Merge branch 'master' into percpu

Conflicts:
	arch/powerpc/platforms/pseries/hvCall.S
	include/linux/percpu.h

54 files changed, 340 insertions, 502 deletions

diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index e7cbaa02cd0b..475e2725fbde 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 674a8374c6d9..e14c492a8a93 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);
@@ -1381,7 +1391,7 @@ sba_coalesce_chunks(struct ioc *ioc, struct device *dev,
 #endif
 
 			/*
-			** Not virtually contigous.
+			** Not virtually contiguous.
 			** Terminate prev chunk.
 			** Start a new chunk.
 			**
@@ -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 9a3abf58cea3..657725742617 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/ia32/ia32_entry.S b/arch/ia64/ia32/ia32_entry.S
index af9405cd70e5..2fd7479aa216 100644
--- a/arch/ia64/ia32/ia32_entry.S
+++ b/arch/ia64/ia32/ia32_entry.S
@@ -79,7 +79,7 @@ GLOBAL_ENTRY(ia32_ret_from_clone)
 (p6)	br.cond.spnt .ia32_strace_check_retval
 	;;					// prevent RAW on r8
 END(ia32_ret_from_clone)
-	// fall thrugh
+	// fall through
 GLOBAL_ENTRY(ia32_ret_from_syscall)
 	PT_REGS_UNWIND_INFO(0)
 
@@ -327,7 +327,7 @@ ia32_syscall_table:
 	data8 compat_sys_writev
 	data8 sys_getsid
 	data8 sys_fdatasync
-	data8 sys32_sysctl
+	data8 compat_sys_sysctl
 	data8 sys_mlock		  /* 150 */
 	data8 sys_munlock
 	data8 sys_mlockall
diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c
index 625ed8f76fce..045b746b9808 100644
--- a/arch/ia64/ia32/sys_ia32.c
+++ b/arch/ia64/ia32/sys_ia32.c
@@ -858,6 +858,9 @@ ia32_do_mmap (struct file *file, unsigned long addr, unsigned long len, int prot
 
 	prot = get_prot32(prot);
 
+	if (flags & MAP_HUGETLB)
+		return -ENOMEM;
+
 #if PAGE_SHIFT > IA32_PAGE_SHIFT
 	mutex_lock(&ia32_mmap_mutex);
 	{
@@ -1628,61 +1631,6 @@ sys32_msync (unsigned int start, unsigned int len, int flags)
 	return sys_msync(addr, len + (start - addr), flags);
 }
 
-struct sysctl32 {
-	unsigned int	name;
-	int		nlen;
-	unsigned int	oldval;
-	unsigned int	oldlenp;
-	unsigned int	newval;
-	unsigned int	newlen;
-	unsigned int	__unused[4];
-};
-
-#ifdef CONFIG_SYSCTL_SYSCALL
-asmlinkage long
-sys32_sysctl (struct sysctl32 __user *args)
-{
-	struct sysctl32 a32;
-	mm_segment_t old_fs = get_fs ();
-	void __user *oldvalp, *newvalp;
-	size_t oldlen;
-	int __user *namep;
-	long ret;
-
-	if (copy_from_user(&a32, args, sizeof(a32)))
-		return -EFAULT;
-
-	/*
-	 * We need to pre-validate these because we have to disable address checking
-	 * before calling do_sysctl() because of OLDLEN but we can't run the risk of the
-	 * user specifying bad addresses here.  Well, since we're dealing with 32 bit
-	 * addresses, we KNOW that access_ok() will always succeed, so this is an
-	 * expensive NOP, but so what...
-	 */
-	namep = (int __user *) compat_ptr(a32.name);
-	oldvalp = compat_ptr(a32.oldval);
-	newvalp = compat_ptr(a32.newval);
-
-	if ((oldvalp && get_user(oldlen, (int __user *) compat_ptr(a32.oldlenp)))
-	    || !access_ok(VERIFY_WRITE, namep, 0)
-	    || !access_ok(VERIFY_WRITE, oldvalp, 0)
-	    || !access_ok(VERIFY_WRITE, newvalp, 0))
-		return -EFAULT;
-
-	set_fs(KERNEL_DS);
-	lock_kernel();
-	ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *) &oldlen,
-			newvalp, (size_t) a32.newlen);
-	unlock_kernel();
-	set_fs(old_fs);
-
-	if (oldvalp && put_user (oldlen, (int __user *) compat_ptr(a32.oldlenp)))
-		return -EFAULT;
-
-	return ret;
-}
-#endif
-
 asmlinkage long
 sys32_newuname (struct new_utsname __user *name)
 {
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index 91df9686a0da..7ae58892ba8d 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 000000000000..d370ee36a182
--- /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 57a2787bc9fb..6ebc229a1c51 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/cacheflush.h b/arch/ia64/include/asm/cacheflush.h
index c8ce2719fee8..429eefc93ee7 100644
--- a/arch/ia64/include/asm/cacheflush.h
+++ b/arch/ia64/include/asm/cacheflush.h
@@ -25,6 +25,7 @@
 #define flush_cache_vmap(start, end)		do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)			\
 do {						\
 	clear_bit(PG_arch_1, &(page)->flags);	\
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 8d3c79cd81e7..7d09a09cdaad 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 86eddee029cb..e14108b19c09 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 91619b31dbf5..bf2e37493e04 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 0d9d16e2d949..cc8335eb3110 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 5282546cdf82..91b920fd7d53 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/kvm.h b/arch/ia64/include/asm/kvm.h
index 18a7e49abbc5..bc90c75adf67 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -60,6 +60,7 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_PIC_MASTER   0
 #define KVM_IRQCHIP_PIC_SLAVE    1
 #define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
 
