summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authordim <dim@FreeBSD.org>2013-11-21 23:09:07 +0000
committerdim <dim@FreeBSD.org>2013-11-21 23:09:07 +0000
commit15069c877cd7d53a245e0b37701d29dbaea64996 (patch)
treecce6e563cf584684a353855162fb2c5ac41a68e2
parent305492af4723b9c7a9118c02471b58651d2ec999 (diff)
downloadFreeBSD-src-15069c877cd7d53a245e0b37701d29dbaea64996.zip
FreeBSD-src-15069c877cd7d53a245e0b37701d29dbaea64996.tar.gz
Pull in r195318 from upstream llvm trunk:
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. This fixes problems with loading X.org driver modules, which could occur when X.org was compiled on i386 with tailcall optimization on, for which ports r312583 was committed as a workaround. After this change, the workaround can be removed. MFC after: 3 days
-rw-r--r--contrib/llvm/lib/Target/X86/X86ISelLowering.cpp22
1 files changed, 8 insertions, 14 deletions
diff --git a/contrib/llvm/lib/Target/X86/X86ISelLowering.cpp b/contrib/llvm/lib/Target/X86/X86ISelLowering.cpp
index c3e69e0..1080925 100644
--- a/contrib/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/contrib/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -2449,21 +2449,15 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
RegsToPass.push_back(std::make_pair(unsigned(X86::EBX),
DAG.getNode(X86ISD::GlobalBaseReg, DebugLoc(), 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;
}
}
OpenPOWER on IntegriCloud