22 files changed, 161 insertions, 240 deletions

diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index 7c589ef81fb..c94e4a3fe2e 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -30,7 +30,7 @@
 	: "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
 	: "cr0", "memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
 	int cmp = (encoded_op >> 24) & 15;
@@ -40,7 +40,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
 
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
 	pagefault_disable();
@@ -82,35 +82,38 @@ static inline int futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
 }
 
 static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+			      u32 oldval, u32 newval)
 {
-	int prev;
+	int ret = 0;
+	u32 prev;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
         __asm__ __volatile__ (
         PPC_RELEASE_BARRIER
-"1:     lwarx   %0,0,%2         # futex_atomic_cmpxchg_inatomic\n\
-        cmpw    0,%0,%3\n\
+"1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
+        cmpw    0,%1,%4\n\
         bne-    3f\n"
-        PPC405_ERR77(0,%2)
-"2:     stwcx.  %4,0,%2\n\
+        PPC405_ERR77(0,%3)
+"2:     stwcx.  %5,0,%3\n\
         bne-    1b\n"
         PPC_ACQUIRE_BARRIER
 "3:	.section .fixup,\"ax\"\n\
-4:	li	%0,%5\n\
+4:	li	%0,%6\n\
 	b	3b\n\
 	.previous\n\
 	.section __ex_table,\"a\"\n\
 	.align 3\n\
 	" PPC_LONG "1b,4b,2b,4b\n\
 	.previous" \
-        : "=&r" (prev), "+m" (*uaddr)
+        : "+r" (ret), "=&r" (prev), "+m" (*uaddr)
         : "r" (uaddr), "r" (oldval), "r" (newval), "i" (-EFAULT)
         : "cc", "memory");
 
-        return prev;
+	*uval = prev;
+        return ret;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 380d48bacd1..26b8c807f8f 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -33,9 +33,25 @@
 //
 //----------------------------------------------------------------------------
 #include <linux/cache.h>
+#include <linux/threads.h>
 #include <asm/types.h>
 #include <asm/mmu.h>
 
+/*
+ * We only have to have statically allocated lppaca structs on
+ * legacy iSeries, which supports at most 64 cpus.
+ */
+#ifdef CONFIG_PPC_ISERIES
+#if NR_CPUS < 64
+#define NR_LPPACAS	NR_CPUS
+#else
+#define NR_LPPACAS	64
+#endif
+#else /* not iSeries */
+#define NR_LPPACAS	1
+#endif
+
+
 /* The Hypervisor barfs if the lppaca crosses a page boundary.  A 1k
  * alignment is sufficient to prevent this */
 struct lppaca {
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 991d5998d6b..fe56a23e1ff 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -240,6 +240,12 @@ struct machdep_calls {
 	 * claims to support kexec.
 	 */
 	int (*machine_kexec_prepare)(struct kimage *image);
+
+	/* Called to perform the _real_ kexec.
+	 * Do NOT allocate memory or fail here. We are past the point of
+	 * no return.
+	 */
+	void (*machine_kexec)(struct kimage *image);
 #endif /* CONFIG_KEXEC */
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 8eaed81ea64..17194fcd404 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -40,8 +40,8 @@
 
 /* MAS registers bit definitions */
 
-#define MAS0_TLBSEL(x)		((x << 28) & 0x30000000)
-#define MAS0_ESEL(x)		((x << 16) & 0x0FFF0000)
+#define MAS0_TLBSEL(x)		(((x) << 28) & 0x30000000)
+#define MAS0_ESEL(x)		(((x) << 16) & 0x0FFF0000)
 #define MAS0_NV(x)		((x) & 0x00000FFF)
 #define MAS0_HES		0x00004000
 #define MAS0_WQ_ALLWAYS		0x00000000
@@ -50,12 +50,12 @@
 
 #define MAS1_VALID		0x80000000
 #define MAS1_IPROT		0x40000000
-#define MAS1_TID(x)		((x << 16) & 0x3FFF0000)
+#define MAS1_TID(x)		(((x) << 16) & 0x3FFF0000)
 #define MAS1_IND		0x00002000
 #define MAS1_TS			0x00001000
 #define MAS1_TSIZE_MASK		0x00000f80
 #define MAS1_TSIZE_SHIFT	7
-#define MAS1_TSIZE(x)		((x << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
+#define MAS1_TSIZE(x)		(((x) << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
 
