Merge branch 'linus' into release

45 files changed, 1248 insertions, 1125 deletions

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 6bd91ed7cd0..3d31636cbaf 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -99,7 +99,7 @@ config GENERIC_IOMAP
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 
@@ -687,3 +687,6 @@ config IRQ_PER_CPU
 
 config IOMMU_HELPER
 	def_bool (IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB || IA64_GENERIC || SWIOTLB)
+
+config IOMMU_API
+	def_bool (DMAR)
diff --git a/arch/ia64/hp/sim/hpsim_irq.c b/arch/ia64/hp/sim/hpsim_irq.c
index c2f58ff364e..cc0a3182db3 100644
--- a/arch/ia64/hp/sim/hpsim_irq.c
+++ b/arch/ia64/hp/sim/hpsim_irq.c
@@ -22,7 +22,7 @@ hpsim_irq_noop (unsigned int irq)
 }
 
 static void
-hpsim_set_affinity_noop (unsigned int a, cpumask_t b)
+hpsim_set_affinity_noop(unsigned int a, const struct cpumask *b)
 {
 }
 
diff --git a/arch/ia64/hp/sim/simeth.c b/arch/ia64/hp/sim/simeth.c
index 3d47839a0c4..e4d8fde6810 100644
--- a/arch/ia64/hp/sim/simeth.c
+++ b/arch/ia64/hp/sim/simeth.c
@@ -167,6 +167,15 @@ netdev_read(int fd, unsigned char *buf, unsigned int len)
 	return ia64_ssc(fd, __pa(buf), len, 0, SSC_NETDEV_RECV);
 }
 
+static const struct net_device_ops simeth_netdev_ops = {
+	.ndo_open		= simeth_open,
+	.ndo_stop		= simeth_close,
+	.ndo_start_xmit		= simeth_tx,
+	.ndo_get_stats		= simeth_get_stats,
+	.ndo_set_multicast_list	= set_multicast_list, /* not yet used */
+
+};
+
 /*
  * Function shared with module code, so cannot be in init section
  *
@@ -206,14 +215,10 @@ simeth_probe1(void)
 
 	memcpy(dev->dev_addr, mac_addr, sizeof(mac_addr));
 
-	local = dev->priv;
+	local = netdev_priv(dev);
 	local->simfd = fd; /* keep track of underlying file descriptor */
 
-	dev->open		= simeth_open;
-	dev->stop		= simeth_close;
-	dev->hard_start_xmit	= simeth_tx;
-	dev->get_stats		= simeth_get_stats;
-	dev->set_multicast_list = set_multicast_list; /* no yet used */
+	dev->netdev_ops = &simeth_netdev_ops;
 
 	err = register_netdev(dev);
 	if (err) {
@@ -325,7 +330,7 @@ simeth_device_event(struct notifier_block *this,unsigned long event, void *ptr)
 	 * we get DOWN then UP.
 	 */
 
-	local = dev->priv;
+	local = netdev_priv(dev);
 	/* now do it for real */
 	r = event == NETDEV_UP ?
 		netdev_attach(local->simfd, dev->irq, ntohl(ifa->ifa_local)):
@@ -380,7 +385,7 @@ frame_print(unsigned char *from, unsigned char *frame, int len)
 static int
 simeth_tx(struct sk_buff *skb, struct net_device *dev)
 {
-	struct simeth_local *local = dev->priv;
+	struct simeth_local *local = netdev_priv(dev);
 
 #if 0
 	/* ensure we have at least ETH_ZLEN bytes (min frame size) */
@@ -443,7 +448,7 @@ simeth_rx(struct net_device *dev)
 	int			len;
 	int			rcv_count = SIMETH_RECV_MAX;
 