 #define KVM_CONTEXT_SIZE	8*1024
 
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index d9b6325a9328..a362e67e0ca6 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -475,7 +475,6 @@ struct kvm_arch {
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
 	int iommu_flags;
-	struct hlist_head irq_ack_notifier_list;
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
diff --git a/arch/ia64/include/asm/mca.h b/arch/ia64/include/asm/mca.h
index c171cdf0a789..43f96ab18fa0 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/numa.h b/arch/ia64/include/asm/numa.h
index 3499ff57bf42..6a8a27cfae3e 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/perfmon_default_smpl.h b/arch/ia64/include/asm/perfmon_default_smpl.h
index 48822c0811d8..74724b24c2b7 100644
--- a/arch/ia64/include/asm/perfmon_default_smpl.h
+++ b/arch/ia64/include/asm/perfmon_default_smpl.h
@@ -67,7 +67,7 @@ typedef struct {
         unsigned long   ip;                     /* where did the overflow interrupt happened  */
         unsigned long   tstamp;                 /* ar.itc when entering perfmon intr. handler */
 
-        unsigned short  cpu;                    /* cpu on which the overfow occured */
+        unsigned short  cpu;                    /* cpu on which the overflow occured */
         unsigned short  set;                    /* event set active when overflow ocurred   */
         int    		tgid;              	/* thread group id (for NPTL, this is getpid()) */
 } pfm_default_smpl_entry_t;
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
index fbee74b15782..e8762688e8e3 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/sn/shubio.h b/arch/ia64/include/asm/sn/shubio.h
index 22a6f18a5313..6052422a22b3 100644
--- a/arch/ia64/include/asm/sn/shubio.h
+++ b/arch/ia64/include/asm/sn/shubio.h
@@ -3289,7 +3289,7 @@ typedef ii_icrb0_e_u_t icrbe_t;
 #define IIO_IIDSR_LVL_SHIFT     0
 #define IIO_IIDSR_LVL_MASK      0x000000ff
 
-/* Xtalk timeout threshhold register (IIO_IXTT) */
+/* Xtalk timeout threshold register (IIO_IXTT) */
 #define IXTT_RRSP_TO_SHFT	55	/* read response timeout */
 #define IXTT_RRSP_TO_MASK	(0x1FULL << IXTT_RRSP_TO_SHFT)
 #define IXTT_RRSP_PS_SHFT	32	/* read responsed TO prescalar */
diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h
index 0b0d5ff062e5..51427eaa51ba 100644
--- a/arch/ia64/include/asm/socket.h
+++ b/arch/ia64/include/asm/socket.h
@@ -69,4 +69,6 @@
 #define SO_PROTOCOL		38
 #define SO_DOMAIN		39
 
+#define SO_RXQ_OVFL             40
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 30bb930e1111..1a91c9121d17 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
@@ -25,108 +25,128 @@
  * by atomically noting the tail and incrementing it by one (thus adding
  * ourself to the queue and noting our position), then waiting until the head
  * becomes equal to the the initial value of the tail.
+ * The pad bits in the middle are used to prevent the next_ticket number
+ * overflowing into the now_serving number.
  *
- *   63                     32  31                      0
+ *   31             17  16    15  14                    0
  *  +----------------------------------------------------+
- *  |  next_ticket_number      |     now_serving         |
+ *  |  now_serving     | padding |   next_ticket         |
  *  +----------------------------------------------------+
  */
 
-#define TICKET_SHIFT	32
+#define TICKET_SHIFT	17
+#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, turn, now_serving;
+	int	*p = (int *)&lock->lock, ticket, serve;
 
-	now_serving = *p;
-	turn = ia64_fetchadd(1, p+1, acq);
+	ticket = ia64_fetchadd(1, p, acq);
 
-	if (turn == now_serving)
+	if (!(((ticket >> TICKET_SHIFT) ^ ticket) & TICKET_MASK))
 		return;
 
-	do {
+	ia64_invala();
+
+	for (;;) {
+		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(serve) : "r"(p) : "memory");
+
+		if (!(((serve >> TICKET_SHIFT) ^ ticket) & TICKET_MASK))
+			return;
 		cpu_relax();
-	} while (ACCESS_ONCE(*p) != turn);
+	}
 }
 
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
-	long tmp = ACCESS_ONCE(lock->lock), try;
-
-	if (!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1L << TICKET_SHIFT) - 1))) {
-		try = tmp + (1L << TICKET_SHIFT);
+	int tmp = ACCESS_ONCE(lock->lock);
 
-		return ia64_cmpxchg(acq, &lock->lock, tmp, try, sizeof (tmp)) == tmp;
-	}
+	if (!(((tmp >> TICKET_SHIFT) ^ tmp) & TICKET_MASK))
+		return ia64_cmpxchg(acq, &lock->lock, tmp, tmp + 1, sizeof (tmp)) == tmp;
 	return 0;
 }
 
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
-	int	*p = (int *)&lock->lock;
+	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
-	(void)ia64_fetchadd(1, p, rel);
+	asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p));
+	ACCESS_ONCE(*p) = (tmp + 2) & ~1;
 }
 
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	int	*p = (int *)&lock->lock, ticket;
+
+	ia64_invala();
+
+	for (;;) {
+		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(ticket) : "r"(p) : "memory");
+		if (!(((ticket >> TICKET_SHIFT) ^ ticket) & TICKET_MASK))
+			return;
+		cpu_relax();
+	}
+}
+
+static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	long tmp = ACCESS_ONCE(lock->lock);
 
-	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1L << TICKET_SHIFT) - 1));
+	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 >> TICKET_SHIFT) - tmp) & ((1L << TICKET_SHIFT) - 1)) > 1;
+	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)
 {
-	while (__raw_spin_is_locked(lock))
-		cpu_relax();
+	__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"
@@ -149,15 +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);			\
@@ -168,16 +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"
@@ -201,9 +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;							\
 										\
@@ -215,7 +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();
@@ -224,9 +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);					\
@@ -237,7 +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);			\
@@ -245,7 +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;
@@ -253,10 +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;
@@ -265,8 +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 b61d136d9bc2..e2b42a52a6d3 100644
--- a/arch/ia64/include/asm/spinlock_types.h
+++ b/arch/ia64/include/asm/spinlock_types.h
@@ -6,16 +6,16 @@
 #endif
 
 typedef struct {
-	volatile unsigned long lock;
-} raw_spinlock_t;
+	volatile unsigned int lock;
+} 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/include/asm/swiotlb.h b/arch/ia64/include/asm/swiotlb.h
index dcbaea7ce128..f0acde68aaea 100644
--- a/arch/ia64/include/asm/swiotlb.h
+++ b/arch/ia64/include/asm/swiotlb.h
@@ -4,8 +4,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/swiotlb.h>
 