 #define MAS2_EPN		0xFFFFF000
 #define MAS2_X0			0x00000040
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 53b64be40eb..da4b2000854 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -101,7 +101,7 @@ extern phys_addr_t kernstart_addr;
 
 #ifdef CONFIG_FLATMEM
 #define ARCH_PFN_OFFSET		(MEMORY_START >> PAGE_SHIFT)
-#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
+#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr)
 #endif
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 51e9e6f90d1..edeb80fdd2c 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -171,6 +171,16 @@ static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 	return bus->sysdata;
 }
 
+static inline struct device_node *pci_bus_to_OF_node(struct pci_bus *bus)
+{
+	struct pci_controller *host;
+
+	if (bus->self)
+		return pci_device_to_OF_node(bus->self);
+	host = pci_bus_to_host(bus);
+	return host ? host->dn : NULL;
+}
+
 static inline int isa_vaddr_is_ioport(void __iomem *address)
 {
 	/* No specific ISA handling on ppc32 at this stage, it
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index d7275758559..c189aa5fe1f 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -70,21 +70,6 @@ static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 #define of_node_to_nid of_node_to_nid
 
-/**
- * of_irq_map_pci - Resolve the interrupt for a PCI device
- * @pdev:	the device whose interrupt is to be resolved
- * @out_irq:	structure of_irq filled by this function
- *
- * This function resolves the PCI interrupt for a given PCI device. If a
- * device-node exists for a given pci_dev, it will use normal OF tree
- * walking. If not, it will implement standard swizzling and walk up the
- * PCI tree until an device-node is found, at which point it will finish
- * resolving using the OF tree walking.
- */
-struct pci_dev;
-struct of_irq;
-extern int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq);
-
 extern void of_instantiate_rtc(void);
 
 /* These includes are put at the bottom because they may contain things
diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h
index 8447d89fbe7..bb1e2cdeb9b 100644
--- a/arch/powerpc/include/asm/rwsem.h
+++ b/arch/powerpc/include/asm/rwsem.h
@@ -13,11 +13,6 @@
  * by Paul Mackerras <paulus@samba.org>.
  */
 
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <asm/atomic.h>
-#include <asm/system.h>
-
 /*
  * the semaphore definition
  */
@@ -33,47 +28,6 @@
 #define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
-struct rw_semaphore {
-	long			count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE,					\
-	__SPIN_LOCK_UNLOCKED((name).wait_lock),			\
-	LIST_HEAD_INIT((name).wait_list)			\
-	__RWSEM_DEP_MAP_INIT(name)				\
-}
-
-#define DECLARE_RWSEM(name)		\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)					\
-	do {						\
-		static struct lock_class_key __key;	\
-							\
-		__init_rwsem((sem), #sem, &__key);	\
-	} while (0)
-
 /*
  * lock for reading
  */
@@ -174,10 +128,5 @@ static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
 	return atomic_long_add_return(delta, (atomic_long_t *)&sem->count);
 }
 
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return sem->count != 0;
-}
-
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_RWSEM_H */
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index 55cba4a8a95..f8cd9fba4d3 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -18,7 +18,7 @@
 #include <asm/mmu.h>
 
 _GLOBAL(__setup_cpu_603)
-	mflr	r4
+	mflr	r5
 BEGIN_MMU_FTR_SECTION
 	li	r10,0
 	mtspr	SPRN_SPRG_603_LRU,r10		/* init SW LRU tracking */
@@ -27,60 +27,60 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
-	mflr	r4
+	mflr	r5
 	bl	setup_common_caches
 	bl	setup_604_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750cx)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	bl	setup_750cx
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_750fx)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	bl	setup_750fx
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_7400)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_7400_workarounds
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_7410)
-	mflr	r4
+	mflr	r5
 	bl	__init_fpu_registers
 	bl	setup_7410_workarounds
 	bl	setup_common_caches
 	bl	setup_750_7400_hid0
 	li	r3,0
 	mtspr	SPRN_L2CR2,r3
-	mtlr	r4
+	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_745x)
-	mflr	r4
+	mflr	r5
 	bl	setup_common_caches
 	bl	setup_745x_specifics
-	mtlr	r4
+	mtlr	r5
 	blr
 
