Merge branch 'topic/hda' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6 into devel

43 files changed, 454 insertions, 364 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 1ee596cd942..2d7f56a98e0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -87,9 +87,6 @@ config GENERIC_TIME_VSYSCALL
 	bool
 	default y
 
-config HAVE_LEGACY_PER_CPU_AREA
-	def_bool y
-
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index e7cbaa02cd0..475e2725fbd 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -103,4 +103,4 @@ archprepare: make_nr_irqs_h FORCE
 PHONY += make_nr_irqs_h FORCE
 
 make_nr_irqs_h: FORCE
-	$(Q)$(MAKE) $(build)=arch/ia64/kernel include/asm-ia64/nr-irqs.h
+	$(Q)$(MAKE) $(build)=arch/ia64/kernel include/generated/nr-irqs.h
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index f332e3fe423..e14c492a8a9 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -677,12 +677,19 @@ sba_alloc_range(struct ioc *ioc, struct device *dev, size_t size)
 			spin_unlock_irqrestore(&ioc->saved_lock, flags);
 
 			pide = sba_search_bitmap(ioc, dev, pages_needed, 0);
-			if (unlikely(pide >= (ioc->res_size << 3)))
-				panic(__FILE__ ": I/O MMU @ %p is out of mapping resources\n",
-				      ioc->ioc_hpa);
+			if (unlikely(pide >= (ioc->res_size << 3))) {
+				printk(KERN_WARNING "%s: I/O MMU @ %p is"
+				       "out of mapping resources, %u %u %lx\n",
+				       __func__, ioc->ioc_hpa, ioc->res_size,
+				       pages_needed, dma_get_seg_boundary(dev));
+				return -1;
+			}
 #else
-			panic(__FILE__ ": I/O MMU @ %p is out of mapping resources\n",
-			      ioc->ioc_hpa);
+			printk(KERN_WARNING "%s: I/O MMU @ %p is"
+			       "out of mapping resources, %u %u %lx\n",
+			       __func__, ioc->ioc_hpa, ioc->res_size,
+			       pages_needed, dma_get_seg_boundary(dev));
+			return -1;
 #endif
 		}
 	}
@@ -965,6 +972,8 @@ static dma_addr_t sba_map_page(struct device *dev, struct page *page,
 #endif
 
 	pide = sba_alloc_range(ioc, dev, size);
+	if (pide < 0)
+		return 0;
 
 	iovp = (dma_addr_t) pide << iovp_shift;
 
@@ -1320,6 +1329,7 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev,
 	unsigned long dma_offset, dma_len; /* start/len of DMA stream */
 	int n_mappings = 0;
 	unsigned int max_seg_size = dma_get_max_seg_size(dev);
+	int idx;
 
 	while (nents > 0) {
 		unsigned long vaddr = (unsigned long) sba_sg_address(startsg);
@@ -1418,16 +1428,22 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev,
 		vcontig_sg->dma_length = vcontig_len;
 		dma_len = (dma_len + dma_offset + ~iovp_mask) & iovp_mask;
 		ASSERT(dma_len <= DMA_CHUNK_SIZE);
-		dma_sg->dma_address = (dma_addr_t) (PIDE_FLAG
-			| (sba_alloc_range(ioc, dev, dma_len) << iovp_shift)
-			| dma_offset);
+		idx = sba_alloc_range(ioc, dev, dma_len);
+		if (idx < 0) {
+			dma_sg->dma_length = 0;
+			return -1;
+		}
+		dma_sg->dma_address = (dma_addr_t)(PIDE_FLAG | (idx << iovp_shift)
+						   | dma_offset);
 		n_mappings++;
 	}
 
 	return n_mappings;
 }
 
-
+static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
+			       int nents, enum dma_data_direction dir,
+			       struct dma_attrs *attrs);
 /**
  * sba_map_sg - map Scatter/Gather list
  * @dev: instance of PCI owned by the driver that's asking.
@@ -1493,6 +1509,10 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
 	** Access to the virtual address is what forces a two pass algorithm.
 	*/
 	coalesced = sba_coalesce_chunks(ioc, dev, sglist, nents);
+	if (coalesced < 0) {
+		sba_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
+		return 0;
+	}
 
 	/*
 	** Program the I/O Pdir
diff --git a/arch/ia64/ia32/elfcore32.h b/arch/ia64/ia32/elfcore32.h
index 9a3abf58cea..65772574261 100644
--- a/arch/ia64/ia32/elfcore32.h
+++ b/arch/ia64/ia32/elfcore32.h
@@ -11,8 +11,6 @@
 #include <asm/intrinsics.h>
 #include <asm/uaccess.h>
 
-#define USE_ELF_CORE_DUMP 1
-
 /* Override elfcore.h */
 #define _LINUX_ELFCORE_H 1
 typedef unsigned int elf_greg_t;
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index 91df9686a0d..7ae58892ba8 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -132,6 +132,12 @@ extern int __devinitdata pxm_to_nid_map[MAX_PXM_DOMAINS];
 extern int __initdata nid_to_pxm_map[MAX_NUMNODES];
 #endif
 
+static inline bool arch_has_acpi_pdc(void) { return true; }
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
+}
+
 #define acpi_unlazy_tlb(x)
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/ia64/include/asm/asm-offsets.h b/arch/ia64/include/asm/asm-offsets.h
new file mode 100644
index 00000000000..d370ee36a18
--- /dev/null
+++ b/arch/ia64/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h
index 57a2787bc9f..6ebc229a1c5 100644
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -127,7 +127,7 @@ clear_bit_unlock (int nr, volatile void *addr)
  * @addr: Address to start counting from
  *
  * Similarly to clear_bit_unlock, the implementation uses a store
- * with release semantics. See also __raw_spin_unlock().
+ * with release semantics. See also arch_spin_unlock().
  */
 static __inline__ void
 __clear_bit_unlock(int nr, void *addr)
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 8d3c79cd81e..7d09a09cdaa 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -73,7 +73,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 	if (!dev->dma_mask)
 		return 0;
 
-	return addr + size <= *dev->dma_mask;
+	return addr + size - 1 <= *dev->dma_mask;
 }
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h
index 86eddee029c..e14108b19c0 100644
--- a/arch/ia64/include/asm/elf.h
+++ b/arch/ia64/include/asm/elf.h
@@ -25,7 +25,6 @@
 #define ELF_DATA	ELFDATA2LSB
 #define ELF_ARCH	EM_IA_64
 
-#define USE_ELF_CORE_DUMP
 #define CORE_DUMP_USE_REGSET
 
 /* Least-significant four bits of ELF header's e_flags are OS-specific.  The bits are
diff --git a/arch/ia64/include/asm/hw_irq.h b/arch/ia64/include/asm/hw_irq.h
index 91619b31dbf..bf2e37493e0 100644
--- a/arch/ia64/include/asm/hw_irq.h
+++ b/arch/ia64/include/asm/hw_irq.h
@@ -59,7 +59,13 @@ typedef u16 ia64_vector;
 extern int ia64_first_device_vector;
 extern int ia64_last_device_vector;
 
+#if defined(CONFIG_SMP) && (defined(CONFIG_IA64_GENERIC) || defined (CONFIG_IA64_DIG))
+/* Reserve the lower priority vector than device vectors for "move IRQ" IPI */
+#define IA64_IRQ_MOVE_VECTOR		0x30	/* "move IRQ" IPI */
+#define IA64_DEF_FIRST_DEVICE_VECTOR	0x31
+#else
 #define IA64_DEF_FIRST_DEVICE_VECTOR	0x30
+#endif
 #define IA64_DEF_LAST_DEVICE_VECTOR	0xe7
 #define IA64_FIRST_DEVICE_VECTOR	ia64_first_device_vector
 #define IA64_LAST_DEVICE_VECTOR		ia64_last_device_vector
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 0d9d16e2d94..cc8335eb311 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -424,6 +424,8 @@ __writeq (unsigned long val, volatile void __iomem *addr)
 extern void __iomem * ioremap(unsigned long offset, unsigned long size);
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
 extern void iounmap (volatile void __iomem *addr);
+extern void __iomem * early_ioremap (unsigned long phys_addr, unsigned long size);
+extern void early_iounmap (volatile void __iomem *addr, unsigned long size);
 
