which generates more efficient and more obviously conformant
code. We now test for overflow of the multiply then force
the result to -1 if so. On X86, this generates nice code
like this:
__Z4testl: ## @_Z4testl
## BB#0: ## %entry
subl $12, %esp
movl $4, %eax
mull 16(%esp)
testl %edx, %edx
movl $-1, %ecx
cmovel %eax, %ecx
movl %ecx, (%esp)
call __Znam
addl $12, %esp
ret
llvm-svn: 108927
causing clang to compile this code into something that correctly throws a
length error, fixing a potential integer overflow security attack:
void *test(long N) {
return new int[N];
}
int main() {
test(1L << 62);
}
We do this even when exceptions are disabled, because it is better for the
code to abort than for the attack to succeed.
This is heavily based on a patch that Fariborz wrote.
llvm-svn: 108915
mostly in avoiding unnecessary work at compile time but also in producing more
sensible block orderings.
Move the destructor cleanups for local variables over to use lazy cleanups.
Eventually all cleanups will do this; for now we have some awkward code
duplication.
Tell IR generation just to never produce landing pads in -fno-exceptions.
This is a much more comprehensive solution to a problem which previously was
half-solved by checks in most cleanup-generation spots.
llvm-svn: 108270
emit metadata associating allocas and global values with a Decl*. This feature
is controlled by an option that (intentionally) cannot be enabled on the command
line.
To use this feature, simply set
CodeGenOptions.EmitDeclMetadata = true;
and then interpret the completely underspecified metadata. :)
llvm-svn: 107739
self-host. Hopefully these results hold up on different platforms.
I tried to keep the GNU ObjC runtime happy, but it's hard for me to test.
Reimplement how clang generates IR for exceptions. Instead of creating new
invoke destinations which sequentially chain to the previous destination,
push a more semantic representation of *why* we need the cleanup/catch/filter
behavior, then collect that information into a single landing pad upon request.
Also reorganizes how normal cleanups (i.e. cleanups triggered by non-exceptional
control flow) are generated, since it's actually fairly closely tied in with
the former. Remove the need to track which cleanup scope a block is associated
with.
Document a lot of previously poorly-understood (by me, at least) behavior.
The new framework implements the Horrible Hack (tm), which requires every
landing pad to have a catch-all so that inlining will work. Clang no longer
requires the Horrible Hack just to make exceptions flow correctly within
a function, however. The HH is an unfortunate requirement of LLVM's EH IR.
llvm-svn: 107631
have CGF create and make accessible standard int32,int64 and
intptr types. This fixes a ton of 80 column violations
introduced by LLVMContextification and cleans up stuff a lot.
llvm-svn: 106977
load/store nonsense in the epilog. For example, for:
int foo(int X) {
int A[100];
return A[X];
}
we used to generate:
%arrayidx = getelementptr inbounds [100 x i32]* %A, i32 0, i64 %idxprom ; <i32*> [#uses=1]
%tmp1 = load i32* %arrayidx ; <i32> [#uses=1]
store i32 %tmp1, i32* %retval
%0 = load i32* %retval ; <i32> [#uses=1]
ret i32 %0
}
which codegen'd to this code:
_foo: ## @foo
## BB#0: ## %entry
subq $408, %rsp ## imm = 0x198
movl %edi, 400(%rsp)
movl 400(%rsp), %edi
movslq %edi, %rax
movl (%rsp,%rax,4), %edi
movl %edi, 404(%rsp)
movl 404(%rsp), %eax
addq $408, %rsp ## imm = 0x198
ret
Now we generate:
%arrayidx = getelementptr inbounds [100 x i32]* %A, i32 0, i64 %idxprom ; <i32*> [#uses=1]
%tmp1 = load i32* %arrayidx ; <i32> [#uses=1]
ret i32 %tmp1
}
and:
_foo: ## @foo
## BB#0: ## %entry
subq $408, %rsp ## imm = 0x198
movl %edi, 404(%rsp)
movl 404(%rsp), %edi
movslq %edi, %rax
movl (%rsp,%rax,4), %eax
addq $408, %rsp ## imm = 0x198
ret
This actually does matter, cutting out 2000 lines of IR from CGStmt.ll
for example.
Another interesting effect is that altivec.h functions which are dead
now get dce'd by the inliner. Hence all the changes to
builtins-ppc-altivec.c to ensure the calls aren't dead.
llvm-svn: 106970
variables within blocks. We loosely follow GCC's mangling, but since
these are always internal symbols the names don't really matter. I
intend to revisit block mangling later, because GCC's mangling is
rather verbose. <rdar://problem/8015719>.
llvm-svn: 104610
assignment operators.