 /* Enable caches for 603's, 604, 750 & 7400 */
@@ -194,10 +194,10 @@ setup_750cx:
 	cror	4*cr0+eq,4*cr0+eq,4*cr1+eq
 	cror	4*cr0+eq,4*cr0+eq,4*cr2+eq
 	bnelr
-	lwz	r6,CPU_SPEC_FEATURES(r5)
+	lwz	r6,CPU_SPEC_FEATURES(r4)
 	li	r7,CPU_FTR_CAN_NAP
 	andc	r6,r6,r7
-	stw	r6,CPU_SPEC_FEATURES(r5)
+	stw	r6,CPU_SPEC_FEATURES(r4)
 	blr
 
 /* 750fx specific
@@ -225,12 +225,12 @@ BEGIN_FTR_SECTION
 	andis.	r11,r11,L3CR_L3E@h
 	beq	1f
 END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
-	lwz	r6,CPU_SPEC_FEATURES(r5)
+	lwz	r6,CPU_SPEC_FEATURES(r4)
 	andi.	r0,r6,CPU_FTR_L3_DISABLE_NAP
 	beq	1f
 	li	r7,CPU_FTR_CAN_NAP
 	andc	r6,r6,r7
-	stw	r6,CPU_SPEC_FEATURES(r5)
+	stw	r6,CPU_SPEC_FEATURES(r4)
 1:
 	mfspr	r11,SPRN_HID0
 
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 8d74a24c550..e8e915ce3d8 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2076,8 +2076,8 @@ static void __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s)
 	 * pointer on ppc64 and booke as we are running at 0 in real mode
 	 * on ppc64 and reloc_offset is always 0 on booke.
 	 */
-	if (s->cpu_setup) {
-		s->cpu_setup(offset, s);
+	if (t->cpu_setup) {
+		t->cpu_setup(offset, t);
 	}
 #endif /* CONFIG_PPC64 || CONFIG_BOOKE */
 }
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index 49a170af814..a5f8672eeff 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -87,7 +87,10 @@ void machine_kexec(struct kimage *image)
 
 	save_ftrace_enabled = __ftrace_enabled_save();
 
-	default_machine_kexec(image);
+	if (ppc_md.machine_kexec)
+		ppc_md.machine_kexec(image);
+	else
+		default_machine_kexec(image);
 
 	__ftrace_enabled_restore(save_ftrace_enabled);
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index ebf9846f3c3..f4adf89d761 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -27,20 +27,6 @@ extern unsigned long __toc_start;
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
- * We only have to have statically allocated lppaca structs on
- * legacy iSeries, which supports at most 64 cpus.
- */
-#ifdef CONFIG_PPC_ISERIES
-#if NR_CPUS < 64
-#define NR_LPPACAS	NR_CPUS
-#else
-#define NR_LPPACAS	64
-#endif
-#else /* not iSeries */
-#define NR_LPPACAS	1
-#endif
-
-/*
  * The structure which the hypervisor knows about - this structure
  * should not cross a page boundary.  The vpa_init/register_vpa call
  * is now known to fail if the lppaca structure crosses a page
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 10a44e68ef1..eb341be9a4d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/of_address.h>
+#include <linux/of_pci.h>
 #include <linux/mm.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 7a1d5cb7693..8303a6c65ef 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -353,6 +353,7 @@ static void switch_booke_debug_regs(struct thread_struct *new_thread)
 			prime_debug_regs(new_thread);
 }
 #else	/* !CONFIG_PPC_ADV_DEBUG_REGS */
+#ifndef CONFIG_HAVE_HW_BREAKPOINT
 static void set_debug_reg_defaults(struct thread_struct *thread)
 {
 	if (thread->dabr) {
@@ -360,6 +361,7 @@ static void set_debug_reg_defaults(struct thread_struct *thread)
 		set_dabr(0);
 	}
 }
+#endif /* !CONFIG_HAVE_HW_BREAKPOINT */
 #endif	/* CONFIG_PPC_ADV_DEBUG_REGS */
 
 int set_dabr(unsigned long dabr)
@@ -670,11 +672,11 @@ void flush_thread(void)
 {
 	discard_lazy_cpu_state();
 
