Merge branch 'perf/core' into perf/uprobes

Merge in latest upstream (and the latest perf development tree),
to prepare for tooling changes, and also to pick up v3.4 MM
changes that the uprobes code needs to take care of.

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

19 files changed, 330 insertions, 208 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index e37963c1df4d..1ced6413ea03 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -15,6 +15,8 @@
 #ifndef __ASM_GENERIC_ATOMIC_H
 #define __ASM_GENERIC_ATOMIC_H
 
+#include <asm/cmpxchg.h>
+
 #ifdef CONFIG_SMP
 /* Force people to define core atomics */
 # if !defined(atomic_add_return) || !defined(atomic_sub_return) || \
@@ -52,7 +54,6 @@
 #define atomic_set(v, i) (((v)->counter) = (i))
 
 #include <linux/irqflags.h>
-#include <asm/system.h>
 
 /**
  * atomic_add_return - add integer to atomic variable
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
new file mode 100644
index 000000000000..639d7a4d033b
--- /dev/null
+++ b/include/asm-generic/barrier.h
@@ -0,0 +1,50 @@
+/* Generic barrier definitions, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_BARRIER_H
+#define __ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#define nop() asm volatile ("nop")
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ *
+ * This implementation only contains a compiler barrier.
+ */
+
+#define mb()	asm volatile ("": : :"memory")
+#define rmb()	mb()
+#define wmb()	asm volatile ("": : :"memory")
+
+#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 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()		do {} while (0)
+#define smp_read_barrier_depends()	do {} while (0)
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index ecc44a8e2b44..9ae6c34dc191 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,7 +2,7 @@
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
 #include <asm/types.h>
-#include <asm/system.h>
+#include <linux/irqflags.h>
 
 #ifdef CONFIG_SMP
 #include <asm/spinlock.h>
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 84458b0c38d1..2520a6e241dc 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -134,7 +134,7 @@ extern void warn_slowpath_null(const char *file, const int line);
 #endif
 
 #define WARN_ON_ONCE(condition)	({				\
-	static bool __warned;					\
+	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once))				\
@@ -144,7 +144,7 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 
 #define WARN_ONCE(condition, format...)	({			\
-	static bool __warned;					\
+	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once))				\
@@ -154,7 +154,7 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 
 #define WARN_TAINT_ONCE(condition, taint, format...)	({	\
-	static bool __warned;					\
+	static bool __section(.data.unlikely) __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once))				\
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 213ac6e8fe39..14883026015d 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -1,22 +1,98 @@
+/*
+ * Generic UP xchg and cmpxchg using interrupt disablement.  Does not
+ * support SMP.
+ */
+
 #ifndef __ASM_GENERIC_CMPXCHG_H
 #define __ASM_GENERIC_CMPXCHG_H
 
-/*
- * Generic cmpxchg
- *
- * Uses the local cmpxchg. Does not support SMP.
- */
 #ifdef CONFIG_SMP
 #error "Cannot use generic cmpxchg on SMP"
 #endif
 
+#include <linux/types.h>
+#include <linux/irqflags.h>
+
+#ifndef xchg
+
+/*
+ * This function doesn't exist, so you'll get a linker error if
+ * something tries to do an invalidly-sized xchg().
+ */
+extern void __xchg_called_with_bad_pointer(void);
+
+static inline
+unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	unsigned long ret, flags;
+
+	switch (size) {
+	case 1:
+#ifdef __xchg_u8
+		return __xchg_u8(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u8 *)ptr;
+		*(volatile u8 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u8 */
+
+	case 2:
+#ifdef __xchg_u16
+		return __xchg_u16(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u16 *)ptr;
+		*(volatile u16 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u16 */
+
+	case 4:
+#ifdef __xchg_u32
+		return __xchg_u32(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u32 *)ptr;
+		*(volatile u32 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u32 */
+
+#ifdef CONFIG_64BIT
+	case 8:
+#ifdef __xchg_u64
+		return __xchg_u64(x, ptr);
+#else
+		local_irq_save(flags);
+		ret = *(volatile u64 *)ptr;
+		*(volatile u64 *)ptr = x;
+		local_irq_restore(flags);
+		return ret;
+#endif /* __xchg_u64 */
+#endif /* CONFIG_64BIT */
+
+	default:
+		__xchg_called_with_bad_pointer();
+		return x;
+	}
+}
+
+#define xchg(ptr, x) \
+	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
+
+#endif /* xchg */
+
 /*
  * Atomic compare and exchange.
  *
  * Do not define __HAVE_ARCH_CMPXCHG because we want to use it to check whether
  * a cmpxchg primitive faster than repeated local irq save/restore exists.
  */
+#include <asm-generic/cmpxchg-local.h>
+
 #define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
 #define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
 