-	local = dev->priv;
+	local = netdev_priv(dev);
 	/*
 	 * the loop concept has been borrowed from other drivers
 	 * looks to me like it's a throttling thing to avoid pushing to many
@@ -507,7 +512,7 @@ simeth_interrupt(int irq, void *dev_id)
 static struct net_device_stats *
 simeth_get_stats(struct net_device *dev)
 {
-	struct simeth_local *local = dev->priv;
+	struct simeth_local *local = netdev_priv(dev);
 
 	return &local->stats;
 }
diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c
index 5e92ae00bdb..16ef61a91d9 100644
--- a/arch/ia64/ia32/sys_ia32.c
+++ b/arch/ia64/ia32/sys_ia32.c
@@ -1767,25 +1767,24 @@ groups16_from_user(struct group_info *group_info, short __user *grouplist)
 asmlinkage long
 sys32_getgroups16 (int gidsetsize, short __user *grouplist)
 {
+	const struct cred *cred = current_cred();
 	int i;
 
 	if (gidsetsize < 0)
 		return -EINVAL;
 
-	get_group_info(current->group_info);
-	i = current->group_info->ngroups;
+	i = cred->group_info->ngroups;
 	if (gidsetsize) {
 		if (i > gidsetsize) {
 			i = -EINVAL;
 			goto out;
 		}
-		if (groups16_to_user(grouplist, current->group_info)) {
+		if (groups16_to_user(grouplist, cred->group_info)) {
 			i = -EFAULT;
 			goto out;
 		}
 	}
 out:
-	put_group_info(current->group_info);
 	return i;
 }
 
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index ccbe8ae47a6..3b25bd9dca9 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -14,3 +14,4 @@ unifdef-y += gcc_intrin.h
 unifdef-y += intrinsics.h
 unifdef-y += perfmon.h
 unifdef-y += ustack.h
+unifdef-y += swab.h
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 50c2b83fd5a..d37292bd987 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -17,12 +17,6 @@
 #include <asm/intrinsics.h>
 #include <asm/system.h>
 
-/*
- * On IA-64, counter must always be volatile to ensure that that the
- * memory accesses are ordered.
- */
-typedef struct { volatile __s32 counter; } atomic_t;
-typedef struct { volatile __s64 counter; } atomic64_t;
 
 #define ATOMIC_INIT(i)		((atomic_t) { (i) })
 #define ATOMIC64_INIT(i)	((atomic64_t) { (i) })
diff --git a/arch/ia64/include/asm/byteorder.h b/arch/ia64/include/asm/byteorder.h
index 69bd41d7c26..0f84c5cb703 100644
--- a/arch/ia64/include/asm/byteorder.h
+++ b/arch/ia64/include/asm/byteorder.h
@@ -1,42 +1,7 @@
 #ifndef _ASM_IA64_BYTEORDER_H
 #define _ASM_IA64_BYTEORDER_H
 
-/*
- * Modified 1998, 1999
- *	David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co.
- */
-
-#include <asm/types.h>
-#include <asm/intrinsics.h>
-#include <linux/compiler.h>
-
-static __inline__ __attribute_const__ __u64
-__ia64_swab64 (__u64 x)
-{
-	__u64 result;
-
-	result = ia64_mux1(x, ia64_mux1_rev);
-	return result;
-}
-
-static __inline__ __attribute_const__ __u32
-__ia64_swab32 (__u32 x)
-{
-	return __ia64_swab64(x) >> 32;
-}
-
-static __inline__ __attribute_const__ __u16
-__ia64_swab16(__u16 x)
-{
-	return __ia64_swab64(x) >> 48;
-}
-
-#define __arch__swab64(x) __ia64_swab64(x)
-#define __arch__swab32(x) __ia64_swab32(x)
-#define __arch__swab16(x) __ia64_swab16(x)
-
-#define __BYTEORDER_HAS_U64__
-
+#include <asm/swab.h>
 #include <linux/byteorder/little_endian.h>
 