-#ifdef CONFIG_HAVE_HW_BREAKPOINTS
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
 	flush_ptrace_hw_breakpoint(current);
-#else /* CONFIG_HAVE_HW_BREAKPOINTS */
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
 	set_debug_reg_defaults(&current->thread);
-#endif /* CONFIG_HAVE_HW_BREAKPOINTS */
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
 }
 
 void
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index c2b7a07cc3d..47187cc2cf0 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -2,95 +2,11 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/pci_regs.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
 #include <asm/prom.h>
-#include <asm/pci-bridge.h>
-
-#ifdef CONFIG_PCI
-int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq)
-{
-	struct device_node *dn, *ppnode;
-	struct pci_dev *ppdev;
-	u32 lspec;
-	u32 laddr[3];
-	u8 pin;
-	int rc;
-
-	/* Check if we have a device node, if yes, fallback to standard OF
-	 * parsing
-	 */
-	dn = pci_device_to_OF_node(pdev);
-	if (dn) {
-		rc = of_irq_map_one(dn, 0, out_irq);
-		if (!rc)
-			return rc;
-	}
-
-	/* Ok, we don't, time to have fun. Let's start by building up an
-	 * interrupt spec.  we assume #interrupt-cells is 1, which is standard
-	 * for PCI. If you do different, then don't use that routine.
-	 */
-	rc = pci_read_config_byte(pdev, PCI_INTERRUPT_PIN, &pin);
-	if (rc != 0)
-		return rc;
-	/* No pin, exit */
-	if (pin == 0)
-		return -ENODEV;
-
-	/* Now we walk up the PCI tree */
-	lspec = pin;
-	for (;;) {
-		/* Get the pci_dev of our parent */
-		ppdev = pdev->bus->self;
-
-		/* Ouch, it's a host bridge... */
-		if (ppdev == NULL) {
-#ifdef CONFIG_PPC64
-			ppnode = pci_bus_to_OF_node(pdev->bus);
-#else
-			struct pci_controller *host;
-			host = pci_bus_to_host(pdev->bus);
-			ppnode = host ? host->dn : NULL;
-#endif
-			/* No node for host bridge ? give up */
-			if (ppnode == NULL)
-				return -EINVAL;
-		} else
-			/* We found a P2P bridge, check if it has a node */
-			ppnode = pci_device_to_OF_node(ppdev);
-
-		/* Ok, we have found a parent with a device-node, hand over to
-		 * the OF parsing code.
-		 * We build a unit address from the linux device to be used for
-		 * resolution. Note that we use the linux bus number which may
-		 * not match your firmware bus numbering.
-		 * Fortunately, in most cases, interrupt-map-mask doesn't include
-		 * the bus number as part of the matching.
-		 * You should still be careful about that though if you intend
-		 * to rely on this function (you ship  a firmware that doesn't
-		 * create device nodes for all PCI devices).
-		 */
-		if (ppnode)
-			break;
-
-		/* We can only get here if we hit a P2P bridge with no node,
-		 * let's do standard swizzling and try again
-		 */
-		lspec = pci_swizzle_interrupt_pin(pdev, lspec);
-		pdev = ppdev;
-	}
-
-	laddr[0] = (pdev->bus->number << 16)
-		| (pdev->devfn << 8);
-	laddr[1]  = laddr[2] = 0;
-	return of_irq_map_raw(ppnode, &lspec, 1, laddr, out_irq);
-}
-EXPORT_SYMBOL_GPL(of_irq_map_pci);
-#endif /* CONFIG_PCI */
 
 void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop,
 		unsigned long *busno, unsigned long *phys, unsigned long *size)
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8a0deefac08..b9150f07d26 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -160,7 +160,7 @@ SECTIONS
 		INIT_RAM_FS
 	}
 
-	PERCPU(PAGE_SIZE)
+	PERCPU(L1_CACHE_BYTES, PAGE_SIZE)
 
 	. = ALIGN(8);
 	.machine.desc : AT(ADDR(.machine.desc) - LOAD_OFFSET) {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index bf5cb91f07d..0dc95c0aa3b 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -186,7 +186,7 @@ static void unmap_cpu_from_node(unsigned long cpu)
 	dbg("removing cpu %lu from node %d\n", cpu, node);
 
