20 files changed, 539 insertions, 178 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 1ced6413ea03..33bd2de3bc1e 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -136,12 +136,6 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
   int c, old;
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index c084767c88bc..59811df58c5b 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -38,12 +38,15 @@ extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
 	csum_partial_copy((src), (dst), (len), (sum))
 #endif
 
+#ifndef ip_fast_csum
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
  * which always checksum on 4 octet boundaries.
  */
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
+#endif
 
+#ifndef csum_fold
 /*
  * Fold a partial checksum
  */
@@ -54,6 +57,7 @@ static inline __sum16 csum_fold(__wsum csum)
 	sum = (sum & 0xffff) + (sum >> 16);
 	return (__force __sum16)~sum;
 }
+#endif
 
 #ifndef csum_tcpudp_nofold
 /*
diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
index 2533fddd34a6..d8d4c898c1bb 100644
--- a/include/asm-generic/cmpxchg-local.h
+++ b/include/asm-generic/cmpxchg-local.h
@@ -21,7 +21,7 @@ static inline unsigned long __cmpxchg_local_generic(volatile void *ptr,
 	if (size == 8 && sizeof(unsigned long) != 8)
 		wrong_size_cmpxchg(ptr);
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	switch (size) {
 	case 1: prev = *(u8 *)ptr;
 		if (prev == old)
@@ -42,7 +42,7 @@ static inline unsigned long __cmpxchg_local_generic(volatile void *ptr,
 	default:
 		wrong_size_cmpxchg(ptr);
 	}
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 	return prev;
 }
 
@@ -55,11 +55,11 @@ static inline u64 __cmpxchg64_local_generic(volatile void *ptr,
 	u64 prev;
 	unsigned long flags;
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	prev = *(u64 *)ptr;
 	if (prev == old)
 		*(u64 *)ptr = new;
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 	return prev;
 }
 
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 14883026015d..811fb1e9b061 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -92,6 +92,16 @@ unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
  */
 #include <asm-generic/cmpxchg-local.h>
 
+#ifndef cmpxchg_local
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#endif
+
+#ifndef cmpxchg64_local
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
 #define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
 #define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
 
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 9a62937c56ca..51969436b8b8 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -4,66 +4,12 @@
 #include <linux/time.h>
 #include <linux/jiffies.h>
 
-typedef unsigned long __nocast cputime_t;
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
-#define cputime_to_scaled(__ct)		(__ct)
-#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
-
-typedef u64 __nocast cputime64_t;
-
-#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
-#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
-
-#define nsecs_to_cputime64(__ct)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64(__ct))
-
-
-/*
- * Convert cputime to microseconds and back.
- */
-#define cputime_to_usecs(__ct)		\
-	jiffies_to_usecs(cputime_to_jiffies(__ct))
-#define usecs_to_cputime(__usec)	\
-	jiffies_to_cputime(usecs_to_jiffies(__usec))
-#define usecs_to_cputime64(__usec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
-
-/*
- * Convert cputime to seconds and back.
- */
-#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
-#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
-
-/*
- * Convert cputime to timespec and back.
- */
-#define timespec_to_cputime(__val)	\
-	jiffies_to_cputime(timespec_to_jiffies(__val))
-#define cputime_to_timespec(__ct,__val)	\
-	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to timeval and back.
- */
-#define timeval_to_cputime(__val)	\
-	jiffies_to_cputime(timeval_to_jiffies(__val))
-#define cputime_to_timeval(__ct,__val)	\
-	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to clock and back.
- */
-#define cputime_to_clock_t(__ct)	\
-	jiffies_to_clock_t(cputime_to_jiffies(__ct))
-#define clock_t_to_cputime(__x)		\
-	jiffies_to_cputime(clock_t_to_jiffies(__x))
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+# include <asm-generic/cputime_jiffies.h>
+#endif
 
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+# include <asm-generic/cputime_nsecs.h>
+#endif
 
