19 files changed, 268 insertions, 102 deletions

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 53f91b1ae53a..2c85a0f647b7 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -8,6 +8,7 @@ header-y += int-ll64.h
 header-y += ioctl.h
 header-y += ioctls.h
 header-y += ipcbuf.h
+header-y += kvm_para.h
 header-y += mman-common.h
 header-y += mman.h
 header-y += msgbuf.h
diff --git a/include/asm-generic/bitsperlong.h b/include/asm-generic/bitsperlong.h
index 4ae54e07de83..a7b0914348fd 100644
--- a/include/asm-generic/bitsperlong.h
+++ b/include/asm-generic/bitsperlong.h
@@ -28,5 +28,9 @@
 #error Inconsistent word size. Check asm/bitsperlong.h
 #endif
 
+#ifndef BITS_PER_LONG_LONG
+#define BITS_PER_LONG_LONG 64
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_GENERIC_BITS_PER_LONG */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 2520a6e241dc..7d10f962aa13 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -3,10 +3,18 @@
 
 #include <linux/compiler.h>
 
+#ifdef CONFIG_GENERIC_BUG
+#define BUGFLAG_WARNING		(1 << 0)
+#define BUGFLAG_TAINT(taint)	(BUGFLAG_WARNING | ((taint) << 8))
+#define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
+#endif
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+
 #ifdef CONFIG_BUG
 
 #ifdef CONFIG_GENERIC_BUG
-#ifndef __ASSEMBLY__
 struct bug_entry {
 #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
 	unsigned long	bug_addr;
@@ -23,12 +31,6 @@ struct bug_entry {
 #endif
 	unsigned short	flags;
 };
-#endif		/* __ASSEMBLY__ */
-
-#define BUGFLAG_WARNING		(1 << 0)
-#define BUGFLAG_TAINT(taint)	(BUGFLAG_WARNING | ((taint) << 8))
-#define BUG_GET_TAINT(bug)	((bug)->flags >> 8)
-
 #endif	/* CONFIG_GENERIC_BUG */
 
 /*
@@ -60,7 +62,6 @@ struct bug_entry {
  * to provide better diagnostics.
  */
 #ifndef __WARN_TAINT
-#ifndef __ASSEMBLY__
 extern __printf(3, 4)
 void warn_slowpath_fmt(const char *file, const int line,
 		       const char *fmt, ...);
@@ -69,7 +70,6 @@ void warn_slowpath_fmt_taint(const char *file, const int line, unsigned taint,
 			     const char *fmt, ...);
 extern void warn_slowpath_null(const char *file, const int line);
 #define WANT_WARN_ON_SLOWPATH
-#endif
 #define __WARN()		warn_slowpath_null(__FILE__, __LINE__)
 #define __WARN_printf(arg...)	warn_slowpath_fmt(__FILE__, __LINE__, arg)
 #define __WARN_printf_taint(taint, arg...)				\
@@ -202,4 +202,6 @@ extern void warn_slowpath_null(const char *file, const int line);
 # define WARN_ON_SMP(x)			({0;})
 #endif
 
+#endif /* __ASSEMBLY__ */
+
 #endif
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
index 85a3ffaa0242..2be8a2dbc868 100644
--- a/include/asm-generic/dma-coherent.h
+++ b/include/asm-generic/dma-coherent.h
@@ -3,13 +3,15 @@
 
 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 /*
- * These two functions are only for dma allocator.
+ * These three functions are only for dma allocator.
  * Don't use them in device drivers.
  */
 int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 				       dma_addr_t *dma_handle, void **ret);
 int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
 
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+			    void *cpu_addr, size_t size, int *ret);
 /*
  * Standard interface
  */
@@ -27,6 +29,7 @@ dma_mark_declared_memory_occupied(struct device *dev,
 #else
 #define dma_alloc_from_coherent(dev, size, handle, ret) (0)
 #define dma_release_from_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
 #endif
 