-#endif
+#endif /* __ASM_GENERIC_CMPXCHG_H */
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 9fa3f96e38cf..2e248d8924dc 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -2,6 +2,7 @@
 #define _ASM_GENERIC_DMA_MAPPING_H
 
 #include <linux/kmemcheck.h>
+#include <linux/bug.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-debug.h>
 #include <linux/dma-attrs.h>
diff --git a/include/asm-generic/exec.h b/include/asm-generic/exec.h
new file mode 100644
index 000000000000..567766b0074a
--- /dev/null
+++ b/include/asm-generic/exec.h
@@ -0,0 +1,19 @@
+/* Generic process execution definitions, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_EXEC_H
+#define __ASM_GENERIC_EXEC_H
+
+#define arch_align_stack(x) (x)
+
+#endif /* __ASM_GENERIC_EXEC_H */
diff --git a/include/asm-generic/getorder.h b/include/asm-generic/getorder.h
index 67e7245dc9b3..65e4468ac53d 100644
--- a/include/asm-generic/getorder.h
+++ b/include/asm-generic/getorder.h
@@ -4,21 +4,58 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler.h>
+#include <linux/log2.h>
 
-/* Pure 2^n version of get_order */
-static inline __attribute_const__ int get_order(unsigned long size)
+/*
+ * Runtime evaluation of get_order()
+ */
+static inline __attribute_const__
+int __get_order(unsigned long size)
 {
 	int order;
 
-	size = (size - 1) >> (PAGE_SHIFT - 1);
-	order = -1;
-	do {
-		size >>= 1;
-		order++;
-	} while (size);
+	size--;
+	size >>= PAGE_SHIFT;
+#if BITS_PER_LONG == 32
+	order = fls(size);
+#else
+	order = fls64(size);
+#endif
 	return order;
 }
 
+/**
+ * get_order - Determine the allocation order of a memory size
+ * @size: The size for which to get the order
+ *
+ * Determine the allocation order of a particular sized block of memory.  This
+ * is on a logarithmic scale, where:
+ *
+ *	0 -> 2^0 * PAGE_SIZE and below
+ *	1 -> 2^1 * PAGE_SIZE to 2^0 * PAGE_SIZE + 1
+ *	2 -> 2^2 * PAGE_SIZE to 2^1 * PAGE_SIZE + 1
+ *	3 -> 2^3 * PAGE_SIZE to 2^2 * PAGE_SIZE + 1
+ *	4 -> 2^4 * PAGE_SIZE to 2^3 * PAGE_SIZE + 1
+ *	...
+ *
+ * The order returned is used to find the smallest allocation granule required
+ * to hold an object of the specified size.
+ *
+ * The result is undefined if the size is 0.
+ *
+ * This function may be used to initialise variables with compile time
+ * evaluations of constants.
+ */
+#define get_order(n)						\
+(								\
+	__builtin_constant_p(n) ? (				\
+		((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT :	\
+		(((n) < (1UL << PAGE_SHIFT)) ? 0 :		\
+		 ilog2((n) - 1) - PAGE_SHIFT + 1)		\
+	) :							\
+	__get_order(n)						\
+)
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_GENERIC_GETORDER_H */
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 1ff4e221cb4d..5f52690c3c8f 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -142,9 +142,9 @@ extern int __must_check gpiochip_reserve(int start, int ngpio);
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
 extern int __must_check gpiochip_remove(struct gpio_chip *chip);
-extern struct gpio_chip *gpiochip_find(void *data,
+extern struct gpio_chip *gpiochip_find(const void *data,
 					int (*match)(struct gpio_chip *chip,
-						     void *data));
+						     const void *data));
 
