Merge tag 'vexpress/fixes-for-3.15' of git://git.linaro.org/people/pawel.moll/linux into fixes

ARM Versatile Express fixes for 3.15

This series contains straight-forward fixes for different
Versatile Express infrastructure drivers:

- NULL pointer dereference on the error path in the clk driver
- out of boundary array access in the dcscb driver
- broken restart/power off implementation
- mis-interpreted voltage unit in the spc driver

* tag 'vexpress/fixes-for-3.15' of git://git.linaro.org/people/pawel.moll/linux:
  ARM: vexpress/TC2: Convert OPP voltage to uV before storing
  power/reset: vexpress: Fix restart/power off operation
  arm/mach-vexpress: array accessed out of bounds
  clk: vexpress: NULL dereference on error path

Includes an update to 3.15-rc2

Signed-off-by: Arnd Bergmann <arnd@arndb.de>

52 files changed, 466 insertions, 198 deletions

diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
deleted file mode 100644
index c32245c3d1e9..000000000000
--- a/arch/arc/include/asm/barrier.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_BARRIER_H
-#define __ASM_BARRIER_H
-
-#ifndef __ASSEMBLY__
-
-/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */
-#define mb() __asm__ __volatile__ ("" : : : "memory")
-#define rmb() mb()
-#define wmb() mb()
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-#define read_barrier_depends()  mb()
-
-/* TODO-vineetg verify the correctness of macros here */
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#endif
-
-#define smp_read_barrier_depends()      do { } while (0)
-
-#endif
-
-#endif
diff --git a/arch/arm/boot/dts/spear320-hmi.dts b/arch/arm/boot/dts/spear320-hmi.dts
index 3075d2d3a8be..0aa6fef5ce22 100644
--- a/arch/arm/boot/dts/spear320-hmi.dts
+++ b/arch/arm/boot/dts/spear320-hmi.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr320 Evaluation Baord
  *
- * Copyright 2012 Shiraz Hashim <shiraz.hashim@st.com>
+ * Copyright 2012 Shiraz Hashim <shiraz.linux.kernel@gmail.com>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/configs/bcm_defconfig b/arch/arm/configs/bcm_defconfig
index 01004640ee4d..3df3f3a79ef4 100644
--- a/arch/arm/configs/bcm_defconfig
+++ b/arch/arm/configs/bcm_defconfig
@@ -132,7 +132,7 @@ CONFIG_CRC_ITU_T=y
 CONFIG_CRC7=y
 CONFIG_XZ_DEC=y
 CONFIG_AVERAGE=y
-CONFIG_PINCTRL_CAPRI=y
+CONFIG_PINCTRL_BCM281XX=y
 CONFIG_WATCHDOG=y
 CONFIG_BCM_KONA_WDT=y
 CONFIG_BCM_KONA_WDT_DEBUG=y
diff --git a/arch/arm/mach-spear/headsmp.S b/arch/arm/mach-spear/headsmp.S
index ed85473a047f..c52192dc3d9f 100644
--- a/arch/arm/mach-spear/headsmp.S
+++ b/arch/arm/mach-spear/headsmp.S
@@ -3,7 +3,7 @@
  *
  * Picked from realview
  * Copyright (c) 2012 ST Microelectronics Limited
- * Shiraz Hashim <shiraz.hashim@st.com>
+ * Shiraz Hashim <shiraz.linux.kernel@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index 5c4a19887b2b..c19751fff2c6 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -4,7 +4,7 @@
  * based upon linux/arch/arm/mach-realview/platsmp.c
  *
  * Copyright (C) 2012 ST Microelectronics Ltd.
- * Shiraz Hashim <shiraz.hashim@st.com>
+ * Shiraz Hashim <shiraz.linux.kernel@gmail.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/arch/arm/mach-spear/time.c b/arch/arm/mach-spear/time.c
index c4d0931fc6ee..26fda4ed4d51 100644
--- a/arch/arm/mach-spear/time.c
+++ b/arch/arm/mach-spear/time.c
@@ -2,7 +2,7 @@
  * arch/arm/plat-spear/time.c
  *
  * Copyright (C) 2010 ST Microelectronics
- * Shiraz Hashim<shiraz.hashim@st.com>
+ * Shiraz Hashim<shiraz.linux.kernel@gmail.com>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 788495d35cf9..30b993399ed7 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -51,12 +51,14 @@ static int dcscb_allcpus_mask[2];
 static int dcscb_power_up(unsigned int cpu, unsigned int cluster)
 {
 	unsigned int rst_hold, cpumask = (1 << cpu);
-	unsigned int all_mask = dcscb_allcpus_mask[cluster];
+	unsigned int all_mask;
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	if (cpu >= 4 || cluster >= 2)
 		return -EINVAL;
 
+	all_mask = dcscb_allcpus_mask[cluster];
+
 	/*
 	 * Since this is called with IRQs enabled, and no arch_spin_lock_irq
 	 * variant exists, we need to disable IRQs manually here.
@@ -101,11 +103,12 @@ static void dcscb_power_down(void)
 	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 	cpumask = (1 << cpu);
-	all_mask = dcscb_allcpus_mask[cluster];
 
 	pr_debug("%s: cpu %u cluster %u\n", __func__, cpu, cluster);
 	BUG_ON(cpu >= 4 || cluster >= 2);
 
