Merge branch 'linus' into x86/xen

23 files changed, 273 insertions, 95 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 03980cb04291..e3cba0b45600 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -21,12 +21,15 @@ config X86
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
+	select ARCH_WANT_OPTIONAL_GPIOLIB if !X86_RDC321X
 	select HAVE_KRETPROBES
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index bc5553b496f7..9fea73706479 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -182,8 +182,6 @@ static unsigned		outcnt;
 static int  fill_inbuf(void);
 static void flush_window(void);
 static void error(char *m);
-static void gzip_mark(void **);
-static void gzip_release(void **);
 
 /*
  * This is set up by the setup-routine at boot-time
@@ -196,9 +194,6 @@ extern int input_len;
 
 static long bytes_out;
 
-static void *malloc(int size);
-static void free(void *where);
-
 static void *memset(void *s, int c, unsigned n);
 static void *memcpy(void *dest, const void *src, unsigned n);
 
@@ -220,40 +215,6 @@ static int lines, cols;
 
 #include "../../../../lib/inflate.c"
 
-static void *malloc(int size)
-{
-	void *p;
-
-	if (size < 0)
-		error("Malloc error");
-	if (free_mem_ptr <= 0)
-		error("Memory error");
-
-	free_mem_ptr = (free_mem_ptr + 3) & ~3;	/* Align */
-
-	p = (void *)free_mem_ptr;
-	free_mem_ptr += size;
-
-	if (free_mem_ptr >= free_mem_end_ptr)
-		error("Out of memory");
-
-	return p;
-}
-
-static void free(void *where)
-{	/* Don't care */
-}
-
-static void gzip_mark(void **ptr)
-{
-	*ptr = (void *) free_mem_ptr;
-}
-
-static void gzip_release(void **ptr)
-{
-	free_mem_ptr = (memptr) *ptr;
-}
-
 static void scroll(void)
 {
 	int i;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 021d71bc69b5..ffc1bb4fed7d 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -201,7 +201,7 @@ sysexit_from_sys_call:
 	movl RDI-ARGOFFSET(%rsp),%r8d	/* reload 5th syscall arg */
 	.endm
 
-	.macro auditsys_exit exit
+	.macro auditsys_exit exit,ebpsave=RBP
 	testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10)
 	jnz int_ret_from_sys_call
 	TRACE_IRQS_ON
@@ -214,7 +214,7 @@ sysexit_from_sys_call:
 	call audit_syscall_exit
 	GET_THREAD_INFO(%r10)
 	movl RAX-ARGOFFSET(%rsp),%eax	/* reload syscall return value */
-	movl RBP-ARGOFFSET(%rsp),%ebp	/* reload user register value */
+	movl \ebpsave-ARGOFFSET(%rsp),%ebp /* reload user register value */
 	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
 	cli
 	TRACE_IRQS_OFF
@@ -347,7 +347,7 @@ cstar_auditsys:
 	jmp cstar_dispatch
 
 sysretl_audit:
-	auditsys_exit sysretl_from_sys_call
+	auditsys_exit sysretl_from_sys_call, RCX /* user %ebp in RCX slot */
 #endif
 
 cstar_tracesys:
@@ -826,4 +826,10 @@ ia32_sys_call_table:
 	.quad sys32_fallocate
 	.quad compat_sys_timerfd_settime	/* 325 */
 	.quad compat_sys_timerfd_gettime
+	.quad compat_sys_signalfd4
+	.quad sys_eventfd2
+	.quad sys_epoll_create1
+	.quad sys_dup3			/* 330 */
+	.quad sys_pipe2
+	.quad sys_inotify_init1
 ia32_syscall_end:
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index f00afdf61e67..d3c64088b981 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -238,7 +238,7 @@ asmlinkage long sys32_pipe(int __user *fd)
 	int retval;
 	int fds[2];
 
