Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

26 files changed, 154 insertions, 392 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/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 218ba5b67d92..64790353951f 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/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/um/include/shared/os.h b/arch/um/include/shared/os.h
index 75298d3358e7..08eec0b691b0 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -136,6 +136,7 @@ extern int os_ioctl_generic(int fd, unsigned int cmd, unsigned long arg);
 extern int os_get_ifname(int fd, char *namebuf);
 extern int os_set_slip(int fd);
 extern int os_mode_fd(int fd, int mode);
+extern int os_fsync_file(int fd);
 
 extern int os_seek_file(int fd, unsigned long long offset);
 extern int os_open_file(const char *file, struct openflags flags, int mode);
diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c
index f116db15d402..30fdd5d0067b 100644
--- a/arch/um/kernel/physmem.c
+++ b/arch/um/kernel/physmem.c
@@ -103,6 +103,7 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end,
 	 */
 	os_seek_file(physmem_fd, __pa(&__syscall_stub_start));
 	os_write_file(physmem_fd, &__syscall_stub_start, PAGE_SIZE);
+	os_fsync_file(physmem_fd);
 
 	bootmap_size = init_bootmem(pfn, pfn + delta);
 	free_bootmem(__pa(reserve_end) + bootmap_size,
diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c
index 07a750197bb0..08d90fba952c 100644
--- a/arch/um/os-Linux/file.c
+++ b/arch/um/os-Linux/file.c
@@ -237,6 +237,12 @@ void os_close_file(int fd)
 {
 	close(fd);
 }
+int os_fsync_file(int fd)
+{
+	if (fsync(fd) < 0)
+	    return -errno;
+	return 0;
+}
 
 int os_seek_file(int fd, unsigned long long offset)
 {
diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c
index e1704ff600ff..df9191acd926 100644
--- a/arch/um/os-Linux/main.c
+++ b/arch/um/os-Linux/main.c
@@ -151,6 +151,7 @@ int __init main(int argc, char **argv, char **envp)
 #endif
 
 	do_uml_initcalls();
+	change_sig(SIGPIPE, 0);
 	ret = linux_main(argc, argv);
 
 	/*
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 3c4af77e51a2..897e9ad0c108 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -12,337 +12,117 @@
 #include <string.h>
 #include <sys/stat.h>
 #include <sys/mman.h>
-#include <sys/param.h>
+#include <sys/vfs.h>
+#include <linux/magic.h>
 #include <init.h>
 #include <os.h>
 
-/* Modified by which_tmpdir, which is called during early boot */
-static char *default_tmpdir = "/tmp";
-
-/*
- *  Modified when creating the physical memory file and when checking
- * the tmp filesystem for usability, both happening during early boot.
- */
+/* Set by make_tempfile() during early boot. */
 static char *tempdir = NULL;
 
-static void __init find_tempdir(void)
+/* Check if dir is on tmpfs. Return 0 if yes, -1 if no or error. */
+static int __init check_tmpfs(const char *dir)
 {
-	const char *dirs[] = { "TMP", "TEMP", "TMPDIR", NULL };
-	int i;
-	char *dir = NULL;
-
-	if (tempdir != NULL)
-		/* We've already been called */
-		return;
-	for (i = 0; dirs[i]; i++) {
-		dir = getenv(dirs[i]);
-		if ((dir != NULL) && (*dir != '\0'))
-			break;
-	}
-	if ((dir == NULL) || (*dir == '\0'))
-		dir = default_tmpdir;
+	struct statfs st;
 
-	tempdir = malloc(strlen(dir) + 2);
-	if (tempdir == NULL) {
-		fprintf(stderr, "Failed to malloc tempdir, "
-			"errno = %d\n", errno);
-		return;
-	}
-	strcpy(tempdir, dir);
-	strcat(tempdir, "/");
-}
-
-/*
- * Remove bytes from the front of the buffer and refill it so that if there's a
- * partial string that we care about, it will be completed, and we can recognize
- * it.
- */
-static int pop(int fd, char *buf, size_t size, size_t npop)
-{
-	ssize_t n;
-	size_t len = strlen(&buf[npop]);
-
-	memmove(buf, &buf[npop], len + 1);
-	n = read(fd, &buf[len], size - len - 1);
-	if (n < 0)
-		return -errno;
-
-	buf[len + n] = '\0';
-	return 1;
-}
-
-/*
- * This will return 1, with the first character in buf being the
- * character following the next instance of c in the file.  This will
- * read the file as needed.  If there's an error, -errno is returned;
- * if the end of the file is reached, 0 is returned.
- */
-static int next(int fd, char *buf, size_t size, char c)
-{
-	ssize_t n;
-	char *ptr;
-
-	while ((ptr = strchr(buf, c)) == NULL) {
-		n = read(fd, buf, size - 1);
-		if (n == 0)
-			return 0;
-		else if (n < 0)
-			return -errno;
-
-		buf[n] = '\0';
+	printf("Checking if %s is on tmpfs...", dir);
+	if (statfs(dir, &st) < 0) {
+		printf("%s\n", strerror(errno));
+	} else if (st.f_type != TMPFS_MAGIC) {
+		printf("no\n");
+	} else {
+		printf("OK\n");
+		return 0;
 	}
-
-	return pop(fd, buf, size, ptr - buf + 1);
+	return -1;
 }
 
