22 files changed, 322 insertions, 163 deletions

diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 8bbea6aa40d9..efe5acfc79c3 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -94,10 +94,10 @@ bs_die:
 
 	.section ".bsdata", "a"
 bugger_off_msg:
-	.ascii	"Direct booting from floppy is no longer supported.\r\n"
-	.ascii	"Please use a boot loader program instead.\r\n"
+	.ascii	"Direct floppy boot is not supported. "
+	.ascii	"Use a boot loader program instead.\r\n"
 	.ascii	"\n"
-	.ascii	"Remove disk and press any key to reboot . . .\r\n"
+	.ascii	"Remove disk and press any key to reboot ...\r\n"
 	.byte	0
 
 #ifdef CONFIG_EFI_STUB
@@ -111,7 +111,7 @@ coff_header:
 #else
 	.word	0x8664				# x86-64
 #endif
-	.word	2				# nr_sections
+	.word	3				# nr_sections
 	.long	0 				# TimeDateStamp
 	.long	0				# PointerToSymbolTable
 	.long	1				# NumberOfSymbols
@@ -158,8 +158,8 @@ extra_header_fields:
 #else
 	.quad	0				# ImageBase
 #endif
-	.long	0x1000				# SectionAlignment
-	.long	0x200				# FileAlignment
+	.long	0x20				# SectionAlignment
+	.long	0x20				# FileAlignment
 	.word	0				# MajorOperatingSystemVersion
 	.word	0				# MinorOperatingSystemVersion
 	.word	0				# MajorImageVersion
@@ -200,8 +200,10 @@ extra_header_fields:
 
 	# Section table
 section_table:
-	.ascii	".text"
-	.byte	0
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".setup"
 	.byte	0
 	.byte	0
 	.long	0
@@ -217,9 +219,8 @@ section_table:
 
 	#
 	# The EFI application loader requires a relocation section
-	# because EFI applications must be relocatable. But since
-	# we don't need the loader to fixup any relocs for us, we
-	# just create an empty (zero-length) .reloc section header.
+	# because EFI applications must be relocatable. The .reloc
+	# offset & size fields are filled in by build.c.
 	#
 	.ascii	".reloc"
 	.byte	0
@@ -233,6 +234,25 @@ section_table:
 	.word	0				# NumberOfRelocations
 	.word	0				# NumberOfLineNumbers
 	.long	0x42100040			# Characteristics (section flags)
+
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".text"
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0				# startup_{32,64}
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0				# startup_{32,64}
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0x60500020			# Characteristics (section flags)
+
 #endif /* CONFIG_EFI_STUB */
 
 	# Kernel attributes; used by setup.  This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 3f61f6e2b46f..4b8e165ee572 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -50,6 +50,8 @@ typedef unsigned int   u32;
 u8 buf[SETUP_SECT_MAX*512];
 int is_big_kernel;
 
+#define PECOFF_RELOC_RESERVE 0x20
+
 /*----------------------------------------------------------------------*/
 
 static const u32 crctab32[] = {
@@ -133,11 +135,103 @@ static void usage(void)
 	die("Usage: build setup system [> image]");
 }
 
