store i32 16
+ gi = __builtin_object_size(arr[2].end, 3);
+}
+
+// CHECK-LABEL: @test7
+void test7() {
+ // Note: sizeof(struct Data) - 2*sizeof(int) == 40
+
+ // Chop the char arrays + final int of t[10] off the end.
+ struct Data *const data = my_malloc(sizeof(*data)-2*sizeof(int));
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&data->t[1], 0);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&data->t[1], 1);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&data->t[1], 2);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&data->t[1], 3);
+
+ // CHECK: store i32 0
+ gi = __builtin_object_size(data->pad, 0);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(data->pad, 1);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(data->pad, 2);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(data->pad, 3);
+
+ struct Data *const arr = my_calloc(sizeof(*data)-sizeof(int), 2);
+ // CHECK: store i32 80
+ gi = __builtin_object_size(&arr[0].t[1], 0);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&arr[0].t[1], 1);
+ // CHECK: store i32 80
+ gi = __builtin_object_size(&arr[0].t[1], 2);
+ // CHECK: store i32 36
+ gi = __builtin_object_size(&arr[0].t[1], 3);
+
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&arr[1].t[1], 0);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&arr[1].t[1], 1);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&arr[1].t[1], 2);
+ // CHECK: store i32 32
+ gi = __builtin_object_size(&arr[1].t[1], 3);
+
+ // CHECK: store i32 0
+ gi = __builtin_object_size(arr[1].pad, 0);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(arr[1].pad, 1);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(arr[1].pad, 2);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(arr[1].pad, 3);
+}
+
+// CHECK-LABEL: @test8
+void test8() {
+ // Non-const pointers aren't currently supported. They (hopefully) will be in
+ // the near future.
+ void *buf = my_calloc(100, 5);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 false)
+ gi = __builtin_object_size(buf, 0);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 false)
+ gi = __builtin_object_size(buf, 1);
+ // CHECK: call i64 @llvm.objectsize.i64.p0i8(i8* %{{.*}}, i1 true)
+ gi = __builtin_object_size(buf, 2);
+ // CHECK: store i32 0
+ gi = __builtin_object_size(buf, 3);
+}
Index: lib/Sema/SemaDeclAttr.cpp
===================================================================
--- lib/Sema/SemaDeclAttr.cpp
+++ lib/Sema/SemaDeclAttr.cpp
@@ -705,6 +705,98 @@
Attr.getAttributeSpellingListIndex()));
}
+/// Checks to be sure that the given parameter number is inbounds, and is an
+/// some integral type. Will emit appropriate diagnostics if this returns false.
+///
+/// FuncParamNo is expected to be from the user, so is base-1. AttrArgNo is used
+/// to actually retrieve the argument, so it's base-0.
+static bool checkParamIsIntegerType(Sema &S, const FunctionProtoType *FPT,
+ const AttributeList &Attr,
+ unsigned FuncParamNo, unsigned AttrArgNo) {
+ assert(Attr.getArg(AttrArgNo).is<Expr *>());
+ // FuncParamNo is base-1
+ if (FuncParamNo < 1 || FuncParamNo > FPT->getNumParams()) {
+ auto SrcLoc = Attr.getArgAsExpr(AttrArgNo)->getLocStart();
+ auto UserArgNo = AttrArgNo + 1;
+ S.Diag(SrcLoc, diag::err_attribute_argument_out_of_range)
+ << Attr.getName() << UserArgNo << FPT->getNumParams();
+ return false;
+ }
+
+ if (!FPT->getParamType(FuncParamNo - 1)->isIntegerType()) {
+ auto SrcLoc = Attr.getArgAsExpr(AttrArgNo)->getLocStart();
+ S.Diag(SrcLoc, diag::err_attribute_integers_only) << Attr.getName();
+ return false;
+ }
+ return true;
+}
+
+/// \brief Wrapper around checkUInt32Argument, with an extra check to be sure
+/// that the result will fit into a regular (signed) int. All args have the same
+/// purpose as they do in checkUInt32Argument.