-extern int swiotlb_force;
-
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
 extern void pci_swiotlb_init(void);
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 5a5347f5c4e4..10a8f21ca9e3 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -311,11 +311,12 @@
 #define __NR_preadv			1319
 #define __NR_pwritev			1320
 #define __NR_rt_tgsigqueueinfo		1321
+#define __NR_recvmmsg			1322
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls			298 /* length of syscall table */
+#define NR_syscalls			299 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/asm/xen/hypervisor.h b/arch/ia64/include/asm/xen/hypervisor.h
index 88afb54501e4..67455c2ed2b1 100644
--- a/arch/ia64/include/asm/xen/hypervisor.h
+++ b/arch/ia64/include/asm/xen/hypervisor.h
@@ -37,35 +37,9 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>	/* to compile feature.c */
 #include <xen/features.h>		/* to comiple xen-netfront.c */
+#include <xen/xen.h>
 #include <asm/xen/hypercall.h>
 
-/* xen_domain_type is set before executing any C code by early_xen_setup */
-enum xen_domain_type {
-	XEN_NATIVE,	/* running on bare hardware */
-	XEN_PV_DOMAIN,	/* running in a PV domain */
-	XEN_HVM_DOMAIN,	/* running in a Xen hvm domain*/
-};
-
-#ifdef CONFIG_XEN
-extern enum xen_domain_type xen_domain_type;
-#else
-#define xen_domain_type		XEN_NATIVE
-#endif
-
-#define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain() &&			\
-				 xen_domain_type == XEN_PV_DOMAIN)
-#define xen_hvm_domain()	(xen_domain() &&			\
-				 xen_domain_type == XEN_HVM_DOMAIN)
-
-#ifdef CONFIG_XEN_DOM0
-#define xen_initial_domain()	(xen_pv_domain() &&			\
-				 (xen_start_info->flags & SIF_INITDOMAIN))
-#else
-#define xen_initial_domain()	(0)
-#endif
-
-
 #ifdef CONFIG_XEN
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 6b7edcab0cb5..e1236349c99f 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 dbda7bde6112..000000000000
--- 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/crash.c b/arch/ia64/kernel/crash.c
index 6631a9dfafdc..b942f4032d7a 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -239,32 +239,29 @@ kdump_init_notifier(struct notifier_block *self, unsigned long val, void *data)
 #ifdef CONFIG_SYSCTL
 static ctl_table kdump_ctl_table[] = {
 	{
-		.ctl_name = CTL_UNNUMBERED,
 		.procname = "kdump_on_init",
 		.data = &kdump_on_init,
 		.maxlen = sizeof(int),
 		.mode = 0644,
-		.proc_handler = &proc_dointvec,
+		.proc_handler = proc_dointvec,
 	},
 	{
-		.ctl_name = CTL_UNNUMBERED,
 		.procname = "kdump_on_fatal_mca",
 		.data = &kdump_on_fatal_mca,
 		.maxlen = sizeof(int),
 		.mode = 0644,
-		.proc_handler = &proc_dointvec,
+		.proc_handler = proc_dointvec,
 	},
-	{ .ctl_name = 0 }
+	{ }
 };
 
 static ctl_table sys_table[] = {
 	{
-	  .ctl_name = CTL_KERN,
 	  .procname = "kernel",
 	  .mode = 0555,
 	  .child = kdump_ctl_table,
 	},
-	{ .ctl_name = 0 }
+	{ }
 };
 #endif
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index d0e7d37017b4..d75b872ca4dc 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1806,6 +1806,7 @@ sys_call_table:
 	data8 sys_preadv
 	data8 sys_pwritev			// 1320
 	data8 sys_rt_tgsigqueueinfo
+	data8 sys_recvmmsg
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/ia64/kernel/esi.c b/arch/ia64/kernel/esi.c
index d5764a3d74af..b091111270cb 100644
--- a/arch/ia64/kernel/esi.c
+++ b/arch/ia64/kernel/esi.c
@@ -84,7 +84,7 @@ static int __init esi_init (void)
 		      case ESI_DESC_ENTRY_POINT:
 			break;
 		      default:
-			printk(KERN_WARNING "Unkown table type %d found in "
+			printk(KERN_WARNING "Unknown table type %d found in "
 			       "ESI table, ignoring rest of table\n", *p);
 			return -ENODEV;
 		}
diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c
index dab4d393908c..95ac77aeae9b 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 7d8951229e7c..94ee9d067cbd 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 dd9d7b54f1a1..d4093a173a3e 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 d2877a7bfe2e..32f2639e9b0a 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -887,6 +887,65 @@ ia64_mca_modify_comm(const struct task_struct *previous_current)
 	memcpy(current->comm, comm, sizeof(current->comm));
 }
 