 #endif
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
new file mode 100644
index 000000000000..272ecba9f588
--- /dev/null
+++ b/include/asm-generic/cputime_jiffies.h
@@ -0,0 +1,72 @@
+#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
+#define _ASM_GENERIC_CPUTIME_JIFFIES_H
+
+typedef unsigned long __nocast cputime_t;
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
+
+typedef u64 __nocast cputime64_t;
+
+#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
+#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
+
+
+/*
+ * Convert nanoseconds to cputime
+ */
+#define nsecs_to_cputime64(__nsec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
+#define nsecs_to_cputime(__nsec)	\
+	jiffies_to_cputime(nsecs_to_jiffies(__nsec))
+
+
+/*
+ * Convert cputime to microseconds and back.
+ */
+#define cputime_to_usecs(__ct)		\
+	jiffies_to_usecs(cputime_to_jiffies(__ct))
+#define usecs_to_cputime(__usec)	\
+	jiffies_to_cputime(usecs_to_jiffies(__usec))
+#define usecs_to_cputime64(__usec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
+
+/*
+ * Convert cputime to seconds and back.
+ */
+#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
+#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
+
+/*
+ * Convert cputime to timespec and back.
+ */
+#define timespec_to_cputime(__val)	\
+	jiffies_to_cputime(timespec_to_jiffies(__val))
+#define cputime_to_timespec(__ct,__val)	\
+	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to timeval and back.
+ */
+#define timeval_to_cputime(__val)	\
+	jiffies_to_cputime(timeval_to_jiffies(__val))
+#define cputime_to_timeval(__ct,__val)	\
+	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to clock and back.
+ */
+#define cputime_to_clock_t(__ct)	\
+	jiffies_to_clock_t(cputime_to_jiffies(__ct))
+#define clock_t_to_cputime(__x)		\
+	jiffies_to_cputime(clock_t_to_jiffies(__x))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
+
+#endif
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
new file mode 100644
index 000000000000..a8ece9a33aef
--- /dev/null
+++ b/include/asm-generic/cputime_nsecs.h
@@ -0,0 +1,104 @@
+/*
+ * Definitions for measuring cputime in nsecs resolution.
+ *
+ * Based on <arch/ia64/include/asm/cputime.h>
+ *
+ * Copyright (C) 2007 FUJITSU LIMITED
+ * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
+#define _ASM_GENERIC_CPUTIME_NSECS_H
+
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+
+/*
+ * Convert cputime <-> jiffies (HZ)
+ */
+#define cputime_to_jiffies(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__jif)	\
+	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies64_to_cputime64(__jif)	\
+	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
+
+
+/*
+ * Convert cputime <-> nanoseconds
+ */
+#define nsecs_to_cputime(__nsecs)	((__force u64)(__nsecs))
+
+
+/*
+ * Convert cputime <-> microseconds
+ */
+#define cputime_to_usecs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_USEC)
+#define usecs_to_cputime(__usecs)	\
+	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs)	\
+	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
+
+/*
+ * Convert cputime <-> seconds
+ */
+#define cputime_to_secs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_SEC)
+#define secs_to_cputime(__secs)		\
+	(__force cputime_t)((__secs) * NSEC_PER_SEC)
+
+/*
+ * Convert cputime <-> timespec (nsec)
+ */
+static inline cputime_t timespec_to_cputime(const struct timespec *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
+{
+	val->tv_sec  = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_nsec = (__force u64) ct % NSEC_PER_SEC;
+}
+
+/*
+ * Convert cputime <-> timeval (msec)
+ */
+static inline cputime_t timeval_to_cputime(const struct timeval *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
+{
+	val->tv_sec = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC;
+}
+
+/*
+ * Convert cputime <-> clock (USER_HZ)
+ */
+#define cputime_to_clock_t(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)		\
+	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	cputime_to_clock_t((__force cputime_t)__ct)
+
+#endif
diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
index ccf7b4f34a3c..6c32af918c2f 100644
--- a/include/asm-generic/dma-mapping-broken.h
+++ b/include/asm-generic/dma-mapping-broken.h
@@ -16,6 +16,22 @@ extern void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
 		    dma_addr_t dma_handle);
 