+static bool checkPositiveIntArgument(Sema &S, const AttributeList &Attr,
+ const Expr *Expr, int &Val,
+ unsigned Idx = UINT_MAX) {
+ uint32_t UVal;
+ if (!checkUInt32Argument(S, Attr, Expr, UVal, Idx))
+ return false;
+
+ if (UVal > std::numeric_limits<int>::max()) {
+ llvm::APSInt I(32); // for toString
+ I = UVal;
+ S.Diag(Expr->getExprLoc(), diag::err_ice_too_large)
+ << I.toString(10, false) << 32 << /* Unsigned */ 0;
+ return false;
+ }
+
+ Val = (int)UVal;
+ return true;
+}
+
+static void handleAllocSizeAttr(Sema &S, Decl *D, const AttributeList &Attr) {
+ if (!checkAttributeAtLeastNumArgs(S, Attr, 1) ||
+ !checkAttributeAtMostNumArgs(S, Attr, 2))
+ return;
+
+ auto *FD = dyn_cast<FunctionDecl>(D);
+ if (FD == nullptr || !FD->hasPrototype()) {
+ S.Diag(Attr.getLoc(), diag::warn_attribute_wrong_decl_type)
+ << Attr.getName() << 4;
+ return;
+ }
+
+ auto *FPT = FD->getType()->castAs<FunctionProtoType>();
+ if (!FPT->getReturnType()->isPointerType()) {
+ S.Diag(Attr.getLoc(), diag::warn_attribute_return_pointers_only)
+ << Attr.getName();
+ return;
+ }
+
+ auto *SizeExpr = Attr.getArgAsExpr(0);
+ int SizeArgNo;
+ // Paramater indices are 1-based, hence Index=1
+ if (!checkPositiveIntArgument(S, Attr, SizeExpr, SizeArgNo, /*Index=*/1))
+ return;
+
+ if (!checkParamIsIntegerType(S, FPT, Attr, SizeArgNo, /*AttrArgNo=*/0))
+ return;
+
+ // Args are 1-based, so 0 implies that the arg was not present
+ int NumberArgNo = 0;
+ if (Attr.getNumArgs() == 2) {
+ auto *NumberExpr = Attr.getArgAsExpr(1);
+ // Paramater indices are 1-based, hence Index=2
+ if (!checkPositiveIntArgument(S, Attr, NumberExpr, NumberArgNo,
+ /*Index=*/2))
+ return;
+ if (!checkParamIsIntegerType(S, FPT, Attr, NumberArgNo, /*AttrArgNo=*/1))
+ return;
+ }
+
+ D->addAttr(::new (S.Context) AllocSizeAttr(
+ Attr.getRange(), S.Context, SizeArgNo, NumberArgNo,
+ Attr.getAttributeSpellingListIndex()));
+}
static bool checkTryLockFunAttrCommon(Sema &S, Decl *D,
const AttributeList &Attr,
@@ -4753,6 +4845,9 @@
case AttributeList::AT_AlignValue:
handleAlignValueAttr(S, D, Attr);
break;
+ case AttributeList::AT_AllocSize:
+ handleAllocSizeAttr(S, D, Attr);
+ break;
case AttributeList::AT_AlwaysInline:
handleAlwaysInlineAttr(S, D, Attr);
break;
Index: lib/AST/ExprConstant.cpp
===================================================================
--- lib/AST/ExprConstant.cpp
+++ lib/AST/ExprConstant.cpp
@@ -513,9 +513,14 @@
/// gets a chance to look at it.
EM_PotentialConstantExpressionUnevaluated,
- /// Evaluate as a constant expression. Continue evaluating if we find a
- /// MemberExpr with a base that can't be evaluated.
- EM_DesignatorFold,
+ /// Evaluate as a constant expression. Continue evaluating if either:
+ /// - We find a MemberExpr with a base that can't be evaluated.
+ /// - We find a variable initialized with a call to a function that has
+ /// the alloc_size attribute on it.
+ /// In either case, the LValue returned shall have an invalid base; in the
+ /// former, the base will be the invalid MemberExpr, in the latter, the
+ /// base will be the CallExpr.