 /*
  * String version of IO memory access ops:
diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h
index 5282546cdf8..91b920fd7d5 100644
--- a/arch/ia64/include/asm/irq.h
+++ b/arch/ia64/include/asm/irq.h
@@ -13,7 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/cpumask.h>
-#include <asm-ia64/nr-irqs.h>
+#include <generated/nr-irqs.h>
 
 static __inline__ int
 irq_canonicalize (int irq)
diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h
index c171cdf0a78..43f96ab18fa 100644
--- a/arch/ia64/include/asm/mca.h
+++ b/arch/ia64/include/asm/mca.h
@@ -106,6 +106,11 @@ struct ia64_sal_os_state {
 	unsigned long		os_status;		/* OS status to SAL, enum below */
 	unsigned long		context;		/* 0 if return to same context
 							   1 if return to new context */
+
+	/* I-resources */
+	unsigned long		iip;
+	unsigned long		ipsr;
+	unsigned long		ifs;
 };
 
 enum {
diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h
index 688a812c017..61c7b1750b1 100644
--- a/arch/ia64/include/asm/meminit.h
+++ b/arch/ia64/include/asm/meminit.h
@@ -61,7 +61,7 @@ extern int register_active_ranges(u64 start, u64 len, int nid);
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 # define LARGE_GAP	0x40000000 /* Use virtual mem map if hole is > than this */
-  extern unsigned long vmalloc_end;
+  extern unsigned long VMALLOC_END;
   extern struct page *vmem_map;
   extern int find_largest_hole(u64 start, u64 end, void *arg);
   extern int create_mem_map_page_table(u64 start, u64 end, void *arg);
diff --git a/arch/ia64/include/asm/numa.h b/arch/ia64/include/asm/numa.h
index 3499ff57bf4..6a8a27cfae3 100644
--- a/arch/ia64/include/asm/numa.h
+++ b/arch/ia64/include/asm/numa.h
@@ -22,8 +22,6 @@
 
 #include <asm/mmzone.h>
 
-#define NUMA_NO_NODE	-1
-
 extern u16 cpu_to_node_map[NR_CPUS] __cacheline_aligned;
 extern cpumask_t node_to_cpu_mask[MAX_NUMNODES] __cacheline_aligned;
 extern pg_data_t *pgdat_list[MAX_NUMNODES];
diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h
index 8840a690d1e..69bf13857a9 100644
--- a/arch/ia64/include/asm/pgtable.h
+++ b/arch/ia64/include/asm/pgtable.h
@@ -228,8 +228,7 @@ ia64_phys_addr_valid (unsigned long addr)
 #define VMALLOC_START		(RGN_BASE(RGN_GATE) + 0x200000000UL)
 #ifdef CONFIG_VIRTUAL_MEM_MAP
 # define VMALLOC_END_INIT	(RGN_BASE(RGN_GATE) + (1UL << (4*PAGE_SHIFT - 9)))
-# define VMALLOC_END		vmalloc_end
-  extern unsigned long vmalloc_end;
+extern unsigned long VMALLOC_END;
 #else
 #if defined(CONFIG_SPARSEMEM) && defined(CONFIG_SPARSEMEM_VMEMMAP)
 /* SPARSEMEM_VMEMMAP uses half of vmalloc... */
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 3eaeedf1aef..7fa90f73f6b 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -229,7 +229,7 @@ struct cpuinfo_ia64 {
 #endif
 };
 
-DECLARE_PER_CPU(struct cpuinfo_ia64, cpu_info);
+DECLARE_PER_CPU(struct cpuinfo_ia64, ia64_cpu_info);
 
 /*
  * The "local" data variable.  It refers to the per-CPU data of the currently executing
@@ -237,8 +237,8 @@ DECLARE_PER_CPU(struct cpuinfo_ia64, cpu_info);
  * Do not use the address of local_cpu_data, since it will be different from
  * cpu_data(smp_processor_id())!
  */
-#define local_cpu_data		(&__ia64_per_cpu_var(cpu_info))
-#define cpu_data(cpu)		(&per_cpu(cpu_info, cpu))
+#define local_cpu_data		(&__ia64_per_cpu_var(ia64_cpu_info))
+#define cpu_data(cpu)		(&per_cpu(ia64_cpu_info, cpu))
 
 extern void print_cpu_info (struct cpuinfo_ia64 *);
 
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index fbee74b1578..e8762688e8e 100644
--- a/arch/ia64/include/asm/rwsem.h
+++ b/arch/ia64/include/asm/rwsem.h
@@ -47,7 +47,7 @@ struct rw_semaphore {
 #define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
 
 #define __RWSEM_INITIALIZER(name) \
-	{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, \
+	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
 	  LIST_HEAD_INIT((name).wait_list) }
 
 #define DECLARE_RWSEM(name) \
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 239ecdc9516..1a91c9121d1 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -17,7 +17,7 @@
 #include <asm/intrinsics.h>
 #include <asm/system.h>
 
-#define __raw_spin_lock_init(x)			((x)->lock = 0)
+#define arch_spin_lock_init(x)			((x)->lock = 0)
 
 /*
  * Ticket locks are conceptually two parts, one indicating the current head of
@@ -38,7 +38,7 @@
 #define TICKET_BITS	15
 #define	TICKET_MASK	((1 << TICKET_BITS) - 1)
 
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 {
 	int	*p = (int *)&lock->lock, ticket, serve;
 
@@ -58,7 +58,7 @@ static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 	}
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->lock);
 
@@ -67,7 +67,7 @@ static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 	return 0;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
@@ -75,7 +75,7 @@ static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
 }
 
-static __always_inline void __ticket_spin_unlock_wait(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	int	*p = (int *)&lock->lock, ticket;
 
@@ -89,64 +89,64 @@ static __always_inline void __ticket_spin_unlock_wait(raw_spinlock_t *lock)
 	}
 }
 
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	long tmp = ACCESS_ONCE(lock->lock);
 
 	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK);
 }
 
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
 	long tmp = ACCESS_ONCE(lock->lock);
 
 	return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1;
 }
 
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
 	return __ticket_spin_is_locked(lock);
 }
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
 	return __ticket_spin_is_contended(lock);
 }
-#define __raw_spin_is_contended	__raw_spin_is_contended
+#define arch_spin_is_contended	arch_spin_is_contended
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	__ticket_spin_lock(lock);
 }
 
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	return __ticket_spin_trylock(lock);
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	__ticket_spin_unlock(lock);
 }
 
-static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 						  unsigned long flags)
 {
-	__raw_spin_lock(lock);
+	arch_spin_lock(lock);
 }
 
-static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	__ticket_spin_unlock_wait(lock);
 }
 
-#define __raw_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
-#define __raw_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
+#define arch_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
+#define arch_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
 
 #ifdef ASM_SUPPORTED
 
 static __always_inline void
-__raw_read_lock_flags(raw_rwlock_t *lock, unsigned long flags)
+arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 {
 	__asm__ __volatile__ (
 		"tbit.nz p6, p0 = %1,%2\n"
@@ -169,15 +169,15 @@ __raw_read_lock_flags(raw_rwlock_t *lock, unsigned long flags)
 		: "p6", "p7", "r2", "memory");
 }
 
-#define __raw_read_lock(lock) __raw_read_lock_flags(lock, 0)
+#define arch_read_lock(lock) arch_read_lock_flags(lock, 0)
 
 #else /* !ASM_SUPPORTED */
 
-#define __raw_read_lock_flags(rw, flags) __raw_read_lock(rw)
+#define arch_read_lock_flags(rw, flags) arch_read_lock(rw)
 
-#define __raw_read_lock(rw)								\
+#define arch_read_lock(rw)								\
 do {											\
-	raw_rwlock_t *__read_lock_ptr = (rw);						\
+	arch_rwlock_t *__read_lock_ptr = (rw);						\
 											\
 	while (unlikely(ia64_fetchadd(1, (int *) __read_lock_ptr, acq) < 0)) {		\
 		ia64_fetchadd(-1, (int *) __read_lock_ptr, rel);			\
@@ -188,16 +188,16 @@ do {											\
 