 #endif
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
new file mode 100644
index 000000000000..294b1e755ab2
--- /dev/null
+++ b/include/asm-generic/dma-contiguous.h
@@ -0,0 +1,28 @@
+#ifndef ASM_DMA_CONTIGUOUS_H
+#define ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_CMA
+
+#include <linux/device.h>
+#include <linux/dma-contiguous.h>
+
+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
+{
+	if (dev)
+		dev->cma_area = cma;
+	if (!dev && !dma_contiguous_default_area)
+		dma_contiguous_default_area = cma;
+}
+
+#endif
+#endif
+
+#endif
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 2e248d8924dc..de8bf89940f8 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -176,4 +176,59 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL)
 #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL)
 
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+/**
+ * dma_mmap_attrs - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
+ * @handle: device-view address returned from dma_alloc_attrs
+ * @size: size of memory originally requested in dma_alloc_attrs
+ * @attrs: attributes of mapping properties requested in dma_alloc_attrs
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
+ * into user space.  The coherent DMA buffer must not be freed by the
+ * driver until the user space mapping has been released.
+ */
+static inline int
+dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
+	       dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->mmap)
+		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
+
+static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
+		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	DEFINE_DMA_ATTRS(attrs);
+	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
+	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
+}
+
+int
+dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+static inline int
+dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
+		      dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->get_sgtable)
+		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
+					attrs);
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size);
+}
+
+#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL)
+
 #endif
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index 9e5b0356e2bb..a48937d4a5ea 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -120,6 +120,10 @@
 #define F_GETOWN_EX	16
 #endif
 
+#ifndef F_GETOWNER_UIDS
+#define F_GETOWNER_UIDS	17
+#endif
+
 #define F_OWNER_TID	0
 #define F_OWNER_PID	1
 #define F_OWNER_PGRP	2
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 5f52690c3c8f..365ea09ed3b0 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(const void *data,
+extern struct gpio_chip *gpiochip_find(void *data,
 					int (*match)(struct gpio_chip *chip,
-						     const void *data));
+						     void *data));
 
 
 /* Always use the library code for GPIO management calls,
@@ -179,6 +179,8 @@ extern void gpio_free_array(const struct gpio *array, size_t num);
 
 /* bindings for managed devices that want to request gpios */
 int devm_gpio_request(struct device *dev, unsigned gpio, const char *label);
+int devm_gpio_request_one(struct device *dev, unsigned gpio,
+			  unsigned long flags, const char *label);
 void devm_gpio_free(struct device *dev, unsigned int gpio);
 
 #ifdef CONFIG_GPIO_SYSFS
diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h
index 0232ccb76f2b..90f99c74dd38 100644
--- a/include/asm-generic/kmap_types.h
+++ b/include/asm-generic/kmap_types.h
@@ -2,39 +2,9 @@
 #define _ASM_GENERIC_KMAP_TYPES_H
 
 #ifdef __WITH_KM_FENCE
-# define KMAP_D(n) __KM_FENCE_##n ,
+# define KM_TYPE_NR 41
 #else
-# define KMAP_D(n)
+# define KM_TYPE_NR 20
 #endif
 
