Linux-libre 4.5-gnu

24 files changed, 347 insertions, 268 deletions

diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index bd425302c..16da6380e 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -3,6 +3,7 @@
 generic-y += bitsperlong.h
 generic-y += cputime.h
 generic-y += current.h
+generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 7da5503c0..e08d15184 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void)
 	u32 irqstat;
 
 	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	dsb(sy);
 	return irqstat;
 }
 
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 3ff5642d9..112cc1a5d 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -60,38 +60,11 @@ extern void arm_heavy_mb(void);
 #define dma_wmb()	barrier()
 #endif
 
-#ifndef CONFIG_SMP
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#else
-#define smp_mb()	dmb(ish)
-#define smp_rmb()	smp_mb()
-#define smp_wmb()	dmb(ishst)
-#endif
-
-#define smp_store_release(p, v)						\
-do {									\
-	compiletime_assert_atomic_type(*p);				\
-	smp_mb();							\
-	WRITE_ONCE(*p, v);						\
-} while (0)
-
-#define smp_load_acquire(p)						\
-({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
-	compiletime_assert_atomic_type(*p);				\
-	smp_mb();							\
-	___p1;								\
-})
-
-#define read_barrier_depends()		do { } while(0)
-#define smp_read_barrier_depends()	do { } while(0)
-
-#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
+#define __smp_mb()	dmb(ish)
+#define __smp_rmb()	__smp_mb()
+#define __smp_wmb()	dmb(ishst)
 
-#define smp_mb__before_atomic()	smp_mb()
-#define smp_mb__after_atomic()	smp_mb()
+#include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index e7335a921..4e6e88a6b 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -5,8 +5,6 @@
 #include <linux/types.h>
 #include <asm/opcodes.h>
 
-#ifdef CONFIG_BUG
-
 /*
  * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling.
  * We need to be careful not to conflict with those used by other modules and
@@ -47,7 +45,7 @@ do {								\
 	unreachable();						\
 } while (0)
 
-#else  /* not CONFIG_DEBUG_BUGVERBOSE */
+#else
 
 #define __BUG(__file, __line, __value)				\
 do {								\
@@ -57,7 +55,6 @@ do {								\
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */
 
 #define HAVE_ARCH_BUG
-#endif  /* CONFIG_BUG */
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h
index 0f8424924..3848259be 100644
--- a/arch/arm/include/asm/cpuidle.h
+++ b/arch/arm/include/asm/cpuidle.h
@@ -30,7 +30,7 @@ static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev,
 struct device_node;
 
 struct cpuidle_ops {
-	int (*suspend)(int cpu, unsigned long arg);
+	int (*suspend)(unsigned long arg);
 	int (*init)(struct device_node *, int cpu);
 };
 
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 85e374f87..b23c6c81c 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -228,10 +228,26 @@ static inline int cpu_is_xsc3(void)
 }
 #endif
 
-#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3)
-#define	cpu_is_xscale()	0
+#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3) && \
+    !defined(CONFIG_CPU_MOHAWK)
+#define	cpu_is_xscale_family() 0
 #else
-#define	cpu_is_xscale()	1
+static inline int cpu_is_xscale_family(void)
+{
+	unsigned int id;
+	id = read_cpuid_id() & 0xffffe000;
+
+	switch (id) {
+	case 0x69052000: /* Intel XScale 1 */
+	case 0x69054000: /* Intel XScale 2 */
+	case 0x69056000: /* Intel XScale 3 */
+	case 0x56056000: /* Marvell XScale 3 */
+	case 0x56158000: /* Marvell Mohawk */
+		return 1;
+	}
+
+	return 0;
+}
 #endif
 
 /*
diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h
index 662c7bd06..e1f07764b 100644
--- a/arch/arm/include/asm/div64.h
+++ b/arch/arm/include/asm/div64.h
@@ -5,9 +5,9 @@
 #include <asm/compiler.h>
 
 /*
- * The semantics of do_div() are:
+ * The semantics of __div64_32() are:
  *
- * uint32_t do_div(uint64_t *n, uint32_t base)
+ * uint32_t __div64_32(uint64_t *n, uint32_t base)
  * {
  * 	uint32_t remainder = *n % base;
  * 	*n = *n / base;
@@ -16,8 +16,9 @@
  *
  * In other words, a 64-bit dividend with a 32-bit divisor producing
  * a 64-bit result and a 32-bit remainder.  To accomplish this optimally
- * we call a special __do_div64 helper with completely non standard
- * calling convention for arguments and results (beware).
+ * we override the generic version in lib/div64.c to call our __do_div64
+ * assembly implementation with completely non standard calling convention
+ * for arguments and results (beware).
  */
 