 #endif /* _ASM_IA64_BYTEORDER_H */
diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h
index 3627116fb0e..36429a53263 100644
--- a/arch/ia64/include/asm/irq.h
+++ b/arch/ia64/include/asm/irq.h
@@ -27,7 +27,7 @@ irq_canonicalize (int irq)
 }
 
 extern void set_irq_affinity_info (unsigned int irq, int dest, int redir);
-bool is_affinity_mask_valid(cpumask_t cpumask);
+bool is_affinity_mask_valid(cpumask_var_t cpumask);
 
 #define is_affinity_mask_valid is_affinity_mask_valid
 
diff --git a/arch/ia64/include/asm/kvm.h b/arch/ia64/include/asm/kvm.h
index f38472ac226..68aa6da807c 100644
--- a/arch/ia64/include/asm/kvm.h
+++ b/arch/ia64/include/asm/kvm.h
@@ -166,8 +166,6 @@ struct saved_vpd {
 };
 
 struct kvm_regs {
-	char *saved_guest;
-	char *saved_stack;
 	struct saved_vpd vpd;
 	/*Arch-regs*/
 	int mp_state;
@@ -200,6 +198,10 @@ struct kvm_regs {
 	unsigned long fp_psr;       /*used for lazy float register */
 	unsigned long saved_gp;
 	/*for phycial  emulation */
+
+	union context saved_guest;
+
+	unsigned long reserved[64];	/* for future use */
 };
 
 struct kvm_sregs {
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index c60d324da54..34866366165 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -23,17 +23,6 @@
 #ifndef __ASM_KVM_HOST_H
 #define __ASM_KVM_HOST_H
 
-
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/kvm.h>
-#include <linux/kvm_para.h>
-#include <linux/kvm_types.h>
-
-#include <asm/pal.h>
-#include <asm/sal.h>
-
-#define KVM_MAX_VCPUS 4
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -50,70 +39,132 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT	6
 #define EXIT_REASON_IPI			7
 #define EXIT_REASON_PTC_G		8
+#define EXIT_REASON_DEBUG		20
 
 /*Define vmm address space and vm data space.*/
-#define KVM_VMM_SIZE (16UL<<20)
+#define KVM_VMM_SIZE (__IA64_UL_CONST(16)<<20)
 #define KVM_VMM_SHIFT 24
-#define KVM_VMM_BASE 0xD000000000000000UL
-#define VMM_SIZE (8UL<<20)
+#define KVM_VMM_BASE 0xD000000000000000
+#define VMM_SIZE (__IA64_UL_CONST(8)<<20)
 