-int main(int argc, char ** argv)
-{
 #ifdef CONFIG_EFI_STUB
-	unsigned int file_sz, pe_header;
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	unsigned int pe_header;
+	unsigned short num_sections;
+	u8 *section;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+	num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+	section = &buf[pe_header + 0xa8];
+#else
+	section = &buf[pe_header + 0xb8];
 #endif
+
+	while (num_sections > 0) {
+		if (strncmp((char*)section, section_name, 8) == 0) {
+			/* section header size field */
+			put_unaligned_le32(size, section + 0x8);
+
+			/* section header vma field */
+			put_unaligned_le32(offset, section + 0xc);
+
+			/* section header 'size of initialised data' field */
+			put_unaligned_le32(size, section + 0x10);
+
+			/* section header 'file offset' field */
+			put_unaligned_le32(offset, section + 0x14);
+
+			break;
+		}
+		section += 0x28;
+		num_sections--;
+	}
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+	u32 setup_offset = 0x200;
+	u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+	u32 setup_size = reloc_offset - setup_offset;
+
+	update_pecoff_section_header(".setup", setup_offset, setup_size);
+	update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+	/*
+	 * Modify .reloc section contents with a single entry. The
+	 * relocation is applied to offset 10 of the relocation section.
+	 */
+	put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+	put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+	unsigned int pe_header;
+	unsigned int text_sz = file_sz - text_start;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of image */
+	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+	/*
+	 * Size of code: Subtract the size of the first sector (512 bytes)
+	 * which includes the header.
+	 */
+	put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * Address of entry point.
+	 *
+	 * The EFI stub entry point is +16 bytes from the start of
+	 * the .text section.
+	 */
+	put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+	/*
+	 * Address of entry point. startup_32 is at the beginning and
+	 * the 64-bit entry point (startup_64) is always 512 bytes
+	 * after. The EFI stub entry point is 16 bytes after that, as
+	 * the first instruction allows legacy loaders to jump over
+	 * the EFI stub initialisation
+	 */
+	put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+	update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
+int main(int argc, char ** argv)
+{
 	unsigned int i, sz, setup_sectors;
 	int c;
 	u32 sys_size;
@@ -163,6 +257,12 @@ int main(int argc, char ** argv)
 		die("Boot block hasn't got boot flag (0xAA55)");
 	fclose(file);
 
+#ifdef CONFIG_EFI_STUB
+	/* Reserve 0x20 bytes for .reloc section */
+	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+	c += PECOFF_RELOC_RESERVE;
+#endif
+
 	/* Pad unused space with zeros */
 	setup_sectors = (c + 511) / 512;
 	if (setup_sectors < SETUP_SECT_MIN)
@@ -170,6 +270,10 @@ int main(int argc, char ** argv)
 	i = setup_sectors*512;
 	memset(buf+c, 0, i-c);
 
+#ifdef CONFIG_EFI_STUB
+	update_pecoff_setup_and_reloc(i);
+#endif
+
 	/* Set the default root device */
 	put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
 
@@ -194,66 +298,8 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(sys_size, &buf[0x1f4]);
 
 #ifdef CONFIG_EFI_STUB
-	file_sz = sz + i + ((sys_size * 16) - sz);
-
-	pe_header = get_unaligned_le32(&buf[0x3c]);
-
-	/* Size of image */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
-	/*
-	 * Subtract the size of the first section (512 bytes) which
-	 * includes the header and .reloc section. The remaining size
-	 * is that of the .text section.
-	 */
-	file_sz -= 512;
-
-	/* Size of code */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
-	/*
-	 * Address of entry point.
-	 *
-	 * The EFI stub entry point is +16 bytes from the start of
-	 * the .text section.
-	 */
-	put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
-	/* .text size */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
-	/* .text vma */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
-	/* .text size of initialised data */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
-	/* .text file offset */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
-	/*
-	 * Address of entry point. startup_32 is at the beginning and
-	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after. The EFI stub entry point is 16 bytes after that, as
-	 * the first instruction allows legacy loaders to jump over
-	 * the EFI stub initialisation
-	 */
-	put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
-	/* .text size */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
-	/* .text vma */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
-	/* .text size of initialised data */
-	put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
-	/* .text file offset */
-	put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+	update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
 
 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, stdout) != i)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 0e3793b821ef..dc580c42851c 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -54,6 +54,20 @@ struct nmiaction {
 	__register_nmi_handler((t), &fn##_na);	\
 })
 
+/*
+ * For special handlers that register/unregister in the
+ * init section only.  This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n)		\
+({							\
+	static struct nmiaction fn##_na __initdata = {		\
+		.handler = (fn),			\
+		.name = (n),				\
+		.flags = (fg),				\
+	};						\
+	__register_nmi_handler((t), &fn##_na);	\
+})
+
 int __register_nmi_handler(unsigned int, struct nmiaction *);
 
