22 files changed, 436 insertions, 237 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 2346d271fbfd..f3f5e2641432 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -12,6 +12,18 @@ CFLAGS_prom_init.o      += -fPIC
 CFLAGS_btext.o		+= -fPIC
 endif
 
+ifdef CONFIG_FTRACE
+# Do not trace early boot code
+CFLAGS_REMOVE_cputable.o = -pg
+CFLAGS_REMOVE_prom_init.o = -pg
+
+ifdef CONFIG_DYNAMIC_FTRACE
+# dynamic ftrace setup.
+CFLAGS_REMOVE_ftrace.o = -pg
+endif
+
+endif
+
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \
 				   init_task.o process.o systbl.o idle.o \
@@ -78,6 +90,8 @@ obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o \
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
+
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
 ifneq ($(CONFIG_PPC_INDIRECT_IO),y)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 0c8614d9875c..7231a708af0d 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -30,6 +30,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
+#include <asm/ftrace.h>
 
 #undef SHOW_SYSCALLS
 #undef SHOW_SYSCALLS_TASK
@@ -1035,3 +1036,129 @@ machine_check_in_rtas:
 	/* XXX load up BATs and panic */
 
 #endif /* CONFIG_PPC_RTAS */
+
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+	stwu	r1,-48(r1)
+	stw	r3, 12(r1)
+	stw	r4, 16(r1)
+	stw	r5, 20(r1)
+	stw	r6, 24(r1)
+	mflr	r3
+	stw	r7, 28(r1)
+	mfcr	r5
+	stw	r8, 32(r1)
+	stw	r9, 36(r1)
+	stw	r10,40(r1)
+	stw	r3, 44(r1)
+	stw	r5, 8(r1)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	.globl mcount_call
+mcount_call:
+	bl	ftrace_stub
+	nop
+	lwz	r6, 8(r1)
+	lwz	r0, 44(r1)
+	lwz	r3, 12(r1)
+	mtctr	r0
+	lwz	r4, 16(r1)
+	mtcr	r6
+	lwz	r5, 20(r1)
+	lwz	r6, 24(r1)
+	lwz	r0, 52(r1)
+	lwz	r7, 28(r1)
+	lwz	r8, 32(r1)
+	mtlr	r0
+	lwz	r9, 36(r1)
+	lwz	r10,40(r1)
+	addi	r1, r1, 48
+	bctr
+
+_GLOBAL(ftrace_caller)
+	/* Based off of objdump optput from glibc */
+	stwu	r1,-48(r1)
+	stw	r3, 12(r1)
+	stw	r4, 16(r1)
+	stw	r5, 20(r1)
+	stw	r6, 24(r1)
+	mflr	r3
+	lwz	r4, 52(r1)
+	mfcr	r5
+	stw	r7, 28(r1)
+	stw	r8, 32(r1)
+	stw	r9, 36(r1)
+	stw	r10,40(r1)
+	stw	r3, 44(r1)
+	stw	r5, 8(r1)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+	lwz	r6, 8(r1)
+	lwz	r0, 44(r1)
+	lwz	r3, 12(r1)
+	mtctr	r0
+	lwz	r4, 16(r1)
+	mtcr	r6
+	lwz	r5, 20(r1)
+	lwz	r6, 24(r1)
+	lwz	r0, 52(r1)
+	lwz	r7, 28(r1)
+	lwz	r8, 32(r1)
+	mtlr	r0
+	lwz	r9, 36(r1)
+	lwz	r10,40(r1)
+	addi	r1, r1, 48
+	bctr
+#else
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+	stwu	r1,-48(r1)
+	stw	r3, 12(r1)
+	stw	r4, 16(r1)
+	stw	r5, 20(r1)
+	stw	r6, 24(r1)
+	mflr	r3
+	lwz	r4, 52(r1)
+	mfcr	r5
+	stw	r7, 28(r1)
+	stw	r8, 32(r1)
+	stw	r9, 36(r1)
+	stw	r10,40(r1)
+	stw	r3, 44(r1)
+	stw	r5, 8(r1)
+
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	LOAD_REG_ADDR(r5, ftrace_trace_function)
+	lwz	r5,0(r5)
+
+	mtctr	r5
+	bctrl
+
+	nop
+
+	lwz	r6, 8(r1)
+	lwz	r0, 44(r1)
+	lwz	r3, 12(r1)
+	mtctr	r0
+	lwz	r4, 16(r1)
+	mtcr	r6
+	lwz	r5, 20(r1)
+	lwz	r6, 24(r1)
+	lwz	r0, 52(r1)
+	lwz	r7, 28(r1)
+	lwz	r8, 32(r1)
+	mtlr	r0
+	lwz	r9, 36(r1)
+	lwz	r10,40(r1)
+	addi	r1, r1, 48
+	bctr
+#endif
+
+_GLOBAL(ftrace_stub)
+	blr
+
+#endif /* CONFIG_MCOUNT */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index c0db5b769e55..2f511a969d2c 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -31,6 +31,7 @@
 #include <asm/bug.h>
 #include <asm/ptrace.h>
 #include <asm/irqflags.h>
+#include <asm/ftrace.h>
 