 #endif /* !ASM_SUPPORTED */
 
-#define __raw_read_unlock(rw)					\
+#define arch_read_unlock(rw)					\
 do {								\
-	raw_rwlock_t *__read_lock_ptr = (rw);			\
+	arch_rwlock_t *__read_lock_ptr = (rw);			\
 	ia64_fetchadd(-1, (int *) __read_lock_ptr, rel);	\
 } while (0)
 
 #ifdef ASM_SUPPORTED
 
 static __always_inline void
-__raw_write_lock_flags(raw_rwlock_t *lock, unsigned long flags)
+arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags)
 {
 	__asm__ __volatile__ (
 		"tbit.nz p6, p0 = %1, %2\n"
@@ -221,9 +221,9 @@ __raw_write_lock_flags(raw_rwlock_t *lock, unsigned long flags)
 		: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
 }
 
-#define __raw_write_lock(rw) __raw_write_lock_flags(rw, 0)
+#define arch_write_lock(rw) arch_write_lock_flags(rw, 0)
 
-#define __raw_write_trylock(rw)							\
+#define arch_write_trylock(rw)							\
 ({										\
 	register long result;							\
 										\
@@ -235,7 +235,7 @@ __raw_write_lock_flags(raw_rwlock_t *lock, unsigned long flags)
 	(result == 0);								\
 })
 
-static inline void __raw_write_unlock(raw_rwlock_t *x)
+static inline void arch_write_unlock(arch_rwlock_t *x)
 {
 	u8 *y = (u8 *)x;
 	barrier();
@@ -244,9 +244,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *x)
 
 #else /* !ASM_SUPPORTED */
 
-#define __raw_write_lock_flags(l, flags) __raw_write_lock(l)
+#define arch_write_lock_flags(l, flags) arch_write_lock(l)
 
-#define __raw_write_lock(l)								\
+#define arch_write_lock(l)								\
 ({											\
 	__u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1);			\
 	__u32 *ia64_write_lock_ptr = (__u32 *) (l);					\
@@ -257,7 +257,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *x)
 	} while (ia64_val);								\
 })
 
-#define __raw_write_trylock(rw)						\
+#define arch_write_trylock(rw)						\
 ({									\
 	__u64 ia64_val;							\
 	__u64 ia64_set_val = ia64_dep_mi(-1, 0, 31,1);			\
@@ -265,7 +265,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *x)
 	(ia64_val == 0);						\
 })
 
-static inline void __raw_write_unlock(raw_rwlock_t *x)
+static inline void arch_write_unlock(arch_rwlock_t *x)
 {
 	barrier();
 	x->write_lock = 0;
@@ -273,10 +273,10 @@ static inline void __raw_write_unlock(raw_rwlock_t *x)
 
 #endif /* !ASM_SUPPORTED */
 
-static inline int __raw_read_trylock(raw_rwlock_t *x)
+static inline int arch_read_trylock(arch_rwlock_t *x)
 {
 	union {
-		raw_rwlock_t lock;
+		arch_rwlock_t lock;
 		__u32 word;
 	} old, new;
 	old.lock = new.lock = *x;
@@ -285,8 +285,8 @@ static inline int __raw_read_trylock(raw_rwlock_t *x)
 	return (u32)ia64_cmpxchg4_acq((__u32 *)(x), new.word, old.word) == old.word;
 }
 
-#define _raw_spin_relax(lock)	cpu_relax()
-#define _raw_read_relax(lock)	cpu_relax()
-#define _raw_write_relax(lock)	cpu_relax()
+#define arch_spin_relax(lock)	cpu_relax()
+#define arch_read_relax(lock)	cpu_relax()
+#define arch_write_relax(lock)	cpu_relax()
 
 #endif /*  _ASM_IA64_SPINLOCK_H */
diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h
index 474e46f1ab4..e2b42a52a6d 100644
--- a/arch/ia64/include/asm/spinlock_types.h
+++ b/arch/ia64/include/asm/spinlock_types.h
@@ -7,15 +7,15 @@
 
 typedef struct {
 	volatile unsigned int lock;
-} raw_spinlock_t;
+} arch_spinlock_t;
 
-#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
 
 typedef struct {
 	volatile unsigned int read_counter	: 31;
 	volatile unsigned int write_lock	:  1;
-} raw_rwlock_t;
+} arch_rwlock_t;
 
-#define __RAW_RW_LOCK_UNLOCKED		{ 0, 0 }
+#define __ARCH_RW_LOCK_UNLOCKED		{ 0, 0 }
 
 #endif
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 6b7edcab0cb..e1236349c99 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -18,10 +18,6 @@ obj-$(CONFIG_IA64_GENERIC)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o
 
-ifneq ($(CONFIG_ACPI_PROCESSOR),)
-obj-y				+= acpi-processor.o
-endif
-
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_MODULES)		+= module.o
@@ -81,17 +77,14 @@ define cmd_nr_irqs
 endef
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
-arch/$(SRCARCH)/kernel/nr-irqs.s: $(srctree)/arch/$(SRCARCH)/kernel/nr-irqs.c \
-				$(wildcard $(srctree)/include/asm-ia64/*/irq.h)
+arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
-include/asm-ia64/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
+include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
 	$(Q)mkdir -p $(dir $@)
 	$(call cmd,nr_irqs)
 
-clean-files += $(objtree)/include/asm-ia64/nr-irqs.h
-
 #
 # native ivt.S, entry.S and fsys.S
 #
diff --git a/arch/ia64/kernel/acpi-processor.c b/arch/ia64/kernel/acpi-processor.c
deleted file mode 100644
index dbda7bde611..00000000000
--- a/arch/ia64/kernel/acpi-processor.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * arch/ia64/kernel/acpi-processor.c
- *
- * Copyright (C) 2005 Intel Corporation
- * 	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- * 	- Added _PDC for platforms with Intel CPUs
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/acpi.h>
-
-#include <acpi/processor.h>
-#include <asm/acpi.h>
-
-static void init_intel_pdc(struct acpi_processor *pr)
-{
-	struct acpi_object_list *obj_list;
-	union acpi_object *obj;
-	u32 *buf;
-
-	/* allocate and initialize pdc. It will be used later. */
-	obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL);
-	if (!obj_list) {
-		printk(KERN_ERR "Memory allocation error\n");
-		return;
-	}
-
-	obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL);
-	if (!obj) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj_list);
-		return;
-	}
-
-	buf = kmalloc(12, GFP_KERNEL);
-	if (!buf) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj);
-		kfree(obj_list);
-		return;
-	}
-
-	buf[0] = ACPI_PDC_REVISION_ID;
-	buf[1] = 1;
-	buf[2] = ACPI_PDC_EST_CAPABILITY_SMP;
-	/*
-	 * The default of PDC_SMP_T_SWCOORD bit is set for IA64 cpu so
-	 * that OSPM is capable of native ACPI throttling software
-	 * coordination using BIOS supplied _TSD info.
-	 */
-	buf[2] |= ACPI_PDC_SMP_T_SWCOORD;
-
-	obj->type = ACPI_TYPE_BUFFER;
-	obj->buffer.length = 12;
-	obj->buffer.pointer = (u8 *) buf;
-	obj_list->count = 1;
-	obj_list->pointer = obj;
-	pr->pdc = obj_list;
-
-	return;
-}
-
-/* Initialize _PDC data based on the CPU vendor */
-void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
-{
-	pr->pdc = NULL;
-	init_intel_pdc(pr);
-	return;
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_init_pdc);
-
-void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr)
-{
-	if (pr->pdc) {
-		kfree(pr->pdc->pointer->buffer.pointer);
-		kfree(pr->pdc->pointer);
-		kfree(pr->pdc);
-		pr->pdc = NULL;
-	}
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc);
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index baec6f00f7f..40574ae1140 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -702,11 +702,23 @@ int __init early_acpi_boot_init(void)
 		printk(KERN_ERR PREFIX
 		       "Error parsing MADT - no LAPIC entries\n");
 
+#ifdef CONFIG_SMP
+	if (available_cpus == 0) {
+		printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n");
+		printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id());
+		smp_boot_data.cpu_phys_id[available_cpus] =
+		    hard_smp_processor_id();
+		available_cpus = 1;	/* We've got at least one of these, no? */
+	}
+	smp_boot_data.cpu_count = available_cpus;
+#endif
+	/* Make boot-up look pretty */
+	printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus,
+	       total_cpus);
+
 	return 0;
 }
 