 void unregister_nmi_handler(unsigned int, const char *);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd6882308e..e1f3a17034fc 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
 #define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) 	\
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 
@@ -77,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index becf47b81735..6149b476d9df 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -149,7 +149,6 @@
 /* 4 bits of software ack period */
 #define UV2_ACK_MASK			0x7UL
 #define UV2_ACK_UNITS_SHFT		3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
 #define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 
 /*
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e76c191a835..d5fd66f0d4cd 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -20,7 +20,6 @@
 #include <linux/bitops.h>
 #include <linux/ioport.h>
 #include <linux/suspend.h>
-#include <linux/kmemleak.h>
 #include <asm/e820.h>
 #include <asm/io.h>
 #include <asm/iommu.h>
@@ -95,11 +94,6 @@ static u32 __init allocate_aperture(void)
 		return 0;
 	}
 	memblock_reserve(addr, aper_size);
-	/*
-	 * Kmemleak should not scan this block as it may not be mapped via the
-	 * kernel direct mapping.
-	 */
-	kmemleak_ignore(phys_to_virt(addr));
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
 			aper_size >> 10, addr);
 	insert_aperture_resource((u32)addr, aper_size);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ac96561d1a99..5f0ff597437c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1195,7 +1195,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 	BUG_ON(!cfg->vector);
 
 	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+	for_each_cpu(cpu, cfg->domain)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 
 	cfg->vector = 0;
@@ -1203,7 +1203,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 
 	if (likely(!cfg->move_in_progress))
 		return;
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+	for_each_cpu(cpu, cfg->old_domain) {
 		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
 								vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 0a687fd185e6..da27c5d2168a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1274,7 +1274,7 @@ static void mce_timer_fn(unsigned long data)
 	 */
 	iv = __this_cpu_read(mce_next_interval);
 	if (mce_notify_irq())
-		iv = max(iv, (unsigned long) HZ/100);
+		iv = max(iv / 2, (unsigned long) HZ/100);
 	else
 		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
 	__this_cpu_write(mce_next_interval, iv);
@@ -1557,7 +1557,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
-	unsigned long iv = __this_cpu_read(mce_next_interval);
+	unsigned long iv = check_interval * HZ;
 
 	setup_timer(t, mce_timer_fn, smp_processor_id());
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6da0183..c4706cf9c011 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 		if (!cpuc->shared_regs)
 			goto error;
 	}
+	cpuc->is_fake = 1;
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (bytes != sizeof(frame))
 			break;
 
-		if (fp < compat_ptr(regs->sp))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		if (bytes != sizeof(frame))
 			break;
 
-		if ((unsigned long)fp < regs->sp)
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf54493..7241e2fc3c17 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@ struct cpu_hw_events {
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
 	unsigned int		group_flag;
+	int			is_fake;
 
 	/*
 	 * Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
+	void		(*pebs_aliases)(struct perf_event *event);
 
 	/*
 	 * Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546ec6aef..187c294bc658 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
 {
 	if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
-		return false;
+		return idx;
 
-	if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
-		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01bb;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
-		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
-	} else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+	if (idx == EXTRA_REG_RSP_0)
+		return EXTRA_REG_RSP_1;
+
+	if (idx == EXTRA_REG_RSP_1)
+		return EXTRA_REG_RSP_0;
+
+	return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+	event->hw.extra_reg.idx = idx;
+
+	if (idx == EXTRA_REG_RSP_0) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
 		event->hw.config |= 0x01b7;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+	} else if (idx == EXTRA_REG_RSP_1) {
+		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+		event->hw.config |= 0x01bb;
+		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
 	}
-
-	if (event->hw.extra_reg.idx == orig_idx)
-		return false;
-
-	return true;
 }
 
 /*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 	struct event_constraint *c = &emptyconstraint;
 	struct er_account *era;
 	unsigned long flags;
-	int orig_idx = reg->idx;
+	int idx = reg->idx;
 