+	all_mask = dcscb_allcpus_mask[cluster];
+
 	__mcpm_cpu_going_down(cpu, cluster);
 
 	arch_spin_lock(&dcscb_lock);
diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c
index c26ef5b92ca7..2c2754e79cb3 100644
--- a/arch/arm/mach-vexpress/spc.c
+++ b/arch/arm/mach-vexpress/spc.c
@@ -392,7 +392,7 @@ static irqreturn_t ve_spc_irq_handler(int irq, void *data)
  *  +--------------------------+
  *  | 31      20 | 19        0 |
  *  +--------------------------+
- *  |   u_volt   |  freq(kHz)  |
+ *  |   m_volt   |  freq(kHz)  |
  *  +--------------------------+
  */
 #define MULT_FACTOR	20
@@ -414,7 +414,7 @@ static int ve_spc_populate_opps(uint32_t cluster)
 		ret = ve_spc_read_sys_cfg(SYSCFG_SCC, off, &data);
 		if (!ret) {
 			opps->freq = (data & FREQ_MASK) * MULT_FACTOR;
-			opps->u_volt = data >> VOLT_SHIFT;
+			opps->u_volt = (data >> VOLT_SHIFT) * 1000;
 		} else {
 			break;
 		}
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index e6f80fcf013b..a4acddad0c78 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -259,7 +259,7 @@ start_ap:
 	 * Switch into virtual mode:
 	 */
 	movl r16=(IA64_PSR_IT|IA64_PSR_IC|IA64_PSR_DT|IA64_PSR_RT|IA64_PSR_DFH|IA64_PSR_BN \
-		  |IA64_PSR_DI|IA64_PSR_AC)
+		  |IA64_PSR_DI)
 	;;
 	mov cr.ipsr=r16
 	movl r17=1f
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index 689ffcaa284e..18e794a57248 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -58,7 +58,7 @@
 #include <asm/unistd.h>
 #include <asm/errno.h>
 
-#if 1
+#if 0
 # define PSR_DEFAULT_BITS	psr.ac
 #else
 # define PSR_DEFAULT_BITS	0
diff --git a/arch/ia64/kvm/vmm_ivt.S b/arch/ia64/kvm/vmm_ivt.S
index 24018484c6e9..397e34a63e18 100644
--- a/arch/ia64/kvm/vmm_ivt.S
+++ b/arch/ia64/kvm/vmm_ivt.S
@@ -64,7 +64,7 @@
 #include "kvm_minstate.h"
 #include "vti.h"
 
-#if 1
+#if 0
 # define PSR_DEFAULT_BITS   psr.ac
 #else
 # define PSR_DEFAULT_BITS   0
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index e422b38d3113..9e67cdea3c74 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -29,15 +29,15 @@ void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start,
 void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page,
 	unsigned long pfn);
 void (*flush_icache_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(flush_icache_range);
 void (*local_flush_icache_range)(unsigned long start, unsigned long end);
 
 void (*__flush_cache_vmap)(void);
 void (*__flush_cache_vunmap)(void);
 
 void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
-void (*__invalidate_kernel_vmap_range)(unsigned long vaddr, int size);
-
 EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range);
+void (*__invalidate_kernel_vmap_range)(unsigned long vaddr, int size);
 
 /* MIPS specific cache operations */
 void (*flush_cache_sigtramp)(unsigned long addr);
diff --git a/arch/parisc/include/asm/shmparam.h b/arch/parisc/include/asm/shmparam.h
index 628ddc22faa8..afe1300ab667 100644
--- a/arch/parisc/include/asm/shmparam.h
+++ b/arch/parisc/include/asm/shmparam.h
@@ -1,8 +1,7 @@
 #ifndef _ASMPARISC_SHMPARAM_H
 #define _ASMPARISC_SHMPARAM_H
 
-#define __ARCH_FORCE_SHMLBA 	1
-
-#define SHMLBA 0x00400000   /* attach addr needs to be 4 Mb aligned */
+#define SHMLBA	   PAGE_SIZE	/* attach addr a multiple of this */
+#define SHM_COLOUR 0x00400000	/* shared mappings colouring */
 
 #endif /* _ASMPARISC_SHMPARAM_H */
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index a6ffc775a9f8..f6448c7c62b5 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -323,7 +323,8 @@ void flush_dcache_page(struct page *page)
 		 * specifically accesses it, of course) */
 
 		flush_tlb_page(mpnt, addr);
-		if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) {
+		if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
+				      != (addr & (SHM_COLOUR - 1))) {
 			__flush_cache_page(mpnt, addr, page_to_phys(page));
 			if (old_addr)
 				printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index b7cadc4a06cd..31ffa9b55322 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -45,7 +45,7 @@
 
 static int get_offset(unsigned int last_mmap)
 {
-	return (last_mmap & (SHMLBA-1)) >> PAGE_SHIFT;
+	return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT;
 }
 
 static unsigned long shared_align_offset(unsigned int last_mmap,
@@ -57,8 +57,8 @@ static unsigned long shared_align_offset(unsigned int last_mmap,
 static inline unsigned long COLOR_ALIGN(unsigned long addr,
 			 unsigned int last_mmap, unsigned long pgoff)
 {
-	unsigned long base = (addr+SHMLBA-1) & ~(SHMLBA-1);
-	unsigned long off  = (SHMLBA-1) &
+	unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1);
+	unsigned long off  = (SHM_COLOUR-1) &
 		(shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT);
 
 	return base + off;
@@ -101,7 +101,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) && last_mmap &&
 		    (addr - shared_align_offset(last_mmap, pgoff))
-				& (SHMLBA - 1))
+				& (SHM_COLOUR - 1))
 			return -EINVAL;
 		goto found_addr;
 	}
@@ -122,7 +122,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.length = len;
 	info.low_limit = mm->mmap_legacy_base;
 	info.high_limit = mmap_upper_limit();
-	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0;
 	info.align_offset = shared_align_offset(last_mmap, pgoff);
 	addr = vm_unmapped_area(&info);
 