-
-
 int __init acpi_boot_init(void)
 {
 
@@ -769,18 +781,8 @@ int __init acpi_boot_init(void)
 	if (acpi_table_parse(ACPI_SIG_FADT, acpi_parse_fadt))
 		printk(KERN_ERR PREFIX "Can't find FADT\n");
 
+#ifdef CONFIG_ACPI_NUMA
 #ifdef CONFIG_SMP
-	if (available_cpus == 0) {
-		printk(KERN_INFO "ACPI: Found 0 CPUS; assuming 1\n");
-		printk(KERN_INFO "CPU 0 (0x%04x)", hard_smp_processor_id());
-		smp_boot_data.cpu_phys_id[available_cpus] =
-		    hard_smp_processor_id();
-		available_cpus = 1;	/* We've got at least one of these, no? */
-	}
-	smp_boot_data.cpu_count = available_cpus;
-
-	smp_build_cpu_map();
-# ifdef CONFIG_ACPI_NUMA
 	if (srat_num_cpus == 0) {
 		int cpu, i = 1;
 		for (cpu = 0; cpu < smp_boot_data.cpu_count; cpu++)
@@ -789,14 +791,9 @@ int __init acpi_boot_init(void)
 				node_cpuid[i++].phys_id =
 				    smp_boot_data.cpu_phys_id[cpu];
 	}
-# endif
 #endif
-#ifdef CONFIG_ACPI_NUMA
 	build_cpu_to_node_map();
 #endif
-	/* Make boot-up look pretty */
-	printk(KERN_INFO "%d CPUs available, %d CPUs total\n", available_cpus,
-	       total_cpus);
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 696eff28a0c..17a9fba3893 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1051,7 +1051,7 @@ END(ia64_delay_loop)
  * intermediate precision so that we can produce a full 64-bit result.
  */
 GLOBAL_ENTRY(ia64_native_sched_clock)
-	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
+	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	mov.m r9=ar.itc		// fetch cycle-counter				(35 cyc)
 	;;
 	ldf8 f8=[r8]
@@ -1077,7 +1077,7 @@ sched_clock = ia64_native_sched_clock
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 GLOBAL_ENTRY(cycle_to_cputime)
 	alloc r16=ar.pfs,1,0,0,0
-	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
+	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	;;
 	ldf8 f8=[r8]
 	;;
diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c
index 14d39e30062..461b99902bf 100644
--- a/arch/ia64/kernel/ia64_ksyms.c
+++ b/arch/ia64/kernel/ia64_ksyms.c
@@ -30,7 +30,7 @@ EXPORT_SYMBOL(max_low_pfn);	/* defined by bootmem.c, but not exported by generic
 #endif
 
 #include <asm/processor.h>
-EXPORT_SYMBOL(per_cpu__cpu_info);
+EXPORT_SYMBOL(per_cpu__ia64_cpu_info);
 #ifdef CONFIG_SMP
 EXPORT_SYMBOL(per_cpu__local_per_cpu_offset);
 #endif
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index dab4d393908..95ac77aeae9 100644
--- a/arch/ia64/kernel/iosapic.c
+++ b/arch/ia64/kernel/iosapic.c
@@ -793,12 +793,12 @@ iosapic_register_intr (unsigned int gsi,
 			goto unlock_iosapic_lock;
 	}
 
-	spin_lock(&irq_desc[irq].lock);
+	raw_spin_lock(&irq_desc[irq].lock);
 	dest = get_target_cpu(gsi, irq);
 	dmode = choose_dmode();
 	err = register_intr(gsi, irq, dmode, polarity, trigger);
 	if (err < 0) {
-		spin_unlock(&irq_desc[irq].lock);
+		raw_spin_unlock(&irq_desc[irq].lock);
 		irq = err;
 		goto unlock_iosapic_lock;
 	}
@@ -817,7 +817,7 @@ iosapic_register_intr (unsigned int gsi,
 	       (polarity == IOSAPIC_POL_HIGH ? "high" : "low"),
 	       cpu_logical_id(dest), dest, irq_to_vector(irq));
 
-	spin_unlock(&irq_desc[irq].lock);
+	raw_spin_unlock(&irq_desc[irq].lock);
  unlock_iosapic_lock:
 	spin_unlock_irqrestore(&iosapic_lock, flags);
 	return irq;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 7d8951229e7..94ee9d067cb 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -71,7 +71,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	if (i < NR_IRQS) {
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
+		raw_spin_lock_irqsave(&irq_desc[i].lock, flags);
 		action = irq_desc[i].action;
 		if (!action)
 			goto skip;
@@ -91,7 +91,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_putc(p, '\n');
 skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		raw_spin_unlock_irqrestore(&irq_desc[i].lock, flags);
 	} else if (i == NR_IRQS)
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
 	return 0;
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index dd9d7b54f1a..d4093a173a3 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -260,7 +260,6 @@ void __setup_vector_irq(int cpu)
 }
 
 #if defined(CONFIG_SMP) && (defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG))
-#define IA64_IRQ_MOVE_VECTOR	IA64_DEF_FIRST_DEVICE_VECTOR
 
 static enum vector_domain_type {
 	VECTOR_DOMAIN_NONE,
@@ -345,7 +344,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 
 		desc = irq_desc + irq;
 		cfg = irq_cfg + irq;
-		spin_lock(&desc->lock);
+		raw_spin_lock(&desc->lock);
 		if (!cfg->move_cleanup_count)
 			goto unlock;
 
@@ -358,7 +357,7 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 		spin_unlock_irqrestore(&vector_lock, flags);
 		cfg->move_cleanup_count--;
 	unlock:
-		spin_unlock(&desc->lock);
+		raw_spin_unlock(&desc->lock);
 	}
 	return IRQ_HANDLED;
 }
@@ -659,11 +658,8 @@ init_IRQ (void)
 	register_percpu_irq(IA64_SPURIOUS_INT_VECTOR, NULL);
 #ifdef CONFIG_SMP
 #if defined(CONFIG_IA64_GENERIC) || defined(CONFIG_IA64_DIG)
-	if (vector_domain_type != VECTOR_DOMAIN_NONE) {
-		BUG_ON(IA64_FIRST_DEVICE_VECTOR != IA64_IRQ_MOVE_VECTOR);
-		IA64_FIRST_DEVICE_VECTOR++;
+	if (vector_domain_type != VECTOR_DOMAIN_NONE)
 		register_percpu_irq(IA64_IRQ_MOVE_VECTOR, &irq_move_irqaction);
-	}
 #endif
 #endif
 #ifdef CONFIG_PERFMON
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 496ac7a9948..32f2639e9b0 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -888,9 +888,10 @@ ia64_mca_modify_comm(const struct task_struct *previous_current)
 }
 
 static void
-finish_pt_regs(struct pt_regs *regs, const pal_min_state_area_t *ms,
+finish_pt_regs(struct pt_regs *regs, struct ia64_sal_os_state *sos,
 		unsigned long *nat)
 {
+	const pal_min_state_area_t *ms = sos->pal_min_state;
 	const u64 *bank;
 
 	/* If ipsr.ic then use pmsa_{iip,ipsr,ifs}, else use
@@ -904,6 +905,10 @@ finish_pt_regs(struct pt_regs *regs, const pal_min_state_area_t *ms,
 		regs->cr_iip = ms->pmsa_xip;
 		regs->cr_ipsr = ms->pmsa_xpsr;
 		regs->cr_ifs = ms->pmsa_xfs;
+
+		sos->iip = ms->pmsa_iip;
+		sos->ipsr = ms->pmsa_ipsr;
+		sos->ifs = ms->pmsa_ifs;
 	}
 	regs->pr = ms->pmsa_pr;
 	regs->b0 = ms->pmsa_br0;
@@ -1079,7 +1084,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 	memcpy(old_regs, regs, sizeof(*regs));
 	old_regs->loadrs = loadrs;
 	old_unat = old_regs->ar_unat;
-	finish_pt_regs(old_regs, ms, &old_unat);
+	finish_pt_regs(old_regs, sos, &old_unat);
 