-	/* already allocated shared msr */
-	if (reg->alloc)
+	/*
+	 * reg->alloc can be set due to existing state, so for fake cpuc we
+	 * need to ignore this, otherwise we might fail to allocate proper fake
+	 * state for this extra reg constraint. Also see the comment below.
+	 */
+	if (reg->alloc && !cpuc->is_fake)
 		return NULL; /* call x86_get_event_constraint() */
 
 again:
-	era = &cpuc->shared_regs->regs[reg->idx];
+	era = &cpuc->shared_regs->regs[idx];
 	/*
 	 * we use spin_lock_irqsave() to avoid lockdep issues when
 	 * passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
 
 	if (!atomic_read(&era->ref) || era->config == reg->config) {
 
+		/*
+		 * If its a fake cpuc -- as per validate_{group,event}() we
+		 * shouldn't touch event state and we can avoid doing so
+		 * since both will only call get_event_constraints() once
+		 * on each event, this avoids the need for reg->alloc.
+		 *
+		 * Not doing the ER fixup will only result in era->reg being
+		 * wrong, but since we won't actually try and program hardware
+		 * this isn't a problem either.
+		 */
+		if (!cpuc->is_fake) {
+			if (idx != reg->idx)
+				intel_fixup_er(event, idx);
+
+			/*
+			 * x86_schedule_events() can call get_event_constraints()
+			 * multiple times on events in the case of incremental
+			 * scheduling(). reg->alloc ensures we only do the ER
+			 * allocation once.
+			 */
+			reg->alloc = 1;
+		}
+
 		/* lock in msr value */
 		era->config = reg->config;
 		era->reg = reg->reg;
@@ -1180,17 +1213,17 @@ again:
 		/* one more user */
 		atomic_inc(&era->ref);
 
-		/* no need to reallocate during incremental event scheduling */
-		reg->alloc = 1;
-
 		/*
 		 * need to call x86_get_event_constraint()
 		 * to check if associated event has constraints
 		 */
 		c = NULL;
-	} else if (intel_try_alt_er(event, orig_idx)) {
-		raw_spin_unlock_irqrestore(&era->lock, flags);
-		goto again;
+	} else {
+		idx = intel_alt_er(idx);
+		if (idx != reg->idx) {
+			raw_spin_unlock_irqrestore(&era->lock, flags);
+			goto again;
+		}
 	}
 	raw_spin_unlock_irqrestore(&era->lock, flags);
 
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
 	struct er_account *era;
 
 	/*
-	 * only put constraint if extra reg was actually
-	 * allocated. Also takes care of event which do
-	 * not use an extra shared reg
+	 * Only put constraint if extra reg was actually allocated. Also takes
+	 * care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake cpuc we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+	 * either since it'll be thrown out.
 	 */
-	if (!reg->alloc)
+	if (!reg->alloc || cpuc->is_fake)
 		return;
 
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
 {
-	int ret = x86_pmu_hw_config(event);
-
-	if (ret)
-		return ret;
-
-	if (event->attr.precise_ip &&
-	    (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
 		/*
 		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
 		 * (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 */
 		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
 
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use UOPS_RETIRED.ALL
+		 * (0x01c2), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * UOPS_RETIRED.ALL counts the number of cycles that retires
+		 * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+		 * larger than the maximum number of micro-ops that can be
+		 * retired per cycle (4) and then inverting the condition, we
+		 * count all cycles that retire 16 or less micro-ops, which
+		 * is every cycle.
+		 *
+		 * Thereby we gain a PEBS capable cycle counter.
+		 */
+		u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+		x86_pmu.pebs_aliases(event);
 
 	if (intel_pmu_needs_lbr_smpl(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
+	.pebs_aliases		= intel_pebs_aliases_core2,
 
 	.format_attrs		= intel_arch3_formats_attr,
 
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
-		x86_add_quirk(intel_sandybridge_quirk);
 	case 45: /* SandyBridge, "Romely-EP" */
+		x86_add_quirk(intel_sandybridge_quirk);
+	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc27f6e5..35e2192df9f4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e31bf8d5c4d2..149b8d9c6ad4 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -42,7 +42,7 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs)
 static void __init init_nmi_testsuite(void)
 {
 	/* trap all the unknown NMIs we may generate */
-	register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+	register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
 }
 
 static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@ static void __init test_nmi_ipi(struct cpumask *mask)
 {
 	unsigned long timeout;
 