+static void
+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
+	 * pmsa_{xip,xpsr,xfs}
+	 */
+	if (ia64_psr(regs)->ic) {
+		regs->cr_iip = ms->pmsa_iip;
+		regs->cr_ipsr = ms->pmsa_ipsr;
+		regs->cr_ifs = ms->pmsa_ifs;
+	} else {
+		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;
+	regs->ar_rsc = ms->pmsa_rsc;
+	copy_reg(&ms->pmsa_gr[1-1], ms->pmsa_nat_bits, &regs->r1, nat);
+	copy_reg(&ms->pmsa_gr[2-1], ms->pmsa_nat_bits, &regs->r2, nat);
+	copy_reg(&ms->pmsa_gr[3-1], ms->pmsa_nat_bits, &regs->r3, nat);
+	copy_reg(&ms->pmsa_gr[8-1], ms->pmsa_nat_bits, &regs->r8, nat);
+	copy_reg(&ms->pmsa_gr[9-1], ms->pmsa_nat_bits, &regs->r9, nat);
+	copy_reg(&ms->pmsa_gr[10-1], ms->pmsa_nat_bits, &regs->r10, nat);
+	copy_reg(&ms->pmsa_gr[11-1], ms->pmsa_nat_bits, &regs->r11, nat);
+	copy_reg(&ms->pmsa_gr[12-1], ms->pmsa_nat_bits, &regs->r12, nat);
+	copy_reg(&ms->pmsa_gr[13-1], ms->pmsa_nat_bits, &regs->r13, nat);
+	copy_reg(&ms->pmsa_gr[14-1], ms->pmsa_nat_bits, &regs->r14, nat);
+	copy_reg(&ms->pmsa_gr[15-1], ms->pmsa_nat_bits, &regs->r15, nat);
+	if (ia64_psr(regs)->bn)
+		bank = ms->pmsa_bank1_gr;
+	else
+		bank = ms->pmsa_bank0_gr;
+	copy_reg(&bank[16-16], ms->pmsa_nat_bits, &regs->r16, nat);
+	copy_reg(&bank[17-16], ms->pmsa_nat_bits, &regs->r17, nat);
+	copy_reg(&bank[18-16], ms->pmsa_nat_bits, &regs->r18, nat);
+	copy_reg(&bank[19-16], ms->pmsa_nat_bits, &regs->r19, nat);
+	copy_reg(&bank[20-16], ms->pmsa_nat_bits, &regs->r20, nat);
+	copy_reg(&bank[21-16], ms->pmsa_nat_bits, &regs->r21, nat);
+	copy_reg(&bank[22-16], ms->pmsa_nat_bits, &regs->r22, nat);
+	copy_reg(&bank[23-16], ms->pmsa_nat_bits, &regs->r23, nat);
+	copy_reg(&bank[24-16], ms->pmsa_nat_bits, &regs->r24, nat);
+	copy_reg(&bank[25-16], ms->pmsa_nat_bits, &regs->r25, nat);
+	copy_reg(&bank[26-16], ms->pmsa_nat_bits, &regs->r26, nat);
+	copy_reg(&bank[27-16], ms->pmsa_nat_bits, &regs->r27, nat);
+	copy_reg(&bank[28-16], ms->pmsa_nat_bits, &regs->r28, nat);
+	copy_reg(&bank[29-16], ms->pmsa_nat_bits, &regs->r29, nat);
+	copy_reg(&bank[30-16], ms->pmsa_nat_bits, &regs->r30, nat);
+	copy_reg(&bank[31-16], ms->pmsa_nat_bits, &regs->r31, nat);
+}
+
 /* On entry to this routine, we are running on the per cpu stack, see
  * mca_asm.h.  The original stack has not been touched by this event.  Some of
  * the original stack's registers will be in the RBS on this stack.  This stack
@@ -921,7 +980,6 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 	u64 r12 = ms->pmsa_gr[12-1], r13 = ms->pmsa_gr[13-1];
 	u64 ar_bspstore = regs->ar_bspstore;
 	u64 ar_bsp = regs->ar_bspstore + (loadrs >> 16);
-	const u64 *bank;
 	const char *msg;
 	int cpu = smp_processor_id();
 
@@ -1024,54 +1082,9 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 	p = (char *)r12 - sizeof(*regs);
 	old_regs = (struct pt_regs *)p;
 	memcpy(old_regs, regs, sizeof(*regs));
-	/* If ipsr.ic then use pmsa_{iip,ipsr,ifs}, else use
-	 * pmsa_{xip,xpsr,xfs}
-	 */
-	if (ia64_psr(regs)->ic) {
-		old_regs->cr_iip = ms->pmsa_iip;
-		old_regs->cr_ipsr = ms->pmsa_ipsr;
-		old_regs->cr_ifs = ms->pmsa_ifs;
-	} else {
-		old_regs->cr_iip = ms->pmsa_xip;
-		old_regs->cr_ipsr = ms->pmsa_xpsr;
-		old_regs->cr_ifs = ms->pmsa_xfs;
-	}
-	old_regs->pr = ms->pmsa_pr;
-	old_regs->b0 = ms->pmsa_br0;
 	old_regs->loadrs = loadrs;
-	old_regs->ar_rsc = ms->pmsa_rsc;
 	old_unat = old_regs->ar_unat;
-	copy_reg(&ms->pmsa_gr[1-1], ms->pmsa_nat_bits, &old_regs->r1, &old_unat);
-	copy_reg(&ms->pmsa_gr[2-1], ms->pmsa_nat_bits, &old_regs->r2, &old_unat);
-	copy_reg(&ms->pmsa_gr[3-1], ms->pmsa_nat_bits, &old_regs->r3, &old_unat);
-	copy_reg(&ms->pmsa_gr[8-1], ms->pmsa_nat_bits, &old_regs->r8, &old_unat);
-	copy_reg(&ms->pmsa_gr[9-1], ms->pmsa_nat_bits, &old_regs->r9, &old_unat);
-	copy_reg(&ms->pmsa_gr[10-1], ms->pmsa_nat_bits, &old_regs->r10, &old_unat);
-	copy_reg(&ms->pmsa_gr[11-1], ms->pmsa_nat_bits, &old_regs->r11, &old_unat);
-	copy_reg(&ms->pmsa_gr[12-1], ms->pmsa_nat_bits, &old_regs->r12, &old_unat);
-	copy_reg(&ms->pmsa_gr[13-1], ms->pmsa_nat_bits, &old_regs->r13, &old_unat);
-	copy_reg(&ms->pmsa_gr[14-1], ms->pmsa_nat_bits, &old_regs->r14, &old_unat);
-	copy_reg(&ms->pmsa_gr[15-1], ms->pmsa_nat_bits, &old_regs->r15, &old_unat);
-	if (ia64_psr(old_regs)->bn)
-		bank = ms->pmsa_bank1_gr;
-	else
-		bank = ms->pmsa_bank0_gr;
-	copy_reg(&bank[16-16], ms->pmsa_nat_bits, &old_regs->r16, &old_unat);
-	copy_reg(&bank[17-16], ms->pmsa_nat_bits, &old_regs->r17, &old_unat);
-	copy_reg(&bank[18-16], ms->pmsa_nat_bits, &old_regs->r18, &old_unat);
-	copy_reg(&bank[19-16], ms->pmsa_nat_bits, &old_regs->r19, &old_unat);
-	copy_reg(&bank[20-16], ms->pmsa_nat_bits, &old_regs->r20, &old_unat);
-	copy_reg(&bank[21-16], ms->pmsa_nat_bits, &old_regs->r21, &old_unat);
-	copy_reg(&bank[22-16], ms->pmsa_nat_bits, &old_regs->r22, &old_unat);
-	copy_reg(&bank[23-16], ms->pmsa_nat_bits, &old_regs->r23, &old_unat);
-	copy_reg(&bank[24-16], ms->pmsa_nat_bits, &old_regs->r24, &old_unat);
-	copy_reg(&bank[25-16], ms->pmsa_nat_bits, &old_regs->r25, &old_unat);
-	copy_reg(&bank[26-16], ms->pmsa_nat_bits, &old_regs->r26, &old_unat);
-	copy_reg(&bank[27-16], ms->pmsa_nat_bits, &old_regs->r27, &old_unat);
-	copy_reg(&bank[28-16], ms->pmsa_nat_bits, &old_regs->r28, &old_unat);
-	copy_reg(&bank[29-16], ms->pmsa_nat_bits, &old_regs->r29, &old_unat);
-	copy_reg(&bank[30-16], ms->pmsa_nat_bits, &old_regs->r30, &old_unat);
-	copy_reg(&bank[31-16], ms->pmsa_nat_bits, &old_regs->r31, &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
@@ -1141,6 +1154,8 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 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, sos, &old_unat);
 	return previous_current;
 }
 