 /*
  * Define vm_buffer, used by PAL Services, base address.
- * Note: vmbuffer is in the VMM-BLOCK, the size must be < 8M
+ * Note: vm_buffer is in the VMM-BLOCK, the size must be < 8M
  */
 #define KVM_VM_BUFFER_BASE (KVM_VMM_BASE + VMM_SIZE)
-#define KVM_VM_BUFFER_SIZE (8UL<<20)
-
-/*Define Virtual machine data layout.*/
-#define KVM_VM_DATA_SHIFT  24
-#define KVM_VM_DATA_SIZE (1UL << KVM_VM_DATA_SHIFT)
-#define KVM_VM_DATA_BASE (KVM_VMM_BASE + KVM_VMM_SIZE)
-
-
-#define KVM_P2M_BASE    KVM_VM_DATA_BASE
-#define KVM_P2M_OFS     0
-#define KVM_P2M_SIZE    (8UL << 20)
-
-#define KVM_VHPT_BASE   (KVM_P2M_BASE + KVM_P2M_SIZE)
-#define KVM_VHPT_OFS    KVM_P2M_SIZE
-#define KVM_VHPT_BLOCK_SIZE   (2UL << 20)
-#define VHPT_SHIFT      18
-#define VHPT_SIZE       (1UL << VHPT_SHIFT)
-#define VHPT_NUM_ENTRIES (1<<(VHPT_SHIFT-5))
-
-#define KVM_VTLB_BASE   (KVM_VHPT_BASE+KVM_VHPT_BLOCK_SIZE)
-#define KVM_VTLB_OFS    (KVM_VHPT_OFS+KVM_VHPT_BLOCK_SIZE)
-#define KVM_VTLB_BLOCK_SIZE   (1UL<<20)
-#define VTLB_SHIFT      17
-#define VTLB_SIZE       (1UL<<VTLB_SHIFT)
-#define VTLB_NUM_ENTRIES (1<<(VTLB_SHIFT-5))
-
-#define KVM_VPD_BASE   (KVM_VTLB_BASE+KVM_VTLB_BLOCK_SIZE)
-#define KVM_VPD_OFS    (KVM_VTLB_OFS+KVM_VTLB_BLOCK_SIZE)
-#define KVM_VPD_BLOCK_SIZE   (2UL<<20)
-#define VPD_SHIFT       16
-#define VPD_SIZE        (1UL<<VPD_SHIFT)
-
-#define KVM_VCPU_BASE   (KVM_VPD_BASE+KVM_VPD_BLOCK_SIZE)
-#define KVM_VCPU_OFS    (KVM_VPD_OFS+KVM_VPD_BLOCK_SIZE)
-#define KVM_VCPU_BLOCK_SIZE   (2UL<<20)
-#define VCPU_SHIFT 18
-#define VCPU_SIZE (1UL<<VCPU_SHIFT)
-#define MAX_VCPU_NUM KVM_VCPU_BLOCK_SIZE/VCPU_SIZE
-
-#define KVM_VM_BASE     (KVM_VCPU_BASE+KVM_VCPU_BLOCK_SIZE)
-#define KVM_VM_OFS      (KVM_VCPU_OFS+KVM_VCPU_BLOCK_SIZE)
-#define KVM_VM_BLOCK_SIZE     (1UL<<19)
-
-#define KVM_MEM_DIRTY_LOG_BASE (KVM_VM_BASE+KVM_VM_BLOCK_SIZE)
-#define KVM_MEM_DIRTY_LOG_OFS  (KVM_VM_OFS+KVM_VM_BLOCK_SIZE)
-#define KVM_MEM_DIRTY_LOG_SIZE (1UL<<19)
-
-/* Get vpd, vhpt, tlb, vcpu, base*/
-#define VPD_ADDR(n) (KVM_VPD_BASE+n*VPD_SIZE)
-#define VHPT_ADDR(n) (KVM_VHPT_BASE+n*VHPT_SIZE)
-#define VTLB_ADDR(n) (KVM_VTLB_BASE+n*VTLB_SIZE)
-#define VCPU_ADDR(n) (KVM_VCPU_BASE+n*VCPU_SIZE)
+#define KVM_VM_BUFFER_SIZE (__IA64_UL_CONST(8)<<20)
+
+/*
+ * kvm guest's data area looks as follow:
+ *
+ *            +----------------------+	-------	KVM_VM_DATA_SIZE
+ *	      |	    vcpu[n]'s data   |	 |     ___________________KVM_STK_OFFSET
+ *     	      |			     |	 |    /			  |
+ *     	      |	       ..........    |	 |   /vcpu's struct&stack |
+ *     	      |	       ..........    |	 |  /---------------------|---- 0
+ *	      |	    vcpu[5]'s data   |	 | /	   vpd		  |
+ *	      |	    vcpu[4]'s data   |	 |/-----------------------|
+ *	      |	    vcpu[3]'s data   |	 /	   vtlb		  |
+ *	      |	    vcpu[2]'s data   |	/|------------------------|
+ *	      |	    vcpu[1]'s data   |/  |	   vhpt		  |
+ *	      |	    vcpu[0]'s data   |____________________________|