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flag,
+				    struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	return dma_alloc_coherent(dev, size, dma_handle, flag);
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *cpu_addr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
+{
+	/* attrs is not supported and ignored */
+	dma_free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index a9432fc6b8ba..bde646995d10 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/of.h>
+#include <linux/pinctrl/pinctrl.h>
 
 #ifdef CONFIG_GPIOLIB
 
@@ -46,16 +47,20 @@ struct gpio;
 struct seq_file;
 struct module;
 struct device_node;
+struct gpio_desc;
 
 /**
  * struct gpio_chip - abstract a GPIO controller
  * @label: for diagnostics
  * @dev: optional device providing the GPIOs
  * @owner: helps prevent removal of modules exporting active GPIOs
+ * @list: links gpio_chips together for traversal
  * @request: optional hook for chip-specific activation, such as
  *	enabling module power and clock; may sleep
  * @free: optional hook for chip-specific deactivation, such as
  *	disabling module power and clock; may sleep
+ * @get_direction: returns direction for signal "offset", 0=out, 1=in,
+ *	(same as GPIOF_DIR_XXX), or negative error
  * @direction_input: configures signal "offset" as input, or returns error
  * @get: returns value for signal "offset"; for output signals this
  *	returns either the value actually sensed, or zero
@@ -72,6 +77,7 @@ struct device_node;
  *	negative during registration, requests dynamic ID allocation.
  * @ngpio: the number of GPIOs handled by this controller; the last GPIO
  *	handled is (base + ngpio - 1).
+ * @desc: array of ngpio descriptors. Private.
  * @can_sleep: flag must be set iff get()/set() methods sleep, as they
  *	must while accessing GPIO expander chips over I2C or SPI
  * @names: if set, must be an array of strings to use as alternative
@@ -95,12 +101,14 @@ struct gpio_chip {
 	const char		*label;
 	struct device		*dev;
 	struct module		*owner;
+	struct list_head        list;
 
 	int			(*request)(struct gpio_chip *chip,
 						unsigned offset);
 	void			(*free)(struct gpio_chip *chip,
 						unsigned offset);
-
+	int			(*get_direction)(struct gpio_chip *chip,
+						unsigned offset);
 	int			(*direction_input)(struct gpio_chip *chip,
 						unsigned offset);
 	int			(*get)(struct gpio_chip *chip,
@@ -120,6 +128,7 @@ struct gpio_chip {
 						struct gpio_chip *chip);
 	int			base;
 	u16			ngpio;
+	struct gpio_desc	*desc;
 	const char		*const *names;
 	unsigned		can_sleep:1;
 	unsigned		exported:1;
@@ -134,12 +143,20 @@ struct gpio_chip {
 	int (*of_xlate)(struct gpio_chip *gc,
 		        const struct of_phandle_args *gpiospec, u32 *flags);
 #endif
+#ifdef CONFIG_PINCTRL
+	/*
+	 * If CONFIG_PINCTRL is enabled, then gpio controllers can optionally
+	 * describe the actual pin range which they serve in an SoC. This
+	 * information would be used by pinctrl subsystem to configure
+	 * corresponding pins for gpio usage.
+	 */
+	struct list_head pin_ranges;
+#endif
 };
 
 extern const char *gpiochip_is_requested(struct gpio_chip *chip,
 			unsigned offset);
 extern struct gpio_chip *gpio_to_chip(unsigned gpio);
-extern int __must_check gpiochip_reserve(int start, int ngpio);
 
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
@@ -179,12 +196,6 @@ extern int gpio_request_one(unsigned gpio, unsigned long flags, const char *labe
 extern int gpio_request_array(const struct gpio *array, size_t num);
 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
 
