Add call sequence start and end for __tls_get_addr

[timshen]

Summary

This is a fix for bug http://llvm.org/bugs/show_bug.cgi?id=25839.

For a PIC TLS variable access in a function, prologue (mflr followed by std and stdu) gets scheduled after a tls_get_addr call. tls_get_addr messed up LR but no one saves/restores it.

Also added a test for save/restore clobbered registers during calling __tls_get_addr.

[timshen]

Ping?

[kbarton]

It's a minor nit, but I think it's good to include a general description of the problem in the summary (or at least a link to the bugzilla report).

[kbarton]

LGTM.

[timshen]

Thanks iteratee for committing as r257137 !

lib/Target/PowerPC/PPCTLSDynamicCall.cpp

bool processBlock(MachineBasicBlock &MBB) {
           Opc2 = PPC::GETtlsADDR32;
           break;
         case PPC::ADDItlsldLADDR32:
           Opc1 = PPC::ADDItlsldL32;
           Opc2 = PPC::GETtlsldADDR32;
           break;
         }
 
+        // Don't really need to save data to the stack - the clobbered
+        // registers are already saved when the SDNode (e.g. PPCaddiTlsgdLAddr)
+        // gets translated to the pseudo instruction (e.g. ADDItlsgdLADDR).
+        BuildMI(MBB, I, DL, TII->get(PPC::ADJCALLSTACKDOWN)).addImm(0);
+
         // Expand into two ops built prior to the existing instruction.
         MachineInstr *Addi = BuildMI(MBB, I, DL, TII->get(Opc1), GPR3)
           .addReg(InReg);
         Addi->addOperand(MI->getOperand(2));
 
         // The ADDItls* instruction is the first instruction in the
         // repair range.
         MachineBasicBlock::iterator First = I;
         --First;
 
         MachineInstr *Call = (BuildMI(MBB, I, DL, TII->get(Opc2), GPR3)
                               .addReg(GPR3));
         Call->addOperand(MI->getOperand(3));
 
+        BuildMI(MBB, I, DL, TII->get(PPC::ADJCALLSTACKUP)).addImm(0).addImm(0);
+
         BuildMI(MBB, I, DL, TII->get(TargetOpcode::COPY), OutReg)
           .addReg(GPR3);
 
         // The COPY is the last instruction in the repair range.
         MachineBasicBlock::iterator Last = I;
         --Last;
 
         // Move past the original instruction and remove it.

test/CodeGen/PowerPC/tls_get_addr_clobbers.ll

+; RUN: llc -mtriple="powerpc64le-unknown-linux-gnu" -relocation-model=pic < %s | FileCheck %s
+
+@a = thread_local global i32* null, align 8
+
+define void @test_foo(i32* nocapture %x01, i32* nocapture %x02, i32* nocapture %x03, i32* nocapture %x04, i32* nocapture %x05, i32* nocapture %x06, i32* nocapture %x07, i32* nocapture %x08) #0 {
+entry:
+
+; CHECK-LABEL: test_foo:
+; CHECK: stdu 1, {{-?[0-9]+}}(1)
+; CHECK-DAG: mr [[BACKUP_3:[0-9]+]], 3
+; CHECK-DAG: mr [[BACKUP_4:[0-9]+]], 4
+; CHECK-DAG: mr [[BACKUP_5:[0-9]+]], 5
+; CHECK-DAG: mr [[BACKUP_6:[0-9]+]], 6
+; CHECK-DAG: mr [[BACKUP_7:[0-9]+]], 7
+; CHECK-DAG: mr [[BACKUP_8:[0-9]+]], 8
+; CHECK-DAG: mr [[BACKUP_9:[0-9]+]], 9
+; CHECK-DAG: mr [[BACKUP_10:[0-9]+]], 10
+; CHECK-DAG: std [[BACKUP_3]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_4]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_5]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_6]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_7]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_8]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_9]], {{[0-9]+}}(1)
+; CHECK-DAG: std [[BACKUP_10]], {{[0-9]+}}(1)
+; CHECK: bl __tls_get_addr
+; CHECK-DAG: stw 3, 0([[BACKUP_3]])
+; CHECK-DAG: stw 3, 0([[BACKUP_4]])
+; CHECK-DAG: stw 3, 0([[BACKUP_5]])
+; CHECK-DAG: stw 3, 0([[BACKUP_6]])
+; CHECK-DAG: stw 3, 0([[BACKUP_7]])
+; CHECK-DAG: stw 3, 0([[BACKUP_8]])
+; CHECK-DAG: stw 3, 0([[BACKUP_9]])
+; CHECK-DAG: stw 3, 0([[BACKUP_10]])
+; CHECK: blr
+
+  %0 = load i32*, i32** @a, align 8
+  %cmp = icmp eq i32* %0, null
+  br i1 %cmp, label %return, label %if.end
+
+if.end:                                           ; preds = %entry
+  store i32 0, i32* %x01, align 4
+  store i32 0, i32* %x02, align 4
+  store i32 0, i32* %x03, align 4
+  store i32 0, i32* %x04, align 4
+  store i32 0, i32* %x05, align 4
+  store i32 0, i32* %x06, align 4
+  store i32 0, i32* %x07, align 4
+  store i32 0, i32* %x08, align 4
+  br label %return
+
+return:                                           ; preds = %entry, %if.end
+  ret void
+}

test/CodeGen/PowerPC/tls_get_addr_stackframe.ll

+; RUN: llc -mtriple="powerpc64le-unknown-linux-gnu" -relocation-model=pic < %s | FileCheck %s
+; CHECK-LABEL: foo_test:
+; CHECK: mflr 0
+; CHECK: __tls_get_addr
+
+%struct1.2.41 = type { %struct2.0.39, %struct3.1.40, %struct1.2.41* }
+%struct2.0.39 = type { i64, i32, i32, i32, i32 }
+%struct3.1.40 = type { [160 x i8] }
+
+@tls_var = external thread_local global %struct1.2.41*, align 8
+
+define void @foo_test() {
+  %1 = load %struct1.2.41*, %struct1.2.41** @tls_var, align 8
+  br i1 undef, label %foo.exit, label %2
+
+; <label>:2                                       ; preds = %0
+  br i1 undef, label %foo.exit, label %3
+
+; <label>:3                                       ; preds = %2
+  %4 = getelementptr inbounds %struct1.2.41, %struct1.2.41* %1, i64 0, i32 0, i32 3
+  %5 = load i32, i32* %4, align 8
+  %6 = add nsw i32 %5, -1
+  %7 = icmp eq i32 %6, 0
+  br i1 %7, label %8, label %foo.exit
+
+; <label>:8                                       ; preds = %3
+  tail call void undef(%struct1.2.41* undef, %struct1.2.41* nonnull undef)
+  br label %foo.exit
+
+foo.exit:                                         ; preds = %8, %3, %2, %0
+  ret void
+}