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
-		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	} else {
 		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
 		       cpu, node);
@@ -1289,10 +1289,9 @@ u64 memory_hotplug_max(void)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-/* Vrtual Processor Home Node (VPHN) support */
+/* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
-#define VPHN_NR_CHANGE_CTRS (8)
-static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS];
+static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
 static cpumask_t cpu_associativity_changes_mask;
 static int vphn_enabled;
 static void set_topology_timer(void);
@@ -1303,16 +1302,18 @@ static void set_topology_timer(void);
  */
 static void setup_cpu_associativity_change_counters(void)
 {
-	int cpu = 0;
+	int cpu;
+
+	/* The VPHN feature supports a maximum of 8 reference points */
+	BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8);
 
 	for_each_possible_cpu(cpu) {
-		int i = 0;
+		int i;
 		u8 *counts = vphn_cpu_change_counts[cpu];
 		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
 
-		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+		for (i = 0; i < distance_ref_points_depth; i++)
 			counts[i] = hypervisor_counts[i];
-		}
 	}
 }
 
@@ -1329,7 +1330,7 @@ static void setup_cpu_associativity_change_counters(void)
  */
 static int update_cpu_associativity_changes_mask(void)
 {
-	int cpu = 0, nr_cpus = 0;
+	int cpu, nr_cpus = 0;
 	cpumask_t *changes = &cpu_associativity_changes_mask;
 
 	cpumask_clear(changes);
@@ -1339,8 +1340,8 @@ static int update_cpu_associativity_changes_mask(void)
 		u8 *counts = vphn_cpu_change_counts[cpu];
 		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
 
-		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
-			if (hypervisor_counts[i] > counts[i]) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			if (hypervisor_counts[i] != counts[i]) {
 				counts[i] = hypervisor_counts[i];
 				changed = 1;
 			}
@@ -1354,8 +1355,11 @@ static int update_cpu_associativity_changes_mask(void)
 	return nr_cpus;
 }
 
-/* 6 64-bit registers unpacked into 12 32-bit associativity values */
-#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32))
+/*
+ * 6 64-bit registers unpacked into 12 32-bit associativity values. To form
+ * the complete property we have to add the length in the first cell.
+ */
+#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32) + 1)
 
 /*
  * Convert the associativity domain numbers returned from the hypervisor
@@ -1363,15 +1367,14 @@ static int update_cpu_associativity_changes_mask(void)
  */
 static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 {
-	int i = 0;
-	int nr_assoc_doms = 0;
+	int i, nr_assoc_doms = 0;
 	const u16 *field = (const u16*) packed;
 
 #define VPHN_FIELD_UNUSED	(0xffff)
 #define VPHN_FIELD_MSB		(0x8000)
 #define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
 
-	for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) {
+	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
 		if (*field == VPHN_FIELD_UNUSED) {
 			/* All significant fields processed, and remaining
 			 * fields contain the reserved value of all 1's.
@@ -1379,14 +1382,12 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 			 */
 			unpacked[i] = *((u32*)field);
 			field += 2;
-		}
-		else if (*field & VPHN_FIELD_MSB) {
+		} else if (*field & VPHN_FIELD_MSB) {
 			/* Data is in the lower 15 bits of this field */
 			unpacked[i] = *field & VPHN_FIELD_MASK;
 			field++;
 			nr_assoc_doms++;
-		}
-		else {
+		} else {
 			/* Data is in the lower 15 bits of this field
 			 * concatenated with the next 16 bit field
 			 */
@@ -1396,6 +1397,9 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
 		}
 	}
 
+	/* The first cell contains the length of the property */
+	unpacked[0] = nr_assoc_doms;
+
 	return nr_assoc_doms;
 }
 
@@ -1405,7 +1409,7 @@ static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
  */
 static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
 {
-	long rc = 0;
+	long rc;
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
 	u64 flags = 1;
 	int hwcpu = get_hard_smp_processor_id(cpu);
@@ -1419,7 +1423,7 @@ static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
 static long vphn_get_associativity(unsigned long cpu,
 					unsigned int *associativity)
 {
-	long rc = 0;
+	long rc;
 
 	rc = hcall_vphn(cpu, associativity);
 