 #ifdef __ARMEB__
@@ -28,199 +29,101 @@
 #define __xh "r1"
 #endif
 
-#define __do_div_asm(n, base)					\
-({								\
-	register unsigned int __base      asm("r4") = base;	\
-	register unsigned long long __n   asm("r0") = n;	\
-	register unsigned long long __res asm("r2");		\
-	register unsigned int __rem       asm(__xh);		\
-	asm(	__asmeq("%0", __xh)				\
-		__asmeq("%1", "r2")				\
-		__asmeq("%2", "r0")				\
-		__asmeq("%3", "r4")				\
-		"bl	__do_div64"				\
-		: "=r" (__rem), "=r" (__res)			\
-		: "r" (__n), "r" (__base)			\
-		: "ip", "lr", "cc");				\
-	n = __res;						\
-	__rem;							\
-})
-
-#if __GNUC__ < 4 || !defined(CONFIG_AEABI)
+static inline uint32_t __div64_32(uint64_t *n, uint32_t base)
+{
+	register unsigned int __base      asm("r4") = base;
+	register unsigned long long __n   asm("r0") = *n;
+	register unsigned long long __res asm("r2");
+	register unsigned int __rem       asm(__xh);
+	asm(	__asmeq("%0", __xh)
+		__asmeq("%1", "r2")
+		__asmeq("%2", "r0")
+		__asmeq("%3", "r4")
+		"bl	__do_div64"
+		: "=r" (__rem), "=r" (__res)
+		: "r" (__n), "r" (__base)
+		: "ip", "lr", "cc");
+	*n = __res;
+	return __rem;
+}
+#define __div64_32 __div64_32
+
+#if !defined(CONFIG_AEABI)
 
 /*
- * gcc versions earlier than 4.0 are simply too problematic for the
- * optimized implementation below. First there is gcc PR 15089 that
- * tend to trig on more complex constructs, spurious .global __udivsi3
- * are inserted even if none of those symbols are referenced in the
- * generated code, and those gcc versions are not able to do constant
- * propagation on long long values anyway.
+ * In OABI configurations, some uses of the do_div function
+ * cause gcc to run out of registers. To work around that,
+ * we can force the use of the out-of-line version for
+ * configurations that build a OABI kernel.
  */
-#define do_div(n, base) __do_div_asm(n, base)
-
-#elif __GNUC__ >= 4
+#define do_div(n, base) __div64_32(&(n), base)
 