+ EM_OffsetFold,
} EvalMode;
/// Are we checking whether the expression is a potential constant
@@ -618,7 +623,7 @@
case EM_PotentialConstantExpression:
case EM_ConstantExpressionUnevaluated:
case EM_PotentialConstantExpressionUnevaluated:
- case EM_DesignatorFold:
+ case EM_OffsetFold:
HasActiveDiagnostic = false;
return OptionalDiagnostic();
}
@@ -698,7 +703,7 @@
case EM_ConstantExpression:
case EM_ConstantExpressionUnevaluated:
case EM_ConstantFold:
- case EM_DesignatorFold:
+ case EM_OffsetFold:
return false;
}
llvm_unreachable("Missed EvalMode case");
@@ -727,14 +732,14 @@
case EM_ConstantExpressionUnevaluated:
case EM_ConstantFold:
case EM_IgnoreSideEffects:
- case EM_DesignatorFold:
+ case EM_OffsetFold:
return false;
}
llvm_unreachable("Missed EvalMode case");
}
bool allowInvalidBaseExpr() const {
- return EvalMode == EM_DesignatorFold;
+ return EvalMode == EM_OffsetFold;
}
};
@@ -771,11 +776,10 @@
struct FoldOffsetRAII {
EvalInfo &Info;
EvalInfo::EvaluationMode OldMode;
- explicit FoldOffsetRAII(EvalInfo &Info, bool Subobject)
+ explicit FoldOffsetRAII(EvalInfo &Info)
: Info(Info), OldMode(Info.EvalMode) {
if (!Info.checkingPotentialConstantExpression())
- Info.EvalMode = Subobject ? EvalInfo::EM_DesignatorFold
- : EvalInfo::EM_ConstantFold;
+ Info.EvalMode = EvalInfo::EM_OffsetFold;
}
~FoldOffsetRAII() { Info.EvalMode = OldMode; }
@@ -4824,6 +4828,129 @@
// Pointer Evaluation
//===----------------------------------------------------------------------===//
+static bool isCallToAllocSizeFunction(const CallExpr *E) {
+ auto *Callee = E->getDirectCallee();
+ return Callee != nullptr && Callee->hasAttr<AllocSizeAttr>();
+}
+
+static bool isBaseAnAllocSizeCall(const LValue &LVal) {
+ auto *Base = LVal.getLValueBase().dyn_cast<const Expr *>();
+ auto *CE = dyn_cast_or_null<CallExpr>(Base);
+ return CE != nullptr && isCallToAllocSizeFunction(CE);
+}
+
+static bool getNumBytesReturnedByAllocSizeFunction(const ASTContext &Ctx,
+ const LValue &LVal,
+ CharUnits &Result) {
+ assert(isBaseAnAllocSizeCall(LVal));
+ auto *Call = cast<CallExpr>(LVal.getLValueBase().get<const Expr *>());
+ auto *AllocSize = Call->getCalleeDecl()->getAttr<AllocSizeAttr>();
+
+ // alloc_size args are base-1, 0 means not present.
+ assert(AllocSize->getElemSizeParam() != 0);
+ unsigned SizeArgNo = AllocSize->getElemSizeParam() - 1;
+ unsigned BitsInSizeT = Ctx.getTypeSize(Ctx.getSizeType());
+ if (Call->getNumArgs() <= SizeArgNo)
+ return false;
+
+ APSInt SizeOfElem(/*BitWidth=*/BitsInSizeT, /*IsUnsigned=*/true);
+ if (!Call->getArg(SizeArgNo)->EvaluateAsInt(
+ SizeOfElem, Ctx, /*AllowSideEffects=*/Expr::SE_AllowSideEffects))
+ return false;
+
+ bool WasNumArgSpecified = AllocSize->getNumElemsParam() != 0;
+ if (!WasNumArgSpecified) {
+ Result = CharUnits::fromQuantity(SizeOfElem.getZExtValue());
+ return true;
+ }
+
+ APSInt NumberOfElems(/*BitWidth=*/BitsInSizeT, /*IsUnsigned=*/true);
+ // Argument numbers start at 1
+ unsigned NumArgNo = AllocSize->getNumElemsParam() - 1;
+ if (!Call->getArg(NumArgNo)->EvaluateAsInt(
+ NumberOfElems, Ctx, /*AllowSideEffects=*/Expr::SE_AllowSideEffects))
+ return false;
+
+ bool Overflow = false;
+ auto BytesAvailable = SizeOfElem.umul_ov(NumberOfElems, Overflow);
+ if (Overflow)
+ return false;
+
+ Result = CharUnits::fromQuantity(BytesAvailable.getZExtValue());
+ return true;
+}
+
+// Attempts to evaluate the given LValue as the result of a call to a function
+// with the alloc_size attribute on it. This is an extremely fun case, as it is
+// very different from many things we try to handle in ExprConstant (e.g. "we
+// know that this is a block of memory, but can make no guarantees about its
+// value"). Also, it requires a bit of whole-function static analysis, because
+// code like the following needs to be correctly handled:
+//
+// void foo() {
+// void *ptr = malloc(sizeof(int));
+// for (int i = 0; i < 2; i++) {
+// printf("%ld\n", __builtin_object_size(ptr, 0));
+// free(ptr);
+// ptr = malloc(sizeof(int) * 2);
+// }
+// }
+//
+// Where "correct", in our current implementation, means "fails".