-	retval = do_pipe(fds);
+	retval = do_pipe_flags(fds, 0);
 	if (retval)
 		goto out;
 	if (copy_to_user(fd, fds, sizeof(fds)))
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index a3ddad18aaa3..fa2161d5003b 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -150,6 +150,10 @@ static int __init acpi_sleep_setup(char *str)
 			acpi_realmode_flags |= 2;
 		if (strncmp(str, "s3_beep", 7) == 0)
 			acpi_realmode_flags |= 4;
+#ifdef CONFIG_HIBERNATION
+		if (strncmp(str, "s4_nohwsig", 10) == 0)
+			acpi_no_s4_hw_signature();
+#endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
 		str = strchr(str, ',');
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index bf9b441331e9..9ee24e6bc4b0 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -219,7 +219,6 @@
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <linux/pm.h>
-#include <linux/pm_legacy.h>
 #include <linux/capability.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 0ea6a19bfdfe..ad2b15a1334d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -468,7 +468,7 @@ void hpet_disable(void)
 #define RTC_NUM_INTS		1
 
 static unsigned long hpet_rtc_flags;
-static unsigned long hpet_prev_update_sec;
+static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
 static unsigned long hpet_t1_cmp;
@@ -575,6 +575,9 @@ int hpet_set_rtc_irq_bit(unsigned long bit_mask)
 
 	hpet_rtc_flags |= bit_mask;
 
+	if ((bit_mask & RTC_UIE) && !(oldbits & RTC_UIE))
+		hpet_prev_update_sec = -1;
+
 	if (!oldbits)
 		hpet_rtc_timer_init();
 
@@ -652,7 +655,7 @@ static void hpet_rtc_timer_reinit(void)
 		if (hpet_rtc_flags & RTC_PIE)
 			hpet_pie_count += lost_ints;
 		if (printk_ratelimit())
-			printk(KERN_WARNING "rtc: lost %d interrupts\n",
+			printk(KERN_WARNING "hpet1: lost %d rtc interrupts\n",
 				lost_ints);
 	}
 }
@@ -670,7 +673,8 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
 
 	if (hpet_rtc_flags & RTC_UIE &&
 	    curr_time.tm_sec != hpet_prev_update_sec) {
-		rtc_int_flag = RTC_UF;
+		if (hpet_prev_update_sec >= 0)
+			rtc_int_flag = RTC_UF;
 		hpet_prev_update_sec = curr_time.tm_sec;
 	}
 
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 0373e88de95a..1f26fd9ec4f4 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -43,10 +43,11 @@
 
 #define BUILD_IRQ(nr)				\
 	asmlinkage void IRQ_NAME(nr);		\
-	asm("\n.p2align\n"			\
+	asm("\n.text\n.p2align\n"		\
 	    "IRQ" #nr "_interrupt:\n\t"		\
 	    "push $~(" #nr ") ; "		\
-	    "jmp common_interrupt");
+	    "jmp common_interrupt\n"		\
+	    ".previous");
 
 #define BI(x,y) \
 	BUILD_IRQ(x##y)
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 43c019f85f0d..6c27679ec6aa 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -431,7 +431,6 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 		regs->ip = (unsigned long)p->ainsn.insn;
 }
 
-/* Called with kretprobe_lock held */
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 				      struct pt_regs *regs)
 {
@@ -682,8 +681,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 
 	INIT_HLIST_HEAD(&empty_rp);
-	spin_lock_irqsave(&kretprobe_lock, flags);
-	head = kretprobe_inst_table_head(current);
+	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
@@ -732,7 +730,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	spin_unlock_irqrestore(&kretprobe_lock, flags);
+	kretprobe_hash_unlock(current, &flags);
 
 	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c
index 0e867676b5a5..6ba87830d4b1 100644
--- a/arch/x86/kernel/module_64.c
+++ b/arch/x86/kernel/module_64.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/bug.h>
 
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 151f2d171f7c..19e7fc7c2c4f 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/crash_dump.h>
 #include <linux/dma-mapping.h>
 #include <linux/bitops.h>
 #include <linux/pci_ids.h>
@@ -167,6 +168,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl);
 static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev);
 static void calioc2_tce_cache_blast(struct iommu_table *tbl);
 static void calioc2_dump_error_regs(struct iommu_table *tbl);
+static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl);
+static void get_tce_space_from_tar(void);
 
 static struct cal_chipset_ops calgary_chip_ops = {
 	.handle_quirks = calgary_handle_quirks,
@@ -830,7 +833,11 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar)
 
 	tbl = pci_iommu(dev->bus);
 	tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space;
-	tce_free(tbl, 0, tbl->it_size);
+
+	if (is_kdump_kernel())
+		calgary_init_bitmap_from_tce_table(tbl);
+	else
+		tce_free(tbl, 0, tbl->it_size);
 
 	if (is_calgary(dev->device))
 		tbl->chip_ops = &calgary_chip_ops;
@@ -1209,6 +1216,10 @@ static int __init calgary_init(void)
 	if (ret)
 		return ret;
 