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
index 285aae8431c6..53292abf846c 100644
--- a/arch/ia64/kernel/pci-swiotlb.c
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -41,7 +41,7 @@ struct dma_map_ops swiotlb_dma_ops = {
 void __init swiotlb_dma_init(void)
 {
 	dma_ops = &swiotlb_dma_ops;
-	swiotlb_init();
+	swiotlb_init(1);
 }
 
 void __init pci_swiotlb_init(void)
@@ -51,7 +51,7 @@ void __init pci_swiotlb_init(void)
 		swiotlb = 1;
 		printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
 		machvec_init("dig");
-		swiotlb_init();
+		swiotlb_init(1);
 		dma_ops = &swiotlb_dma_ops;
 #else
 		panic("Unable to find Intel IOMMU");
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index f1782705b1f7..5246285a95fb 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -522,42 +522,37 @@ EXPORT_SYMBOL(pfm_sysctl);
 
 static ctl_table pfm_ctl_table[]={
 	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "debug",
 		.data		= &pfm_sysctl.debug,
 		.maxlen		= sizeof(int),
 		.mode		= 0666,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "debug_ovfl",
 		.data		= &pfm_sysctl.debug_ovfl,
 		.maxlen		= sizeof(int),
 		.mode		= 0666,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "fastctxsw",
 		.data		= &pfm_sysctl.fastctxsw,
 		.maxlen		= sizeof(int),
 		.mode		= 0600,
-		.proc_handler	=  &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "expert_mode",
 		.data		= &pfm_sysctl.expert_mode,
 		.maxlen		= sizeof(int),
 		.mode		= 0600,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= proc_dointvec,
 	},
 	{}
 };
 static ctl_table pfm_sysctl_dir[] = {
 	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "perfmon",
 		.mode		= 0555,
 		.child		= pfm_ctl_table,
@@ -566,7 +561,6 @@ static ctl_table pfm_sysctl_dir[] = {
 };
 static ctl_table pfm_sysctl_root[] = {
 	{
-		.ctl_name	= CTL_KERN,
 		.procname	= "kernel",
 		.mode		= 0555,
 		.child		= pfm_sysctl_dir,
@@ -2206,7 +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;
 
@@ -2231,18 +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);
 	}
 
@@ -3523,7 +3518,7 @@ pfm_use_debug_registers(struct task_struct *task)
  * IA64_THREAD_DBG_VALID set. This indicates a task which was
  * able to use the debug registers for debugging purposes via
  * ptrace(). Therefore we know it was not using them for
- * perfmormance monitoring, so we only decrement the number
+ * performance monitoring, so we only decrement the number
  * of "ptraced" debug register users to keep the count up to date
  */
 int
diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c
index 92ed83f34036..609d50056a6c 100644
--- a/arch/ia64/kernel/sys_ia64.c
+++ b/arch/ia64/kernel/sys_ia64.c
@@ -100,51 +100,7 @@ sys_getpagesize (void)
 asmlinkage unsigned long
 ia64_brk (unsigned long brk)
 {
-	unsigned long rlim, retval, newbrk, oldbrk;
-	struct mm_struct *mm = current->mm;
-
-	/*
-	 * Most of this replicates the code in sys_brk() except for an additional safety
-	 * check and the clearing of r8.  However, we can't call sys_brk() because we need
-	 * to acquire the mmap_sem before we can do the test...
-	 */
-	down_write(&mm->mmap_sem);
-
-	if (brk < mm->end_code)
-		goto out;
-	newbrk = PAGE_ALIGN(brk);
-	oldbrk = PAGE_ALIGN(mm->brk);
-	if (oldbrk == newbrk)
-		goto set_brk;
-
-	/* Always allow shrinking brk. */
-	if (brk <= mm->brk) {
-		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
-			goto set_brk;
-		goto out;
-	}
-
-	/* Check against unimplemented/unmapped addresses: */
-	if ((newbrk - oldbrk) > RGN_MAP_LIMIT || REGION_OFFSET(newbrk) > RGN_MAP_LIMIT)
-		goto out;
-
-	/* Check against rlimit.. */
-	rlim = current->signal->rlim[RLIMIT_DATA].rlim_cur;
-	if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
-		goto out;
-
-	/* Check against existing mmap mappings. */
-	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
-		goto out;
-
-	/* Ok, looks good - let it rip. */
-	if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
-		goto out;
-set_brk:
-	mm->brk = brk;
-out:
-	retval = mm->brk;
-	up_write(&mm->mmap_sem);
+	unsigned long retval = sys_brk(brk);
 	force_successful_syscall_return();
 	return retval;
 }
@@ -185,39 +141,6 @@ int ia64_mmap_check(unsigned long addr, unsigned long len,
 	return 0;
 }
 