 /*
  * System calls.
@@ -870,3 +871,67 @@ _GLOBAL(enter_prom)
 	ld	r0,16(r1)
 	mtlr    r0
         blr
+
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+_GLOBAL(mcount)
+_GLOBAL(_mcount)
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	.globl mcount_call
+mcount_call:
+	bl	ftrace_stub
+	nop
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+	blr
+
+_GLOBAL(ftrace_caller)
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	ld	r11, 0(r1)
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	ld	r4, 16(r11)
+	subi	r3, r3, MCOUNT_INSN_SIZE
+.globl ftrace_call
+ftrace_call:
+	bl	ftrace_stub
+	nop
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+_GLOBAL(ftrace_stub)
+	blr
+#else
+_GLOBAL(mcount)
+	blr
+
+_GLOBAL(_mcount)
+	/* Taken from output of objdump from lib64/glibc */
+	mflr	r3
+	ld	r11, 0(r1)
+	stdu	r1, -112(r1)
+	std	r3, 128(r1)
+	ld	r4, 16(r11)
+
+	subi	r3, r3, MCOUNT_INSN_SIZE
+	LOAD_REG_ADDR(r5,ftrace_trace_function)
+	ld	r5,0(r5)
+	ld	r5,0(r5)
+	mtctr	r5
+	bctrl
+
+	nop
+	ld	r0, 128(r1)
+	mtlr	r0
+	addi	r1, r1, 112
+_GLOBAL(ftrace_stub)
+	blr
+
+#endif
+#endif
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
new file mode 100644
index 000000000000..3855ceb937b0
--- /dev/null
+++ b/arch/powerpc/kernel/ftrace.c
@@ -0,0 +1,154 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes out to P.A. Semi, Inc for supplying me with a PPC64 box.
+ *
+ */
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/cacheflush.h>
+#include <asm/ftrace.h>
+
+
+static unsigned int ftrace_nop = 0x60000000;
+
+#ifdef CONFIG_PPC32
+# define GET_ADDR(addr) addr
+#else
+/* PowerPC64's functions are data that points to the functions */
+# define GET_ADDR(addr) *(unsigned long *)addr
+#endif
+
+
+static unsigned int notrace ftrace_calc_offset(long ip, long addr)
+{
+	return (int)(addr - ip);
+}
+
+notrace unsigned char *ftrace_nop_replace(void)
+{
+	return (char *)&ftrace_nop;
+}
+
+notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+	static unsigned int op;
+
+	/*
+	 * It would be nice to just use create_function_call, but that will
+	 * update the code itself. Here we need to just return the
+	 * instruction that is going to be modified, without modifying the
+	 * code.
+	 */
+	addr = GET_ADDR(addr);
+
+	/* Set to "bl addr" */
+	op = 0x48000001 | (ftrace_calc_offset(ip, addr) & 0x03fffffc);
+
+	/*
+	 * No locking needed, this must be called via kstop_machine
+	 * which in essence is like running on a uniprocessor machine.
+	 */
+	return (unsigned char *)&op;
+}
+
+#ifdef CONFIG_PPC64
+# define _ASM_ALIGN	" .align 3 "
+# define _ASM_PTR	" .llong "
+#else
+# define _ASM_ALIGN	" .align 2 "
+# define _ASM_PTR	" .long "
+#endif
+
+notrace int
+ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+		   unsigned char *new_code)
+{
+	unsigned replaced;
+	unsigned old = *(unsigned *)old_code;
+	unsigned new = *(unsigned *)new_code;
+	int faulted = 0;
+
+	/*
+	 * Note: Due to modules and __init, code can
+	 *  disappear and change, we need to protect against faulting
+	 *  as well as code changing.
+	 *
+	 * No real locking needed, this code is run through
+	 * kstop_machine.
+	 */
+	asm volatile (
+		"1: lwz		%1, 0(%2)\n"
+		"   cmpw	%1, %5\n"
+		"   bne		2f\n"
+		"   stwu	%3, 0(%2)\n"
+		"2:\n"
+		".section .fixup, \"ax\"\n"
+		"3:	li %0, 1\n"
+		"	b 2b\n"
+		".previous\n"
+		".section __ex_table,\"a\"\n"
+		_ASM_ALIGN "\n"
+		_ASM_PTR "1b, 3b\n"
+		".previous"
+		: "=r"(faulted), "=r"(replaced)
+		: "r"(ip), "r"(new),
+		  "0"(faulted), "r"(old)
+		: "memory");
+
+	if (replaced != old && replaced != new)
+		faulted = 2;
+
+	if (!faulted)
+		flush_icache_range(ip, ip + 8);
+
+	return faulted;
+}
+
+notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	int ret;
+
+	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = ftrace_modify_code(ip, old, new);
+
+	return ret;
+}
+
+notrace int ftrace_mcount_set(unsigned long *data)
+{
+	unsigned long ip = (long)(&mcount_call);
+	unsigned long *addr = data;
+	unsigned char old[MCOUNT_INSN_SIZE], *new;
+
+	/*
+	 * Replace the mcount stub with a pointer to the
+	 * ip recorder function.
+	 */
+	memcpy(old, &mcount_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(ip, *addr);
+	*addr = ftrace_modify_code(ip, old, new);
+
+	return 0;
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	/* This is running in kstop_machine */
+
+	ftrace_mcount_set(data);
+
+	return 0;
+}
+
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index c2b9dc4fce5d..22b5d2c459a3 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -368,7 +368,12 @@ interrupt_base:
 