+	/* Purely for kdump kernel case */
+	if (is_kdump_kernel())
+		get_tce_space_from_tar();
+
 	do {
 		dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev);
 		if (!dev)
@@ -1339,6 +1350,61 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev)
 	return (val != 0xffffffff);
 }
 
+/*
+ * calgary_init_bitmap_from_tce_table():
+ * Funtion for kdump case. In the second/kdump kernel initialize
+ * the bitmap based on the tce table entries obtained from first kernel
+ */
+static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl)
+{
+	u64 *tp;
+	unsigned int index;
+	tp = ((u64 *)tbl->it_base);
+	for (index = 0 ; index < tbl->it_size; index++) {
+		if (*tp != 0x0)
+			set_bit(index, tbl->it_map);
+		tp++;
+	}
+}
+
+/*
+ * get_tce_space_from_tar():
+ * Function for kdump case. Get the tce tables from first kernel
+ * by reading the contents of the base adress register of calgary iommu
+ */
+static void get_tce_space_from_tar()
+{
+	int bus;
+	void __iomem *target;
+	unsigned long tce_space;
+
+	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
+		struct calgary_bus_info *info = &bus_info[bus];
+		unsigned short pci_device;
+		u32 val;
+
+		val = read_pci_config(bus, 0, 0, 0);
+		pci_device = (val & 0xFFFF0000) >> 16;
+
+		if (!is_cal_pci_dev(pci_device))
+			continue;
+		if (info->translation_disabled)
+			continue;
+
+		if (calgary_bus_has_devices(bus, pci_device) ||
+						translate_empty_slots) {
+			target = calgary_reg(bus_info[bus].bbar,
+						tar_offset(bus));
+			tce_space = be64_to_cpu(readq(target));
+			tce_space = tce_space & TAR_SW_BITS;
+
+			tce_space = tce_space & (~specified_table_size);
+			info->tce_space = (u64 *)__va(tce_space);
+		}
+	}
+	return;
+}
+
 void __init detect_calgary(void)
 {
 	int bus;
@@ -1394,7 +1460,8 @@ void __init detect_calgary(void)
 		return;
 	}
 
-	specified_table_size = determine_tce_table_size(max_pfn * PAGE_SIZE);
+	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
+					saved_max_pfn : max_pfn) * PAGE_SIZE);
 
 	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
 		struct calgary_bus_info *info = &bus_info[bus];
@@ -1412,10 +1479,16 @@ void __init detect_calgary(void)
 
 		if (calgary_bus_has_devices(bus, pci_device) ||
 		    translate_empty_slots) {
-			tbl = alloc_tce_table();
-			if (!tbl)
-				goto cleanup;
-			info->tce_space = tbl;
+			/*
+			 * If it is kdump kernel, find and use tce tables
+			 * from first kernel, else allocate tce tables here
+			 */
+			if (!is_kdump_kernel()) {
+				tbl = alloc_tce_table();
+				if (!tbl)
+					goto cleanup;
+				info->tce_space = tbl;
+			}
 			calgary_found = 1;
 		}
 	}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0c3927accb00..53bc653ed5ca 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -128,7 +128,7 @@ void cpu_idle(void)
 
 	/* endless idle loop with no priority at all */
 	while (1) {
-		tick_nohz_stop_sched_tick();
+		tick_nohz_stop_sched_tick(1);
 		while (!need_resched()) {
 
 			check_pgt_cache();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e8a8e1b99817..3fb62a7d9a16 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -120,7 +120,7 @@ void cpu_idle(void)
 	current_thread_info()->status |= TS_POLLING;
 	/* endless idle loop with no priority at all */
 	while (1) {
-		tick_nohz_stop_sched_tick();
+		tick_nohz_stop_sched_tick(1);
 		while (!need_resched()) {
 
 			rmb();
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4aacb9f52e3..b520dae02bf4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -597,11 +597,11 @@ void __init setup_arch(char **cmdline_p)
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
 	pre_setup_arch_hook();
-	early_cpu_init();
 #else
 	printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
+	early_cpu_init();
 	early_ioremap_init();
 
 	ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
@@ -665,9 +665,6 @@ void __init setup_arch(char **cmdline_p)
 	bss_resource.start = virt_to_phys(&__bss_start);
 	bss_resource.end = virt_to_phys(&__bss_stop)-1;
 