-static inline unsigned long
-do_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, unsigned long pgoff)
-{
-	struct file *file = NULL;
-
-	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
-	if (!(flags & MAP_ANONYMOUS)) {
-		file = fget(fd);
-		if (!file)
-			return -EBADF;
-
-		if (!file->f_op || !file->f_op->mmap) {
-			addr = -ENODEV;
-			goto out;
-		}
-	}
-
-	/* Careful about overflows.. */
-	len = PAGE_ALIGN(len);
-	if (!len || len > TASK_SIZE) {
-		addr = -EINVAL;
-		goto out;
-	}
-
-	down_write(&current->mm->mmap_sem);
-	addr = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
-	up_write(&current->mm->mmap_sem);
-
-out:	if (file)
-		fput(file);
-	return addr;
-}
-
 /*
  * mmap2() is like mmap() except that the offset is expressed in units
  * of PAGE_SIZE (instead of bytes).  This allows to mmap2() (pieces
@@ -226,7 +149,7 @@ out:	if (file)
 asmlinkage unsigned long
 sys_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, long pgoff)
 {
-	addr = do_mmap2(addr, len, prot, flags, fd, pgoff);
+	addr = sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
 	if (!IS_ERR((void *) addr))
 		force_successful_syscall_return();
 	return addr;
@@ -238,7 +161,7 @@ sys_mmap (unsigned long addr, unsigned long len, int prot, int flags, int fd, lo
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
 
-	addr = do_mmap2(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
+	addr = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
 	if (!IS_ERR((void *) addr))
 		force_successful_syscall_return();
 	return addr;
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 4990495d7531..a35c661e5e89 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -473,7 +473,7 @@ void update_vsyscall_tz(void)
 {
 }
 
-void update_vsyscall(struct timespec *wall, struct clocksource *c)
+void update_vsyscall(struct timespec *wall, struct clocksource *c, u32 mult)
 {
         unsigned long flags;
 
@@ -481,7 +481,7 @@ void update_vsyscall(struct timespec *wall, struct clocksource *c)
 
         /* copy fsyscall clock data */
         fsyscall_gtod_data.clk_mask = c->mask;
-        fsyscall_gtod_data.clk_mult = c->mult;
+        fsyscall_gtod_data.clk_mult = mult;
         fsyscall_gtod_data.clk_shift = c->shift;
         fsyscall_gtod_data.clk_fsys_mmio = c->fsys_mmio;
         fsyscall_gtod_data.clk_cycle_last = c->cycle_last;
diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c
index 6db08599ebbc..776dd40397e2 100644
--- a/arch/ia64/kernel/unaligned.c
+++ b/arch/ia64/kernel/unaligned.c
@@ -60,7 +60,6 @@ dump (const char *str, void *vp, size_t len)
  */
 int no_unaligned_warning;
 int unaligned_dump_stack;
-static int noprint_warning;
 
 /*
  * For M-unit:
@@ -1357,9 +1356,8 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs)
 			/* watch for command names containing %s */
 			printk(KERN_WARNING "%s", buf);
 		} else {
-			if (no_unaligned_warning && !noprint_warning) {
-				noprint_warning = 1;
-				printk(KERN_WARNING "%s(%d) encountered an "
+			if (no_unaligned_warning) {
+				printk_once(KERN_WARNING "%s(%d) encountered an "
 				       "unaligned exception which required\n"
 				       "kernel assistance, which degrades "
 				       "the performance of the application.\n"
diff --git a/arch/ia64/kvm/Makefile b/arch/ia64/kvm/Makefile
index 0bb99b732908..1089b3e918ac 100644
--- a/arch/ia64/kvm/Makefile
+++ b/arch/ia64/kvm/Makefile
@@ -49,7 +49,7 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 
 common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
-		coalesced_mmio.o irq_comm.o)
+		coalesced_mmio.o irq_comm.o assigned-dev.o)
 
 ifeq ($(CONFIG_IOMMU_API),y)
 common-objs += $(addprefix ../../../virt/kvm/, iommu.o)
diff --git a/arch/ia64/kvm/asm-offsets.c b/arch/ia64/kvm/asm-offsets.c
index 0c3564a7a033..9324c875caf5 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/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 0ad09f05efa9..5fdeec5fddcf 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -124,7 +124,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
 
 static  DEFINE_SPINLOCK(vp_lock);
 
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
 	long  status;
 	long  tmp_base;
@@ -137,7 +137,7 @@ void kvm_arch_hardware_enable(void *garbage)
 	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
 	local_irq_restore(saved_psr);
 	if (slot < 0)
-		return;
+		return -EINVAL;
 
 	spin_lock(&vp_lock);
 	status = ia64_pal_vp_init_env(kvm_vsa_base ?
@@ -145,7 +145,7 @@ void kvm_arch_hardware_enable(void *garbage)
 			__pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base);
 	if (status != 0) {
 		printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n");
-		return ;
+		return -EINVAL;
 	}
 
 	if (!kvm_vsa_base) {
@@ -154,6 +154,8 @@ void kvm_arch_hardware_enable(void *garbage)
 	}
 	spin_unlock(&vp_lock);
 	ia64_ptr_entry(0x3, slot);
+
+	return 0;
 }
 
 void kvm_arch_hardware_disable(void *garbage)
@@ -851,8 +853,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm,
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_IOAPIC:
-		memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm),
-				sizeof(struct kvm_ioapic_state));
+		r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -868,9 +869,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_IOAPIC:
-		memcpy(ioapic_irqchip(kvm),
-				&chip->chip.ioapic,
-				sizeof(struct kvm_ioapic_state));
+		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -944,7 +943,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 {
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
-	int r = -EINVAL;
+	int r = -ENOTTY;
 