 	rlwimi	r11,r13,0,26,31		/* Insert static perms */
 
-	rlwinm	r11,r11,0,20,15		/* Clear U0-U3 */
+	/*
+	 * Clear U0-U3 and WL1 IL1I IL1D IL2I IL2D bits which are added
+	 * on newer 440 cores like the 440x6 used on AMCC 460EX/460GT (see
+	 * include/asm-powerpc/pgtable-ppc32.h for details).
+	 */
+	rlwinm	r11,r11,0,20,10
 
 	/* find the TLB index that caused the fault.  It has to be here. */
 	tlbsx	r10, 0, r10
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index e31aca9208eb..1882bf419fa6 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -120,7 +120,8 @@ EXPORT_SYMBOL(_outsl_ns);
 
 #define IO_CHECK_ALIGN(v,a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
 
-void _memset_io(volatile void __iomem *addr, int c, unsigned long n)
+notrace void
+_memset_io(volatile void __iomem *addr, int c, unsigned long n)
 {
 	void *p = (void __force *)addr;
 	u32 lc = c;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2f73f705d564..dcc946e67099 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(irq_desc);
 
 int distribute_irqs = 1;
 
-static inline unsigned long get_hard_enabled(void)
+static inline notrace unsigned long get_hard_enabled(void)
 {
 	unsigned long enabled;
 
@@ -108,13 +108,13 @@ static inline unsigned long get_hard_enabled(void)
 	return enabled;
 }
 
-static inline void set_soft_enabled(unsigned long enable)
+static inline notrace void set_soft_enabled(unsigned long enable)
 {
 	__asm__ __volatile__("stb %0,%1(13)"
 	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
-void raw_local_irq_restore(unsigned long en)
+notrace void raw_local_irq_restore(unsigned long en)
 {
 	/*
 	 * get_paca()->soft_enabled = en;
@@ -1073,7 +1073,7 @@ static const struct file_operations virq_debug_fops = {
 static int __init irq_debugfs_init(void)
 {
 	if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
-				 NULL, &virq_debug_fops))
+				 NULL, &virq_debug_fops) == NULL)
 		return -ENOMEM;
 
 	return 0;
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 61dd17449ddc..4d96e1db55ee 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -33,13 +33,14 @@ static struct legacy_serial_info {
 	phys_addr_t			taddr;
 } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
 