-#ifdef CONFIG_X86_64
-	early_cpu_init();
-#endif
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index 47c3d249e638..b45ef8ddd651 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
 	return do_sigaltstack(uss, uoss, regs->sp);
 }
 
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err = 0;
+
+	BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
+			sizeof(tsk->thread.xstate->fxsave));
+
+	if ((unsigned long)buf % 16)
+		printk("save_i387: bad fpstate %p\n", buf);
+
+	if (!used_math())
+		return 0;
+	clear_used_math(); /* trigger finit */
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		err = save_i387_checking((struct i387_fxsave_struct __user *)
+					 buf);
+		if (err)
+			return err;
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		stts();
+	} else {
+		if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
+				   sizeof(struct i387_fxsave_struct)))
+			return -1;
+	}
+	return 1;
+}
+
+/*
+ * This restores directly out of user space. Exceptions are handled.
+ */
+static inline int restore_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err;
+
+	if (!used_math()) {
+		err = init_fpu(tsk);
+		if (err)
+			return err;
+	}
+
+	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
+		clts();
+		task_thread_info(current)->status |= TS_USEDFPU;
+	}
+	return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+}
 
 /*
  * Do a signal return; undo the signal stack.
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index adff5562f5fd..d44395ff34c3 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -326,3 +326,9 @@ ENTRY(sys_call_table)
 	.long sys_fallocate
 	.long sys_timerfd_settime	/* 325 */
 	.long sys_timerfd_gettime
+	.long sys_signalfd4
+	.long sys_eventfd2
+	.long sys_epoll_create1
+	.long sys_dup3			/* 330 */
+	.long sys_pipe2
+	.long sys_inotify_init1
diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index 5dfef9fa061a..62fa440678d8 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -42,7 +42,6 @@
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
-static bootmem_data_t node0_bdata;
 
 /*
  * numa interface - we expect the numa architecture specific code to have
@@ -385,7 +384,7 @@ void __init initmem_init(unsigned long start_pfn,
 	for_each_online_node(nid)
 		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));
 
-	NODE_DATA(0)->bdata = &node0_bdata;
+	NODE_DATA(0)->bdata = &bootmem_node_data[0];
 	setup_bootmem_allocator();
 }
 
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 0b3d567e686d..8f307d914c2e 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 	return 1;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -133,9 +134,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 	pgd = pgd_offset(mm, addr);
 	pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
-		if (pud_none(*pud))
-			huge_pmd_share(mm, addr, pud);
-		pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		if (sz == PUD_SIZE) {
+			pte = (pte_t *)pud;
+		} else {
+			BUG_ON(sz != PMD_SIZE);
+			if (pud_none(*pud))
+				huge_pmd_share(mm, addr, pud);
+			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 
@@ -151,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 	pgd = pgd_offset(mm, addr);
 	if (pgd_present(*pgd)) {
 		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud))
+		if (pud_present(*pud)) {
+			if (pud_large(*pud))
+				return (pte_t *)pud;
 			pmd = pmd_offset(pud, addr);
+		}
 	}
 	return (pte_t *) pmd;
 }
@@ -188,6 +197,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -208,6 +222,11 @@ int pmd_huge(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PSE);
 }
 
+int pud_huge(pud_t pud)
+{
+	return !!(pud_val(pud) & _PAGE_PSE);
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -216,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 
 	page = pte_page(*(pte_t *)pmd);
 	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pud);
+	if (page)
+		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
 	return page;
 }
+
 #endif
 
 /* x86_64 also uses this file */
@@ -228,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
@@ -240,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 	}
 
 full_search:
-	addr = ALIGN(start_addr, HPAGE_SIZE);
+	addr = ALIGN(start_addr, huge_page_size(h));
 
 	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
 		/* At this point:  (!vma || addr < vma->vm_end). */
@@ -262,7 +295,7 @@ full_search:
 		}
 		if (addr + mm->cached_hole_size < vma->vm_start)
 		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+		addr = ALIGN(vma->vm_end, huge_page_size(h));
 	}
 }
 
@@ -270,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		unsigned long addr0, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev_vma;
 	unsigned long base = mm->mmap_base, addr = addr0;
@@ -290,7 +324,7 @@ try_again:
 		goto fail;
 