 	switch (ioctl) {
 	case KVM_SET_MEMORY_REGION: {
@@ -985,10 +984,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,
diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h
index 360724d3ae69..988911b4cc7a 100644
--- a/arch/ia64/kvm/vcpu.h
+++ b/arch/ia64/kvm/vcpu.h
@@ -388,6 +388,9 @@ static inline u64 __gpfn_is_io(u64 gpfn)
 #define _vmm_raw_spin_lock(x)	 do {}while(0)
 #define _vmm_raw_spin_unlock(x) do {}while(0)
 #else
+typedef struct {
+	volatile unsigned int lock;
+} vmm_spinlock_t;
 #define _vmm_raw_spin_lock(x)						\
 	do {								\
 		__u32 *ia64_spinlock_ptr = (__u32 *) (x);		\
@@ -405,12 +408,12 @@ static inline u64 __gpfn_is_io(u64 gpfn)
 
 #define _vmm_raw_spin_unlock(x)				\
 	do { barrier();				\
-		((spinlock_t *)x)->raw_lock.lock = 0; } \
+		((vmm_spinlock_t *)x)->lock = 0; } \
 while (0)
 #endif
 
-void vmm_spin_lock(spinlock_t *lock);
-void vmm_spin_unlock(spinlock_t *lock);
+void vmm_spin_lock(vmm_spinlock_t *lock);
+void vmm_spin_unlock(vmm_spinlock_t *lock);
 enum {
 	I_TLB = 1,
 	D_TLB = 2
diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c
index f4b4c899bb6c..7a62f75778c5 100644
--- a/arch/ia64/kvm/vmm.c
+++ b/arch/ia64/kvm/vmm.c
@@ -60,12 +60,12 @@ static void __exit kvm_vmm_exit(void)
 	return ;
 }
 
-void vmm_spin_lock(spinlock_t *lock)
+void vmm_spin_lock(vmm_spinlock_t *lock)
 {
 	_vmm_raw_spin_lock(lock);
 }
 
-void vmm_spin_unlock(spinlock_t *lock)
+void vmm_spin_unlock(vmm_spinlock_t *lock)
 {
 	_vmm_raw_spin_unlock(lock);
 }
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 20b3852f7a6e..4332f7ee5203 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -182,7 +182,7 @@ void mark_pages_dirty(struct kvm_vcpu *v, u64 pte, u64 ps)
 {
 	u64 i, dirty_pages = 1;
 	u64 base_gfn = (pte&_PAGE_PPN_MASK) >> PAGE_SHIFT;
-	spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
+	vmm_spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
 	void *dirty_bitmap = (void *)KVM_MEM_DIRTY_LOG_BASE;
 
 	dirty_pages <<= ps <= PAGE_SHIFT ? 0 : ps - PAGE_SHIFT;
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 2a140627dfd6..3dccdd8eb275 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/mm/tlb.c b/arch/ia64/mm/tlb.c
index f426dc78d959..ee09d261f2e6 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -100,24 +100,36 @@ wrap_mmu_context (struct mm_struct *mm)
  * this primitive it can be moved up to a spinaphore.h header.
  */
 struct spinaphore {
-	atomic_t	cur;
+	unsigned long	ticket;
+	unsigned long	serve;
 };
 
 static inline void spinaphore_init(struct spinaphore *ss, int val)
 {
-	atomic_set(&ss->cur, val);
+	ss->ticket = 0;
+	ss->serve = val;
 }
 
 static inline void down_spin(struct spinaphore *ss)
 {
-	while (unlikely(!atomic_add_unless(&ss->cur, -1, 0)))
-		while (atomic_read(&ss->cur) == 0)
-			cpu_relax();
+	unsigned long t = ia64_fetchadd(1, &ss->ticket, acq), serve;
+
+	if (time_before(t, ss->serve))
+		return;
+
+	ia64_invala();
+
+	for (;;) {
+		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(serve) : "r"(&ss->serve) : "memory");
+		if (time_before(t, serve))
+			return;
+		cpu_relax();
+	}
 }
 
 static inline void up_spin(struct spinaphore *ss)
 {
-	atomic_add(1, &ss->cur);
+	ia64_fetchadd(1, &ss->serve, rel);
 }
 
 static struct spinaphore ptcg_sem;
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index 7de76dd352fe..df639db779f9 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -56,10 +56,13 @@ int raw_pci_read(unsigned int seg, unsigned int bus, unsigned int devfn,
 	if ((seg | reg) <= 255) {
 		addr = PCI_SAL_ADDRESS(seg, bus, devfn, reg);
 		mode = 0;
-	} else {
+	} else if (sal_revision >= SAL_VERSION_CODE(3,2)) {
 		addr = PCI_SAL_EXT_ADDRESS(seg, bus, devfn, reg);
 		mode = 1;
+	} else {
+		return -EINVAL;
 	}
+
 	result = ia64_sal_pci_config_read(addr, mode, len, &data);
 	if (result != 0)
 		return -EINVAL;
@@ -80,9 +83,11 @@ int raw_pci_write(unsigned int seg, unsigned int bus, unsigned int devfn,
 	if ((seg | reg) <= 255) {
 		addr = PCI_SAL_ADDRESS(seg, bus, devfn, reg);
 		mode = 0;
-	} else {
+	} else if (sal_revision >= SAL_VERSION_CODE(3,2)) {
 		addr = PCI_SAL_EXT_ADDRESS(seg, bus, devfn, reg);
 		mode = 1;
+	} else {
+		return -EINVAL;
 	}
 	result = ia64_sal_pci_config_write(addr, mode, len, value);
 	if (result != 0)
@@ -126,6 +131,7 @@ alloc_pci_controller (int seg)
 }
 
 struct pci_root_info {
+	struct acpi_device *bridge;
 	struct pci_controller *controller;
 	char *name;
 };
@@ -292,9 +298,20 @@ static __devinit acpi_status add_window(struct acpi_resource *res, void *data)
 	window->offset = offset;
 