 /*
@@ -199,6 +210,43 @@ extern void gpio_unexport(unsigned gpio);
 
 #endif	/* CONFIG_GPIO_SYSFS */
 
+#ifdef CONFIG_PINCTRL
+
+/**
+ * struct gpio_pin_range - pin range controlled by a gpio chip
+ * @head: list for maintaining set of pin ranges, used internally
+ * @pctldev: pinctrl device which handles corresponding pins
+ * @range: actual range of pins controlled by a gpio controller
+ */
+
+struct gpio_pin_range {
+	struct list_head node;
+	struct pinctrl_dev *pctldev;
+	struct pinctrl_gpio_range range;
+};
+
+int gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
+			   unsigned int gpio_offset, unsigned int pin_offset,
+			   unsigned int npins);
+void gpiochip_remove_pin_ranges(struct gpio_chip *chip);
+
+#else
+
+static inline int
+gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
+		       unsigned int gpio_offset, unsigned int pin_offset,
+		       unsigned int npins)
+{
+	return 0;
+}
+
+static inline void
+gpiochip_remove_pin_ranges(struct gpio_chip *chip)
+{
+}
+
+#endif /* CONFIG_PINCTRL */
+
 #else	/* !CONFIG_GPIOLIB */
 
 static inline bool gpio_is_valid(int number)
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 448303bdb85f..ac9da00e9f2c 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -12,7 +12,6 @@
 #define __ASM_GENERIC_IO_H
 
 #include <asm/page.h> /* I/O is all done through memory accesses */
-#include <asm/cacheflush.h>
 #include <linux/types.h>
 
 #ifdef CONFIG_GENERIC_IOMAP
@@ -54,8 +53,18 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 #endif
 
 #define readb __raw_readb
-#define readw(addr) __le16_to_cpu(__raw_readw(addr))
-#define readl(addr) __le32_to_cpu(__raw_readl(addr))
+
+#define readw readw
+static inline u16 readw(const volatile void __iomem *addr)
+{
+	return __le16_to_cpu(__raw_readw(addr));
+}
+
+#define readl readl
+static inline u32 readl(const volatile void __iomem *addr)
+{
+	return __le32_to_cpu(__raw_readl(addr));
+}
 
 #ifndef __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
@@ -83,19 +92,29 @@ static inline void __raw_writel(u32 b, volatile void __iomem *addr)
 #define writel(b,addr) __raw_writel(__cpu_to_le32(b),addr)
 
 #ifdef CONFIG_64BIT
+#ifndef __raw_readq
 static inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	return *(const volatile u64 __force *) addr;
 }
-#define readq(addr) __le64_to_cpu(__raw_readq(addr))
+#endif
+
+#define readq readq
+static inline u64 readq(const volatile void __iomem *addr)
+{
+	return __le64_to_cpu(__raw_readq(addr));
+}
 
+#ifndef __raw_writeq
 static inline void __raw_writeq(u64 b, volatile void __iomem *addr)
 {
 	*(volatile u64 __force *) addr = b;
 }
-#define writeq(b,addr) __raw_writeq(__cpu_to_le64(b),addr)
 #endif
 