+ *            +----------------------+	 |
+ *	      |	   memory dirty log  |	 |
+ *            +----------------------+	 |
+ *	      |	   vm's data struct  |	 |
+ *            +----------------------+	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |	  vm's p2m table  |	 |
+ *	      |			     |	 |
+ *            |			     |	 |
+ *	      |			     |	 |  |
+ * vm's data->|			     |   |  |
+ *	      +----------------------+ ------- 0
+ * To support large memory, needs to increase the size of p2m.
+ * To support more vcpus, needs to ensure it has enough space to
+ * hold vcpus' data.
+ */
+
+#define KVM_VM_DATA_SHIFT	26
+#define KVM_VM_DATA_SIZE	(__IA64_UL_CONST(1) << KVM_VM_DATA_SHIFT)
+#define KVM_VM_DATA_BASE	(KVM_VMM_BASE + KVM_VM_DATA_SIZE)
+
+#define KVM_P2M_BASE		KVM_VM_DATA_BASE
+#define KVM_P2M_SIZE		(__IA64_UL_CONST(24) << 20)
+
+#define VHPT_SHIFT		16
+#define VHPT_SIZE		(__IA64_UL_CONST(1) << VHPT_SHIFT)
+#define VHPT_NUM_ENTRIES	(__IA64_UL_CONST(1) << (VHPT_SHIFT-5))
+
+#define VTLB_SHIFT		16
+#define VTLB_SIZE		(__IA64_UL_CONST(1) << VTLB_SHIFT)
+#define VTLB_NUM_ENTRIES	(1UL << (VHPT_SHIFT-5))
+
+#define VPD_SHIFT		16
+#define VPD_SIZE		(__IA64_UL_CONST(1) << VPD_SHIFT)
+
+#define VCPU_STRUCT_SHIFT	16
+#define VCPU_STRUCT_SIZE	(__IA64_UL_CONST(1) << VCPU_STRUCT_SHIFT)
+
+#define KVM_STK_OFFSET		VCPU_STRUCT_SIZE
+
+#define KVM_VM_STRUCT_SHIFT	19
+#define KVM_VM_STRUCT_SIZE	(__IA64_UL_CONST(1) << KVM_VM_STRUCT_SHIFT)
+
+#define KVM_MEM_DIRY_LOG_SHIFT	19
+#define KVM_MEM_DIRTY_LOG_SIZE (__IA64_UL_CONST(1) << KVM_MEM_DIRY_LOG_SHIFT)
+
+#ifndef __ASSEMBLY__
+
+/*Define the max vcpus and memory for Guests.*/
+#define KVM_MAX_VCPUS	(KVM_VM_DATA_SIZE - KVM_P2M_SIZE - KVM_VM_STRUCT_SIZE -\
+			KVM_MEM_DIRTY_LOG_SIZE) / sizeof(struct kvm_vcpu_data)
+#define KVM_MAX_MEM_SIZE (KVM_P2M_SIZE >> 3 << PAGE_SHIFT)
+
+#define VMM_LOG_LEN 256
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+#include <linux/kvm_types.h>
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/page.h>
+
+struct kvm_vcpu_data {
+	char vcpu_vhpt[VHPT_SIZE];
+	char vcpu_vtlb[VTLB_SIZE];
+	char vcpu_vpd[VPD_SIZE];
+	char vcpu_struct[VCPU_STRUCT_SIZE];
+};
+
+struct kvm_vm_data {
+	char kvm_p2m[KVM_P2M_SIZE];
+	char kvm_vm_struct[KVM_VM_STRUCT_SIZE];
+	char kvm_mem_dirty_log[KVM_MEM_DIRTY_LOG_SIZE];
+	struct kvm_vcpu_data vcpu_data[KVM_MAX_VCPUS];
+};
+
+#define VCPU_BASE(n)	KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, vcpu_data[n])
+#define VM_BASE		KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, kvm_vm_struct)
+#define KVM_MEM_DIRTY_LOG_BASE	KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, kvm_mem_dirty_log)
+
+#define VHPT_BASE(n) (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vhpt))
+#define VTLB_BASE(n) (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vtlb))
+#define VPD_BASE(n)  (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vpd))
+#define VCPU_STRUCT_BASE(n)	(VCPU_BASE(n) + \
+				offsetof(struct kvm_vcpu_data, vcpu_struct))
 