@@ -1445,9 +1449,9 @@ static long vphn_get_associativity(unsigned long cpu,
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu = 0, nid = 0, old_nid = 0;
+	int cpu, nid, old_nid;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
-	struct sys_device *sysdev = NULL;
+	struct sys_device *sysdev;
 
 	for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
 		vphn_get_associativity(cpu, associativity);
@@ -1512,7 +1516,9 @@ int start_topology_update(void)
 {
 	int rc = 0;
 
-	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+	/* Disabled until races with load balancing are fixed */
+	if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
+	    get_lppaca()->shared_proc) {
 		vphn_enabled = 1;
 		setup_cpu_associativity_change_counters();
 		init_timer_deferrable(&topology_timer);
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 1ec06576f61..c14d09f614f 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -38,13 +38,11 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
  * neesd to be flushed. This function will either perform the flush
  * immediately or will batch it up if the current CPU has an active
  * batch on it.
- *
- * Must be called from within some kind of spinlock/non-preempt region...
  */
 void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, unsigned long pte, int huge)
 {
-	struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
+	struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
 	unsigned long vsid, vaddr;
 	unsigned int psize;
 	int ssize;
@@ -99,6 +97,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!batch->active) {
 		flush_hash_page(vaddr, rpte, psize, ssize, 0);
+		put_cpu_var(ppc64_tlb_batch);
 		return;
 	}
 
@@ -127,6 +126,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	batch->index = ++i;
 	if (i >= PPC64_TLB_BATCH_NR)
 		__flush_tlb_pending(batch);
+	put_cpu_var(ppc64_tlb_batch);
 }
 
 /*
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 187a7d32f86..a3d2ce54ea2 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -70,7 +70,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	if (!IS_ERR(tmp)) {
 		struct nameidata nd;
 
-		ret = path_lookup(tmp, LOOKUP_PARENT, &nd);
+		ret = kern_path_parent(tmp, &nd);
 		if (!ret) {
 			nd.flags |= LOOKUP_OPEN | LOOKUP_CREATE;
 			ret = spufs_create(&nd, flags, mode, neighbor);
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
index fdb7384c0c4..f0491cc2890 100644
--- a/arch/powerpc/platforms/iseries/dt.c
+++ b/arch/powerpc/platforms/iseries/dt.c
@@ -242,8 +242,8 @@ static void __init dt_cpus(struct iseries_flat_dt *dt)
 	pft_size[0] = 0; /* NUMA CEC cookie, 0 for non NUMA  */
 	pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE);
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (lppaca_of(i).dyn_proc_status >= 2)
+	for (i = 0; i < NR_LPPACAS; i++) {
+		if (lppaca[i].dyn_proc_status >= 2)
 			continue;
 
 		snprintf(p, 32 - (p - buf), "@%d", i);
@@ -251,7 +251,7 @@ static void __init dt_cpus(struct iseries_flat_dt *dt)
 
 		dt_prop_str(dt, "device_type", device_type_cpu);
 
-		index = lppaca_of(i).dyn_hv_phys_proc_index;
+		index = lppaca[i].dyn_hv_phys_proc_index;
 		d = &xIoHriProcessorVpd[index];
 
 		dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024);
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index b0863410517..2946ae10fbf 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -680,6 +680,7 @@ void * __init iSeries_early_setup(void)
 	 * on but calling this function multiple times is fine.
 	 */
 	identify_cpu(0, mfspr(SPRN_PVR));
+	initialise_paca(&boot_paca, 0);
 
 	powerpc_firmware_features |= FW_FEATURE_ISERIES;
 	powerpc_firmware_features |= FW_FEATURE_LPAR;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 5d3ea9f60dd..ca5d5898d32 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -713,6 +713,13 @@ EXPORT_SYMBOL(arch_free_page);
 /* NB: reg/unreg are called while guarded with the tracepoints_mutex */
 extern long hcall_tracepoint_refcount;
 
+/* 
+ * Since the tracing code might execute hcalls we need to guard against
+ * recursion. One example of this are spinlocks calling H_YIELD on
+ * shared processor partitions.
+ */
+static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
+
 void hcall_tracepoint_regfunc(void)
 {
 	hcall_tracepoint_refcount++;
@@ -725,12 +732,42 @@ void hcall_tracepoint_unregfunc(void)
 
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_entry(opcode, args);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 
 void __trace_hcall_exit(long opcode, unsigned long retval,
 			unsigned long *retbuf)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_exit(opcode, retval, retbuf);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 #endif