-static struct __initdata of_device_id parents[] = {
+static struct __initdata of_device_id legacy_serial_parents[] = {
 	{.type = "soc",},
 	{.type = "tsi-bridge",},
 	{.type = "opb", },
 	{.compatible = "ibm,opb",},
 	{.compatible = "simple-bus",},
 	{.compatible = "wrs,epld-localbus",},
+	{},
 };
 
 static unsigned int legacy_serial_count;
@@ -136,6 +137,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	if (of_get_property(np, "clock-frequency", NULL) == NULL)
 		return -1;
 
+	/* if reg-shift or offset, don't try to use it */
+	if ((of_get_property(np, "reg-shift", NULL) != NULL) ||
+		(of_get_property(np, "reg-offset", NULL) != NULL))
+		return -1;
+
 	/* if rtas uses this device, don't try to use it as well */
 	if (of_get_property(np, "used-by-rtas", NULL) != NULL)
 		return -1;
@@ -322,7 +328,7 @@ void __init find_legacy_serial_ports(void)
 		struct device_node *parent = of_get_parent(np);
 		if (!parent)
 			continue;
-		if (of_match_node(parents, parent) != NULL) {
+		if (of_match_node(legacy_serial_parents, parent) != NULL) {
 			index = add_legacy_soc_port(np, np);
 			if (index >= 0 && np == stdout)
 				legacy_serial_console = index;
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 704375bda73a..b732b5f8e356 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -172,7 +172,7 @@ static void kexec_prepare_cpus(void)
 {
 	int my_cpu, i, notified=-1;
 
-	smp_call_function(kexec_smp_down, NULL, 0, /* wait */0);
+	smp_call_function(kexec_smp_down, NULL, /* wait */0);
 	my_cpu = get_cpu();
 
 	/* check the others cpus are now down (via paca hw cpu id == -1) */
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index e79ad8afda07..3f37a6e62771 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -76,6 +76,8 @@ struct of_device* of_platform_device_create(struct device_node *np,
 		return NULL;
 
 	dev->dma_mask = 0xffffffffUL;
+	dev->dev.coherent_dma_mask = DMA_32BIT_MASK;
+
 	dev->dev.bus = &of_platform_bus_type;
 
 	/* We do not fill the DMA ops for platform devices by default.
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 52750745edfd..30eedfc5a566 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -189,7 +189,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	dev->cfg_size = pci_cfg_space_size(dev);
 
-	sprintf(pci_name(dev), "%04x:%02x:%02x.%d", pci_domain_nr(bus),
+	dev_set_name(&dev->dev, "%04x:%02x:%02x.%d", pci_domain_nr(bus),
 		dev->bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn));
 	dev->class = get_int_prop(node, "class-code", 0);
 	dev->revision = get_int_prop(node, "revision-id", 0);
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index cf6b5a7d8b3f..a8d02506468a 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -8,7 +8,6 @@
 #include <linux/screen_info.h>
 #include <linux/vt_kern.h>
 #include <linux/nvram.h>
-#include <linux/console.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
@@ -43,6 +42,7 @@
 #include <asm/div64.h>
 #include <asm/signal.h>
 #include <asm/dcr.h>
+#include <asm/ftrace.h>
 
 #ifdef CONFIG_PPC32
 extern void transfer_to_handler(void);
@@ -68,6 +68,10 @@ EXPORT_SYMBOL(single_step_exception);
 EXPORT_SYMBOL(sys_sigreturn);
 #endif
 
+#ifdef CONFIG_FTRACE
+EXPORT_SYMBOL(_mcount);
+#endif
+
 EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strncpy);
 EXPORT_SYMBOL(strcat);
@@ -160,7 +164,6 @@ EXPORT_SYMBOL(screen_info);
 EXPORT_SYMBOL(timer_interrupt);
 EXPORT_SYMBOL(irq_desc);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
-EXPORT_SYMBOL(console_drivers);
 EXPORT_SYMBOL(cacheable_memcpy);
 #endif
 
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 31729a9387df..2c7e8e87f770 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -48,6 +48,20 @@ do
 		fi
 	done
 