@@ -161,7 +161,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (flags & MAP_FIXED) {
 		if ((flags & MAP_SHARED) && last_mmap &&
 		    (addr - shared_align_offset(last_mmap, pgoff))
-			& (SHMLBA - 1))
+			& (SHM_COLOUR - 1))
 			return -EINVAL;
 		goto found_addr;
 	}
@@ -182,7 +182,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	info.align_mask = last_mmap ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0;
 	info.align_offset = shared_align_offset(last_mmap, pgoff);
 	addr = vm_unmapped_area(&info);
 	if (!(addr & ~PAGE_MASK))
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 80e5dd248934..83ead0ea127d 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -392,7 +392,7 @@
 	ENTRY_COMP(vmsplice)
 	ENTRY_COMP(move_pages)		/* 295 */
 	ENTRY_SAME(getcpu)
-	ENTRY_SAME(epoll_pwait)
+	ENTRY_COMP(epoll_pwait)
 	ENTRY_COMP(statfs64)
 	ENTRY_COMP(fstatfs64)
 	ENTRY_COMP(kexec_load)		/* 300 */
diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
index 413dc1769299..b2b441b32341 100644
--- a/arch/parisc/lib/memcpy.c
+++ b/arch/parisc/lib/memcpy.c
@@ -470,7 +470,7 @@ static unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
 		return 0;
 
 	/* if a load or store fault occured we can get the faulty addr */
-	d = &__get_cpu_var(exception_data);
+	d = this_cpu_ptr(&exception_data);
 	fault_addr = d->fault_addr;
 
 	/* error in load or store? */
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 9d08c71a967e..747550762f3c 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -151,7 +151,7 @@ int fixup_exception(struct pt_regs *regs)
 	fix = search_exception_tables(regs->iaoq[0]);
 	if (fix) {
 		struct exception_data *d;
-		d = &__get_cpu_var(exception_data);
+		d = this_cpu_ptr(&exception_data);
 		d->fault_ip = regs->iaoq[0];
 		d->fault_space = regs->isr;
 		d->fault_addr = regs->ior;
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 2a4779091a58..155013da27e0 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -208,7 +208,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus,
 			  unsigned long in_devfn)
 {
 	struct pci_controller* hose;
-	struct pci_bus *bus = NULL;
+	struct pci_bus *tmp_bus, *bus = NULL;
 	struct device_node *hose_node;
 
 	/* Argh ! Please forgive me for that hack, but that's the
@@ -229,10 +229,12 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus,
 	 * used on pre-domains setup. We return the first match
 	 */
 
-	list_for_each_entry(bus, &pci_root_buses, node) {
-		if (in_bus >= bus->number && in_bus <= bus->busn_res.end)
+	list_for_each_entry(tmp_bus, &pci_root_buses, node) {
+		if (in_bus >= tmp_bus->number &&
+		    in_bus <= tmp_bus->busn_res.end) {
+			bus = tmp_bus;
 			break;
-		bus = NULL;
+		}
 	}
 	if (bus == NULL || bus->dev.of_node == NULL)
 		return -ENODEV;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 4ebbb9e99286..3b181b22cd46 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -232,6 +232,7 @@ int __node_distance(int a, int b)
 
 	return distance;
 }
+EXPORT_SYMBOL(__node_distance);
 
 static void initialize_distance_lookup_table(int nid,
 		const __be32 *associativity)
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index d091aa1aaf11..bf9c823d4020 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -31,4 +31,23 @@
 #define SIGP_STATUS_INCORRECT_STATE	0x00000200UL
 #define SIGP_STATUS_NOT_RUNNING		0x00000400UL
 
+#ifndef __ASSEMBLY__
+
+static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status)
+{
+	register unsigned int reg1 asm ("1") = parm;
+	int cc;
+
+	asm volatile(
+		"	sigp	%1,%2,0(%3)\n"
+		"	ipm	%0\n"
+		"	srl	%0,28\n"
+		: "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc");
+	if (status && cc == 1)
+		*status = reg1;
+	return cc;
+}
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* __S390_ASM_SIGP_H */
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 160779394096..21703f85b48d 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -7,6 +7,8 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
+#include <asm/sigp.h>
+
 #ifdef CONFIG_SMP
 
 #include <asm/lowcore.h>
@@ -50,9 +52,18 @@ static inline int smp_store_status(int cpu) { return 0; }
 static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_yield(void) { }
-static inline void smp_stop_cpu(void) { }
 static inline void smp_fill_possible_mask(void) { }
 
+static inline void smp_stop_cpu(void)
+{
+	u16 pcpu = stap();
+
+	for (;;) {
+		__pcpu_sigp(pcpu, SIGP_STOP, 0, NULL);
+		cpu_relax();
+	}
+}
+
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h
index 5eb5c9ddb120..3802d2d3a18d 100644
--- a/arch/s390/include/uapi/asm/unistd.h
+++ b/arch/s390/include/uapi/asm/unistd.h
@@ -282,7 +282,8 @@
 #define __NR_finit_module	344
 #define __NR_sched_setattr	345
 #define __NR_sched_getattr	346
-#define NR_syscalls 345
+#define __NR_renameat2		347
+#define NR_syscalls 348
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 824c39dfddfc..45cdb37aa6f8 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -1,5 +1,5 @@
 /*
- *  Compat sytem call wrappers.
+ *  Compat system call wrappers.
  *
  *    Copyright IBM Corp. 2014
  */
@@ -213,3 +213,4 @@ COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, i
 COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
 COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
 COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
+COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index e6af9406987c..acb412442e5e 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -144,10 +144,10 @@ void show_registers(struct pt_regs *regs)
 	char *mode;
 