 
 /* Always use the library code for GPIO management calls,
diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h
index 787abbb6d867..d030d2c2647a 100644
--- a/include/asm-generic/mman-common.h
+++ b/include/asm-generic/mman-common.h
@@ -48,6 +48,10 @@
 #define MADV_HUGEPAGE	14		/* Worth backing with hugepages */
 #define MADV_NOHUGEPAGE	15		/* Not worth backing with hugepages */
 
+#define MADV_DONTDUMP   16		/* Explicity exclude from the core dump,
+					   overrides the coredump filter bits */
+#define MADV_DODUMP	17		/* Clear the MADV_NODUMP flag */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
diff --git a/include/asm-generic/pci-bridge.h b/include/asm-generic/pci-bridge.h
index 4a5aca2a2c94..a5b5d5a89a4f 100644
--- a/include/asm-generic/pci-bridge.h
+++ b/include/asm-generic/pci-bridge.h
@@ -45,6 +45,11 @@ static inline void pci_add_flags(int flags)
 	pci_flags |= flags;
 }
 
+static inline void pci_clear_flags(int flags)
+{
+	pci_flags &= ~flags;
+}
+
 static inline int pci_has_flag(int flag)
 {
 	return pci_flags & flag;
@@ -52,6 +57,7 @@ static inline int pci_has_flag(int flag)
 #else
 static inline void pci_set_flags(int flags) { }
 static inline void pci_add_flags(int flags) { }
+static inline void pci_clear_flags(int flags) { }
 static inline int pci_has_flag(int flag)
 {
 	return 0;
diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h
index 26373cff4546..e80a0495e5b0 100644
--- a/include/asm-generic/pci.h
+++ b/include/asm-generic/pci.h
@@ -6,30 +6,6 @@
 #ifndef _ASM_GENERIC_PCI_H
 #define _ASM_GENERIC_PCI_H
 
-/**
- * pcibios_resource_to_bus - convert resource to PCI bus address
- * @dev: device which owns this resource
- * @region: converted bus-centric region (start,end)
- * @res: resource to convert
- *
- * Convert a resource to a PCI device bus address or bus window.
- */
-static inline void
-pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
-			 struct resource *res)
-{
-	region->start = res->start;
-	region->end = res->end;
-}
-
-static inline void
-pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
-			struct pci_bus_region *region)
-{
-	res->start = region->start;
-	res->end = region->end;
-}
-
 static inline struct resource *
 pcibios_select_root(struct pci_dev *pdev, struct resource *res)
 {
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 76bff2bff15e..125c54e98517 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -5,6 +5,7 @@
 #ifdef CONFIG_MMU
 
 #include <linux/mm_types.h>
+#include <linux/bug.h>
 
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
@@ -425,6 +426,8 @@ extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 				unsigned long size);
 #endif
 