 	/* Next stack a struct switch_stack.  mca_asm.S built a partial
 	 * switch_stack, copy it and fill in the blanks using pt_regs and
@@ -1150,7 +1155,7 @@ no_mod:
 	mprintk(KERN_INFO "cpu %d, %s %s, original stack not modified\n",
 			smp_processor_id(), type, msg);
 	old_unat = regs->ar_unat;
-	finish_pt_regs(regs, ms, &old_unat);
+	finish_pt_regs(regs, sos, &old_unat);
 	return previous_current;
 }
 
diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S
index 7461d2573d4..d5bdf9de36b 100644
--- a/arch/ia64/kernel/mca_asm.S
+++ b/arch/ia64/kernel/mca_asm.S
@@ -59,7 +59,7 @@
 ia64_do_tlb_purge:
 #define O(member)	IA64_CPUINFO_##member##_OFFSET
 
-	GET_THIS_PADDR(r2, cpu_info)	// load phys addr of cpu_info into r2
+	GET_THIS_PADDR(r2, ia64_cpu_info) // load phys addr of cpu_info into r2
 	;;
 	addl r17=O(PTCE_STRIDE),r2
 	addl r2=O(PTCE_BASE),r2
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 599b233bef7..5246285a95f 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2200,7 +2200,7 @@ pfm_alloc_file(pfm_context_t *ctx)
 {
 	struct file *file;
 	struct inode *inode;
-	struct dentry *dentry;
+	struct path path;
 	char name[32];
 	struct qstr this;
 
@@ -2225,18 +2225,19 @@ pfm_alloc_file(pfm_context_t *ctx)
 	/*
 	 * allocate a new dcache entry
 	 */
-	dentry = d_alloc(pfmfs_mnt->mnt_sb->s_root, &this);
-	if (!dentry) {
+	path.dentry = d_alloc(pfmfs_mnt->mnt_sb->s_root, &this);
+	if (!path.dentry) {
 		iput(inode);
 		return ERR_PTR(-ENOMEM);
 	}
+	path.mnt = mntget(pfmfs_mnt);
 
-	dentry->d_op = &pfmfs_dentry_operations;
-	d_add(dentry, inode);
+	path.dentry->d_op = &pfmfs_dentry_operations;
+	d_add(path.dentry, inode);
 
-	file = alloc_file(pfmfs_mnt, dentry, FMODE_READ, &pfm_file_ops);
+	file = alloc_file(&path, FMODE_READ, &pfm_file_ops);
 	if (!file) {
-		dput(dentry);
+		path_put(&path);
 		return ERR_PTR(-ENFILE);
 	}
 
diff --git a/arch/ia64/kernel/relocate_kernel.S b/arch/ia64/kernel/relocate_kernel.S
index 32f6fc131fb..c370e02f006 100644
--- a/arch/ia64/kernel/relocate_kernel.S
+++ b/arch/ia64/kernel/relocate_kernel.S
@@ -61,7 +61,7 @@ GLOBAL_ENTRY(relocate_new_kernel)
 
 	// purge all TC entries
 #define O(member)       IA64_CPUINFO_##member##_OFFSET
-        GET_THIS_PADDR(r2, cpu_info)    // load phys addr of cpu_info into r2
+        GET_THIS_PADDR(r2, ia64_cpu_info) // load phys addr of cpu_info into r2
         ;;
         addl r17=O(PTCE_STRIDE),r2
         addl r2=O(PTCE_BASE),r2
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 1de86c96801..a1ea8791977 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -74,7 +74,7 @@ unsigned long __per_cpu_offset[NR_CPUS];
 EXPORT_SYMBOL(__per_cpu_offset);
 #endif
 
-DEFINE_PER_CPU(struct cpuinfo_ia64, cpu_info);
+DEFINE_PER_CPU(struct cpuinfo_ia64, ia64_cpu_info);
 DEFINE_PER_CPU(unsigned long, local_per_cpu_offset);
 unsigned long ia64_cycles_per_usec;
 struct ia64_boot_param *ia64_boot_param;
@@ -566,19 +566,18 @@ setup_arch (char **cmdline_p)
 	early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
+#  ifdef CONFIG_ACPI_HOTPLUG_CPU
 	prefill_possible_map();
-#endif
+#  endif
 	per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
 		32 : cpus_weight(early_cpu_possible_map)),
 		additional_cpus > 0 ? additional_cpus : 0);
 # endif
-#else
-# ifdef CONFIG_SMP
-	smp_build_cpu_map();	/* happens, e.g., with the Ski simulator */
-# endif
 #endif /* CONFIG_APCI_BOOT */
 
+#ifdef CONFIG_SMP
+	smp_build_cpu_map();
+#endif
 	find_memory();
 
 	/* process SAL system table: */
@@ -856,18 +855,6 @@ identify_cpu (struct cpuinfo_ia64 *c)
 }
 
 /*
- * In UP configuration, setup_per_cpu_areas() is defined in
- * include/linux/percpu.h
- */
-#ifdef CONFIG_SMP
-void __init
-setup_per_cpu_areas (void)
-{
-	/* start_kernel() requires this... */
-}
-#endif
-
-/*
  * Do the following calculations:
  *
  * 1. the max. cache line size.
@@ -980,7 +967,7 @@ cpu_init (void)
 	 * depends on the data returned by identify_cpu().  We break the dependency by
 	 * accessing cpu_data() through the canonical per-CPU address.
 	 */
-	cpu_info = cpu_data + ((char *) &__ia64_per_cpu_var(cpu_info) - __per_cpu_start);
+	cpu_info = cpu_data + ((char *) &__ia64_per_cpu_var(ia64_cpu_info) - __per_cpu_start);
 	identify_cpu(cpu_info);
 
 #ifdef CONFIG_MCKINLEY
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 0a0c77b2c98..1295ba327f6 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -166,6 +166,12 @@ SECTIONS
 	}
 #endif
 
+#ifdef	CONFIG_SMP
+  . = ALIGN(PERCPU_PAGE_SIZE);
+  __cpu0_per_cpu = .;
+  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
+#endif
+
   . = ALIGN(PAGE_SIZE);
   __init_end = .;
 
@@ -198,11 +204,6 @@ SECTIONS
   data : { } :data
   .data : AT(ADDR(.data) - LOAD_OFFSET)
 	{
-#ifdef	CONFIG_SMP
-  . = ALIGN(PERCPU_PAGE_SIZE);
-		__cpu0_per_cpu = .;
-  . = . + PERCPU_PAGE_SIZE;	/* cpu0 per-cpu space */
-#endif
 		INIT_TASK_DATA(PAGE_SIZE)
 		CACHELINE_ALIGNED_DATA(SMP_CACHE_BYTES)
 		READ_MOSTLY_DATA(SMP_CACHE_BYTES)
diff --git a/arch/ia64/kvm/asm-offsets.c b/arch/ia64/kvm/asm-offsets.c
index 0c3564a7a03..9324c875caf 100644
--- a/arch/ia64/kvm/asm-offsets.c
+++ b/arch/ia64/kvm/asm-offsets.c
@@ -22,7 +22,6 @@
  *
  */
 
-#include <linux/autoconf.h>
 #include <linux/kvm_host.h>
 #include <linux/kbuild.h>
 
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 2f724d2bf29..54bf5405981 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -154,38 +154,99 @@ static void *cpu_data;
 void * __cpuinit
 per_cpu_init (void)
 {
-	int cpu;
-	static int first_time=1;
+	static bool first_time = true;
+	void *cpu0_data = __cpu0_per_cpu;
+	unsigned int cpu;
+
+	if (!first_time)
+		goto skip;
+	first_time = false;
 
 	/*
-	 * get_free_pages() cannot be used before cpu_init() done.  BSP
-	 * allocates "NR_CPUS" pages for all CPUs to avoid that AP calls
-	 * get_zeroed_page().
+	 * get_free_pages() cannot be used before cpu_init() done.
+	 * BSP allocates PERCPU_PAGE_SIZE bytes for all possible CPUs
+	 * to avoid that AP calls get_zeroed_page().
 	 */
-	if (first_time) {
-		void *cpu0_data = __cpu0_per_cpu;
+	for_each_possible_cpu(cpu) {
+		void *src = cpu == 0 ? cpu0_data : __phys_per_cpu_start;
 