 	mode = user_mode(regs) ? "User" : "Krnl";
-	printk("%s PSW : %p %p (%pSR)\n",
-	       mode, (void *) regs->psw.mask,
-	       (void *) regs->psw.addr,
-	       (void *) regs->psw.addr);
+	printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr);
+	if (!user_mode(regs))
+		printk(" (%pSR)", (void *)regs->psw.addr);
+	printk("\n");
 	printk("           R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x "
 	       "P:%x AS:%x CC:%x PM:%x", mask_bits(regs, PSW_MASK_PER),
 	       mask_bits(regs, PSW_MASK_DAT), mask_bits(regs, PSW_MASK_IO),
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 4ac8fafec95f..1c82619eb4f7 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -64,7 +64,7 @@ void update_cr_regs(struct task_struct *task)
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
 			cr_new &= ~(1UL << 55);
 		if (cr_new != cr)
-			__ctl_load(cr, 0, 0);
+			__ctl_load(cr_new, 0, 0);
 		/* Set or clear transaction execution TDC bits 62 and 63. */
 		__ctl_store(cr, 2, 2);
 		cr_new = cr & ~3UL;
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f70f2489fa5f..88d1ca81e2dd 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1027,3 +1027,35 @@ void __init setup_arch(char **cmdline_p)
 	/* Setup zfcpdump support */
 	setup_zfcpdump();
 }
+
+#ifdef CONFIG_32BIT
+static int no_removal_warning __initdata;
+
+static int __init parse_no_removal_warning(char *str)
+{
+	no_removal_warning = 1;
+	return 0;
+}
+__setup("no_removal_warning", parse_no_removal_warning);
+
+static int __init removal_warning(void)
+{
+	if (no_removal_warning)
+		return 0;
+	printk(KERN_ALERT "\n\n");
+	printk(KERN_CONT "Warning - you are using a 31 bit kernel!\n\n");
+	printk(KERN_CONT "We plan to remove 31 bit kernel support from the kernel sources in March 2015.\n");
+	printk(KERN_CONT "Currently we assume that nobody is using the 31 bit kernel on old 31 bit\n");
+	printk(KERN_CONT "hardware anymore. If you think that the code should not be removed and also\n");
+	printk(KERN_CONT "future versions of the Linux kernel should be able to run in 31 bit mode\n");
+	printk(KERN_CONT "please let us know. Please write to:\n");
+	printk(KERN_CONT "linux390@de.ibm.com (mail address) and/or\n");
+	printk(KERN_CONT "linux-s390@vger.kernel.org (mailing list).\n\n");
+	printk(KERN_CONT "Thank you!\n\n");
+	printk(KERN_CONT "If this kernel runs on a 64 bit machine you may consider using a 64 bit kernel.\n");
+	printk(KERN_CONT "This message can be disabled with the \"no_removal_warning\" kernel parameter.\n");
+	schedule_timeout_uninterruptible(300 * HZ);
+	return 0;
+}
+early_initcall(removal_warning);
+#endif
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 512ce1cde2a4..86e65ec3422b 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -82,21 +82,6 @@ DEFINE_MUTEX(smp_cpu_state_mutex);
 /*
  * Signal processor helper functions.
  */
-static inline int __pcpu_sigp(u16 addr, u8 order, u32 parm, u32 *status)
-{
-	register unsigned int reg1 asm ("1") = parm;
-	int cc;
-
-	asm volatile(
-		"	sigp	%1,%2,0(%3)\n"
-		"	ipm	%0\n"
-		"	srl	%0,28\n"
-		: "=d" (cc), "+d" (reg1) : "d" (addr), "a" (order) : "cc");
-	if (status && cc == 1)
-		*status = reg1;
-	return cc;
-}
-
 static inline int __pcpu_sigp_relax(u16 addr, u8 order, u32 parm, u32 *status)
 {
 	int cc;
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 542ef488bac1..fe5cdf29a001 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -355,3 +355,4 @@ SYSCALL(sys_kcmp,sys_kcmp,compat_sys_kcmp)
 SYSCALL(sys_finit_module,sys_finit_module,compat_sys_finit_module)
 SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */
 SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr)
+SYSCALL(sys_renameat2,sys_renameat2,compat_sys_renameat2)
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 23f866b4c7f1..7416efe8eae4 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -338,9 +338,6 @@ static inline unsigned long strnlen_user_srst(const char __user *src,
 	register unsigned long reg0 asm("0") = 0;
 	unsigned long tmp1, tmp2;
 
-	if (unlikely(!size))
-		return 0;
-	update_primary_asce(current);
 	asm volatile(
 		"   la    %2,0(%1)\n"
 		"   la    %3,0(%0,%1)\n"
@@ -359,6 +356,8 @@ static inline unsigned long strnlen_user_srst(const char __user *src,
 
 unsigned long __strnlen_user(const char __user *src, unsigned long size)
 {
+	if (unlikely(!size))
+		return 0;
 	update_primary_asce(current);
 	return strnlen_user_srst(src, size);
 }
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 19f623f1f21c..2f51a998a67e 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -126,6 +126,133 @@ static inline int user_space_fault(struct pt_regs *regs)
 	return 0;
 }
 