+static bool tryEvaluateLValueAsAllocSize(const Expr *E, LValue &Result,
+ EvalInfo &Info) {
+ auto ExtractCallExpr = [&Info](const Expr *E) -> const CallExpr *{
+ // A *very* common idiom with e.g. malloc is:
+ // struct Foo *f = (struct Foo *)malloc(sizeof(*f));
+ // We want to succeed on the common case, so we ignore parens/implicit
+ // casts, and, if the function returns void*, a single cast of any kind.
+ auto *MaybeCast = E->IgnoreParenImpCasts();
+ // Ignore one explicit cast
+ auto *Explicit = dyn_cast<CastExpr>(MaybeCast);
+ if (Explicit == nullptr)
+ return dyn_cast<CallExpr>(MaybeCast);
+
+ const Expr *MaybeCall = Explicit->getSubExpr()->IgnoreParenImpCasts();
+ if (auto *Call = dyn_cast<CallExpr>(MaybeCall))
+ if (Call->getCallReturnType(Info.Ctx)->isVoidPointerType())
+ return Call;
+ return nullptr;
+ };
+
+ assert(E->isGLValue());
+ if (!Info.allowInvalidBaseExpr())
+ return false;
+
+ // We're specifically looking for a varaible initialized by a function with
+ // the alloc_size attribute. This requires a lot of guesswork and hand-waving.
+ // FIXME: Code-review note: I would *love* suggestions for a better way to do
+ // this.
+ auto *DRE = dyn_cast<DeclRefExpr>(E);
+ if (DRE == nullptr)
+ return false;
+
+ auto *VD = dyn_cast<VarDecl>(DRE->getDecl());
+ // Don't support parameters (they can be assigned without us knowing) or
+ // static variables (use-before-assign isn't UB)
+ if (VD == nullptr || !VD->isLocalVarDecl())
+ return false;
+
+ // We currently don't support non-constant variables.
+ if (!VD->getType().isConstQualified())
+ return false;
+
+ const Expr *Init = VD->getAnyInitializer();
+ if (Init == nullptr)
+ return false;
+
+ const CallExpr *Call = ExtractCallExpr(Init);
+ if (Call == nullptr || !isCallToAllocSizeFunction(Call))
+ return false;
+
+ Result.setInvalid(Call);
+ return true;
+}
+
namespace {
class PointerExprEvaluator
: public ExprEvaluatorBase<PointerExprEvaluator> {
@@ -5009,6 +5136,19 @@
case CK_FunctionToPointerDecay:
return EvaluateLValue(SubExpr, Result, Info);
+
+ case CK_LValueToRValue: {
+ LValue LVal;
+ if (!EvaluateLValue(E->getSubExpr(), LVal, Info))
+ return tryEvaluateLValueAsAllocSize(E->getSubExpr(), Result, Info);
+
+ APValue RVal;
+ // Note, we use the subexpression's type in order to retain cv-qualifiers.
+ if (!handleLValueToRValueConversion(Info, E, E->getSubExpr()->getType(),
+ LVal, RVal))
+ return tryEvaluateLValueAsAllocSize(E->getSubExpr(), Result, Info);
+ return Success(RVal, E);
+ }
}
return ExprEvaluatorBaseTy::VisitCastExpr(E);
@@ -5119,7 +5259,13 @@
return true;
}
default:
- return ExprEvaluatorBaseTy::VisitCallExpr(E);
+ if (ExprEvaluatorBaseTy::VisitCallExpr(E))
+ return true;
+ if (isCallToAllocSizeFunction(E)) {
+ Result.setInvalid(E);
+ return true;
+ }
+ return false;
}
}
@@ -6372,9 +6518,119 @@
return true;
auto *E = LVal.Base.dyn_cast<const Expr *>();
- (void)E;
- assert(E != nullptr && isa<MemberExpr>(E));
- return false;
+ return E == nullptr || !isa<MemberExpr>(E);
+}
+
+// Helper for TryEvaluateBuiltinObjectSize -- Given an LValue, this will
+// determine how many bytes exist from the beginning of the object to either the
+// end of the current subobject, or the end of the object itself, depending on
+// what the LValue looks like + the value of Type.