 /*IO section definitions*/
 #define IOREQ_READ      1
@@ -389,6 +440,7 @@ struct kvm_vcpu_arch {
 
 	unsigned long opcode;
 	unsigned long cause;
+	char log_buf[VMM_LOG_LEN];
 	union context host;
 	union context guest;
 };
@@ -403,20 +455,19 @@ struct kvm_sal_data {
 };
 
 struct kvm_arch {
+	spinlock_t dirty_log_lock;
+
 	unsigned long	vm_base;
 	unsigned long	metaphysical_rr0;
 	unsigned long	metaphysical_rr4;
 	unsigned long	vmm_init_rr;
-	unsigned long	vhpt_base;
-	unsigned long	vtlb_base;
-	unsigned long 	vpd_base;
-	spinlock_t dirty_log_lock;
+
 	struct kvm_ioapic *vioapic;
 	struct kvm_vm_stat stat;
 	struct kvm_sal_data rdv_sal_data;
 
 	struct list_head assigned_dev_head;
-	struct dmar_domain *intel_iommu_domain;
+	struct iommu_domain *iommu_domain;
 	struct hlist_head irq_ack_notifier_list;
 
 	unsigned long irq_sources_bitmap;
@@ -512,7 +563,7 @@ struct kvm_pt_regs {
 
 static inline struct kvm_pt_regs *vcpu_regs(struct kvm_vcpu *v)
 {
-	return (struct kvm_pt_regs *) ((unsigned long) v + IA64_STK_OFFSET) - 1;
+	return (struct kvm_pt_regs *) ((unsigned long) v + KVM_STK_OFFSET) - 1;
 }
 
 typedef int kvm_vmm_entry(void);
@@ -531,5 +582,6 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 void kvm_sal_emul(struct kvm_vcpu *vcpu);
 
 static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
+#endif /* __ASSEMBLY__*/
 
 #endif
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 12d96e0cd51..21c402365d0 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -57,7 +57,6 @@ extern struct smp_boot_data {
 
 extern char no_int_routing __devinitdata;
 
-extern cpumask_t cpu_online_map;
 extern cpumask_t cpu_core_map[NR_CPUS];
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern int smp_num_siblings;
diff --git a/arch/ia64/include/asm/swab.h b/arch/ia64/include/asm/swab.h
new file mode 100644
index 00000000000..6aa58b699ee
--- /dev/null
+++ b/arch/ia64/include/asm/swab.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_IA64_SWAB_H
+#define _ASM_IA64_SWAB_H
+
+/*
+ * Modified 1998, 1999
+ *	David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co.
+ */
+
+#include <asm/types.h>
+#include <asm/intrinsics.h>
+#include <linux/compiler.h>
+
+static __inline__ __attribute_const__ __u64 __arch_swab64(__u64 x)
+{
+	__u64 result;
+
+	result = ia64_mux1(x, ia64_mux1_rev);
+	return result;
+}
+#define __arch_swab64 __arch_swab64
+
+static __inline__ __attribute_const__ __u32 __arch_swab32(__u32 x)
+{
+	return __arch_swab64(x) >> 32;
+}
+#define __arch_swab32 __arch_swab32
+
+static __inline__ __attribute_const__ __u16 __arch_swab16(__u16 x)
+{
+	return __arch_swab64(x) >> 48;
+}
+#define __arch_swab16 __arch_swab16
+
+#endif /* _ASM_IA64_SWAB_H */
diff --git a/arch/ia64/include/asm/swiotlb.h b/arch/ia64/include/asm/swiotlb.h
index fb79423834d..dcbaea7ce12 100644
--- a/arch/ia64/include/asm/swiotlb.h
+++ b/arch/ia64/include/asm/swiotlb.h
@@ -2,44 +2,7 @@
 #define ASM_IA64__SWIOTLB_H
 