+static int bad_address(void *p)
+{
+	unsigned long dummy;
+
+	return probe_kernel_address((unsigned long *)p, dummy);
+}
+
+#ifdef CONFIG_64BIT
+static void dump_pagetable(unsigned long asce, unsigned long address)
+{
+	unsigned long *table = __va(asce & PAGE_MASK);
+
+	pr_alert("AS:%016lx ", asce);
+	switch (asce & _ASCE_TYPE_MASK) {
+	case _ASCE_TYPE_REGION1:
+		table = table + ((address >> 53) & 0x7ff);
+		if (bad_address(table))
+			goto bad;
+		pr_cont("R1:%016lx ", *table);
+		if (*table & _REGION_ENTRY_INVALID)
+			goto out;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* fallthrough */
+	case _ASCE_TYPE_REGION2:
+		table = table + ((address >> 42) & 0x7ff);
+		if (bad_address(table))
+			goto bad;
+		pr_cont("R2:%016lx ", *table);
+		if (*table & _REGION_ENTRY_INVALID)
+			goto out;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* fallthrough */
+	case _ASCE_TYPE_REGION3:
+		table = table + ((address >> 31) & 0x7ff);
+		if (bad_address(table))
+			goto bad;
+		pr_cont("R3:%016lx ", *table);
+		if (*table & (_REGION_ENTRY_INVALID | _REGION3_ENTRY_LARGE))
+			goto out;
+		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
+		/* fallthrough */
+	case _ASCE_TYPE_SEGMENT:
+		table = table + ((address >> 20) & 0x7ff);
+		if (bad_address(table))
+			goto bad;
+		pr_cont(KERN_CONT "S:%016lx ", *table);
+		if (*table & (_SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_LARGE))
+			goto out;
+		table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+	}
+	table = table + ((address >> 12) & 0xff);
+	if (bad_address(table))
+		goto bad;
+	pr_cont("P:%016lx ", *table);
+out:
+	pr_cont("\n");
+	return;
+bad:
+	pr_cont("BAD\n");
+}
+
+#else /* CONFIG_64BIT */
+
+static void dump_pagetable(unsigned long asce, unsigned long address)
+{
+	unsigned long *table = __va(asce & PAGE_MASK);
+
+	pr_alert("AS:%08lx ", asce);
+	table = table + ((address >> 20) & 0x7ff);
+	if (bad_address(table))
+		goto bad;
+	pr_cont("S:%08lx ", *table);
+	if (*table & _SEGMENT_ENTRY_INVALID)
+		goto out;
+	table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN);
+	table = table + ((address >> 12) & 0xff);
+	if (bad_address(table))
+		goto bad;
+	pr_cont("P:%08lx ", *table);
+out:
+	pr_cont("\n");
+	return;
+bad:
+	pr_cont("BAD\n");
+}
+
+#endif /* CONFIG_64BIT */
+
+static void dump_fault_info(struct pt_regs *regs)
+{
+	unsigned long asce;
+
+	pr_alert("Fault in ");
+	switch (regs->int_parm_long & 3) {
+	case 3:
+		pr_cont("home space ");
+		break;
+	case 2:
+		pr_cont("secondary space ");
+		break;
+	case 1:
+		pr_cont("access register ");
+		break;
+	case 0:
+		pr_cont("primary space ");
+		break;
+	}
+	pr_cont("mode while using ");
+	if (!user_space_fault(regs)) {
+		asce = S390_lowcore.kernel_asce;
+		pr_cont("kernel ");
+	}
+#ifdef CONFIG_PGSTE
+	else if ((current->flags & PF_VCPU) && S390_lowcore.gmap) {
+		struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
+		asce = gmap->asce;
+		pr_cont("gmap ");
+	}
+#endif
+	else {
+		asce = S390_lowcore.user_asce;
+		pr_cont("user ");
+	}
+	pr_cont("ASCE.\n");
+	dump_pagetable(asce, regs->int_parm_long & __FAIL_ADDR_MASK);
+}
+
 static inline void report_user_fault(struct pt_regs *regs, long signr)
 {
 	if ((task_pid_nr(current) > 1) && !show_unhandled_signals)
@@ -138,8 +265,9 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 	       regs->int_code);
 	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
 	printk(KERN_CONT "\n");
-	printk(KERN_ALERT "failing address: %lX\n",
-	       regs->int_parm_long & __FAIL_ADDR_MASK);
+	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
+	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
+	dump_fault_info(regs);
 	show_regs(regs);
 }
 
@@ -177,11 +305,13 @@ static noinline void do_no_context(struct pt_regs *regs)
 	address = regs->int_parm_long & __FAIL_ADDR_MASK;
 	if (!user_space_fault(regs))
 		printk(KERN_ALERT "Unable to handle kernel pointer dereference"
-		       " at virtual kernel address %p\n", (void *)address);
+		       " in virtual kernel address space\n");
 	else
 		printk(KERN_ALERT "Unable to handle kernel paging request"
-		       " at virtual user address %p\n", (void *)address);
-
+		       " in virtual user address space\n");
+	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
+	       regs->int_parm_long & __FAIL_ADDR_MASK, regs->int_parm_long);
+	dump_fault_info(regs);
 	die(regs, "Oops");
 	do_exit(SIGKILL);
 }
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 602f57e590b5..d1b7c377a234 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -250,8 +250,8 @@ archclean:
 PHONY += kvmconfig
 kvmconfig:
 	$(if $(wildcard $(objtree)/.config),, $(error You need an existing .config for this target))
-	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config arch/x86/configs/kvm_guest.config
-	$(Q)yes "" | $(MAKE) oldconfig
+	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config $(srctree)/arch/x86/configs/kvm_guest.config
+	$(Q)yes "" | $(MAKE) -f $(srctree)/Makefile oldconfig
 
 define archhelp
   echo  '* bzImage      - Compressed kernel image (arch/x86/boot/bzImage)'
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fcaf9c961265..7de069afb382 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -60,7 +60,7 @@
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
-			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index eeee23ff75ef..68317c80de7f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -598,7 +598,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
 	struct mce m;
 	int i;
-	unsigned long *v;
 
 	this_cpu_inc(mce_poll_count);
 
@@ -618,8 +617,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
-		v = &get_cpu_var(mce_polled_error);
-		set_bit(0, v);
+		this_cpu_write(mce_polled_error, 1);
 		/*
 		 * Uncorrected or signalled events are handled by the exception
 		 * handler when it is enabled, so don't process those here.
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95ae8c43..9a316b21df8b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -42,7 +42,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
  * cmci_discover_lock protects against parallel discovery attempts
  * which could race against each other.
  */
-static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
+static DEFINE_SPINLOCK(cmci_discover_lock);
 
 #define CMCI_THRESHOLD		1
 #define CMCI_POLL_INTERVAL	(30 * HZ)
@@ -144,14 +144,14 @@ static void cmci_storm_disable_banks(void)
 	int bank;
 	u64 val;
 
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	owned = __get_cpu_var(mce_banks_owned);
 	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
 		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 		val &= ~MCI_CTL2_CMCI_EN;
 		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static bool cmci_storm_detect(void)
@@ -211,7 +211,7 @@ static void cmci_discover(int banks)
 	int i;
 	int bios_wrong_thresh = 0;
 
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		u64 val;
 		int bios_zero_thresh = 0;
@@ -266,7 +266,7 @@ static void cmci_discover(int banks)
 			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
 		}
 	}
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 	if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
 		pr_info_once(
 			"bios_cmci_threshold: Some banks do not have valid thresholds set\n");
@@ -316,10 +316,10 @@ void cmci_clear(void)
 
 	if (!cmci_supported(&banks))
 		return;
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++)
 		__cmci_disable_bank(i);
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static void cmci_rediscover_work_func(void *arg)
@@ -360,9 +360,9 @@ void cmci_disable_bank(int bank)
 	if (!cmci_supported(&banks))
 		return;
 