+static bool determineEndOffset(EvalInfo &Info, const CallExpr *E, unsigned Type,
+ const LValue &Base, CharUnits &Result) {
+ // In the case where we're not dealing with a subobject in the expression, we
+ // ignore the subobject bit.
+ bool SubobjectOnly = (Type & 1) != 0 && !refersToCompleteObject(Base);
+
+ CharUnits AllocSizeBytes;
+ bool IsAllocSizeBase = isBaseAnAllocSizeCall(Base);
+ if (IsAllocSizeBase)
+ if (!getNumBytesReturnedByAllocSizeFunction(Info.Ctx, Base, AllocSizeBytes))
+ return false;
+
+ // We want to evaluate the size of the entire object
+ if (!SubobjectOnly || Base.Designator.Invalid) {
+ if (IsAllocSizeBase) {
+ Result = AllocSizeBytes;
+ return true;
+ }
+
+ // If we can't find the designator and we need to give a lower-bound, then
+ // we can't do anything. If we need to give an upper-bound (i.e. Type==1),
+ // we can fall back to evaluating the full object later.
+ if (Base.Designator.Invalid && Type == 3) {
+ assert(SubobjectOnly);
+ return false;
+ }
+
+ if (Base.InvalidBase)
+ return false;
+
+ QualType BaseTy = getObjectType(Base.getLValueBase());
+ if (BaseTy.isNull())
+ return false;
+
+ return HandleSizeof(Info, E->getExprLoc(), BaseTy, Result);
+ }
+
+ // We want to evaluate the size of a subobject.
+ const auto &Designator = Base.Designator;
+
+ // The following is a moderately common idiom in C:
+ //
+ // struct Foo { int a; char c[1]; };
+ // struct Foo *F = (struct Foo *)malloc(sizeof(struct Foo) + strlen(Bar));
+ // strcpy(&F->c[0], Bar);
+ //
+ // So, if we see that we're examining a 1-length (or 0-length) array at the
+ // end of a struct with an unknown base, we'll either pretend we're
+ // evaluating a full object (this is fine because the designator is at the
+ // end), or we'll give up. If we can't determine how many bytes are available,
+ // then we need to give up if Type==1, because we can't correctly provide an
+ // upper bound. We can, however always, provide a lower bound of 1 for
+ // Type==3.
+ //
+ // Note that this may make our behavior a bit wonky when interacting with
+ // calloc and type=3. Consider:
+ // struct Data { int i; char chars[1]; };
+ // struct Data *D = calloc(sizeof(*D), 2);
+ // __builtin_object_size(D.chars, 3) == 9;
+ // There's a full argument for why this is the least-bad of all alternatives
+ // in test/CodeGen/alloc-size.c (test #6). I just wanted to note this locally.
+ if (Base.InvalidBase &&
+ Designator.Entries.size() == Designator.MostDerivedPathLength &&
+ Designator.MostDerivedIsArrayElement &&
+ Designator.MostDerivedArraySize < 2 &&
+ isDesignatorAtObjectEnd(Info.Ctx, Base)) {
+ if (IsAllocSizeBase) {
+ Result = AllocSizeBytes;
+ return true;
+ }
+ if (Type == 1)
+ return false;
+ // Type==3 uses the standard behavior if we don't have alloc_size.
+ }
+
+ CharUnits BytesPerElem;
+ if (!HandleSizeof(Info, E->getExprLoc(), Designator.MostDerivedType,
+ BytesPerElem))
+ return false;
+
+ // According to the GCC documentation, we want the size of the subobject
+ // denoted by the pointer. But that's not quite right -- what we actually
+ // want is the size of the immediately-enclosing array, if there is one.
+ int64_t ElemsRemaining = 1;
+ if (Designator.MostDerivedIsArrayElement &&
+ Designator.Entries.size() == Designator.MostDerivedPathLength)
+ ElemsRemaining =
+ Designator.MostDerivedArraySize - Designator.Entries.back().ArrayIndex;
+ else if (Designator.isOnePastTheEnd())
+ ElemsRemaining = 0;
+
+ if (ElemsRemaining <= 0) {
+ // We've gone passed the end -- pretend there were zero bytes.