 	if (insert_resource(root, &window->resource)) {
-		printk(KERN_ERR "alloc 0x%llx-0x%llx from %s for %s failed\n",
-			window->resource.start, window->resource.end,
-			root->name, info->name);
+		dev_err(&info->bridge->dev,
+			"can't allocate host bridge window %pR\n",
+			&window->resource);
+	} else {
+		if (offset)
+			dev_info(&info->bridge->dev, "host bridge window %pR "
+				 "(PCI address [%#llx-%#llx])\n",
+				 &window->resource,
+				 window->resource.start - offset,
+				 window->resource.end - offset);
+		else
+			dev_info(&info->bridge->dev,
+				 "host bridge window %pR\n",
+				 &window->resource);
 	}
 
 	return AE_OK;
@@ -314,8 +331,9 @@ pcibios_setup_root_windows(struct pci_bus *bus, struct pci_controller *ctrl)
 		    (res->end - res->start < 16))
 			continue;
 		if (j >= PCI_BUS_NUM_RESOURCES) {
-			printk("Ignoring range [%#llx-%#llx] (%lx)\n",
-					res->start, res->end, res->flags);
+			dev_warn(&bus->dev,
+				 "ignoring host bridge window %pR (no space)\n",
+				 res);
 			continue;
 		}
 		bus->resource[j++] = res;
@@ -359,6 +377,7 @@ pci_acpi_scan_root(struct acpi_device *device, int domain, int bus)
 			goto out3;
 
 		sprintf(name, "PCI Bus %04x:%02x", domain, bus);
+		info.bridge = device;
 		info.controller = controller;
 		info.name = name;
 		acpi_walk_resources(device->handle, METHOD_NAME__CRS,
@@ -715,9 +734,6 @@ int ia64_pci_legacy_write(struct pci_bus *bus, u16 port, u32 val, u8 size)
 	return ret;
 }
 
-/* It's defined in drivers/pci/pci.c */
-extern u8 pci_cache_line_size;
-
 /**
  * set_pci_cacheline_size - determine cacheline size for PCI devices
  *
@@ -726,7 +742,7 @@ extern u8 pci_cache_line_size;
  *
  * Code mostly taken from arch/ia64/kernel/palinfo.c:cache_info().
  */
-static void __init set_pci_cacheline_size(void)
+static void __init set_pci_dfl_cacheline_size(void)
 {
 	unsigned long levels, unique_caches;
 	long status;
@@ -746,7 +762,7 @@ static void __init set_pci_cacheline_size(void)
 			"(status=%ld)\n", __func__, status);
 		return;
 	}
-	pci_cache_line_size = (1 << cci.pcci_line_size) / 4;
+	pci_dfl_cache_line_size = (1 << cci.pcci_line_size) / 4;
 }
 
 u64 ia64_dma_get_required_mask(struct device *dev)
@@ -777,7 +793,7 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init pcibios_init(void)
 {
-	set_pci_cacheline_size();
+	set_pci_dfl_cacheline_size();
 	return 0;
 }
 
diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c
index fd50ff94302b..66f633bff059 100644
--- a/arch/ia64/sn/kernel/io_acpi_init.c
+++ b/arch/ia64/sn/kernel/io_acpi_init.c
@@ -390,7 +390,7 @@ sn_acpi_get_pcidev_info(struct pci_dev *dev, struct pcidev_info **pcidev_info,
 	pcidev_match.handle = NULL;
 
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, rootbus_handle, ACPI_UINT32_MAX,
-			    find_matching_device, &pcidev_match, NULL);
+			    find_matching_device, NULL, &pcidev_match, NULL);
 
 	if (!pcidev_match.handle) {
 		printk(KERN_ERR
diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
index 25831c47c579..308e6595110e 100644
--- a/arch/ia64/sn/kernel/io_common.c
+++ b/arch/ia64/sn/kernel/io_common.c
@@ -119,7 +119,6 @@ sn_pcidev_info_get(struct pci_dev *dev)
  * Additionally note that the struct sn_flush_device_war also has to be
  * removed from arch/ia64/sn/include/xtalk/hubdev.h
  */
-static u8 war_implemented = 0;
 
 static s64 sn_device_fixup_war(u64 nasid, u64 widget, int device,
 			       struct sn_flush_device_common *common)
@@ -128,11 +127,8 @@ static s64 sn_device_fixup_war(u64 nasid, u64 widget, int device,
 	struct sn_flush_device_war *dev_entry;
 	struct ia64_sal_retval isrv = {0,0,0,0};
 
-	if (!war_implemented) {
-		printk(KERN_WARNING "PROM version < 4.50 -- implementing old "
-		       "PROM flush WAR\n");
-		war_implemented = 1;
-	}
+	printk_once(KERN_WARNING
+		"PROM version < 4.50 -- implementing old PROM flush WAR\n");
 
 	war_list = kzalloc(DEV_PER_WIDGET * sizeof(*war_list), GFP_KERNEL);
 	BUG_ON(!war_list);
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index 4c7e74790958..55ac3c4e11d2 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -786,17 +786,18 @@ sn_hwperf_ioctl(struct inode *in, struct file *fp, u32 op, unsigned long arg)
 		break;
 
 	case SN_HWPERF_GET_OBJ_NODE:
-		if (a.sz != sizeof(u64) || a.arg < 0) {
+		i = a.arg;
+		if (a.sz != sizeof(u64) || i < 0) {
 			r = -EINVAL;
 			goto error;
 		}
 		if ((r = sn_hwperf_enum_objects(&nobj, &objs)) == 0) {
-			if (a.arg >= nobj) {
+			if (i >= nobj) {
 				r = -EINVAL;
 				vfree(objs);
 				goto error;
 			}
-			if (objs[(i = a.arg)].id != a.arg) {
+			if (objs[i].id != a.arg) {
 				for (i = 0; i < nobj; i++) {
 					if (objs[i].id == a.arg)
 						break;
diff --git a/arch/ia64/sn/pci/tioca_provider.c b/arch/ia64/sn/pci/tioca_provider.c
index 35b2a27d2e77..efb454534e52 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);