-	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	spin_lock_irqsave(&cmci_discover_lock, flags);
 	__cmci_disable_bank(bank);
-	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static void intel_init_cmci(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 059218ed5208..7c87424d4140 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -59,7 +59,7 @@
 #define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
 #define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT	3	/* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT	3	/* gpu */
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 /* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
 			 1<<RAPL_IDX_PKG_NRG_STAT|\
 			 1<<RAPL_IDX_RAM_NRG_STAT)
 
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT|\
+			 1<<RAPL_IDX_PP1_NRG_STAT)
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_hsw_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
 static struct attribute_group rapl_pmu_events_group = {
 	.name = "events",
 	.attrs = NULL, /* patched at runtime */
@@ -511,6 +535,7 @@ static int rapl_cpu_prepare(int cpu)
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
 	u64 ms;
+	u64 msr_rapl_power_unit_bits;
 
 	if (pmu)
 		return 0;
@@ -518,6 +543,9 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
+	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+		return -1;
+
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
@@ -531,8 +559,7 @@ static int rapl_cpu_prepare(int cpu)
 	 *
 	 * we cache in local PMU instance
 	 */
-	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
-	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
 	/*
@@ -631,11 +658,14 @@ static int __init rapl_pmu_init(void)
 	switch (boot_cpu_data.x86_model) {
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-	case 60: /* Haswell */
-	case 69: /* Haswell-Celeron */
 		rapl_cntr_mask = RAPL_IDX_CLN;
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
+	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
+		rapl_cntr_mask = RAPL_IDX_HSW;
+		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+		break;
 	case 45: /* Sandy Bridge-EP */
 	case 62: /* IvyTown */
 		rapl_cntr_mask = RAPL_IDX_SRV;
@@ -650,7 +680,9 @@ static int __init rapl_pmu_init(void)
 	cpu_notifier_register_begin();
 
 	for_each_online_cpu(cpu) {
-		rapl_cpu_prepare(cpu);
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			goto out;
 		rapl_cpu_init(cpu);
 	}
 
@@ -673,6 +705,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
+out:
 	cpu_notifier_register_done();
 
 	return 0;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index b0cc3809723d..6e2537c32190 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -240,7 +240,7 @@ static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_s
 	return base;
 }
 
-#define KB(x)	((x) * 1024)
+#define KB(x)	((x) * 1024UL)
 #define MB(x)	(KB (KB (x)))
 #define GB(x)	(MB (KB (x)))
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 79a3f9682871..61b17dc2c277 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -897,9 +897,10 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 	struct kprobe *cur = kprobe_running();
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
-	switch (kcb->kprobe_status) {
-	case KPROBE_HIT_SS:
-	case KPROBE_REENTER:
+	if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) {
+		/* This must happen on single-stepping */
+		WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS &&
+			kcb->kprobe_status != KPROBE_REENTER);
 		/*
 		 * We are here because the instruction being single
 		 * stepped caused a page fault. We reset the current
@@ -914,9 +915,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		else
 			reset_current_kprobe();
 		preempt_enable_no_resched();
-		break;
-	case KPROBE_HIT_ACTIVE:
-	case KPROBE_HIT_SSDONE:
+	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
+		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
 		 * We increment the nmissed count for accounting,
 		 * we can also use npre/npostfault count for accounting
@@ -945,10 +945,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 		 * fixup routine could not handle it,
 		 * Let do_page_fault() fix it.
 		 */
-		break;
-	default:
-		break;
 	}
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 654b46574b91..3399d3a99730 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -114,8 +114,8 @@ EXPORT_SYMBOL(machine_real_restart);
  */
 static int __init set_pci_reboot(const struct dmi_system_id *d)
 {
-	if (reboot_type != BOOT_CF9) {
-		reboot_type = BOOT_CF9;
+	if (reboot_type != BOOT_CF9_FORCE) {
+		reboot_type = BOOT_CF9_FORCE;
 		pr_info("%s series board detected. Selecting %s-method for reboots.\n",
 			d->ident, "PCI");
 	}
@@ -458,20 +458,23 @@ void __attribute__((weak)) mach_reboot_fixups(void)
 }
 
 /*
- * Windows compatible x86 hardware expects the following on reboot:
+ * To the best of our knowledge Windows compatible x86 hardware expects
+ * the following on reboot:
  *
  * 1) If the FADT has the ACPI reboot register flag set, try it
  * 2) If still alive, write to the keyboard controller
  * 3) If still alive, write to the ACPI reboot register again
  * 4) If still alive, write to the keyboard controller again
  * 5) If still alive, call the EFI runtime service to reboot
- * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
- * 7) If still alive, inform BIOS to do a proper reboot
+ * 6) If no EFI runtime service, call the BIOS to do a reboot
  *
- * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (7) we'll
- * try to force a triple fault and then cycle between hitting the keyboard
- * controller and doing that
+ * We default to following the same pattern. We also have
+ * two other reboot methods: 'triple fault' and 'PCI', which
+ * can be triggered via the reboot= kernel boot option or
+ * via quirks.
+ *
+ * This means that this function can never return, it can misbehave
+ * by not rebooting properly and hanging.
  */
 static void native_machine_emergency_restart(void)
 {
@@ -492,6 +495,11 @@ static void native_machine_emergency_restart(void)
 	for (;;) {
 		/* Could also try the reset bit in the Hammer NB */
 		switch (reboot_type) {
+		case BOOT_ACPI:
+			acpi_reboot();
+			reboot_type = BOOT_KBD;
+			break;
+
 		case BOOT_KBD:
 			mach_reboot_fixups(); /* For board specific fixups */
 
@@ -509,43 +517,29 @@ static void native_machine_emergency_restart(void)
 			}
 			break;
 