-enum km_type {
-KMAP_D(0)	KM_BOUNCE_READ,
-KMAP_D(1)	KM_SKB_SUNRPC_DATA,
-KMAP_D(2)	KM_SKB_DATA_SOFTIRQ,
-KMAP_D(3)	KM_USER0,
-KMAP_D(4)	KM_USER1,
-KMAP_D(5)	KM_BIO_SRC_IRQ,
-KMAP_D(6)	KM_BIO_DST_IRQ,
-KMAP_D(7)	KM_PTE0,
-KMAP_D(8)	KM_PTE1,
-KMAP_D(9)	KM_IRQ0,
-KMAP_D(10)	KM_IRQ1,
-KMAP_D(11)	KM_SOFTIRQ0,
-KMAP_D(12)	KM_SOFTIRQ1,
-KMAP_D(13)	KM_SYNC_ICACHE,
-KMAP_D(14)	KM_SYNC_DCACHE,
-/* UML specific, for copy_*_user - used in do_op_one_page */
-KMAP_D(15)	KM_UML_USERCOPY,
-KMAP_D(16)	KM_IRQ_PTE,
-KMAP_D(17)	KM_NMI,
-KMAP_D(18)	KM_NMI_PTE,
-KMAP_D(19)	KM_KDB,
-/*
- * Remember to update debug_kmap_atomic() when adding new kmap types!
- */
-KMAP_D(20)	KM_TYPE_NR
-};
-
-#undef KMAP_D
-
 #endif
diff --git a/include/asm-generic/kvm_para.h b/include/asm-generic/kvm_para.h
new file mode 100644
index 000000000000..5cba37f9eae1
--- /dev/null
+++ b/include/asm-generic/kvm_para.h
@@ -0,0 +1,22 @@
+#ifndef _ASM_GENERIC_KVM_PARA_H
+#define _ASM_GENERIC_KVM_PARA_H
+
+#ifdef __KERNEL__
+
+/*
+ * This function is used by architectures that support kvm to avoid issuing
+ * false soft lockup messages.
+ */
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+	return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
+#endif	/* _KERNEL__ */
+
+#endif
diff --git a/include/asm-generic/pci-bridge.h b/include/asm-generic/pci-bridge.h
index a5b5d5a89a4f..20db2e5a0a69 100644
--- a/include/asm-generic/pci-bridge.h
+++ b/include/asm-generic/pci-bridge.h
@@ -30,6 +30,12 @@ enum {
 	PCI_ENABLE_PROC_DOMAINS	= 0x00000010,
 	/* ... except for domain 0 */
 	PCI_COMPAT_DOMAIN_0	= 0x00000020,
+
+	/* PCIe downstream ports are bridges that normally lead to only a
+	 * device 0, but if this is set, we scan all possible devices, not
+	 * just device 0.
+	 */
+	PCI_SCAN_ALL_PCIE_DEVS	= 0x00000040,
 };
 
 #ifdef CONFIG_PCI
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 125c54e98517..ff4947b7a976 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -158,9 +158,8 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-extern pmd_t pmdp_splitting_flush(struct vm_area_struct *vma,
-				  unsigned long address,
-				  pmd_t *pmdp);
+extern void pmdp_splitting_flush(struct vm_area_struct *vma,
+				 unsigned long address, pmd_t *pmdp);
 #endif
 
 #ifndef __HAVE_ARCH_PTE_SAME
@@ -446,6 +445,18 @@ static inline int pmd_write(pmd_t pmd)
 #endif /* __HAVE_ARCH_PMD_WRITE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifndef pmd_read_atomic
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	/*
+	 * Depend on compiler for an atomic pmd read. NOTE: this is
+	 * only going to work, if the pmdval_t isn't larger than
+	 * an unsigned long.
+	 */
+	return *pmdp;
+}
+#endif
+
 /*
  * 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
@@ -459,14 +470,30 @@ static inline int pmd_write(pmd_t pmd)
  * 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.
+ *
+ * For 32bit kernels with a 64bit large pmd_t this automatically takes
+ * care of reading the pmd atomically to avoid SMP race conditions
+ * against pmd_populate() when the mmap_sem is hold for reading by the
+ * caller (a special atomic read not done by "gcc" as in the generic
+ * version above, is also needed when THP is disabled because the page
+ * fault can populate the pmd from under us).
  */
 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;
+	pmd_t pmdval = pmd_read_atomic(pmd);
 	/*
 	 * The barrier will stabilize the pmdval in a register or on
 	 * the stack so that it will stop changing under the code.
+	 *
+	 * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
+	 * pmd_read_atomic is allowed to return a not atomic pmdval
+	 * (for example pointing to an hugepage that has never been
+	 * mapped in the pmd). The below checks will only care about
+	 * the low part of the pmd with 32bit PAE x86 anyway, with the
+	 * exception of pmd_none(). So the important thing is that if
+	 * the low part of the pmd is found null, the high part will
+	 * be also null or the pmd_none() check below would be
+	 * confused.
 	 */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	barrier();
diff --git a/include/asm-generic/posix_types.h b/include/asm-generic/posix_types.h
index 91d44bd4dde3..fe74fccf18db 100644
--- a/include/asm-generic/posix_types.h
+++ b/include/asm-generic/posix_types.h
@@ -23,10 +23,6 @@ typedef __kernel_ulong_t __kernel_ino_t;
 typedef unsigned int	__kernel_mode_t;
 #endif
 