+#ifdef CONFIG_MMU
+
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_trans_huge(pmd_t pmd)
 {
@@ -441,7 +444,66 @@ static inline int pmd_write(pmd_t pmd)
 	return 0;
 }
 #endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * This function is meant to be used by sites walking pagetables with
+ * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
+ * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
+ * into a null pmd and the transhuge page fault can convert a null pmd
+ * into an hugepmd or into a regular pmd (if the hugepage allocation
+ * fails). While holding the mmap_sem in read mode the pmd becomes
+ * stable and stops changing under us only if it's not null and not a
+ * transhuge pmd. When those races occurs and this function makes a
+ * difference vs the standard pmd_none_or_clear_bad, the result is
+ * undefined so behaving like if the pmd was none is safe (because it
+ * can return none anyway). The compiler level barrier() is critically
+ * important to compute the two checks atomically on the same pmdval.
+ */
+static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
+{
+	/* depend on compiler for an atomic pmd read */
+	pmd_t pmdval = *pmd;
+	/*
+	 * The barrier will stabilize the pmdval in a register or on
+	 * the stack so that it will stop changing under the code.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+	if (pmd_none(pmdval))
+		return 1;
+	if (unlikely(pmd_bad(pmdval))) {
+		if (!pmd_trans_huge(pmdval))
+			pmd_clear_bad(pmd);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * This is a noop if Transparent Hugepage Support is not built into
+ * the kernel. Otherwise it is equivalent to
+ * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
+ * places that already verified the pmd is not none and they want to
+ * walk ptes while holding the mmap sem in read mode (write mode don't
+ * need this). If THP is not enabled, the pmd can't go away under the
+ * code even if MADV_DONTNEED runs, but if THP is enabled we need to
+ * run a pmd_trans_unstable before walking the ptes after
+ * split_huge_page_pmd returns (because it may have run when the pmd
+ * become null, but then a page fault can map in a THP and not a
+ * regular page).
+ */
+static inline int pmd_trans_unstable(pmd_t *pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return pmd_none_or_trans_huge_or_clear_bad(pmd);
+#else
+	return 0;
 #endif
+}
+
+#endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/asm-generic/socket.h b/include/asm-generic/socket.h
index 49c1704173e7..b1bea03274d5 100644
--- a/include/asm-generic/socket.h
+++ b/include/asm-generic/socket.h
@@ -67,4 +67,9 @@
 
 #define SO_WIFI_STATUS		41
 #define SCM_WIFI_STATUS	SO_WIFI_STATUS
+#define SO_PEEK_OFF		42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS		43
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/asm-generic/switch_to.h b/include/asm-generic/switch_to.h
new file mode 100644
index 000000000000..052c4ac04fd5
--- /dev/null
+++ b/include/asm-generic/switch_to.h
@@ -0,0 +1,30 @@
+/* Generic task switch macro wrapper, based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __ASM_GENERIC_SWITCH_TO_H
+#define __ASM_GENERIC_SWITCH_TO_H
+
+#include <linux/thread_info.h>
+
+/*
+ * Context switching is now performed out-of-line in switch_to.S
+ */
+extern struct task_struct *__switch_to(struct task_struct *,
+				       struct task_struct *);
+
+#define switch_to(prev, next, last)					\
+	do {								\
+		((last) = __switch_to((prev), (next)));			\
+	} while (0)
+
+#endif /* __ASM_GENERIC_SWITCH_TO_H */
diff --git a/include/asm-generic/system.h b/include/asm-generic/system.h
deleted file mode 100644
index 215efa74f5a2..000000000000
--- a/include/asm-generic/system.h
+++ /dev/null
@@ -1,141 +0,0 @@
-/* Generic system definitions, based on MN10300 definitions.
- *
- * It should be possible to use these on really simple architectures,
- * but it serves more as a starting point for new ports.
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef __ASM_GENERIC_SYSTEM_H
-#define __ASM_GENERIC_SYSTEM_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <linux/irqflags.h>
-
-#include <asm/cmpxchg-local.h>
-#include <asm/cmpxchg.h>
-
-struct task_struct;
-
-/* context switching is now performed out-of-line in switch_to.S */
-extern struct task_struct *__switch_to(struct task_struct *,
-		struct task_struct *);
-#define switch_to(prev, next, last)					\
-	do {								\
-		((last) = __switch_to((prev), (next)));			\
-	} while (0)
-
-#define arch_align_stack(x) (x)
-
-#define nop() asm volatile ("nop")
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- *
- * This implementation only contains a compiler barrier.
- */
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#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 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()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-/*
- * we make sure local_irq_enable() doesn't cause priority inversion
- */
-#ifndef __ASSEMBLY__
-
-/* This function doesn't exist, so you'll get a linker error
- *    if something tries to do an invalid xchg().  */
-extern void __xchg_called_with_bad_pointer(void);
-
-static inline
-unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long ret, flags;
-
-	switch (size) {
-	case 1:
-#ifdef __xchg_u8
-		return __xchg_u8(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u8 *)ptr;
-		*(volatile u8 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u8 */
-
-	case 2:
-#ifdef __xchg_u16
-		return __xchg_u16(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u16 *)ptr;
-		*(volatile u16 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u16 */
-
-	case 4:
-#ifdef __xchg_u32
-		return __xchg_u32(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u32 *)ptr;
-		*(volatile u32 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u32 */
-
-#ifdef CONFIG_64BIT
-	case 8:
-#ifdef __xchg_u64
-		return __xchg_u64(x, ptr);
-#else
-		local_irq_save(flags);
-		ret = *(volatile u64 *)ptr;
-		*(volatile u64 *)ptr = x;
-		local_irq_restore(flags);
-		return ret;
-#endif /* __xchg_u64 */
-#endif /* CONFIG_64BIT */
-
-	default:
-		__xchg_called_with_bad_pointer();
-		return x;
-	}
-}
-
-#define xchg(ptr, x) \
-	((__typeof__(*(ptr))) __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_GENERIC_SYSTEM_H */
diff --git a/include/asm-generic/tlbflush.h b/include/asm-generic/tlbflush.h
index c7af037024c7..d6d0a88430fe 100644
--- a/include/asm-generic/tlbflush.h
+++ b/include/asm-generic/tlbflush.h
@@ -9,6 +9,8 @@
 #error need to implement an architecture specific asm/tlbflush.h
 #endif
 