-		case BOOT_TRIPLE:
-			load_idt(&no_idt);
-			__asm__ __volatile__("int3");
-
-			/* We're probably dead after this, but... */
-			reboot_type = BOOT_KBD;
-			break;
-
-		case BOOT_BIOS:
-			machine_real_restart(MRR_BIOS);
-
-			/* We're probably dead after this, but... */
-			reboot_type = BOOT_TRIPLE;
-			break;
-
-		case BOOT_ACPI:
-			acpi_reboot();
-			reboot_type = BOOT_KBD;
-			break;
-
 		case BOOT_EFI:
 			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode == REBOOT_WARM ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
 						 EFI_SUCCESS, 0, NULL);
-			reboot_type = BOOT_CF9_COND;
+			reboot_type = BOOT_BIOS;
+			break;
+
+		case BOOT_BIOS:
+			machine_real_restart(MRR_BIOS);
+
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_CF9_SAFE;
 			break;
 
-		case BOOT_CF9:
+		case BOOT_CF9_FORCE:
 			port_cf9_safe = true;
 			/* Fall through */
 
-		case BOOT_CF9_COND:
+		case BOOT_CF9_SAFE:
 			if (port_cf9_safe) {
-				u8 reboot_code = reboot_mode == REBOOT_WARM ?
-					0x06 : 0x0E;
+				u8 reboot_code = reboot_mode == REBOOT_WARM ?  0x06 : 0x0E;
 				u8 cf9 = inb(0xcf9) & ~reboot_code;
 				outb(cf9|2, 0xcf9); /* Request hard reset */
 				udelay(50);
@@ -553,7 +547,15 @@ static void native_machine_emergency_restart(void)
 				outb(cf9|reboot_code, 0xcf9);
 				udelay(50);
 			}
-			reboot_type = BOOT_BIOS;
+			reboot_type = BOOT_TRIPLE;
+			break;
+
+		case BOOT_TRIPLE:
+			load_idt(&no_idt);
+			__asm__ __volatile__("int3");
+
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_KBD;
 			break;
 		}
 	}
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bea60671ef8a..f47a104a749c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -308,7 +308,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word9_x86_features =
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
-		F(ADX);
+		F(ADX) | F(SMAP);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a2a1bb7ed8c1..eeecbed26ac7 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -48,6 +48,14 @@ static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_SMEP));
 }
 
+static inline bool guest_cpuid_has_smap(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_SMAP));
+}
+
 static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f5704d9e5ddc..813d31038b93 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3601,20 +3601,27 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+void update_permission_bitmask(struct kvm_vcpu *vcpu,
 		struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
-	bool fault, x, w, u, wf, uf, ff, smep;
+	bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0;
 
-	smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
 		pfec = byte << 1;
 		map = 0;
 		wf = pfec & PFERR_WRITE_MASK;
 		uf = pfec & PFERR_USER_MASK;
 		ff = pfec & PFERR_FETCH_MASK;
+		/*
+		 * PFERR_RSVD_MASK bit is set in PFEC if the access is not
+		 * subject to SMAP restrictions, and cleared otherwise. The
+		 * bit is only meaningful if the SMAP bit is set in CR4.
+		 */
+		smapf = !(pfec & PFERR_RSVD_MASK);
 		for (bit = 0; bit < 8; ++bit) {
 			x = bit & ACC_EXEC_MASK;
 			w = bit & ACC_WRITE_MASK;
@@ -3626,12 +3633,33 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				/* Allow supervisor writes if !cr0.wp */
 				w |= !is_write_protection(vcpu) && !uf;
 				/* Disallow supervisor fetches of user code if cr4.smep */
-				x &= !(smep && u && !uf);
+				x &= !(cr4_smep && u && !uf);
+
+				/*
+				 * SMAP:kernel-mode data accesses from user-mode
+				 * mappings should fault. A fault is considered
+				 * as a SMAP violation if all of the following
+				 * conditions are ture:
+				 *   - X86_CR4_SMAP is set in CR4
+				 *   - An user page is accessed
+				 *   - Page fault in kernel mode
+				 *   - if CPL = 3 or X86_EFLAGS_AC is clear
+				 *
+				 *   Here, we cover the first three conditions.
+				 *   The fourth is computed dynamically in
+				 *   permission_fault() and is in smapf.
+				 *
+				 *   Also, SMAP does not affect instruction
+				 *   fetches, add the !ff check here to make it
+				 *   clearer.
+				 */
+				smap = cr4_smap && u && !uf && !ff;
 			} else
 				/* Not really needed: no U/S accesses on ept  */
 				u = 1;
 
-			fault = (ff && !x) || (uf && !u) || (wf && !w);
+			fault = (ff && !x) || (uf && !u) || (wf && !w) ||
+				(smapf && smap);
 			map |= fault << bit;
 		}
 		mmu->permissions[byte] = map;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 292615274358..3842e70bdb7c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -44,11 +44,17 @@
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
-#define PFERR_PRESENT_MASK (1U << 0)
-#define PFERR_WRITE_MASK (1U << 1)
-#define PFERR_USER_MASK (1U << 2)
-#define PFERR_RSVD_MASK (1U << 3)
-#define PFERR_FETCH_MASK (1U << 4)
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+
+#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
+#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
+#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
 