+#define writeq(b, addr) __raw_writeq(__cpu_to_le64(b), addr)
+#endif /* CONFIG_64BIT */
+
 #ifndef PCI_IOBASE
 #define PCI_IOBASE ((void __iomem *) 0)
 #endif
@@ -148,7 +167,7 @@ static inline void insb(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u8 *buf = buffer;
 		do {
-			u8 x = inb(addr);
+			u8 x = __raw_readb(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -161,7 +180,7 @@ static inline void insw(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u16 *buf = buffer;
 		do {
-			u16 x = inw(addr);
+			u16 x = __raw_readw(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -174,7 +193,7 @@ static inline void insl(unsigned long addr, void *buffer, int count)
 	if (count) {
 		u32 *buf = buffer;
 		do {
-			u32 x = inl(addr);
+			u32 x = __raw_readl(addr + PCI_IOBASE);
 			*buf++ = x;
 		} while (--count);
 	}
@@ -187,7 +206,7 @@ static inline void outsb(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u8 *buf = buffer;
 		do {
-			outb(*buf++, addr);
+			__raw_writeb(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
@@ -199,7 +218,7 @@ static inline void outsw(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u16 *buf = buffer;
 		do {
-			outw(*buf++, addr);
+			__raw_writew(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
@@ -211,54 +230,24 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 	if (count) {
 		const u32 *buf = buffer;
 		do {
-			outl(*buf++, addr);
+			__raw_writel(*buf++, addr + PCI_IOBASE);
 		} while (--count);
 	}
 }
 #endif
 
-static inline void readsl(const void __iomem *addr, void *buf, int len)
-{
-	insl(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void readsw(const void __iomem *addr, void *buf, int len)
-{
-	insw(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void readsb(const void __iomem *addr, void *buf, int len)
-{
-	insb(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesl(const void __iomem *addr, const void *buf, int len)
-{
-	outsl(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesw(const void __iomem *addr, const void *buf, int len)
-{
-	outsw(addr - PCI_IOBASE, buf, len);
-}
-
-static inline void writesb(const void __iomem *addr, const void *buf, int len)
-{
-	outsb(addr - PCI_IOBASE, buf, len);
-}
-
 #ifndef CONFIG_GENERIC_IOMAP
 #define ioread8(addr)		readb(addr)
 #define ioread16(addr)		readw(addr)
-#define ioread16be(addr)	be16_to_cpu(ioread16(addr))
+#define ioread16be(addr)	__be16_to_cpu(__raw_readw(addr))
 #define ioread32(addr)		readl(addr)
-#define ioread32be(addr)	be32_to_cpu(ioread32(addr))
+#define ioread32be(addr)	__be32_to_cpu(__raw_readl(addr))
 
 #define iowrite8(v, addr)	writeb((v), (addr))
 #define iowrite16(v, addr)	writew((v), (addr))
-#define iowrite16be(v, addr)	iowrite16(be16_to_cpu(v), (addr))
+#define iowrite16be(v, addr)	__raw_writew(__cpu_to_be16(v), addr)
 #define iowrite32(v, addr)	writel((v), (addr))
-#define iowrite32be(v, addr)	iowrite32(be32_to_cpu(v), (addr))
+#define iowrite32be(v, addr)	__raw_writel(__cpu_to_be32(v), addr)
 
 #define ioread8_rep(p, dst, count) \
 	insb((unsigned long) (p), (dst), (count))
@@ -286,15 +275,20 @@ static inline void writesb(const void __iomem *addr, const void *buf, int len)
 
 #ifndef CONFIG_GENERIC_IOMAP
 struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef pci_iounmap
 static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
 {
 }
+#endif
 #endif /* CONFIG_GENERIC_IOMAP */
 
 /*
  * Change virtual addresses to physical addresses and vv.
  * These are pretty trivial
  */
+#ifndef virt_to_phys
 static inline unsigned long virt_to_phys(volatile void *address)
 {
 	return __pa((unsigned long)address);
@@ -304,6 +298,7 @@ static inline void *phys_to_virt(unsigned long address)
 {
 	return __va(address);
 }
+#endif
 
 /*
  * Change "struct page" to physical address.
@@ -351,6 +346,7 @@ extern void ioport_unmap(void __iomem *p);
 #define xlate_dev_kmem_ptr(p)	p
 #define xlate_dev_mem_ptr(p)	__va(p)
 
+#ifdef CONFIG_VIRT_TO_BUS
 #ifndef virt_to_bus
 static inline unsigned long virt_to_bus(volatile void *address)
 {
@@ -362,10 +358,18 @@ static inline void *bus_to_virt(unsigned long address)
 	return (void *) address;
 }
 #endif
+#endif
 
