diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 2a39c716c343603f11eea2ae2caa884dc061591f..bce879fb9afd88c6b659fbd18a4a2e0ecaf9da7f 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -332,6 +332,7 @@
 #define PPC_INST_BLR			0x4e800020
 #define PPC_INST_BLRL			0x4e800021
 #define PPC_INST_BCTR			0x4e800420
+#define PPC_INST_BCTRL			0x4e800421
 #define PPC_INST_MULLD			0x7c0001d2
 #define PPC_INST_MULLW			0x7c0001d6
 #define PPC_INST_MULHWU			0x7c000016
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 55e5f76554da63f9b5a655371b09539c26138800..97729642f9556a9e2984dd996079d999e4bf3b3f 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -39,8 +39,8 @@
 #define GP_REGS_SIZE	min(sizeof(elf_gregset_t), sizeof(struct pt_regs))
 #define FP_REGS_SIZE	sizeof(elf_fpregset_t)
 
-#define TRAMP_TRACEBACK	3
-#define TRAMP_SIZE	6
+#define TRAMP_TRACEBACK	4
+#define TRAMP_SIZE	7
 
 /*
  * When we have signals to deliver, we set up on the user stack,
@@ -600,13 +600,15 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp)
 	int i;
 	long err = 0;
 
+	/* bctrl # call the handler */
+	err |= __put_user(PPC_INST_BCTRL, &tramp[0]);
 	/* addi r1, r1, __SIGNAL_FRAMESIZE  # Pop the dummy stackframe */
 	err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) |
-			  (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]);
+			  (__SIGNAL_FRAMESIZE & 0xffff), &tramp[1]);
 	/* li r0, __NR_[rt_]sigreturn| */
-	err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]);
+	err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[2]);
 	/* sc */
-	err |= __put_user(PPC_INST_SC, &tramp[2]);
+	err |= __put_user(PPC_INST_SC, &tramp[3]);
 
 	/* Minimal traceback info */
 	for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++)
@@ -864,12 +866,12 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 
 	/* Set up to return from userspace. */
 	if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) {
-		regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
+		regs->nip = tsk->mm->context.vdso_base + vdso64_rt_sigtramp;
 	} else {
 		err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]);
 		if (err)
 			goto badframe;
-		regs->link = (unsigned long) &frame->tramp[0];
+		regs->nip = (unsigned long) &frame->tramp[0];
 	}
 
 	/* Allocate a dummy caller frame for the signal handler. */
@@ -878,8 +880,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 
 	/* Set up "regs" so we "return" to the signal handler. */
 	if (is_elf2_task()) {
-		regs->nip = (unsigned long) ksig->ka.sa.sa_handler;
-		regs->gpr[12] = regs->nip;
+		regs->ctr = (unsigned long) ksig->ka.sa.sa_handler;
+		regs->gpr[12] = regs->ctr;
 	} else {
 		/* Handler is *really* a pointer to the function descriptor for
 		 * the signal routine.  The first entry in the function
@@ -889,7 +891,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set,
 		func_descr_t __user *funct_desc_ptr =
 			(func_descr_t __user *) ksig->ka.sa.sa_handler;
 
-		err |= get_user(regs->nip, &funct_desc_ptr->entry);
+		err |= get_user(regs->ctr, &funct_desc_ptr->entry);
 		err |= get_user(regs->gpr[2], &funct_desc_ptr->toc);
 	}
 
diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S
index a8cc0409d7d25aa2c0a473d472b51f89fdbcc104..bbf68cd01088b5ab04092c099c922709c44eef1f 100644
--- a/arch/powerpc/kernel/vdso64/sigtramp.S
+++ b/arch/powerpc/kernel/vdso64/sigtramp.S
@@ -6,6 +6,7 @@
  * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp.
  * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp.
  */
+#include <asm/cache.h>		/* IFETCH_ALIGN_BYTES */
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/unistd.h>
@@ -14,21 +15,17 @@
 
 	.text
 
-/* The nop here is a hack.  The dwarf2 unwind routines subtract 1 from
-   the return address to get an address in the middle of the presumed
-   call instruction.  Since we don't have a call here, we artificially
-   extend the range covered by the unwind info by padding before the
-   real start.  */
-	nop
 	.balign 8
+	.balign IFETCH_ALIGN_BYTES
 V_FUNCTION_BEGIN(__kernel_sigtramp_rt64)
-.Lsigrt_start = . - 4
+.Lsigrt_start:
+	bctrl	/* call the handler */
 	addi	r1, r1, __SIGNAL_FRAMESIZE
 	li	r0,__NR_rt_sigreturn
 	sc
 .Lsigrt_end:
 V_FUNCTION_END(__kernel_sigtramp_rt64)
-/* The ".balign 8" above and the following zeros mimic the old stack
+/* The .balign 8 above and the following zeros mimic the old stack
    trampoline layout.  The last magic value is the ucontext pointer,
    chosen in such a way that older libgcc unwind code returns a zero
    for a sigcontext pointer.  */