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
@@ -73,6 +79,8 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 		bool execonly);
+void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+		bool ept);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
@@ -110,10 +118,30 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
  * Will a fault with a given page-fault error code (pfec) cause a permission
  * fault with the given access (in ACC_* format)?
  */
-static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
-				    unsigned pfec)
+static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+				    unsigned pte_access, unsigned pfec)
 {
-	return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
+	int cpl = kvm_x86_ops->get_cpl(vcpu);
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+	/*
+	 * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1.
+	 *
+	 * If CPL = 3, SMAP applies to all supervisor-mode data accesses
+	 * (these are implicit supervisor accesses) regardless of the value
+	 * of EFLAGS.AC.
+	 *
+	 * This computes (cpl < 3) && (rflags & X86_EFLAGS_AC), leaving
+	 * the result in X86_EFLAGS_AC. We then insert it in place of
+	 * the PFERR_RSVD_MASK bit; this bit will always be zero in pfec,
+	 * but it will be one in index if SMAP checks are being overridden.
+	 * It is important to keep this branchless.
+	 */
+	unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC);
+	int index = (pfec >> 1) +
+		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+
+	return (mmu->permissions[index] >> pte_access) & 1;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index b1e6c1bf68d3..123efd3ec29f 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -353,7 +353,7 @@ retry_walk:
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
-	if (unlikely(permission_fault(mmu, pte_access, access))) {
+	if (unlikely(permission_fault(vcpu, mmu, pte_access, access))) {
 		errcode |= PFERR_PRESENT_MASK;
 		goto error;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1320e0f8e611..1f68c5831924 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3484,13 +3484,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			hw_cr4 &= ~X86_CR4_PAE;
 			hw_cr4 |= X86_CR4_PSE;
 			/*
-			 * SMEP is disabled if CPU is in non-paging mode in
-			 * hardware. However KVM always uses paging mode to
+			 * SMEP/SMAP is disabled if CPU is in non-paging mode
+			 * in hardware. However KVM always uses paging mode to
 			 * emulate guest non-paging mode with TDP.
-			 * To emulate this behavior, SMEP needs to be manually
-			 * disabled when guest switches to non-paging mode.
+			 * To emulate this behavior, SMEP/SMAP needs to be
+			 * manually disabled when guest switches to non-paging
+			 * mode.
 			 */
-			hw_cr4 &= ~X86_CR4_SMEP;
+			hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
 		} else if (!(cr4 & X86_CR4_PAE)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 		}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9d1b5cd4d34c..8b8fc0b792ba 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -652,6 +652,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
 		return 1;
 
+	if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP))
+		return 1;
+
 	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
 		return 1;
 
@@ -680,6 +683,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
+	if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
+		update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
+
 	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
 		kvm_update_cpuid(vcpu);
 
@@ -1117,7 +1123,6 @@ static inline u64 get_kernel_ns(void)
 {
 	struct timespec ts;
 
-	WARN_ON(preemptible());
 	ktime_get_ts(&ts);
 	monotonic_to_bootbased(&ts);
 	return timespec_to_ns(&ts);
@@ -4164,7 +4169,8 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 		| (write ? PFERR_WRITE_MASK : 0);
 
 	if (vcpu_match_mmio_gva(vcpu, gva)
-	    && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) {
+	    && !permission_fault(vcpu, vcpu->arch.walk_mmu,
+				 vcpu->arch.access, access)) {
 		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
 					(gva & (PAGE_SIZE - 1));
 		trace_vcpu_match_mmio(gva, *gpa, write, false);
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
index f325af26107c..3323c2745248 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/syscalls/Makefile
@@ -54,5 +54,7 @@ syshdr-$(CONFIG_X86_64)		+= syscalls_64.h
 
 targets	+= $(uapisyshdr-y) $(syshdr-y)
 
+PHONY += all
 all: $(addprefix $(uapi)/,$(uapisyshdr-y))
 all: $(addprefix $(out)/,$(syshdr-y))
+	@:
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 96bc506ac6de..d6b867921612 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -359,3 +359,4 @@
 350	i386	finit_module		sys_finit_module
 351	i386	sched_setattr		sys_sched_setattr
 352	i386	sched_getattr		sys_sched_getattr
+353	i386	renameat2		sys_renameat2
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index e8120346903b..604a37efd4d5 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -40,4 +40,6 @@ $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/ina
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 hostprogs-y	+= relocs
 relocs-objs     := relocs_32.o relocs_64.o relocs_common.o
+PHONY += relocs
 relocs: $(obj)/relocs
+	@:
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index a18eadd8bb40..7005974c3ff3 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -441,10 +441,11 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
 	irq_ctx_init(cpu);
 #else
 	clear_tsk_thread_flag(idle, TIF_FORK);
+#endif
 	per_cpu(kernel_stack, cpu) =
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
-#endif
+
 	xen_setup_runstate_info(cpu);
 	xen_setup_timer(cpu);
 	xen_init_lock_cpu(cpu);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 4d3acc34a998..0ba5f3b967f0 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -274,7 +274,7 @@ void __init xen_init_spinlocks(void)
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;
 	}
-
+	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
@@ -290,6 +290,9 @@ static __init int xen_init_spinlocks_jump(void)
 	if (!xen_pvspin)
 		return 0;
 
+	if (!xen_domain())
+		return 0;
+
 	static_key_slow_inc(&paravirt_ticketlocks_enabled);
 	return 0;
 }
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 33ca6e42a4ca..fd92a64d748e 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -75,6 +75,17 @@ ENDPROC(xen_sysexit)
  * stack state in whatever form its in, we keep things simple by only
  * using a single register which is pushed/popped on the stack.
  */
+
+.macro POP_FS
+1:
+	popw %fs
+.pushsection .fixup, "ax"
+2:	movw $0, (%esp)
+	jmp 1b
+.popsection
+	_ASM_EXTABLE(1b,2b)
+.endm
+
 ENTRY(xen_iret)
 	/* test eflags for special cases */
 	testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
@@ -83,15 +94,13 @@ ENTRY(xen_iret)
 	push %eax
 	ESP_OFFSET=4	# bytes pushed onto stack
 
-	/*
-	 * Store vcpu_info pointer for easy access.  Do it this way to
-	 * avoid having to reload %fs
-	 */
+	/* Store vcpu_info pointer for easy access */
 #ifdef CONFIG_SMP
-	GET_THREAD_INFO(%eax)
-	movl %ss:TI_cpu(%eax), %eax
-	movl %ss:__per_cpu_offset(,%eax,4), %eax
-	mov %ss:xen_vcpu(%eax), %eax
+	pushw %fs
+	movl $(__KERNEL_PERCPU), %eax
+	movl %eax, %fs
+	movl %fs:xen_vcpu, %eax
+	POP_FS
 #else
 	movl %ss:xen_vcpu, %eax
 #endif