-#ifndef __kernel_nlink_t
-typedef __kernel_ulong_t __kernel_nlink_t;
-#endif
-
 #ifndef __kernel_pid_t
 typedef int		__kernel_pid_t;
 #endif
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 5e5e3865f1ed..8ed67779fc09 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -98,9 +98,18 @@ typedef struct siginfo {
 			__ARCH_SI_BAND_T _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
 			int _fd;
 		} _sigpoll;
+
+		/* SIGSYS */
+		struct {
+			void __user *_call_addr; /* calling user insn */
+			int _syscall;	/* triggering system call number */
+			unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
+		} _sigsys;
 	} _sifields;
 } __ARCH_SI_ATTRIBUTES siginfo_t;
 
+/* If the arch shares siginfo, then it has SIGSYS. */
+#define __ARCH_SIGSYS
 #endif
 
 /*
@@ -124,6 +133,11 @@ typedef struct siginfo {
 #define si_addr_lsb	_sifields._sigfault._addr_lsb
 #define si_band		_sifields._sigpoll._band
 #define si_fd		_sifields._sigpoll._fd
+#ifdef __ARCH_SIGSYS
+#define si_call_addr	_sifields._sigsys._call_addr
+#define si_syscall	_sifields._sigsys._syscall
+#define si_arch		_sifields._sigsys._arch
+#endif
 
 #ifdef __KERNEL__
 #define __SI_MASK	0xffff0000u
@@ -134,6 +148,7 @@ typedef struct siginfo {
 #define __SI_CHLD	(4 << 16)
 #define __SI_RT		(5 << 16)
 #define __SI_MESGQ	(6 << 16)
+#define __SI_SYS	(7 << 16)
 #define __SI_CODE(T,N)	((T) | ((N) & 0xffff))
 #else
 #define __SI_KILL	0
@@ -143,6 +158,7 @@ typedef struct siginfo {
 #define __SI_CHLD	0
 #define __SI_RT		0
 #define __SI_MESGQ	0
+#define __SI_SYS	0
 #define __SI_CODE(T,N)	(N)
 #endif
 
@@ -240,6 +256,12 @@ typedef struct siginfo {
 #define NSIGPOLL	6
 
 /*
+ * SIGSYS si_codes
+ */
+#define SYS_SECCOMP		(__SI_SYS|1)	/* seccomp triggered */
+#define NSIGSYS	1
+
+/*
  * sigevent definitions
  * 
  * It seems likely that SIGEV_THREAD will have to be handled from 
diff --git a/include/asm-generic/sizes.h b/include/asm-generic/sizes.h
index ea5d4ef81061..1dcfad9629ef 100644
--- a/include/asm-generic/sizes.h
+++ b/include/asm-generic/sizes.h
@@ -1,47 +1,2 @@
-/*
- * linux/include/asm-generic/sizes.h
- *
- * 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_GENERIC_SIZES_H__
-#define __ASM_GENERIC_SIZES_H__
-
-#define SZ_1				0x00000001
-#define SZ_2				0x00000002
-#define SZ_4				0x00000004
-#define SZ_8				0x00000008
-#define SZ_16				0x00000010
-#define SZ_32				0x00000020
-#define SZ_64				0x00000040
-#define SZ_128				0x00000080
-#define SZ_256				0x00000100
-#define SZ_512				0x00000200
-
-#define SZ_1K				0x00000400
-#define SZ_2K				0x00000800
-#define SZ_4K				0x00001000
-#define SZ_8K				0x00002000
-#define SZ_16K				0x00004000
-#define SZ_32K				0x00008000
-#define SZ_64K				0x00010000
-#define SZ_128K				0x00020000
-#define SZ_256K				0x00040000
-#define SZ_512K				0x00080000
-
-#define SZ_1M				0x00100000
-#define SZ_2M				0x00200000
-#define SZ_4M				0x00400000
-#define SZ_8M				0x00800000
-#define SZ_16M				0x01000000
-#define SZ_32M				0x02000000
-#define SZ_64M				0x04000000
-#define SZ_128M				0x08000000
-#define SZ_256M				0x10000000
-#define SZ_512M				0x20000000
-
-#define SZ_1G				0x40000000
-#define SZ_2G				0x80000000
-
-#endif /* __ASM_GENERIC_SIZES_H__ */
+/* This is a placeholder, to be removed over time */
+#include <linux/sizes.h>
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 5c122ae6bfa6..5b09392db673 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -142,4 +142,18 @@ void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
 			   unsigned int i, unsigned int n,
 			   const unsigned long *args);
 
