aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/X86/X86ISelLowering.cpp
diff options
context:
space:
mode:
authorBill Wendling <isanbard@gmail.com>2013-11-21 07:05:41 +0000
committerBill Wendling <isanbard@gmail.com>2013-11-21 07:05:41 +0000
commit8ae03404a3a38e34474d29f20bf5cd6b7088ada8 (patch)
treeb3996260c849cd4bd838580c871ef32621e73bd8 /lib/Target/X86/X86ISelLowering.cpp
parent3099edd7304fb1b7e1a3a72bcfb466dbeb5b72fd (diff)
downloadexternal_llvm-8ae03404a3a38e34474d29f20bf5cd6b7088ada8.zip
external_llvm-8ae03404a3a38e34474d29f20bf5cd6b7088ada8.tar.gz
external_llvm-8ae03404a3a38e34474d29f20bf5cd6b7088ada8.tar.bz2
Merging r195318:
------------------------------------------------------------------------ r195318 | void | 2013-11-20 23:04:30 -0800 (Wed, 20 Nov 2013) | 29 lines The basic problem is that some mainstream programs cannot deal with the way clang optimizes tail calls, as in this example: int foo(void); int bar(void) { return foo(); } where the call is transformed to: calll .L0$pb .L0$pb: popl %eax .Ltmp0: addl $_GLOBAL_OFFSET_TABLE_+(.Ltmp0-.L0$pb), %eax movl foo@GOT(%eax), %eax popl %ebp jmpl *%eax # TAILCALL However, the GOT references must all be resolved at dlopen() time, and so this approach cannot be used with lazy dynamic linking (e.g. using RTLD_LAZY), which usually populates the PLT with stubs that perform the actual resolving. This patch changes X86TargetLowering::LowerCall() to skip tail call optimization, if the called function is a global or external symbol. Patch by Dimitry Andric! PR15086 ------------------------------------------------------------------------ git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_34@195319 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/X86/X86ISelLowering.cpp')
-rw-r--r--lib/Target/X86/X86ISelLowering.cpp22
1 files changed, 8 insertions, 14 deletions
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 9df0232..0deb181 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -2665,21 +2665,15 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
RegsToPass.push_back(std::make_pair(unsigned(X86::EBX),
DAG.getNode(X86ISD::GlobalBaseReg, SDLoc(), getPointerTy())));
} else {
- // If we are tail calling and generating PIC/GOT style code load the
- // address of the callee into ECX. The value in ecx is used as target of
- // the tail jump. This is done to circumvent the ebx/callee-saved problem
- // for tail calls on PIC/GOT architectures. Normally we would just put the
- // address of GOT into ebx and then call target@PLT. But for tail calls
- // ebx would be restored (since ebx is callee saved) before jumping to the
- // target@PLT.
-
- // Note: The actual moving to ECX is done further down.
+ // If we are tail calling a global or external symbol in GOT pic mode, we
+ // cannot use a direct jump, since that would make lazy dynamic linking
+ // impossible (see PR15086). So pretend this is not a tail call, to
+ // prevent the optimization to a jump.
GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee);
- if (G && !G->getGlobal()->hasHiddenVisibility() &&
- !G->getGlobal()->hasProtectedVisibility())
- Callee = LowerGlobalAddress(Callee, DAG);
- else if (isa<ExternalSymbolSDNode>(Callee))
- Callee = LowerExternalSymbol(Callee, DAG);
+ if ((G && !G->getGlobal()->hasHiddenVisibility() &&
+ !G->getGlobal()->hasProtectedVisibility()) ||
+ isa<ExternalSymbolSDNode>(Callee))
+ isTailCall = false;
}
}