 #include <linux/dma-mapping.h>
-
-/* SWIOTLB interface */
-
-extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
-				     size_t size, int dir);
-extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flags);
-extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-				 size_t size, int dir);
-extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
-					dma_addr_t dev_addr,
-					size_t size, int dir);
-extern void swiotlb_sync_single_for_device(struct device *hwdev,
-					   dma_addr_t dev_addr,
-					   size_t size, int dir);
-extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
-					      dma_addr_t dev_addr,
-					      unsigned long offset,
-					      size_t size, int dir);
-extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
-						 dma_addr_t dev_addr,
-						 unsigned long offset,
-						 size_t size, int dir);
-extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
-				    struct scatterlist *sg, int nelems,
-				    int dir);
-extern void swiotlb_sync_sg_for_device(struct device *hwdev,
-				       struct scatterlist *sg, int nelems,
-				       int dir);
-extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
-			  int nents, int direction);
-extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-			     int nents, int direction);
-extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
-extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle);
-extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
-extern void swiotlb_init(void);
+#include <linux/swiotlb.h>
 
 extern int swiotlb_force;
 
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 35bcb641c9e..76a33a91ca6 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -34,6 +34,7 @@
  * Returns a bitmask of CPUs on Node 'node'.
  */
 #define node_to_cpumask(node) (node_to_cpu_mask[node])
+#define cpumask_of_node(node) (&node_to_cpu_mask[node])
 
 /*
  * Returns the number of the node containing Node 'nid'.
@@ -45,7 +46,7 @@
 /*
  * Returns the number of the first CPU on Node 'node'.
  */
-#define node_to_first_cpu(node) (first_cpu(node_to_cpumask(node)))
+#define node_to_first_cpu(node) (cpumask_first(cpumask_of_node(node)))
 
 /*
  * Determines the node for a given pci bus
@@ -55,7 +56,6 @@
 void build_cpu_to_node_map(void);
 
 #define SD_CPU_INIT (struct sched_domain) {		\
-	.span			= CPU_MASK_NONE,	\
 	.parent			= NULL,			\
 	.child			= NULL,			\
 	.groups			= NULL,			\
@@ -80,7 +80,6 @@ void build_cpu_to_node_map(void);
 
 /* sched_domains SD_NODE_INIT for IA64 NUMA machines */
 #define SD_NODE_INIT (struct sched_domain) {		\
-	.span			= CPU_MASK_NONE,	\
 	.parent			= NULL,			\
 	.child			= NULL,			\
 	.groups			= NULL,			\
@@ -111,6 +110,8 @@ void build_cpu_to_node_map(void);
 #define topology_core_id(cpu)			(cpu_data(cpu)->core_id)
 #define topology_core_siblings(cpu)		(cpu_core_map[cpu])
 #define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
+#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
 #define smt_capable() 				(smp_num_siblings > 1)
 #endif
 
@@ -121,6 +122,10 @@ extern void arch_fix_phys_package_id(int num, u32 slot);
 					node_to_cpumask(pcibus_to_node(bus)) \
 				)
 
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_from_node(pcibus_to_node(bus)))
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_IA64_TOPOLOGY_H */
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index c19b686db9b..d541671caf4 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -203,7 +203,6 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
                             Boot-time Table Parsing
    -------------------------------------------------------------------------- */
 
-static int total_cpus __initdata;
 static int available_cpus __initdata;
 struct acpi_table_madt *acpi_madt __initdata;
 static u8 has_8259;
@@ -1002,7 +1001,7 @@ acpi_map_iosapic(acpi_handle handle, u32 depth, void *context, void **ret)
 	node = pxm_to_node(pxm);
 
 	if (node >= MAX_NUMNODES || !node_online(node) ||
-	    cpus_empty(node_to_cpumask(node)))
+	    cpumask_empty(cpumask_of_node(node)))
 		return AE_OK;
 
 	/* We know a gsi to node mapping! */
diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c
index 9d7e1c66faf..5b0e830c6f3 100644
--- a/