Previously, Sema provided type-checking and template instantiation for
copy assignment operators, then CodeGen would synthesize the actual
body of the copy constructor. Unfortunately, the two were not in sync,
and CodeGen might pick a copy-assignment operator that is different
from what Sema chose, leading to strange failures, e.g., link-time
failures when CodeGen called a copy-assignment operator that was not
instantiation, run-time failures when copy-assignment operators were
overloaded for const/non-const references and the wrong one was
picked, and run-time failures when by-value copy-assignment operators
did not have their arguments properly copy-initialized.
This implementation synthesizes the implicitly-defined copy assignment
operator bodies in Sema, so that the resulting ASTs encode exactly
what CodeGen needs to do; there is no longer any special code in
CodeGen to synthesize copy-assignment operators. The synthesis of the
body is relatively simple, and we generate one of three different
kinds of copy statements for each base or member:
- For a class subobject, call the appropriate copy-assignment
operator, after overload resolution has determined what that is.
- For an array of scalar types or an array of class types that have
trivial copy assignment operators, construct a call to
__builtin_memcpy.
- For an array of class types with non-trivial copy assignment
operators, synthesize a (possibly nested!) for loop whose inner
statement calls the copy constructor.
- For a scalar type, use built-in assignment.
This patch fixes at least a few tests cases in Boost.Spirit that were
failing because CodeGen picked the wrong copy-assignment operator
(leading to link-time failures), and I suspect a number of undiagnosed
problems will also go away with this change.
Some of the diagnostics we had previously have gotten worse with this
change, since we're going through generic code for our
type-checking. I will improve this in a subsequent patch.
llvm-svn: 102853
This introduces FunctionType::ExtInfo to hold the calling convention and the
noreturn attribute. The next patch will extend it to include the regparm
attribute and fix the bug.
llvm-svn: 99920
fixing up a few callers that thought they were propagating NoReturn
information but were in fact saying something about exception
specifications.
llvm-svn: 96766
Fix some bugs with function-try-blocks and simplify normal try-block
code generation.
This implementation excludes a deleting destructor's call to
operator delete() from the function-try-block, which I believe
is correct but which I can't find straightforward support for at
a moment's glance.
llvm-svn: 96670
calling them as subroutines. This triggers whenever the alias optimization
doesn't, i.e. when the dtor has linkonce linkage or there are virtual bases
or it's the deleting dtor.
llvm-svn: 96605
repeatedly reloading from an alloca. We still need to create the alloca
for debug info purposes (although we currently create it in all cases
because of some abstraction boundaries that're hard to break down).
llvm-svn: 96403
At the moment the inlinehint attribute is ignored by the Inliner unless you
pass a -respect-inlinehint option. This will soon be the default.
The inlinehint attribute is set if the inline keyword is explicitly specified
on any declaration.
llvm-svn: 95623
follows (as conservatively as possible) gcc's current behavior: attributes
written on return types that don't apply there are applied to the function
instead, etc. Only parse CC attributes as type attributes, not as decl attributes;
don't accepet noreturn as a decl attribute on ValueDecls, either (it still
needs to apply to other decls, like blocks). Consistently consume CC/noreturn
information throughout codegen; enforce this by removing their default values
in CodeGenTypes::getFunctionInfo().
llvm-svn: 95436
"ASTContext::getTypeSize() / 8". Replace [u]int64_t variables with CharUnits
ones as appropriate.
Also rename RawType, fromRaw(), and getRaw() in CharUnits to QuantityType,
fromQuantity(), and getQuantity() for clarity.
llvm-svn: 93153
This implements a new flag -fcatch-undefined-behavior. The flag turns
on additional runtime checks for:
T a[I];
a[i] abort when i < 0 or i >= I.
Future stuff includes shifts by >= bitwidth amounts.
llvm-svn: 91198
directly into the sret pointer. This is an optimization in C, but is required
for correctness in C++ for classes with a non-trivial copy constructor.
llvm-svn: 90526
Highlights include:
Add a helper to generate __cxa_free_exception and _ZSt9terminatev.
Add a region to handle EH object deallocation for ctor failures for throw.
Add a terminate handler for __cxa_end_catch.