+/**
+ * syscall_get_arch - return the AUDIT_ARCH for the current system call
+ * @task:	task of interest, must be in system call entry tracing
+ * @regs:	task_pt_regs() of @task
+ *
+ * Returns the AUDIT_ARCH_* based on the system call convention in use.
+ *
+ * It's only valid to call this when @task is stopped on entry to a system
+ * call, due to %TIF_SYSCALL_TRACE, %TIF_SYSCALL_AUDIT, or %TIF_SECCOMP.
+ *
+ * Architectures which permit CONFIG_HAVE_ARCH_SECCOMP_FILTER must
+ * provide an implementation of this.
+ */
+int syscall_get_arch(struct task_struct *task, struct pt_regs *regs);
 #endif	/* _ASM_SYSCALL_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index f96a5b58a975..ed6642ad03e0 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -86,6 +86,8 @@ struct mmu_gather {
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
+	unsigned long		start;
+	unsigned long		end;
 	unsigned int		need_flush : 1,	/* Did free PTEs */
 				fast_mode  : 1; /* No batching   */
 
@@ -113,7 +115,8 @@ static inline int tlb_fast_mode(struct mmu_gather *tlb)
 
 void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm);
 void tlb_flush_mmu(struct mmu_gather *tlb);
-void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end);
+void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start,
+							unsigned long end);
 int __tlb_remove_page(struct mmu_gather *tlb, struct page *page);
 
 /* tlb_remove_page
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8aeadf6b553a..4e2e1cc505ab 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -486,8 +486,8 @@
 	CPU_DISCARD(init.data)						\
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
-	*(.init.rodata)							\
 	MCOUNT_REC()							\
+	*(.init.rodata)							\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
 	DEV_DISCARD(init.rodata)					\
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
new file mode 100644
index 000000000000..3f21f1b72e45
--- /dev/null
+++ b/include/asm-generic/word-at-a-time.h
@@ -0,0 +1,52 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This says "generic", but it's actually big-endian only.
+ * Little-endian can use more efficient versions of these
+ * interfaces, see for example
+ *	 arch/x86/include/asm/word-at-a-time.h
+ * for those.
+ */
+
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long high_bits, low_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0xfe) + 1, REPEAT_BYTE(0x7f) }
+
+/* Bit set in the bytes that have a zero */
+static inline long prep_zero_mask(unsigned long val, unsigned long rhs, const struct word_at_a_time *c)
+{
+	unsigned long mask = (val & c->low_bits) + c->low_bits;
+	return ~(mask | rhs);
+}
+
+#define create_zero_mask(mask) (mask)
+
+static inline long find_zero(unsigned long mask)
+{
+	long byte = 0;
+#ifdef CONFIG_64BIT
+	if (mask >> 32)
+		mask >>= 32;
+	else
+		byte = 4;
+#endif
+	if (mask >> 16)
+		mask >>= 16;
+	else
+		byte += 2;
+	return (mask >> 8) ? byte : byte + 1;
+}
+
+static inline bool has_zero(unsigned long val, unsigned long *data, const struct word_at_a_time *c)
+{
+	unsigned long rhs = val | c->low_bits;
+	*data = rhs;
+	return (val + c->high_bits) & ~rhs;
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */