Add a new function attribute, nonlazybind, which inhibits lazy-loading

optimizations when emitting calls to the function;  instead those calls may
use faster relocations which require the function to be immediately resolved
upon loading the dynamic object featuring the call.  This is useful when it
is known that the function will be called frequently and pervasively and
therefore there is no merit in delaying binding of the function.

Currently only implemented for x86-64, where it turns into a call through
the global offset table.

Patch by Dan Gohman, who assures me that he's going to add LangRef documentation
for this once it's committed.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133080 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 20 insertions, 0 deletions

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 294a6a7..1cdf2b6 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -2271,6 +2271,8 @@ X86TargetLowering::LowerCall(SDValue Chain, SDValue Callee,
     const GlobalValue *GV = G->getGlobal();
     if (!GV->hasDLLImportLinkage()) {
       unsigned char OpFlags = 0;
+      bool ExtraLoad = false;
+      unsigned WrapperKind = ISD::DELETED_NODE;
 
       // On ELF targets, in both X86-64 and X86-32 mode, direct calls to
       // external symbols most go through the PLT in PIC mode.  If the symbol
@@ -2288,10 +2290,28 @@ X86TargetLowering::LowerCall(SDValue Chain, SDValue Callee,
         // unless we're building with the leopard linker or later, which
         // automatically synthesizes these stubs.
         OpFlags = X86II::MO_DARWIN_STUB;
+      } else if (Subtarget->isPICStyleRIPRel() &&
+                 isa<Function>(GV) &&
+                 cast<Function>(GV)->hasFnAttr(Attribute::NonLazyBind)) {
+        // If the function is marked as non-lazy, generate an indirect call
+        // which loads from the GOT directly. This avoids runtime overhead
+        // at the cost of eager binding (and one extra byte of encoding).
+        OpFlags = X86II::MO_GOTPCREL;
+        WrapperKind = X86ISD::WrapperRIP;
+        ExtraLoad = true;
       }
 
       Callee = DAG.getTargetGlobalAddress(GV, dl, getPointerTy(),
                                           G->getOffset(), OpFlags);
+
+      // Add a wrapper if needed.
+      if (WrapperKind != ISD::DELETED_NODE)
+        Callee = DAG.getNode(X86ISD::WrapperRIP, dl, getPointerTy(), Callee);
+      // Add extra indirection if needed.
+      if (ExtraLoad)
+        Callee = DAG.getLoad(getPointerTy(), dl, DAG.getEntryNode(), Callee,
+                             MachinePointerInfo::getGOT(),
+                             false, false, 0);
     }
   } else if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee)) {
     unsigned char OpFlags = 0;