+	# ignore register save/restore funcitons
+	if [ "${UNDEF:0:9}" = "_restgpr_" ]; then
+		OK=1
+	fi
+	if [ "${UNDEF:0:11}" = "_rest32gpr_" ]; then
+		OK=1
+	fi
+	if [ "${UNDEF:0:9}" = "_savegpr_" ]; then
+		OK=1
+	fi
+	if [ "${UNDEF:0:11}" = "_save32gpr_" ]; then
+		OK=1
+	fi
+
 	if [ $OK -eq 0 ]; then
 		ERROR=1
 		echo "Error: External symbol '$UNDEF' referenced" \
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 34843c318419..647f3e8677dc 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -747,7 +747,7 @@ static int rtas_ibm_suspend_me(struct rtas_args *args)
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
 	 */
-	if (on_each_cpu(rtas_percpu_suspend_me, &data, 1, 0))
+	if (on_each_cpu(rtas_percpu_suspend_me, &data, 0))
 		data.error = -EINVAL;
 
 	wait_for_completion(&done);
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 5112a4aa801d..19e8fcb9cea8 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -81,7 +81,7 @@ int ucache_bsize;
  * from the address that it was linked at, so we must use RELOC/PTRRELOC
  * to access static data (including strings).  -- paulus
  */
-unsigned long __init early_init(unsigned long dt_ptr)
+notrace unsigned long __init early_init(unsigned long dt_ptr)
 {
 	unsigned long offset = reloc_offset();
 	struct cpu_spec *spec;
@@ -111,7 +111,7 @@ unsigned long __init early_init(unsigned long dt_ptr)
  * This is called very early on the boot process, after a minimal
  * MMU environment has been set up but before MMU_init is called.
  */
-void __init machine_init(unsigned long dt_ptr, unsigned long phys)
+notrace void __init machine_init(unsigned long dt_ptr, unsigned long phys)
 {
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
@@ -133,7 +133,7 @@ void __init machine_init(unsigned long dt_ptr, unsigned long phys)
 
 #ifdef CONFIG_BOOKE_WDT
 /* Checks wdt=x and wdt_period=xx command-line option */
-int __init early_parse_wdt(char *p)
+notrace int __init early_parse_wdt(char *p)
 {
 	if (p && strncmp(p, "0", 1) != 0)
 	       booke_wdt_enabled = 1;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index faeb8f207ea4..da7c058e3731 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -87,6 +87,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 #ifdef CONFIG_ALTIVEC
 	elf_vrreg_t __user *v_regs = (elf_vrreg_t __user *)(((unsigned long)sc->vmx_reserve + 15) & ~0xful);
 #endif
+	unsigned long msr = regs->msr;
 	long err = 0;
 
 	flush_fp_to_thread(current);
@@ -102,7 +103,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 		/* set MSR_VEC in the MSR value in the frame to indicate that sc->v_reg)
 		 * contains valid data.
 		 */
-		regs->msr |= MSR_VEC;
+		msr |= MSR_VEC;
 	}
 	/* We always copy to/from vrsave, it's 0 if we don't have or don't
 	 * use altivec.
@@ -114,6 +115,7 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 	err |= __put_user(&sc->gp_regs, &sc->regs);
 	WARN_ON(!FULL_REGS(regs));
 	err |= __copy_to_user(&sc->gp_regs, regs, GP_REGS_SIZE);
+	err |= __put_user(msr, &sc->gp_regs[PT_MSR]);
 	err |= __copy_to_user(&sc->fp_regs, &current->thread.fpr, FP_REGS_SIZE);
 	err |= __put_user(signr, &sc->signal);
 	err |= __put_user(handler, &sc->handler);
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 1457aa0a08f1..5191b46a611e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -72,12 +72,8 @@ struct smp_ops_t *smp_ops;
 
 static volatile unsigned int cpu_callin_map[NR_CPUS];
 
-void smp_call_function_interrupt(void);
-
 int smt_enabled_at_boot = 1;
 
-static int ipi_fail_ok;
-
 static void (*crash_ipi_function_ptr)(struct pt_regs *) = NULL;
 
 #ifdef CONFIG_PPC64
@@ -99,12 +95,15 @@ void smp_message_recv(int msg)
 {
 	switch(msg) {
 	case PPC_MSG_CALL_FUNCTION:
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 		break;
 	case PPC_MSG_RESCHEDULE:
 		/* XXX Do we have to do this? */
 		set_need_resched();
 		break;
+	case PPC_MSG_CALL_FUNC_SINGLE:
+		generic_smp_call_function_single_interrupt();
+		break;
 	case PPC_MSG_DEBUGGER_BREAK:
 		if (crash_ipi_function_ptr) {
 			crash_ipi_function_ptr(get_irq_regs());
@@ -128,6 +127,19 @@ void smp_send_reschedule(int cpu)
 		smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
 }
 