 /*
- * Decode an octal-escaped and space-terminated path of the form used by
- * /proc/mounts. May be used to decode a path in-place. "out" must be at least
- * as large as the input. The output is always null-terminated. "len" gets the
- * length of the output, excluding the trailing null. Returns 0 if a full path
- * was successfully decoded, otherwise an error.
+ * Choose the tempdir to use. We want something on tmpfs so that our memory is
+ * not subject to the host's vm.dirty_ratio. If a tempdir is specified in the
+ * environment, we use that even if it's not on tmpfs, but we warn the user.
+ * Otherwise, we try common tmpfs locations, and if no tmpfs directory is found
+ * then we fall back to /tmp.
  */
-static int decode_path(const char *in, char *out, size_t *len)
+static char * __init choose_tempdir(void)
 {
-	char *first = out;
-	int c;
+	static const char * const vars[] = {
+		"TMPDIR",
+		"TMP",
+		"TEMP",
+		NULL
+	};
+	static const char fallback_dir[] = "/tmp";
+	static const char * const tmpfs_dirs[] = {
+		"/dev/shm",
+		fallback_dir,
+		NULL
+	};
 	int i;
-	int ret = -EINVAL;
-	while (1) {
-		switch (*in) {
-		case '\0':
-			goto out;
-
-		case ' ':
-			ret = 0;
-			goto out;
-
-		case '\\':
-			in++;
-			c = 0;
-			for (i = 0; i < 3; i++) {
-				if (*in < '0' || *in > '7')
-					goto out;
-				c = (c << 3) | (*in++ - '0');
-			}
-			*(unsigned char *)out++ = (unsigned char) c;
-			break;
-
-		default:
-			*out++ = *in++;
-			break;
+	const char *dir;
+
+	printf("Checking environment variables for a tempdir...");
+	for (i = 0; vars[i]; i++) {
+		dir = getenv(vars[i]);
+		if ((dir != NULL) && (*dir != '\0')) {
+			printf("%s\n", dir);
+			if (check_tmpfs(dir) >= 0)
+				goto done;
+			else
+				goto warn;
 		}
 	}
+	printf("none found\n");
 
-out:
-	*out = '\0';
-	*len = out - first;
-	return ret;
-}
-
-/*
- * Computes the length of s when encoded with three-digit octal escape sequences
- * for the characters in chars.
- */
-static size_t octal_encoded_length(const char *s, const char *chars)
-{
-	size_t len = strlen(s);
-	while ((s = strpbrk(s, chars)) != NULL) {
-		len += 3;
-		s++;
-	}
-
-	return len;
-}
-
-enum {
-	OUTCOME_NOTHING_MOUNTED,
-	OUTCOME_TMPFS_MOUNT,
-	OUTCOME_NON_TMPFS_MOUNT,
-};
-
-/* Read a line of /proc/mounts data looking for a tmpfs mount at "path". */
-static int read_mount(int fd, char *buf, size_t bufsize, const char *path,
-		      int *outcome)
-{
-	int found;
-	int match;
-	char *space;
-	size_t len;
-
-	enum {
-		MATCH_NONE,
-		MATCH_EXACT,
-		MATCH_PARENT,
-	};
-
-	found = next(fd, buf, bufsize, ' ');
-	if (found != 1)
-		return found;
-
-	/*
-	 * If there's no following space in the buffer, then this path is
-	 * truncated, so it can't be the one we're looking for.
-	 */
-	space = strchr(buf, ' ');
-	if (space) {
-		match = MATCH_NONE;
-		if (!decode_path(buf, buf, &len)) {
-			if (!strcmp(buf, path))
-				match = MATCH_EXACT;
-			else if (!strncmp(buf, path, len)
-				 && (path[len] == '/' || !strcmp(buf, "/")))
-				match = MATCH_PARENT;
-		}
-
-		found = pop(fd, buf, bufsize, space - buf + 1);
-		if (found != 1)
-			return found;
-
-		switch (match) {
-		case MATCH_EXACT:
-			if (!strncmp(buf, "tmpfs", strlen("tmpfs")))
-				*outcome = OUTCOME_TMPFS_MOUNT;
-			else
-				*outcome = OUTCOME_NON_TMPFS_MOUNT;
-			break;
-
-		case MATCH_PARENT:
-			/* This mount obscures any previous ones. */
-			*outcome = OUTCOME_NOTHING_MOUNTED;
-			break;
-		}
+	for (i = 0; tmpfs_dirs[i]; i++) {
+		dir = tmpfs_dirs[i];
+		if (check_tmpfs(dir) >= 0)
+			goto done;
 	}
 