-		first_time=0;
+		memcpy(cpu_data, src, __per_cpu_end - __per_cpu_start);
+		__per_cpu_offset[cpu] = (char *)cpu_data - __per_cpu_start;
+		per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
 
-		__per_cpu_offset[0] = (char *) cpu0_data - __per_cpu_start;
-		per_cpu(local_per_cpu_offset, 0) = __per_cpu_offset[0];
+		/*
+		 * percpu area for cpu0 is moved from the __init area
+		 * which is setup by head.S and used till this point.
+		 * Update ar.k3.  This move is ensures that percpu
+		 * area for cpu0 is on the correct node and its
+		 * virtual address isn't insanely far from other
+		 * percpu areas which is important for congruent
+		 * percpu allocator.
+		 */
+		if (cpu == 0)
+			ia64_set_kr(IA64_KR_PER_CPU_DATA, __pa(cpu_data) -
+				    (unsigned long)__per_cpu_start);
 
-		for (cpu = 1; cpu < NR_CPUS; cpu++) {
-			memcpy(cpu_data, __phys_per_cpu_start, __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char *) cpu_data - __per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
-		}
+		cpu_data += PERCPU_PAGE_SIZE;
 	}
+skip:
 	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
 }
 
 static inline void
 alloc_per_cpu_data(void)
 {
-	cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * NR_CPUS-1,
+	cpu_data = __alloc_bootmem(PERCPU_PAGE_SIZE * num_possible_cpus(),
 				   PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 }
+
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas.  All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init
+setup_per_cpu_areas(void)
+{
+	struct pcpu_alloc_info *ai;
+	struct pcpu_group_info *gi;
+	unsigned int cpu;
+	ssize_t static_size, reserved_size, dyn_size;
+	int rc;
+
+	ai = pcpu_alloc_alloc_info(1, num_possible_cpus());
+	if (!ai)
+		panic("failed to allocate pcpu_alloc_info");
+	gi = &ai->groups[0];
+
+	/* units are assigned consecutively to possible cpus */
+	for_each_possible_cpu(cpu)
+		gi->cpu_map[gi->nr_units++] = cpu;
+
+	/* set parameters */
+	static_size = __per_cpu_end - __per_cpu_start;
+	reserved_size = PERCPU_MODULE_RESERVE;
+	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+	if (dyn_size < 0)
+		panic("percpu area overflow static=%zd reserved=%zd\n",
+		      static_size, reserved_size);
+
+	ai->static_size		= static_size;
+	ai->reserved_size	= reserved_size;
+	ai->dyn_size		= dyn_size;
+	ai->unit_size		= PERCPU_PAGE_SIZE;
+	ai->atom_size		= PAGE_SIZE;
+	ai->alloc_size		= PERCPU_PAGE_SIZE;
+
+	rc = pcpu_setup_first_chunk(ai, __per_cpu_start + __per_cpu_offset[0]);
+	if (rc)
+		panic("failed to setup percpu area (err=%d)", rc);
+
+	pcpu_free_alloc_info(ai);
+}
 #else
 #define alloc_per_cpu_data() do { } while (0)
 #endif /* CONFIG_SMP */
@@ -270,8 +331,8 @@ paging_init (void)
 
 		map_size = PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 			sizeof(struct page));
-		vmalloc_end -= map_size;
-		vmem_map = (struct page *) vmalloc_end;
+		VMALLOC_END -= map_size;
+		vmem_map = (struct page *) VMALLOC_END;
 		efi_memmap_walk(create_mem_map_page_table, NULL);
 
 		/*
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index d85ba98d900..19c4b2195dc 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -143,22 +143,120 @@ static void *per_cpu_node_setup(void *cpu_data, int node)
 	int cpu;
 
 	for_each_possible_early_cpu(cpu) {
-		if (cpu == 0) {
-			void *cpu0_data = __cpu0_per_cpu;
-			__per_cpu_offset[cpu] = (char*)cpu0_data -
-				__per_cpu_start;
-		} else if (node == node_cpuid[cpu].nid) {
-			memcpy(__va(cpu_data), __phys_per_cpu_start,
-			       __per_cpu_end - __per_cpu_start);
-			__per_cpu_offset[cpu] = (char*)__va(cpu_data) -
-				__per_cpu_start;
-			cpu_data += PERCPU_PAGE_SIZE;
-		}
+		void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start;
+
+		if (node != node_cpuid[cpu].nid)
+			continue;
+
+		memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start);
+		__per_cpu_offset[cpu] = (char *)__va(cpu_data) -
+			__per_cpu_start;
+
+		/*
+		 * percpu area for cpu0 is moved from the __init area
+		 * which is setup by head.S and used till this point.
+		 * Update ar.k3.  This move is ensures that percpu
+		 * area for cpu0 is on the correct node and its
+		 * virtual address isn't insanely far from other
+		 * percpu areas which is important for congruent
+		 * percpu allocator.
+		 */
+		if (cpu == 0)
+			ia64_set_kr(IA64_KR_PER_CPU_DATA,
+				    (unsigned long)cpu_data -
+				    (unsigned long)__per_cpu_start);
+
+		cpu_data += PERCPU_PAGE_SIZE;
 	}
 #endif
 	return cpu_data;
 }
 
+#ifdef CONFIG_SMP
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas.  All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	struct pcpu_alloc_info *ai;
+	struct pcpu_group_info *uninitialized_var(gi);
+	unsigned int *cpu_map;
+	void *base;
+	unsigned long base_offset;
+	unsigned int cpu;
+	ssize_t static_size, reserved_size, dyn_size;
+	int node, prev_node, unit, nr_units, rc;
+
+	ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids);
+	if (!ai)
+		panic("failed to allocate pcpu_alloc_info");
+	cpu_map = ai->groups[0].cpu_map;
+
+	/* determine base */
+	base = (void *)ULONG_MAX;
+	for_each_possible_cpu(cpu)
+		base = min(base,
+			   (void *)(__per_cpu_offset[cpu] + __per_cpu_start));
+	base_offset = (void *)__per_cpu_start - base;
+
+	/* build cpu_map, units are grouped by node */
+	unit = 0;
+	for_each_node(node)
+		for_each_possible_cpu(cpu)
+			if (node == node_cpuid[cpu].nid)
+				cpu_map[unit++] = cpu;
+	nr_units = unit;
+
+	/* set basic parameters */
+	static_size = __per_cpu_end - __per_cpu_start;
+	reserved_size = PERCPU_MODULE_RESERVE;
+	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+	if (dyn_size < 0)
+		panic("percpu area overflow static=%zd reserved=%zd\n",
+		      static_size, reserved_size);
+
+	ai->static_size		= static_size;
+	ai->reserved_size	= reserved_size;
+	ai->dyn_size		= dyn_size;
+	ai->unit_size		= PERCPU_PAGE_SIZE;
+	ai->atom_size		= PAGE_SIZE;
+	ai->alloc_size		= PERCPU_PAGE_SIZE;
+
+	/*
+	 * CPUs are put into groups according to node.  Walk cpu_map
+	 * and create new groups at node boundaries.
+	 */
+	prev_node = -1;
+	ai->nr_groups = 0;
+	for (unit = 0; unit < nr_units; unit++) {
+		cpu = cpu_map[unit];
+		node = node_cpuid[cpu].nid;
+
+		if (node == prev_node) {
+			gi->nr_units++;
+			continue;
+		}
+		prev_node = node;
+
+		gi = &ai->groups[ai->nr_groups++];
+		gi->nr_units		= 1;
+		gi->base_offset		= __per_cpu_offset[cpu] + base_offset;
+		gi->cpu_map		= &cpu_map[unit];
+	}
+
+	rc = pcpu_setup_first_chunk(ai, base);
+	if (rc)
+		panic("failed to setup percpu area (err=%d)", rc);
+
+	pcpu_free_alloc_info(ai);
+}
+#endif
+
 /**
  * fill_pernode - initialize pernode data.
  * @node: the node id.
@@ -352,7 +450,8 @@ static void __init initialize_pernode_data(void)
 	/* Set the node_data pointer for each per-cpu struct */
 	for_each_possible_early_cpu(cpu) {
 		node = node_cpuid[cpu].nid;
-		per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
+		per_cpu(ia64_cpu_info, cpu).node_data =
+			mem_data[node].node_data;
 	}
 #else
 	{
@@ -360,7 +459,7 @@ static void __init initialize_pernode_data(void)
 		cpu = 0;
 		node = node_cpuid[cpu].nid;
 		cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
-			((char *)&per_cpu__cpu_info - __per_cpu_start));
+			((char *)&per_cpu__ia64_cpu_info - __per_cpu_start));
 		cpu0_cpu_info->node_data = mem_data[node].node_data;
 	}
 #endif /* CONFIG_SMP */
@@ -666,9 +765,9 @@ void __init paging_init(void)
 	sparse_init();
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-	vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
+	VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
 		sizeof(struct page));
-	vmem_map = (struct page *) vmalloc_end;
+	vmem_map = (struct page *) VMALLOC_END;
 	efi_memmap_walk(create_mem_map_page_table, NULL);
 	printk("Virtual mem_map starts at 0x%p\n", vmem_map);
 #endif
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 1857766a63c..b9609c69343 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -44,8 +44,8 @@ extern void ia64_tlb_init (void);
 unsigned long MAX_DMA_ADDRESS = PAGE_OFFSET + 0x100000000UL;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
-unsigned long vmalloc_end = VMALLOC_END_INIT;
-EXPORT_SYMBOL(vmalloc_end);
+unsigned long VMALLOC_END = VMALLOC_END_INIT;
+EXPORT_SYMBOL(VMALLOC_END);
 struct page *vmem_map;
 EXPORT_SYMBOL(vmem_map);
 #endif
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 2a140627dfd..3dccdd8eb27 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -22,6 +22,12 @@ __ioremap (unsigned long phys_addr)
 }
 