+void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNC_SINGLE);
+}
+
+void arch_send_call_function_ipi(cpumask_t mask)
+{
+	unsigned int cpu;
+
+	for_each_cpu_mask(cpu, mask)
+		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
+}
+
 #ifdef CONFIG_DEBUGGER
 void smp_send_debugger_break(int cpu)
 {
@@ -154,215 +166,9 @@ static void stop_this_cpu(void *dummy)
 		;
 }
 
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- * Stolen from the i386 version.
- */
-static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock);
-
-static struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-} *call_data;
-
-/* delay of at least 8 seconds */
-#define SMP_CALL_TIMEOUT	8
-
-/*
- * These functions send a 'generic call function' IPI to other online
- * CPUS in the system.
- *
- * [SUMMARY] Run a function on other CPUs.
- * <func> The function to run. This must be fast and non-blocking.
- * <info> An arbitrary pointer to pass to the function.
- * <nonatomic> currently unused.
- * <wait> If true, wait (atomically) until function has completed on other CPUs.
- * [RETURNS] 0 on success, else a negative status code. Does not return until
- * remote CPUs are nearly ready to execute <<func>> or are or have executed.
- * <map> is a cpu map of the cpus to send IPI to.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-static int __smp_call_function_map(void (*func) (void *info), void *info,
-				   int nonatomic, int wait, cpumask_t map)
-{
-	struct call_data_struct data;
-	int ret = -1, num_cpus;
-	int cpu;
-	u64 timeout;
-
-	if (unlikely(smp_ops == NULL))
-		return ret;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	/* remove 'self' from the map */
-	if (cpu_isset(smp_processor_id(), map))
-		cpu_clear(smp_processor_id(), map);
-
-	/* sanity check the map, remove any non-online processors. */
-	cpus_and(map, map, cpu_online_map);
-
-	num_cpus = cpus_weight(map);
-	if (!num_cpus)
-		goto done;
-
-	call_data = &data;
-	smp_wmb();
-	/* Send a message to all CPUs in the map */
-	for_each_cpu_mask(cpu, map)
-		smp_ops->message_pass(cpu, PPC_MSG_CALL_FUNCTION);
-
-	timeout = get_tb() + (u64) SMP_CALL_TIMEOUT * tb_ticks_per_sec;
-
-	/* Wait for indication that they have received the message */
-	while (atomic_read(&data.started) != num_cpus) {
-		HMT_low();
-		if (get_tb() >= timeout) {
-			printk("smp_call_function on cpu %d: other cpus not "
-				"responding (%d)\n", smp_processor_id(),
-				atomic_read(&data.started));
-			if (!ipi_fail_ok)
-				debugger(NULL);
-			goto out;
-		}
-	}
-
-	/* optionally wait for the CPUs to complete */
-	if (wait) {
-		while (atomic_read(&data.finished) != num_cpus) {
-			HMT_low();
-			if (get_tb() >= timeout) {
-				printk("smp_call_function on cpu %d: other "
-					"cpus not finishing (%d/%d)\n",
-					smp_processor_id(),
-					atomic_read(&data.finished),
-					atomic_read(&data.started));
-				debugger(NULL);
-				goto out;
-			}
-		}
-	}
-
- done:
-	ret = 0;
-
- out:
-	call_data = NULL;
-	HMT_medium();
-	return ret;
-}
-
-static int __smp_call_function(void (*func)(void *info), void *info,
-			       int nonatomic, int wait)
-{
-	int ret;
-	spin_lock(&call_lock);
-	ret =__smp_call_function_map(func, info, nonatomic, wait,
-				       cpu_online_map);
-	spin_unlock(&call_lock);
-	return ret;
-}
-
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-			int wait)
-{
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	return __smp_call_function(func, info, nonatomic, wait);
-}
-EXPORT_SYMBOL(smp_call_function);
-
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int nonatomic, int wait)
-{
-	cpumask_t map = CPU_MASK_NONE;
-	int ret = 0;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	if (!cpu_online(cpu))
-		return -EINVAL;
-
-	cpu_set(cpu, map);
-	if (cpu != get_cpu()) {
-		spin_lock(&call_lock);
-		ret = __smp_call_function_map(func, info, nonatomic, wait, map);
-		spin_unlock(&call_lock);
-	} else {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-	put_cpu();
-	return ret;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
 void smp_send_stop(void)
 {
-	int nolock;
-
-	/* It's OK to fail sending the IPI, since the alternative is to
-	 * be stuck forever waiting on the other CPU to take the interrupt.
-	 *
-	 * It's better to at least continue and go through reboot, since this
-	 * function is usually called at panic or reboot time in the first
-	 * place.
-	 */
-	ipi_fail_ok = 1;
-
-	/* Don't deadlock in case we got called through panic */
-	nolock = !spin_trylock(&call_lock);
-	__smp_call_function_map(stop_this_cpu, NULL, 1, 0, cpu_online_map);
-	if (!nolock)
-		spin_unlock(&call_lock);
-}
-
-void smp_call_function_interrupt(void)
-{
-	void (*func) (void *info);
-	void *info;
-	int wait;
-
-	/* call_data will be NULL if the sender timed out while
-	 * waiting on us to receive the call.
-	 */
-	if (!call_data)
-		return;
-
-	func = call_data->func;
-	info = call_data->info;
-	wait = call_data->wait;
-
-	if (!wait)
-		smp_mb__before_atomic_inc();
-
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
-	(*func)(info);
-	if (wait) {
-		smp_mb__before_atomic_inc();
-		atomic_inc(&call_data->finished);
-	}
+	smp_call_function(stop_this_cpu, NULL, 0);
 }
 