 	/* either no address requested or cant fit in requested address hole */
-	addr = (mm->free_area_cache - len) & HPAGE_MASK;
+	addr = (mm->free_area_cache - len) & huge_page_mask(h);
 	do {
 		/*
 		 * Lookup failure means no vma is above this address,
@@ -321,7 +355,7 @@ try_again:
 		        largest_hole = vma->vm_start - addr;
 
 		/* try just below the current vma->vm_start */
-		addr = (vma->vm_start - len) & HPAGE_MASK;
+		addr = (vma->vm_start - len) & huge_page_mask(h);
 	} while (len <= vma->vm_start);
 
 fail:
@@ -359,22 +393,23 @@ unsigned long
 hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
+	struct hstate *h = hstate_file(file);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
-	if (len & ~HPAGE_MASK)
+	if (len & ~huge_page_mask(h))
 		return -EINVAL;
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
 	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(addr, len))
+		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
 		return addr;
 	}
 
 	if (addr) {
-		addr = ALIGN(addr, HPAGE_SIZE);
+		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
 		    (!vma || addr + len <= vma->vm_start))
@@ -390,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
 
+#ifdef CONFIG_X86_64
+static __init int setup_hugepagesz(char *opt)
+{
+	unsigned long ps = memparse(opt, &opt);
+	if (ps == PMD_SIZE) {
+		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
+	} else if (ps == PUD_SIZE && cpu_has_gbpages) {
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	} else {
+		printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
+			ps >> 20);
+		return 0;
+	}
+	return 1;
+}
+__setup("hugepagesz=", setup_hugepagesz);
+#endif
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 24c1d3c30186..016f335bbeea 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	return (void __iomem *)ret;
 }
 
+void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
+				unsigned long prot_val)
+{
+	return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_prot);
+
 /**
  * iounmap - Free a IO remapping
  * @addr: virtual address from ioremap_*
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9782f42dd319..a4dd793d6003 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -23,8 +23,6 @@
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
-static bootmem_data_t plat_node_bdata[MAX_NUMNODES];
-
 struct memnode memnode;
 
 s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
@@ -198,7 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 		nodedata_phys + pgdat_size - 1);
 
 	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
-	NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
+	NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid];
 	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
 	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;
 
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 7f3329b55d2e..3f90289410e6 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -369,20 +369,34 @@ static int __init ppro_init(char **cpu_type)
 {
 	__u8 cpu_model = boot_cpu_data.x86_model;
 
-	if (cpu_model == 14)
+	switch (cpu_model) {
+	case 0 ... 2:
+		*cpu_type = "i386/ppro";
+		break;
+	case 3 ... 5:
+		*cpu_type = "i386/pii";
+		break;
+	case 6 ... 8:
+		*cpu_type = "i386/piii";
+		break;
+	case 9:
+		*cpu_type = "i386/p6_mobile";
+		break;
+	case 10 ... 13:
+		*cpu_type = "i386/p6";
+		break;
+	case 14:
 		*cpu_type = "i386/core";
-	else if (cpu_model == 15 || cpu_model == 23)
+		break;
+	case 15: case 23:
+		*cpu_type = "i386/core_2";
+		break;
+	case 26:
 		*cpu_type = "i386/core_2";
-	else if (cpu_model > 0xd)
+		break;
+	default:
+		/* Unknown */
 		return 0;
-	else if (cpu_model == 9) {
-		*cpu_type = "i386/p6_mobile";
-	} else if (cpu_model > 5) {
-		*cpu_type = "i386/piii";
-	} else if (cpu_model > 2) {
-		*cpu_type = "i386/pii";
-	} else {
-		*cpu_type = "i386/ppro";
 	}
 
 	model = &op_ppro_spec;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 2aafb67dc5f1..a09505806b82 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -280,6 +280,7 @@ static void pci_track_mmap_page_range(struct vm_area_struct *vma)
 static struct vm_operations_struct pci_mmap_ops = {
 	.open  = pci_track_mmap_page_range,
 	.close = pci_unmap_page_range,
+	.access = generic_access_phys,
 };
 
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 4038cbfe3331..7f58304fafb3 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -173,7 +173,7 @@ ENTRY(xen_sysexit)
 	pushq $__USER32_CS
 	pushq %rdx
 
-	pushq $VGCF_in_syscall
+	pushq $0
 1:	jmp hypercall_iret
 ENDPATCH(xen_sysexit)
 RELOC(xen_sysexit, 1b+1)