 void __iomem *
+early_ioremap (unsigned long phys_addr, unsigned long size)
+{
+	return __ioremap(phys_addr);
+}
+
+void __iomem *
 ioremap (unsigned long phys_addr, unsigned long size)
 {
 	void __iomem *addr;
@@ -102,6 +108,11 @@ ioremap_nocache (unsigned long phys_addr, unsigned long size)
 EXPORT_SYMBOL(ioremap_nocache);
 
 void
+early_iounmap (volatile void __iomem *addr, unsigned long size)
+{
+}
+
+void
 iounmap (volatile void __iomem *addr)
 {
 	if (REGION_NUMBER(addr) == RGN_GATE)
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index 1176506b2ba..e884ba4e031 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -496,13 +496,13 @@ static int sn2_ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l,
 				stat->change_rid, stat->shub_ptc_flushes, stat->nodes_flushed,
 				stat->deadlocks,
-				1000 * stat->lock_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
-				1000 * stat->shub_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec,
-				1000 * stat->shub_itc_clocks_max / per_cpu(cpu_info, cpu).cyc_per_usec,
+				1000 * stat->lock_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
+				1000 * stat->shub_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
+				1000 * stat->shub_itc_clocks_max / per_cpu(ia64_cpu_info, cpu).cyc_per_usec,
 				stat->shub_ptc_flushes_not_my_mm,
 				stat->deadlocks2,
 				stat->shub_ipi_flushes,
-				1000 * stat->shub_ipi_flushes_itc_clocks / per_cpu(cpu_info, cpu).cyc_per_usec);
+				1000 * stat->shub_ipi_flushes_itc_clocks / per_cpu(ia64_cpu_info, cpu).cyc_per_usec);
 	}
 	return 0;
 }
diff --git a/arch/ia64/sn/pci/tioca_provider.c b/arch/ia64/sn/pci/tioca_provider.c
index 35b2a27d2e7..efb454534e5 100644
--- a/arch/ia64/sn/pci/tioca_provider.c
+++ b/arch/ia64/sn/pci/tioca_provider.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/pci.h>
+#include <linux/bitmap.h>
 #include <asm/sn/sn_sal.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/io.h>
@@ -369,7 +370,7 @@ tioca_dma_d48(struct pci_dev *pdev, u64 paddr)
 static dma_addr_t
 tioca_dma_mapped(struct pci_dev *pdev, unsigned long paddr, size_t req_size)
 {
-	int i, ps, ps_shift, entry, entries, mapsize, last_entry;
+	int ps, ps_shift, entry, entries, mapsize;
 	u64 xio_addr, end_xio_addr;
 	struct tioca_common *tioca_common;
 	struct tioca_kernel *tioca_kern;
@@ -410,23 +411,13 @@ tioca_dma_mapped(struct pci_dev *pdev, unsigned long paddr, size_t req_size)
 	map = tioca_kern->ca_pcigart_pagemap;
 	mapsize = tioca_kern->ca_pcigart_entries;
 
-	entry = find_first_zero_bit(map, mapsize);
-	while (entry < mapsize) {
-		last_entry = find_next_bit(map, mapsize, entry);
-
-		if (last_entry - entry >= entries)
-			break;
-
-		entry = find_next_zero_bit(map, mapsize, last_entry);
-	}
-
-	if (entry > mapsize) {
+	entry = bitmap_find_next_zero_area(map, mapsize, 0, entries, 0);
+	if (entry >= mapsize) {
 		kfree(ca_dmamap);
 		goto map_return;
 	}
 
-	for (i = 0; i < entries; i++)
-		set_bit(entry + i, map);
+	bitmap_set(map, entry, entries);
 
 	bus_addr = tioca_kern->ca_pciap_base + (entry * ps);
 
diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c
index f042e192d2f..a3fb7cf9ae1 100644
--- a/arch/ia64/xen/irq_xen.c
+++ b/arch/ia64/xen/irq_xen.c
@@ -63,19 +63,19 @@ xen_free_irq_vector(int vector)
 }
 
 
-static DEFINE_PER_CPU(int, timer_irq) = -1;
-static DEFINE_PER_CPU(int, ipi_irq) = -1;
-static DEFINE_PER_CPU(int, resched_irq) = -1;
-static DEFINE_PER_CPU(int, cmc_irq) = -1;
-static DEFINE_PER_CPU(int, cmcp_irq) = -1;
-static DEFINE_PER_CPU(int, cpep_irq) = -1;
+static DEFINE_PER_CPU(int, xen_timer_irq) = -1;
+static DEFINE_PER_CPU(int, xen_ipi_irq) = -1;
+static DEFINE_PER_CPU(int, xen_resched_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cmc_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cmcp_irq) = -1;
+static DEFINE_PER_CPU(int, xen_cpep_irq) = -1;
 #define NAME_SIZE	15
-static DEFINE_PER_CPU(char[NAME_SIZE], timer_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], ipi_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], resched_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmc_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cmcp_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], cpep_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_timer_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_ipi_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_resched_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmc_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmcp_name);
+static DEFINE_PER_CPU(char[NAME_SIZE], xen_cpep_name);
 #undef NAME_SIZE
 