 extern struct gettimeofday_struct do_gtod;
@@ -596,9 +402,9 @@ int __devinit start_secondary(void *unused)
 
 	secondary_cpu_time_init();
 
-	spin_lock(&call_lock);
+	ipi_call_lock();
 	cpu_set(cpu, cpu_online_map);
-	spin_unlock(&call_lock);
+	ipi_call_unlock();
 
 	local_irq_enable();
 
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 962944038430..3cf0d94ba340 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
+#include <linux/module.h>
 #include <asm/ptrace.h>
 
 /*
@@ -44,3 +45,4 @@ void save_stack_trace(struct stack_trace *trace)
 		sp = newsp;
 	}
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c
index 368a4934f7ee..c3a56d65c5a9 100644
--- a/arch/powerpc/kernel/tau_6xx.c
+++ b/arch/powerpc/kernel/tau_6xx.c
@@ -192,7 +192,7 @@ static void tau_timeout_smp(unsigned long unused)
 
 	/* schedule ourselves to be run again */
 	mod_timer(&tau_timer, jiffies + shrink_timer) ;
-	on_each_cpu(tau_timeout, NULL, 1, 0);
+	on_each_cpu(tau_timeout, NULL, 0);
 }
 
 /*
@@ -234,7 +234,7 @@ int __init TAU_init(void)
 	tau_timer.expires = jiffies + shrink_timer;
 	add_timer(&tau_timer);
 
-	on_each_cpu(TAU_init_smp, NULL, 1, 0);
+	on_each_cpu(TAU_init_smp, NULL, 0);
 
 	printk("Thermal assist unit ");
 #ifdef CONFIG_TAU_INT
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 73401e83739a..f1a38a6c1e2d 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -322,7 +322,7 @@ void snapshot_timebases(void)
 {
 	if (!cpu_has_feature(CPU_FTR_PURR))
 		return;
-	on_each_cpu(snapshot_tb_and_purr, NULL, 0, 1);
+	on_each_cpu(snapshot_tb_and_purr, NULL, 1);
 }
 
 /*
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index c21a626af676..ce245a850db2 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -142,7 +142,7 @@ static void dump_one_vdso_page(struct page *pg, struct page *upg)
 	printk("kpg: %p (c:%d,f:%08lx)", __va(page_to_pfn(pg) << PAGE_SHIFT),
 	       page_count(pg),
 	       pg->flags);
-	if (upg/* && pg != upg*/) {
+	if (upg && !IS_ERR(upg) /* && pg != upg*/) {
 		printk(" upg: %p (c:%d,f:%08lx)", __va(page_to_pfn(upg)
 						       << PAGE_SHIFT),
 		       page_count(upg),
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 0c3000bf8d75..53d57d17a894 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -64,8 +64,6 @@ SECTIONS
 
 	NOTES
 
-	BUG_TABLE
-
 /*
  * Init sections discarded at runtime
  */