-	return next(fd, buf, bufsize, '\n');
+	dir = fallback_dir;
+warn:
+	printf("Warning: tempdir %s is not on tmpfs\n", dir);
+done:
+	/* Make a copy since getenv results may not remain valid forever. */
+	return strdup(dir);
 }
 
-/* which_tmpdir is called only during early boot */
-static int checked_tmpdir = 0;
-
 /*
- * Look for a tmpfs mounted at /dev/shm.  I couldn't find a cleaner
- * way to do this than to parse /proc/mounts.  statfs will return the
- * same filesystem magic number and fs id for both /dev and /dev/shm
- * when they are both tmpfs, so you can't tell if they are different
- * filesystems.  Also, there seems to be no other way of finding the
- * mount point of a filesystem from within it.
- *
- * If a /dev/shm tmpfs entry is found, then we switch to using it.
- * Otherwise, we stay with the default /tmp.
+ * Create an unlinked tempfile in a suitable tempdir. template must be the
+ * basename part of the template with a leading '/'.
  */
-static void which_tmpdir(void)
+static int __init make_tempfile(const char *template)
 {
+	char *tempname;
 	int fd;
-	int found;
-	int outcome;
-	char *path;
-	char *buf;
-	size_t bufsize;
 
-	if (checked_tmpdir)
-		return;
-
-	checked_tmpdir = 1;
-
-	printf("Checking for tmpfs mount on /dev/shm...");
-
-	path = realpath("/dev/shm", NULL);
-	if (!path) {
-		printf("failed to check real path, errno = %d\n", errno);
-		return;
-	}
-	printf("%s...", path);
-
-	/*
-	 * The buffer needs to be able to fit the full octal-escaped path, a
-	 * space, and a trailing null in order to successfully decode it.
-	 */
-	bufsize = octal_encoded_length(path, " \t\n\\") + 2;
-
-	if (bufsize < 128)
-		bufsize = 128;
-
-	buf = malloc(bufsize);
-	if (!buf) {
-		printf("malloc failed, errno = %d\n", errno);
-		goto out;
-	}
-	buf[0] = '\0';
-
-	fd = open("/proc/mounts", O_RDONLY);
-	if (fd < 0) {
-		printf("failed to open /proc/mounts, errno = %d\n", errno);
-		goto out1;
-	}
-
-	outcome = OUTCOME_NOTHING_MOUNTED;
-	while (1) {
-		found = read_mount(fd, buf, bufsize, path, &outcome);
-		if (found != 1)
-			break;
-	}
-
-	if (found < 0) {
-		printf("read returned errno %d\n", -found);
-	} else {
-		switch (outcome) {
-		case OUTCOME_TMPFS_MOUNT:
-			printf("OK\n");
-			default_tmpdir = "/dev/shm";
-			break;
-
-		case OUTCOME_NON_TMPFS_MOUNT:
-			printf("not tmpfs\n");
-			break;
-
-		default:
-			printf("nothing mounted on /dev/shm\n");
-			break;
+	if (tempdir == NULL) {
+		tempdir = choose_tempdir();
+		if (tempdir == NULL) {
+			fprintf(stderr, "Failed to choose tempdir: %s\n",
+				strerror(errno));
+			return -1;
 		}
 	}
 