 struct saved_irq {
@@ -144,64 +144,64 @@ __xen_register_percpu_irq(unsigned int cpu, unsigned int vec,
 	if (xen_slab_ready) {
 		switch (vec) {
 		case IA64_TIMER_VECTOR:
-			snprintf(per_cpu(timer_name, cpu),
-				 sizeof(per_cpu(timer_name, cpu)),
+			snprintf(per_cpu(xen_timer_name, cpu),
+				 sizeof(per_cpu(xen_timer_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_virq_to_irqhandler(VIRQ_ITC, cpu,
 				action->handler, action->flags,
-				per_cpu(timer_name, cpu), action->dev_id);
-			per_cpu(timer_irq, cpu) = irq;
+				per_cpu(xen_timer_name, cpu), action->dev_id);
+			per_cpu(xen_timer_irq, cpu) = irq;
 			break;
 		case IA64_IPI_RESCHEDULE:
-			snprintf(per_cpu(resched_name, cpu),
-				 sizeof(per_cpu(resched_name, cpu)),
+			snprintf(per_cpu(xen_resched_name, cpu),
+				 sizeof(per_cpu(xen_resched_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu,
 				action->handler, action->flags,
-				per_cpu(resched_name, cpu), action->dev_id);
-			per_cpu(resched_irq, cpu) = irq;
+				per_cpu(xen_resched_name, cpu), action->dev_id);
+			per_cpu(xen_resched_irq, cpu) = irq;
 			break;
 		case IA64_IPI_VECTOR:
-			snprintf(per_cpu(ipi_name, cpu),
-				 sizeof(per_cpu(ipi_name, cpu)),
+			snprintf(per_cpu(xen_ipi_name, cpu),
+				 sizeof(per_cpu(xen_ipi_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_IPI_VECTOR, cpu,
 				action->handler, action->flags,
-				per_cpu(ipi_name, cpu), action->dev_id);
-			per_cpu(ipi_irq, cpu) = irq;
+				per_cpu(xen_ipi_name, cpu), action->dev_id);
+			per_cpu(xen_ipi_irq, cpu) = irq;
 			break;
 		case IA64_CMC_VECTOR:
-			snprintf(per_cpu(cmc_name, cpu),
-				 sizeof(per_cpu(cmc_name, cpu)),
+			snprintf(per_cpu(xen_cmc_name, cpu),
+				 sizeof(per_cpu(xen_cmc_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_virq_to_irqhandler(VIRQ_MCA_CMC, cpu,
-						      action->handler,
-						      action->flags,
-						      per_cpu(cmc_name, cpu),
-						      action->dev_id);
-			per_cpu(cmc_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cmc_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cmc_irq, cpu) = irq;
 			break;
 		case IA64_CMCP_VECTOR:
-			snprintf(per_cpu(cmcp_name, cpu),
-				 sizeof(per_cpu(cmcp_name, cpu)),
+			snprintf(per_cpu(xen_cmcp_name, cpu),
+				 sizeof(per_cpu(xen_cmcp_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_CMCP_VECTOR, cpu,
-						     action->handler,
-						     action->flags,
-						     per_cpu(cmcp_name, cpu),
-						     action->dev_id);
-			per_cpu(cmcp_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cmcp_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cmcp_irq, cpu) = irq;
 			break;
 		case IA64_CPEP_VECTOR:
-			snprintf(per_cpu(cpep_name, cpu),
-				 sizeof(per_cpu(cpep_name, cpu)),
+			snprintf(per_cpu(xen_cpep_name, cpu),
+				 sizeof(per_cpu(xen_cpep_name, cpu)),
 				 "%s%d", action->name, cpu);
 			irq = bind_ipi_to_irqhandler(XEN_CPEP_VECTOR, cpu,
-						     action->handler,
-						     action->flags,
-						     per_cpu(cpep_name, cpu),
-						     action->dev_id);
-			per_cpu(cpep_irq, cpu) = irq;
+						action->handler,
+						action->flags,
+						per_cpu(xen_cpep_name, cpu),
+						action->dev_id);
+			per_cpu(xen_cpep_irq, cpu) = irq;
 			break;
 		case IA64_CPE_VECTOR:
 		case IA64_MCA_RENDEZ_VECTOR:
@@ -275,30 +275,33 @@ unbind_evtchn_callback(struct notifier_block *nfb,
 
 	if (action == CPU_DEAD) {
 		/* Unregister evtchn.  */
-		if (per_cpu(cpep_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cpep_irq, cpu), NULL);
-			per_cpu(cpep_irq, cpu) = -1;
+		if (per_cpu(xen_cpep_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cpep_irq, cpu),
+					       NULL);
+			per_cpu(xen_cpep_irq, cpu) = -1;
 		}
-		if (per_cpu(cmcp_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cmcp_irq, cpu), NULL);
-			per_cpu(cmcp_irq, cpu) = -1;
+		if (per_cpu(xen_cmcp_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cmcp_irq, cpu),
+					       NULL);
+			per_cpu(xen_cmcp_irq, cpu) = -1;
 		}
-		if (per_cpu(cmc_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(cmc_irq, cpu), NULL);
-			per_cpu(cmc_irq, cpu) = -1;
+		if (per_cpu(xen_cmc_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_cmc_irq, cpu), NULL);
+			per_cpu(xen_cmc_irq, cpu) = -1;
 		}
-		if (per_cpu(ipi_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(ipi_irq, cpu), NULL);
-			per_cpu(ipi_irq, cpu) = -1;
+		if (per_cpu(xen_ipi_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_ipi_irq, cpu), NULL);
+			per_cpu(xen_ipi_irq, cpu) = -1;
 		}
-		if (per_cpu(resched_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(resched_irq, cpu),
-						NULL);
-			per_cpu(resched_irq, cpu) = -1;
+		if (per_cpu(xen_resched_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu),
+					       NULL);
+			per_cpu(xen_resched_irq, cpu) = -1;
 		}
-		if (per_cpu(timer_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(timer_irq, cpu), NULL);
-			per_cpu(timer_irq, cpu) = -1;
+		if (per_cpu(xen_timer_irq, cpu) >= 0) {
+			unbind_from_irqhandler(per_cpu(xen_timer_irq, cpu),
+					       NULL);
+			per_cpu(xen_timer_irq, cpu) = -1;
 		}
 	}
 	return NOTIFY_OK;
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
index dbeadb9c8e2..c1c544513e8 100644
--- a/arch/ia64/xen/time.c
+++ b/arch/ia64/xen/time.c
@@ -34,15 +34,15 @@
 
 #include "../kernel/fsyscall_gtod_data.h"
 
-DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
-DEFINE_PER_CPU(unsigned long, processed_stolen_time);
-DEFINE_PER_CPU(unsigned long, processed_blocked_time);
+static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
+static DEFINE_PER_CPU(unsigned long, xen_stolen_time);
+static DEFINE_PER_CPU(unsigned long, xen_blocked_time);
 
 /* taken from i386/kernel/time-xen.c */
 static void xen_init_missing_ticks_accounting(int cpu)
 {
 	struct vcpu_register_runstate_memory_area area;
-	struct vcpu_runstate_info *runstate = &per_cpu(runstate, cpu);
+	struct vcpu_runstate_info *runstate = &per_cpu(xen_runstate, cpu);
 	int rc;
 
 	memset(runstate, 0, sizeof(*runstate));
@@ -52,8 +52,8 @@ static void xen_init_missing_ticks_accounting(int cpu)
 				&area);
 	WARN_ON(rc && rc != -ENOSYS);
 
-	per_cpu(processed_blocked_time, cpu) = runstate->time[RUNSTATE_blocked];
-	per_cpu(processed_stolen_time, cpu) = runstate->time[RUNSTATE_runnable]
+	per_cpu(xen_blocked_time, cpu) = runstate->time[RUNSTATE_blocked];
+	per_cpu(xen_stolen_time, cpu) = runstate->time[RUNSTATE_runnable]
 					    + runstate->time[RUNSTATE_offline];
 }
 
@@ -68,7 +68,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
 
 	BUG_ON(preemptible());
 
-	state = &__get_cpu_var(runstate);
+	state = &__get_cpu_var(xen_runstate);
 
 	/*
 	 * The runstate info is always updated by the hypervisor on
@@ -103,12 +103,12 @@ consider_steal_time(unsigned long new_itm)
 	 * This function just checks and reject this effect.
 	 */
 	if (!time_after_eq(runstate.time[RUNSTATE_blocked],
-			   per_cpu(processed_blocked_time, cpu)))
+			   per_cpu(xen_blocked_time, cpu)))
 		blocked = 0;
 
 	if (!time_after_eq(runstate.time[RUNSTATE_runnable] +
 			   runstate.time[RUNSTATE_offline],
-			   per_cpu(processed_stolen_time, cpu)))
+			   per_cpu(xen_stolen_time, cpu)))
 		stolen = 0;
 
 	if (!time_after(delta_itm + new_itm, ia64_get_itc()))
@@ -147,8 +147,8 @@ consider_steal_time(unsigned long new_itm)
 		} else {
 			local_cpu_data->itm_next = delta_itm + new_itm;
 		}
-		per_cpu(processed_stolen_time, cpu) += NS_PER_TICK * stolen;
-		per_cpu(processed_blocked_time, cpu) += NS_PER_TICK * blocked;
+		per_cpu(xen_stolen_time, cpu) += NS_PER_TICK * stolen;
+		per_cpu(xen_blocked_time, cpu) += NS_PER_TICK * blocked;
 	}
 	return delta_itm;
 }