+ Result = CharUnits::Zero();
+ return true;
+ }
+
+ CharUnits BytesRemainingInArray = BytesPerElem * ElemsRemaining;
+ CharUnits SubobjectBytes = Base.Offset + BytesRemainingInArray;
+ // We need to be correct even if the user allocates less bytes than the type
+ // requires.
+ if (IsAllocSizeBase)
+ Result = std::min(SubobjectBytes, AllocSizeBytes);
+ else
+ Result = SubobjectBytes;
+ return true;
}
bool IntExprEvaluator::TryEvaluateBuiltinObjectSize(const CallExpr *E,
@@ -6386,7 +6642,7 @@
// If there are any, but we can determine the pointed-to object anyway, then
// ignore the side-effects.
SpeculativeEvaluationRAII SpeculativeEval(Info);
- FoldOffsetRAII Fold(Info, Type & 1);
+ FoldOffsetRAII Fold(Info);
const Expr *Ptr = ignorePointerCastsAndParens(E->getArg(0));
if (!EvaluatePointer(Ptr, Base, Info))
return false;
@@ -6398,87 +6654,8 @@
if (BaseOffset.isNegative())
return Success(0, E);
- // In the case where we're not dealing with a subobject, we discard the
- // subobject bit.
- bool SubobjectOnly = (Type & 1) != 0 && !refersToCompleteObject(Base);
-
- // If Type & 1 is 0, we need to be able to statically guarantee that the bytes
- // exist. If we can't verify the base, then we can't do that.
- //
- // As a special case, we produce a valid object size for an unknown object
- // with a known designator if Type & 1 is 1. For instance:
- //
- // extern struct X { char buff[32]; int a, b, c; } *p;
- // int a = __builtin_object_size(p->buff + 4, 3); // returns 28
- // int b = __builtin_object_size(p->buff + 4, 2); // returns 0, not 40
- //
- // This matches GCC's behavior.
- if (Base.InvalidBase && !SubobjectOnly)
- return Error(E);
-
- // If we're not examining only the subobject, then we reset to a complete
- // object designator
- //
- // If Type is 1 and we've lost track of the subobject, just find the complete
- // object instead. (If Type is 3, that's not correct behavior and we should
- // return 0 instead.)
- LValue End = Base;
- if (!SubobjectOnly || (End.Designator.Invalid && Type == 1)) {
- QualType T = getObjectType(End.getLValueBase());
- if (T.isNull())
- End.Designator.setInvalid();
- else {
- End.Designator = SubobjectDesignator(T);
- End.Offset = CharUnits::Zero();
- }
- }
-
- // If it is not possible to determine which objects ptr points to at compile
- // time, __builtin_object_size should return (size_t) -1 for type 0 or 1
- // and (size_t) 0 for type 2 or 3.
- if (End.Designator.Invalid)
- return false;
-
- // According to the GCC documentation, we want the size of the subobject
- // denoted by the pointer. But that's not quite right -- what we actually
- // want is the size of the immediately-enclosing array, if there is one.
- int64_t AmountToAdd = 1;
- if (End.Designator.MostDerivedIsArrayElement &&
- End.Designator.Entries.size() == End.Designator.MostDerivedPathLength) {
- // We got a pointer to an array. Step to its end.
- AmountToAdd = End.Designator.MostDerivedArraySize -
- End.Designator.Entries.back().ArrayIndex;
- } else if (End.Designator.isOnePastTheEnd()) {
- // We're already pointing at the end of the object.
- AmountToAdd = 0;
- }
-
- QualType PointeeType = End.Designator.MostDerivedType;
- assert(!PointeeType.isNull());
- if (PointeeType->isIncompleteType() || PointeeType->isFunctionType())
- return Error(E);
-
- if (!HandleLValueArrayAdjustment(Info, E, End, End.Designator.MostDerivedType,
- AmountToAdd))
- return false;
-
- auto EndOffset = End.getLValueOffset();
-
- // The following is a moderately common idiom in C:
- //
- // struct Foo { int a; char c[1]; };
- // struct Foo *F = (struct Foo *)malloc(sizeof(struct Foo) + strlen(Bar));
- // strcpy(&F->c[0], Bar);
- //
- // So, if we see that we're examining a 1-length (or 0-length) array at the
- // end of a struct with an unknown base, we give up instead of breaking code
- // that behaves this way. Note that we only do this when Type=1, because
- // Type=3 is a lower bound, so answering conservatively is fine.
- if (End.InvalidBase && SubobjectOnly && Type == 1 &&
- End.Designator.Entries.size() == End.Designator.MostDerivedPathLength &&
- End.Designator.MostDerivedIsArrayElement &&
- End.Designator.MostDerivedArraySize < 2 &&
- isDesignatorAtObjectEnd(Info.Ctx, End))
+ CharUnits EndOffset;
+ if (!determineEndOffset(Info, E, Type, Base, EndOffset))
return false;
if (BaseOffset > EndOffset)
@@ -6517,7 +6694,7 @@
case EvalInfo::EM_ConstantFold:
case EvalInfo::EM_EvaluateForOverflow:
case EvalInfo::EM_IgnoreSideEffects:
- case EvalInfo::EM_DesignatorFold:
+ case EvalInfo::EM_OffsetFold:
// Leave it to IR generation.
return Error(E);
case EvalInfo::EM_ConstantExpressionUnevaluated:
Index: include/clang/Basic/DiagnosticSemaKinds.td
===================================================================
--- include/clang/Basic/DiagnosticSemaKinds.td
+++ include/clang/Basic/DiagnosticSemaKinds.td
@@ -2060,6 +2060,10 @@
"%0 attribute only applies to pointer arguments">,
InGroup<IgnoredAttributes>;
def err_attribute_pointers_only : Error<warn_attribute_pointers_only.Text>;
+def warn_attribute_integers_only : Warning<
+ "%0 attribute only applies to integer arguments">,
+ InGroup<IgnoredAttributes>;
+def err_attribute_integers_only : Error<warn_attribute_integers_only.Text>;
def warn_attribute_return_pointers_only : Warning<
"%0 attribute only applies to return values that are pointers">,
InGroup<IgnoredAttributes>;
Index: include/clang/Basic/AttrDocs.td
===================================================================
--- include/clang/Basic/AttrDocs.td
+++ include/clang/Basic/AttrDocs.td
@@ -178,6 +178,41 @@
}];
}
+def AllocSizeDocs : Documentation {
+ let Category = DocCatFunction;
+ let Content = [{
+.. Note:: This attribute is not yet fully functional. Specifically, it doesn't
+ yet work with non-const pointers. It is planned to support these in the near
+ future.
+
+The ``alloc_size`` attribute can be placed on functions that return pointers in
+order to hint to the compiler how many bytes of memory will be available at the
+the returned poiner. ``alloc_size`` takes one or two arguments.
+
+- ``alloc_size(N)`` implies that argument number N equals the number of
+ available bytes at the returned pointer.
+- ``alloc_size(N, M)`` implies that the product of argument number N and
+ argument number M equals the number of available bytes at the returned
+ pointer.
+
+Argument numbers are 1-based.
+
+An example of how to use ``alloc_size``
+
+.. code-block:: c
+
+ void *my_malloc(int a) __attribute__((alloc_size(1)));
+ void *my_calloc(int a, int b) __attribute__((alloc_size(1, 2)));
+
+ int main() {
+ void *const p = my_malloc(100);
+ assert(__builtin_object_size(p, 0) == 100);
+ void *const a = my_calloc(20, 5);
+ assert(__builtin_object_size(a, 0) == 100);
+ }
+ }];
+}
+
def EnableIfDocs : Documentation {
let Category = DocCatFunction;
let Content = [{
Index: include/clang/Basic/Attr.td
===================================================================
--- include/clang/Basic/Attr.td
+++ include/clang/Basic/Attr.td
@@ -709,6 +709,14 @@
let Documentation = [Undocumented];
}
+def AllocSize : InheritableAttr {
+ let Spellings = [GCC<"alloc_size">];
+ let Subjects = SubjectList<[Function]>;
+ let Args = [IntArgument<"ElemSizeParam">, IntArgument<"NumElemsParam", 1>];
+ let TemplateDependent = 1;
+ let Documentation = [AllocSizeDocs];
+}
+
def EnableIf : InheritableAttr {
let Spellings = [GNU<"enable_if">];
let Subjects = SubjectList<[Function]>;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