+#include <linux/bug.h>
+
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 	BUG();
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 2292d1af9d70..991ef01cd77e 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -218,7 +218,7 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
 
 /* fs/sendfile.c */
 #define __NR3264_sendfile 71
-__SC_3264(__NR3264_sendfile, sys_sendfile64, sys_sendfile)
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
 
 /* fs/select.c */
 #define __NR_pselect6 72
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index b5e2e4c6b017..8aeadf6b553a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -167,6 +167,7 @@
 	CPU_KEEP(exit.data)						\
 	MEM_KEEP(init.data)						\
 	MEM_KEEP(exit.data)						\
+	*(.data.unlikely)						\
 	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
@@ -615,30 +616,23 @@
 		*(.init.setup)						\
 		VMLINUX_SYMBOL(__setup_end) = .;
 
-#define INITCALLS							\
-	*(.initcallearly.init)						\
-	VMLINUX_SYMBOL(__early_initcall_end) = .;			\
-  	*(.initcall0.init)						\
-  	*(.initcall0s.init)						\
-  	*(.initcall1.init)						\
-  	*(.initcall1s.init)						\
-  	*(.initcall2.init)						\
-  	*(.initcall2s.init)						\
-  	*(.initcall3.init)						\
-  	*(.initcall3s.init)						\
-  	*(.initcall4.init)						\
-  	*(.initcall4s.init)						\
-  	*(.initcall5.init)						\
-  	*(.initcall5s.init)						\
-	*(.initcallrootfs.init)						\
-  	*(.initcall6.init)						\
-  	*(.initcall6s.init)						\
-  	*(.initcall7.init)						\
-  	*(.initcall7s.init)
+#define INIT_CALLS_LEVEL(level)						\
+		VMLINUX_SYMBOL(__initcall##level##_start) = .;		\
+		*(.initcall##level##.init)				\
+		*(.initcall##level##s.init)				\
 
 #define INIT_CALLS							\
 		VMLINUX_SYMBOL(__initcall_start) = .;			\
-		INITCALLS						\
+		*(.initcallearly.init)					\
+		INIT_CALLS_LEVEL(0)					\
+		INIT_CALLS_LEVEL(1)					\
+		INIT_CALLS_LEVEL(2)					\
+		INIT_CALLS_LEVEL(3)					\
+		INIT_CALLS_LEVEL(4)					\
+		INIT_CALLS_LEVEL(5)					\
+		INIT_CALLS_LEVEL(rootfs)				\
+		INIT_CALLS_LEVEL(6)					\
+		INIT_CALLS_LEVEL(7)					\
 		VMLINUX_SYMBOL(__initcall_end) = .;
 
 #define CON_INITCALL							\