+#ifndef memset_io
 #define memset_io(a, b, c)	memset(__io_virt(a), (b), (c))
+#endif
+
+#ifndef memcpy_fromio
 #define memcpy_fromio(a, b, c)	memcpy((a), __io_virt(b), (c))
+#endif
+#ifndef memcpy_toio
 #define memcpy_toio(a, b, c)	memcpy(__io_virt(a), (b), (c))
+#endif
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-generic/mmu.h b/include/asm-generic/mmu.h
index 4f4aa56d6b52..0ed3f1cfb854 100644
--- a/include/asm-generic/mmu.h
+++ b/include/asm-generic/mmu.h
@@ -7,8 +7,12 @@
  */
 #ifndef __ASSEMBLY__
 typedef struct {
-	struct vm_list_struct	*vmlist;
 	unsigned long		end_brk;
+
+#ifdef CONFIG_BINFMT_ELF_FDPIC
+	unsigned long		exec_fdpic_loadmap;
+	unsigned long		interp_fdpic_loadmap;
+#endif
 } mm_context_t;
 #endif
 
diff --git a/include/asm-generic/parport.h b/include/asm-generic/parport.h
index 40528cb977e8..2c9f9d4336ca 100644
--- a/include/asm-generic/parport.h
+++ b/include/asm-generic/parport.h
@@ -10,8 +10,8 @@
  * to devices on the PCI bus.
  */
 
-static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
+static int parport_pc_find_isa_ports(int autoirq, int autodma);
+static int parport_pc_find_nonpci_ports(int autoirq, int autodma)
 {
 #ifdef CONFIG_ISA
 	return parport_pc_find_isa_ports(autoirq, autodma);
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index b36ce40bd1c6..bfd87685fc1f 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -197,16 +197,6 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
-#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
-#define page_test_and_clear_dirty(pfn, mapped)	(0)
-#endif
-
-#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
-#define pte_maybe_dirty(pte)		pte_dirty(pte)
-#else
-#define pte_maybe_dirty(pte)		(1)
-#endif
-
 #ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
 #define page_test_and_clear_young(pfn) (0)
 #endif
@@ -219,6 +209,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef pte_accessible
+# define pte_accessible(pte)		((void)(pte),1)
+#endif
+
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
@@ -449,6 +443,30 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
 #endif
 
+#ifdef __HAVE_COLOR_ZERO_PAGE
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	return pfn == zero_pfn;
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	extern unsigned long zero_pfn;
+	return zero_pfn;
+}
+#endif
+
 #ifdef CONFIG_MMU
 
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
@@ -554,6 +572,112 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
+ * same bit too). It's set only when _PAGE_PRESET is not set and it's
+ * never set if _PAGE_PRESENT is set.
+ *
+ * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
+ * fault triggers on those regions if pte/pmd_numa returns true
+ * (because _PAGE_PRESENT is not set).
+ */
+#ifndef pte_numa
+static inline int pte_numa(pte_t pte)
+{
+	return (pte_flags(pte) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+#ifndef pmd_numa
+static inline int pmd_numa(pmd_t pmd)
+{
+	return (pmd_flags(pmd) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+/*
+ * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
+ * because they're called by the NUMA hinting minor page fault. If we
+ * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
+ * would be forced to set it later while filling the TLB after we
+ * return to userland. That would trigger a second write to memory
+ * that we optimize away by setting _PAGE_ACCESSED here.
+ */
+#ifndef pte_mknonnuma
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	pte = pte_clear_flags(pte, _PAGE_NUMA);
+	return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pmd_mknonnuma
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
+	return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pte_mknuma
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	pte = pte_set_flags(pte, _PAGE_NUMA);
+	return pte_clear_flags(pte, _PAGE_PRESENT);
+}
+#endif
+
+#ifndef pmd_mknuma
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	pmd = pmd_set_flags(pmd, _PAGE_NUMA);
+	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+#endif
+#else
+extern int pte_numa(pte_t pte);
+extern int pmd_numa(pmd_t pmd);
+extern pte_t pte_mknonnuma(pte_t pte);
+extern pmd_t pmd_mknonnuma(pmd_t pmd);
+extern pte_t pte_mknuma(pte_t pte);
+extern pmd_t pmd_mknuma(pmd_t pmd);
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+#else
+static inline int pmd_numa(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pte_numa(pte_t pte)
+{
+	return 0;
+}
+
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/include/asm-generic/signal.h b/include/asm-generic/signal.h
index 98caa306122a..d840c90a157a 100644
--- a/include/asm-generic/signal.h
+++ b/include/asm-generic/signal.h
@@ -10,7 +10,5 @@
 #include <asm/sigcontext.h>
 #undef __HAVE_ARCH_SIG_BITOPS
 