A framework for adding cleanup actions for the exceptional edges only.
llvm-svn: 90305
using the new LLVM support for this. This is temporarily hiding
behind horrible and ugly #ifdefs until the time when the optimizer
is stable (hopefully a week or so). Until then, lets make it "opt in" :)
llvm-svn: 85446
1. CGF now has fewer bytes of state (one pointer instead of a vector).
2. The generated code is determinstic, instead of getting labels in
'map order' based on pointer addresses.
3. Clang now emits one 'indirect goto switch' for each function, instead
of one for each indirect goto. This fixes an M*N = N^2 IR size issue
when there are lots of address-taken labels and lots of indirect gotos.
4. This also makes the default cause do something useful, reducing the
size of the jump table needed (by one).
llvm-svn: 83952
functions when they are explicitly declared, e.g., via a function
template specialization or explicit template instantiation
declaration. Don't try to synthesize bodies for the special member
functions in this case; rather, check whether we have an implicit
declaration and, if so, synthesize the appropriate function
body. Fixes PR5084.
llvm-svn: 83212
Several of the existing methods were identical to their respective
specializations, and so have been removed entirely. Several more 'leaf'
optimizations were introduced.
The getAsFoo() methods which imposed extra conditions, like
getAsObjCInterfacePointerType(), have been left in place.
llvm-svn: 82501
consistent model for handling size expressions for VLAs.
The model is essentially as follows: VLA types own their associated
expression. In some cases, we need to create multiple VLA types to
represent a given VLA (for canonical types, or qualifiers on array types,
or type merging). If we need to create multiple types based off of
the same VLA declaration, we use the new refcounting functionality so they can
all own the expression. The VLASizeMap in CodeGenFunction then uses the size
expression to identify the group of VLA types based off of the same original
declaration.
I'm not particularly attached to the VLA types owning the expression,
but we're stuck with at least until someone comes up with a way
to walk the VLA expressions for a declaration.
I did the parallel fix in ASTContext for DependentSizedArrayType, but I
haven't really looked closely at it, so there might still be issues
there.
I'll clean up the code duplication in ASTContext in a followup commit.
llvm-svn: 79071
Type::getAsReferenceType() -> Type::getAs<ReferenceType>()
Type::getAsRecordType() -> Type::getAs<RecordType>()
Type::getAsPointerType() -> Type::getAs<PointerType>()
Type::getAsBlockPointerType() -> Type::getAs<BlockPointerType>()
Type::getAsLValueReferenceType() -> Type::getAs<LValueReferenceType>()
Type::getAsRValueReferenceType() -> Type::getAs<RValueReferenceType>()
Type::getAsMemberPointerType() -> Type::getAs<MemberPointerType>()
Type::getAsReferenceType() -> Type::getAs<ReferenceType>()
Type::getAsTagType() -> Type::getAs<TagType>()
And remove Type::getAsReferenceType(), etc.
This change is similar to one I made a couple weeks ago, but that was partly
reverted pending some additional design discussion. With Doug's pending smart
pointer changes for Types, it seemed natural to take this approach.
llvm-svn: 77510
- Emit variable declarations as "simple", we want to avoid forcing the creation
of a dummy basic block, but still need to make the variable available for
later use.
- With that, we can now skip IRgen for other unreachable statements (which
don't define a label).
- Anders, I added two fixmes on calls to EmitVLASize, can you check them?
llvm-svn: 76361
until Doug Gregor's Type smart pointer code lands (or more discussion occurs).
These methods just call the new Type::getAs<XXX> methods, so we still have
reduced implementation redundancy. Having explicit getAsXXXType() methods makes
it easier to set breakpoints in the debugger.
llvm-svn: 76193
This method is intended to eventually replace the individual
Type::getAsXXXType<> methods.
The motivation behind this change is twofold:
1) Reduce redundant implementations of Type::getAsXXXType() methods. Most of
them are basically copy-and-paste.
2) By centralizing the implementation of the getAs<Type> logic we can more
smoothly move over to Doug Gregor's proposed canonical type smart pointer
scheme.
Along with this patch:
a) Removed 'Type::getAsPointerType()'; now clients use getAs<PointerType>.
b) Removed 'Type::getAsBlockPointerTypE()'; now clients use getAs<BlockPointerType>.
llvm-svn: 76098
The implementations of these methods can Use Decl::getASTContext() to get the ASTContext.
This commit touches a lot of files since call sites for these methods are everywhere.
I used pre-tokenized "carbon.h" and "cocoa.h" headers to do some timings, and there was no real time difference between before the commit and after it.
llvm-svn: 74501
the type assigned by sema (and is visible with sizeof(__func__) for
example) has nothing to do with what codegen ends up producing.
We should eventually add a method on PredefinedExpr to handle this.
In the meantime, just set up some framework and add some fixme's.
llvm-svn: 69872
in cases like this:
typedef struct {
short instance;
char name[0];
} ATTR_LIST_ENTRY2;
void test() {
ATTR_LIST_ENTRY2 X = (ATTR_LIST_ENTRY2) { .instance = 7, };
}
While it is safe to emit them, it is pretty silly.
llvm-svn: 69687
lazy PCH deserialization. Propagate that argument wherever it needs to
be. No functionality change, except that I've tightened up a few PCH
tests in preparation.
llvm-svn: 69406
in release-assert builds. For automatic variables, explicitly set
a name with setName that does not make a temporary std::string.
This speeds up -emit-llvm-only -disable-free on PR3810 by 4.6%
llvm-svn: 67459
giving them rough classifications (normal types, never-canonical
types, always-dependent types, abstract type representations) and
making it far easier to make sure that we've hit all of the cases when
decoding types.
Switched some switch() statements on the type class over to using this
mechanism, and filtering out those things we don't care about. For
example, CodeGen should never see always-dependent or non-canonical
types, while debug info generation should never see always-dependent
types. More switch() statements on the type class need to be moved
over to using this approach, so that we'll get warnings when we add a
new type then fail to account for it somewhere in the compiler.
As part of this, some types have been renamed:
TypeOfExpr -> TypeOfExprType
FunctionTypeProto -> FunctionProtoType
FunctionTypeNoProto -> FunctionNoProtoType
There shouldn't be any functionality change...
llvm-svn: 65591
- For types whose native representation is a pointer.
- Use to replace ExprConstant.cpp:HasPointerEvalType,
CodeGenFunction::isObjCPointerType.
llvm-svn: 65569
ABI to the CodeGen library. Since C++ code-generation is so
incomplete, we can't exercise much of this mangling code. However, a
few smoke tests show that it's doing the same thing as GCC. When C++
codegen matures, we'll extend the ABI tester to verify name-mangling
as well, and complete the implementation here.
At this point, the major client of name mangling is in the uses of the
new "overloadable" attribute in C, which allows overloading. Any
"overloadable" function in C (or in an extern "C" block in C++) will
be mangled the same way that the corresponding C++ function would be
mangled.
llvm-svn: 64413
Emit the size even if the declared type is a variably modified type. This lets us handle
void f(int n) {
int (*a)[n];
printf("size: %d\n", sizeof(*a));
}
llvm-svn: 61285
assert if the name is not an identifier. Update callers to do the right
thing and avoid this method in unsafe cases. This also fixes an objc
warning that was missing a space, and migrates a couple more to taking
IdentifierInfo and QualTypes instead of std::strings.
llvm-svn: 59936
representing the names of declarations in the C family of
languages. DeclarationName is used in NamedDecl to store the name of
the declaration (naturally), and ObjCMethodDecl is now a NamedDecl.
llvm-svn: 59441
- Use dotted notation for blocks related to a particular statement
type.
- Use .end for landing pads.
No functionality change in NDEBUG mode. :)
llvm-svn: 59210
CodeGenFunction.cpp. Change VisitConditionalOperator to use
constant fold instead of codegen'ing a constant conditional.
Change ForStmt to use EmitBranchOnBoolExpr, this shrinks
expr.c very slightly to 40239 lines.
llvm-svn: 59113
- EmitStmt is no longer required to finish with a current insertion
point defined (i.e. it does not need to make dummy
blocks). Instead, it can clear the insertion point in the builder
which indicates that the current insertion point is unreachable.
- CodeGenFunction provides HaveInsertPoint and EnsureInsertPoint
which respectively test if there is an insert point and ensure an
insertion point exists (by making a dummy block).
- Clearly mark functions in CodeGenFunction which can be called with
no insertion point defined. Currently this is a limited set, and
EmitStmt simply EnsureInsertPoint()s before emitting subsequent IR.
Remove EmitDummyBlock, which is no longer needed. Clients who haven't
already cleared the insertion point (typically via EmitBranch) can do
so by hand.
Remove isDummyBlock, which has effectively been renamed to
HaveInsertPoint.
The main thrust of this change is that we no longer have create dummy
blocks just to destroy them a short time later in EmitBlock in the
common case that there is no unreachable code following something like
a goto.
Additionally, this means that we are not using the hokey condition in
isDummyBlock that a block without a name is a dummy block. Guess how
well that works when we never emit block names!
llvm-svn: 59089
the size of the -O0 output on some cases. For example, on expr.c from
176.gcc, it shrinks the .ll file from 43164 to 42835 lines, and removed
references to two external symbols.
llvm-svn: 59034
- Only supports simple assignment and atomic semantics are ignored.
- Not quite usable yet because the methods do not actually get added
to the class metadata.
- Added ObjCPropertyDecl::getSetterKind (one of Assign, Copy, Retain).
- Rearrange CodeGenFunction so synthesis can reuse function prolog /
epilog code.
llvm-svn: 55365
- Kill unnecessary #includes in .cpp files. This is an automatic
sweep so some things removed are actually used, but happen to be
included by a previous header. I tried to get rid of the obvious
examples and this was the easiest way to trim the #includes in one
fell swoop.
- We now return to regularly scheduled development.
llvm-svn: 54632
- Drop {Decl.h,DeclObjC.h,IdentifierTable.h} from Expr.h
- Moved Sema::getCurMethodDecl() out of line (dependent on
ObjCMethodDecl via dyn_cast).
llvm-svn: 54629
- Follows emission scheme used by llvm-gcc, i.e. invent an id for
each label whose address is taken and replace each indirect goto by
a switch to each possible target.
- Currently we emit a switch for each indirect goto instead of
merging them as llvm-gcc does.
llvm-svn: 54318
- No (intended) functionality change.
- Primary purpose is to clearly separate (lazy) construction of
globals that are a forward declaration or tentative definition from
those that are the final definition.
- Lazy construction is now encapsulated in
GetAddrOf{Function,GlobalVar} while final definitions are
constructed in EmitGlobal{Function,Var}Definition.
- External interface for dealing with globals is now limited to
EmitGlobal and GetAddrOf{Function,GlobalVar}.
- Also updated helper functions dealing with statics, annotations,
and ctors to be private.
llvm-svn: 54179
qualifier in the lvalue, and changes lvalue loads/stores to honor
the volatile flag. Places which need some further attention are marked
with FIXMEs.
Patch by Cédric Venet.
llvm-svn: 52264
much closer to passing the gcc struct layout tests.
It might be possible to refactor this a bit, but I'm not sure there's
actually enough common code for that to be useful.
To get the calling convention completely correct, a bit of
platform-specific code is necessary even for x86-Linux. On x86-Linux, the
alignment of function parameters is extremely strange; as far as I can tell,
it's always 4 except for SSE vectors or structs containing SSE vectors. I'm
continuing to investigate this.
llvm-svn: 51839
actually work (instead of crashing llc), and there's enough info emitted
to get line number information in gdb. This should hopefully be helpful
for debugging non-working programs.
I got rid of the begin/endregion calls because the implementation wasn't
working; someone who knows the debugging info a bit better might try to
add it. I really have no clue how a compiler is supposed to emit them.
This commit shouldn't have any effect without -g.
llvm-svn: 51404
lib/CodeGen/CGExpr.cpp and to change include/clang/AST/Attr.h to
use its own enum for visibility types instead of using
llvm::GlobalValue::VisibilityTypes. These changes eliminate
dependencies in the AST library on LLVM's VMCore library.
llvm-svn: 51398
This is a fairly mechanical/large change. As a result, I avoided making any changes/simplifications that weren't directly related. I did break two Analysis tests. I also have a couple FIXME's in UninitializedValues.cpp. Ted, can you take a look? If the bug isn't obvious, I am happy to dig in and fix it (since I broke it).
llvm-svn: 49748
remaining open issues I've communicated to him:
1) self can be assigned to, and his patch didn't handle it correctly.
2) CollectObjCIvarTypes is N^2 (because each subclass reprocesses
all parent class ivars) and flattens classes. If A derives from B,
and both have an int, I'd expect to get { {i32}, i32}, not { i32, i32}.
David, please review.
llvm-svn: 48970
lib dir and move all the libraries into it. This follows the main
llvm tree, and allows the libraries to be built in parallel. The
top level now enforces that all the libs are built before Driver,
but we don't care what order the libs are built in. This speeds
up parallel builds, particularly incremental ones.
llvm-svn: 48402
John McCall