-	close(fd);
-out1:
-	free(buf);
-out:
-	free(path);
-}
-
-static int __init make_tempfile(const char *template, char **out_tempname,
-				int do_unlink)
-{
-	char *tempname;
-	int fd;
-
-	which_tmpdir();
-	tempname = malloc(MAXPATHLEN);
+	tempname = malloc(strlen(tempdir) + strlen(template) + 1);
 	if (tempname == NULL)
 		return -1;
 
-	find_tempdir();
-	if ((tempdir == NULL) || (strlen(tempdir) >= MAXPATHLEN))
-		goto out;
-
-	if (template[0] != '/')
-		strcpy(tempname, tempdir);
-	else
-		tempname[0] = '\0';
-	strncat(tempname, template, MAXPATHLEN-1-strlen(tempname));
+	strcpy(tempname, tempdir);
+	strcat(tempname, template);
 	fd = mkstemp(tempname);
 	if (fd < 0) {
 		fprintf(stderr, "open - cannot create %s: %s\n", tempname,
 			strerror(errno));
 		goto out;
 	}
-	if (do_unlink && (unlink(tempname) < 0)) {
+	if (unlink(tempname) < 0) {
 		perror("unlink");
 		goto close;
 	}
-	if (out_tempname) {
-		*out_tempname = tempname;
-	} else
-		free(tempname);
+	free(tempname);
 	return fd;
 close:
 	close(fd);
@@ -351,14 +131,14 @@ out:
 	return -1;
 }
 
-#define TEMPNAME_TEMPLATE "vm_file-XXXXXX"
+#define TEMPNAME_TEMPLATE "/vm_file-XXXXXX"
 
 static int __init create_tmp_file(unsigned long long len)
 {
 	int fd, err;
 	char zero;
 
-	fd = make_tempfile(TEMPNAME_TEMPLATE, NULL, 1);
+	fd = make_tempfile(TEMPNAME_TEMPLATE);
 	if (fd < 0)
 		exit(1);
 
@@ -402,7 +182,6 @@ int __init create_mem_file(unsigned long long len)
 	return fd;
 }
 
-
 void __init check_tmpexec(void)
 {
 	void *addr;
@@ -410,14 +189,13 @@ void __init check_tmpexec(void)
 
 	addr = mmap(NULL, UM_KERN_PAGE_SIZE,
 		    PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, fd, 0);
-	printf("Checking PROT_EXEC mmap in %s...",tempdir);
-	fflush(stdout);
+	printf("Checking PROT_EXEC mmap in %s...", tempdir);
 	if (addr == MAP_FAILED) {
 		err = errno;
-		perror("failed");
+		printf("%s\n", strerror(err));
 		close(fd);
 		if (err == EPERM)
-			printf("%s must be not mounted noexec\n",tempdir);
+			printf("%s must be not mounted noexec\n", tempdir);
 		exit(1);
 	}
 	printf("OK\n");
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 7c87424d4140..619f7699487a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -543,7 +543,8 @@ 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))
+	/* protect rdmsrl() to handle virtualization */
+	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));
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 2e263f367b13..9df017ab2285 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -9,12 +9,9 @@ SECTIONS
 #ifdef BUILD_VDSO32
 #include <asm/vdso32.h>
 
-	.hpet_sect : {
-		hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
-	} :text :hpet_sect
+	hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
 
-	.vvar_sect : {
-		vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
+	vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
 
 	/* Place all vvars at the offsets in asm/vvar.h. */
 #define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset;
@@ -22,7 +19,6 @@ SECTIONS
 #include <asm/vvar.h>
 #undef __VVAR_KERNEL_LDS
 #undef EMIT_VVAR
-	} :text :vvar_sect
 #endif
 	. = SIZEOF_HEADERS;
 
@@ -61,7 +57,12 @@ SECTIONS
 	 */
 	. = ALIGN(0x100);
 
-	.text		: { *(.text*) }			:text	=0x90909090
+	.text		: { *(.text*) }			:text	=0x90909090,
+
+	/*
+	 * The comma above works around a bug in gold:
+	 * https://sourceware.org/bugzilla/show_bug.cgi?id=16804
+	 */
 
 	/DISCARD/ : {
 		*(.discard)
@@ -84,8 +85,4 @@ PHDRS
 	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
 	note		PT_NOTE		FLAGS(4);		/* PF_R */
 	eh_frame_hdr	PT_GNU_EH_FRAME;
-#ifdef BUILD_VDSO32
-	vvar_sect	PT_NULL		FLAGS(4);		/* PF_R */
-	hpet_sect	PT_NULL		FLAGS(4);		/* PF_R */
-#endif
 }
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