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_GENERIC_SIGNAL_H */
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index d89dec864d42..1f74be5113b2 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -8,26 +8,6 @@
  * Calling conventions for these system calls can differ, so
  * it's possible to override them.
  */
-#ifndef sys_clone
-asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp,
-			void __user *parent_tid, void __user *child_tid,
-			struct pt_regs *regs);
-#endif
-
-#ifndef sys_fork
-asmlinkage long sys_fork(struct pt_regs *regs);
-#endif
-
-#ifndef sys_vfork
-asmlinkage long sys_vfork(struct pt_regs *regs);
-#endif
-
-#ifndef sys_execve
-asmlinkage long sys_execve(const char __user *filename,
-			   const char __user *const __user *argv,
-			   const char __user *const __user *envp,
-			   struct pt_regs *regs);
-#endif
 
 #ifndef sys_mmap2
 asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
@@ -41,22 +21,8 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 			unsigned long fd, off_t pgoff);
 #endif
 
-#ifndef sys_sigaltstack
-asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
-			struct pt_regs *);
-#endif
-
 #ifndef sys_rt_sigreturn
 asmlinkage long sys_rt_sigreturn(struct pt_regs *regs);
 #endif
 
-#ifndef sys_rt_sigsuspend
-asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize);
-#endif
-
-#ifndef sys_rt_sigaction
-asmlinkage long sys_rt_sigaction(int sig, const struct sigaction __user *act,
-			 struct sigaction __user *oact, size_t sigsetsize);
-#endif
-
 #endif /* __ASM_GENERIC_SYSCALLS_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index ed6642ad03e0..25f01d0bc149 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -78,6 +78,14 @@ struct mmu_gather_batch {
 #define MAX_GATHER_BATCH	\
 	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
+/*
+ * Limit the maximum number of mmu_gather batches to reduce a risk of soft
+ * lockups for non-preemptible kernels on huge machines when a lot of memory
+ * is zapped during unmapping.
+ * 10K pages freed at once should be safe even without a preemption point.
+ */
+#define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
+
 /* struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
@@ -96,6 +104,7 @@ struct mmu_gather {
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
+	unsigned int		batch_count;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
diff --git a/include/asm-generic/trace_clock.h b/include/asm-generic/trace_clock.h
new file mode 100644
index 000000000000..6726f1bafb5e
--- /dev/null
+++ b/include/asm-generic/trace_clock.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_GENERIC_TRACE_CLOCK_H
+#define _ASM_GENERIC_TRACE_CLOCK_H
+/*
+ * Arch-specific trace clocks.
+ */
+
+/*
+ * Additional trace clocks added to the trace_clocks
+ * array in kernel/trace/trace.c
+ * None if the architecture has not defined it.
+ */
+#ifndef ARCH_TRACE_CLOCKS
+# define ARCH_TRACE_CLOCKS
+#endif
+
+#endif  /* _ASM_GENERIC_TRACE_CLOCK_H */
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index 9788568f7978..c184aa8ec8cd 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -7,7 +7,6 @@
  * address space, e.g. all NOMMU machines.
  */
 #include <linux/sched.h>
-#include <linux/mm.h>
 #include <linux/string.h>
 