-	if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+	if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
 				 NMI_FLAG_FIRST, "nmi_selftest")) {
 		nmi_fail = FAILURE;
 		return;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 79c45af81604..25b48edb847c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -639,9 +639,11 @@ void native_machine_shutdown(void)
 	set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
 
 	/*
-	 * O.K Now that I'm on the appropriate processor,
-	 * stop all of the others.
+	 * O.K Now that I'm on the appropriate processor, stop all of the
+	 * others. Also disable the local irq to not receive the per-cpu
+	 * timer interrupt which may trigger scheduler's load balance.
 	 */
+	local_irq_disable();
 	stop_other_cpus();
 #endif
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f56f96da77f5..3fab55bea29b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -382,6 +382,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_mc && match_llc(c, o)))
 			link_mask(llc_shared, cpu, i);
 
+	}
+
+	/*
+	 * This needs a separate iteration over the cpus because we rely on all
+	 * cpu_sibling_mask links to be set-up.
+	 */
+	for_each_cpu(i, cpu_sibling_setup_mask) {
+		o = &cpu_data(i);
+
 		if ((i == cpu) || (has_mc && match_mc(c, o))) {
 			link_mask(core, cpu, i);
 
@@ -410,15 +419,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 /* maps the cpu to the sched domain representing multi-core */
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	/*
-	 * For perf, we return last level cache shared map.
-	 * And for power savings, we return cpu_core_map
-	 */
-	if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
-		return cpu_core_mask(cpu);
-	else
-		return cpu_llc_shared_mask(cpu);
+	return cpu_llc_shared_mask(cpu);
 }
 
 static void impress_friends(void)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67ec00f..677b1ed184c9 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/word-at-a-time.h>
+#include <linux/sched.h>
 
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
+	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+		return len;
+
 	do {
 		ret = __get_user_pages_fast(addr, 1, 0, &page);
 		if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 819137904428..5d7e51f3fd28 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
 #  - (66): the last prefix is 0x66
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
-#
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 
 Table: one byte opcode
 Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
 b5: LGS Gv,Mp
 b6: MOVZX Gv,Eb
 b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
 b9: Grp10 (1A)
 ba: Grp8 Ev,Ib (1A)
 bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
 be: MOVSX Gv,Eb
 bf: MOVSX Gv,Ew
 # 0x0f 0xc0-0xcf
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 97141c26a13a..bc4e9d84157f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -62,7 +62,8 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
 		extra += PMD_SIZE;
 #endif
 		/* The first 2/4M doesn't use large pages. */
-		extra += mr->end - mr->start;
+		if (mr->start < PMD_SIZE)
+			extra += mr->end - mr->start;
 
 		ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	} else
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 732af3a96183..4599c3e8bcb6 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,6 +176,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		return;
 	}
 
+	node_set(node, numa_nodes_parsed);
+
 	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
 	       node, pxm,
 	       (unsigned long long) start, (unsigned long long) end - 1);
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e31bcd8f2eee..fd41a9262d65 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -782,7 +782,7 @@ BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
 EXPORT_SYMBOL_GPL(intel_scu_notifier);
 
 /* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
 {
 	int i;
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3ae0e61abd23..59880afa851f 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1295,7 +1295,6 @@ static void __init enable_timeouts(void)
 		 */
 		mmr_image |= (1L << SOFTACK_MSHIFT);
 		if (is_uv2_hub()) {
-			mmr_image &= ~(1L << UV2_LEG_SHFT);
 			mmr_image |= (1L << UV2_EXT_SHFT);
 		}
 		write_mmr_misc_control(pnode, mmr_image);
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6c3a15..ddcf39b1a18d 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@ BEGIN {
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO
 
-	lprefix1_expr = "\\(66\\)"
+	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\(F2\\)"
+	lprefix3_expr = "\\((F2|!F3)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
 	# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, lprefix1_expr)) {
 			lptable1[idx] = add_flags(lptable1[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix2_expr)) {
+		}
+		if (match(ext, lprefix2_expr)) {
 			lptable2[idx] = add_flags(lptable2[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix3_expr)) {
+		}
+		if (match(ext, lprefix3_expr)) {
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
-		} else {
+		}
+		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
 	}