 #include <asm/segment.h>
@@ -32,7 +31,9 @@ static inline void set_fs(mm_segment_t fs)
 }
 #endif
 
+#ifndef segment_eq
 #define segment_eq(a, b) ((a).seg == (b).seg)
+#endif
 
 #define VERIFY_READ	0
 #define VERIFY_WRITE	1
@@ -168,12 +169,18 @@ static inline __must_check long __copy_to_user(void __user *to,
 		-EFAULT;					\
 })
 
+#ifndef __put_user_fn
+
 static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
 {
 	size = __copy_to_user(ptr, x, size);
 	return size ? -EFAULT : size;
 }
 
+#define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
+
+#endif
+
 extern int __put_user_bad(void) __attribute__((noreturn));
 
 #define __get_user(x, ptr)					\
@@ -224,12 +231,17 @@ extern int __put_user_bad(void) __attribute__((noreturn));
 		-EFAULT;					\
 })
 
+#ifndef __get_user_fn
 static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 {
 	size = __copy_from_user(x, ptr, size);
 	return size ? -EFAULT : size;
 }
 
+#define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
+
+#endif
+
 extern int __get_user_bad(void) __attribute__((noreturn));
 
 #ifndef __copy_from_user_inatomic
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index a36991ab334e..4077b5d9ff81 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -9,9 +9,6 @@
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_LLSEEK
 #endif
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 
 /*
  * "Conditional" syscalls
@@ -20,5 +17,12 @@
  * but it doesn't work on all toolchains, so we just do it by hand
  */
 #ifndef cond_syscall
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#ifdef CONFIG_SYMBOL_PREFIX
+#define __SYMBOL_PREFIX CONFIG_SYMBOL_PREFIX
+#else
+#define __SYMBOL_PREFIX
+#endif
+#define cond_syscall(x) asm(".weak\t" __SYMBOL_PREFIX #x "\n\t" \
+			    ".set\t" __SYMBOL_PREFIX #x "," \
+			    __SYMBOL_PREFIX "sys_ni_syscall")
 #endif
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index d1ea7ce0b4cb..afa12c7a025c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -149,6 +149,33 @@
 #define TRACE_SYSCALLS()
 #endif
 
+#ifdef CONFIG_CLKSRC_OF
+#define CLKSRC_OF_TABLES() . = ALIGN(8);				\
+			   VMLINUX_SYMBOL(__clksrc_of_table) = .;	\
+			   *(__clksrc_of_table)				\
+			   *(__clksrc_of_table_end)
+#else
+#define CLKSRC_OF_TABLES()
+#endif
+
+#ifdef CONFIG_IRQCHIP
+#define IRQCHIP_OF_MATCH_TABLE()					\
+	. = ALIGN(8);							\
+	VMLINUX_SYMBOL(__irqchip_begin) = .;				\
+	*(__irqchip_of_table)		  				\
+	*(__irqchip_of_end)
+#else
+#define IRQCHIP_OF_MATCH_TABLE()
+#endif
+
+#ifdef CONFIG_COMMON_CLK
+#define CLK_OF_TABLES() . = ALIGN(8);				\
+			VMLINUX_SYMBOL(__clk_of_table) = .;	\
+			*(__clk_of_table)			\
+			*(__clk_of_table_end)
+#else
+#define CLK_OF_TABLES()
+#endif
 
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
@@ -493,7 +520,10 @@
 	DEV_DISCARD(init.rodata)					\
 	CPU_DISCARD(init.rodata)					\
 	MEM_DISCARD(init.rodata)					\
-	KERNEL_DTB()
+	CLK_OF_TABLES()							\
+	CLKSRC_OF_TABLES()						\
+	KERNEL_DTB()							\
+	IRQCHIP_OF_MATCH_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text)							\