-#include <asm/bug.h>
+#else
 
 /*
- * If the divisor happens to be constant, we determine the appropriate
- * inverse at compile time to turn the division into a few inline
- * multiplications instead which is much faster. And yet only if compiling
- * for ARMv4 or higher (we need umull/umlal) and if the gcc version is
- * sufficiently recent to perform proper long long constant propagation.
- * (It is unfortunate that gcc doesn't perform all this internally.)
+ * gcc versions earlier than 4.0 are simply too problematic for the
+ * __div64_const32() code in asm-generic/div64.h. First there is
+ * gcc PR 15089 that tend to trig on more complex constructs, spurious
+ * .global __udivsi3 are inserted even if none of those symbols are
+ * referenced in the generated code, and those gcc versions are not able
+ * to do constant propagation on long long values anyway.
  */
-#define do_div(n, base)							\
-({									\
-	unsigned int __r, __b = (base);					\
-	if (!__builtin_constant_p(__b) || __b == 0 ||			\
-	    (__LINUX_ARM_ARCH__ < 4 && (__b & (__b - 1)) != 0)) {	\
-		/* non-constant divisor (or zero): slow path */		\
-		__r = __do_div_asm(n, __b);				\
-	} else if ((__b & (__b - 1)) == 0) {				\
-		/* Trivial: __b is constant and a power of 2 */		\
-		/* gcc does the right thing with this code.  */		\
-		__r = n;						\
-		__r &= (__b - 1);					\
-		n /= __b;						\
-	} else {							\
-		/* Multiply by inverse of __b: n/b = n*(p/b)/p       */	\
-		/* We rely on the fact that most of this code gets   */	\
-		/* optimized away at compile time due to constant    */	\
-		/* propagation and only a couple inline assembly     */	\
-		/* instructions should remain. Better avoid any      */	\
-		/* code construct that might prevent that.           */	\
-		unsigned long long __res, __x, __t, __m, __n = n;	\
-		unsigned int __c, __p, __z = 0;				\
-		/* preserve low part of n for reminder computation */	\
-		__r = __n;						\
-		/* determine number of bits to represent __b */		\
-		__p = 1 << __div64_fls(__b);				\
-		/* compute __m = ((__p << 64) + __b - 1) / __b */	\
-		__m = (~0ULL / __b) * __p;				\
-		__m += (((~0ULL % __b + 1) * __p) + __b - 1) / __b;	\
-		/* compute __res = __m*(~0ULL/__b*__b-1)/(__p << 64) */	\
-		__x = ~0ULL / __b * __b - 1;				\
-		__res = (__m & 0xffffffff) * (__x & 0xffffffff);	\
-		__res >>= 32;						\
-		__res += (__m & 0xffffffff) * (__x >> 32);		\
-		__t = __res;						\
-		__res += (__x & 0xffffffff) * (__m >> 32);		\
-		__t = (__res < __t) ? (1ULL << 32) : 0;			\
-		__res = (__res >> 32) + __t;				\
-		__res += (__m >> 32) * (__x >> 32);			\
-		__res /= __p;						\
-		/* Now sanitize and optimize what we've got. */		\
-		if (~0ULL % (__b / (__b & -__b)) == 0) {		\
-			/* those cases can be simplified with: */	\
-			__n /= (__b & -__b);				\
-			__m = ~0ULL / (__b / (__b & -__b));		\
-			__p = 1;					\
-			__c = 1;					\
-		} else if (__res != __x / __b) {			\
-			/* We can't get away without a correction    */	\
-			/* to compensate for bit truncation errors.  */	\
-			/* To avoid it we'd need an additional bit   */	\
-			/* to represent __m which would overflow it. */	\
-			/* Instead we do m=p/b and n/b=(n*m+m)/p.    */	\
-			__c = 1;					\
-			/* Compute __m = (__p << 64) / __b */		\
-			__m = (~0ULL / __b) * __p;			\
-			__m += ((~0ULL % __b + 1) * __p) / __b;		\
-		} else {						\
-			/* Reduce __m/__p, and try to clear bit 31   */	\
-			/* of __m when possible otherwise that'll    */	\
-			/* need extra overflow handling later.       */	\
-			unsigned int __bits = -(__m & -__m);		\
-			__bits |= __m >> 32;				\
-			__bits = (~__bits) << 1;			\
-			/* If __bits == 0 then setting bit 31 is     */	\
-			/* unavoidable.  Simply apply the maximum    */	\
-			/* possible reduction in that case.          */	\
-			/* Otherwise the MSB of __bits indicates the */	\
-			/* best reduction we should apply.           */	\
-			if (!__bits) {					\
-				__p /= (__m & -__m);			\
-				__m /= (__m & -__m);			\
-			} else {					\
-				__p >>= __div64_fls(__bits);		\
-				__m >>= __div64_fls(__bits);		\
-			}						\
-			/* No correction needed. */			\
-			__c = 0;					\
-		}							\
-		/* Now we have a combination of 2 conditions:        */	\
-		/* 1) whether or not we need a correction (__c), and */	\
-		/* 2) whether or not there might be an overflow in   */	\
-		/*    the cross product (__m & ((1<<63) | (1<<31)))  */	\
-		/* Select the best insn combination to perform the   */	\
-		/* actual __m * __n / (__p << 64) operation.         */	\
-		if (!__c) {						\
-			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
-				"mov	%Q0, #0"			\
-				: "=&r" (__res)				\
-				: "r" (__m), "r" (__n)			\
-				: "cc" );				\
-		} else if (!(__m & ((1ULL << 63) | (1ULL << 31)))) {	\
-			__res = __m;					\
-			asm (	"umlal	%Q0, %R0, %Q1, %Q2\n\t"		\
-				"mov	%Q0, #0"			\
-				: "+&r" (__res)				\
-				: "r" (__m), "r" (__n)			\
-				: "cc" );				\
-		} else {						\
-			asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"		\
-				"cmn	%Q0, %Q1\n\t"			\
-				"adcs	%R0, %R0, %R1\n\t"		\
-				"adc	%Q0, %3, #0"			\
-				: "=&r" (__res)				\
-				: "r" (__m), "r" (__n), "r" (__z)	\
-				: "cc" );				\
-		}							\
-		if (!(__m & ((1ULL << 63) | (1ULL << 31)))) {		\
-			asm (	"umlal	%R0, %Q0, %R1, %Q2\n\t"		\
-				"umlal	%R0, %Q0, %Q1, %R2\n\t"		\
-				"mov	%R0, #0\n\t"			\
-				"umlal	%Q0, %R0, %R1, %R2"		\
-				: "+&r" (__res)				\
-				: "r" (__m), "r" (__n)			\
-				: "cc" );				\
-		} else {						\
-			asm (	"umlal	%R0, %Q0, %R2, %Q3\n\t"		\
-				"umlal	%R0, %1, %Q2, %R3\n\t"		\
-				"mov	%R0, #0\n\t"			\
-				"adds	%Q0, %1, %Q0\n\t"		\
-				"adc	%R0, %R0, #0\n\t"		\
-				"umlal	%Q0, %R0, %R2, %R3"		\
-				: "+&r" (__res), "+&r" (__z)		\
-				: "r" (__m), "r" (__n)			\
-				: "cc" );				\
-		}							\
-		__res /= __p;						\
-		/* The reminder can be computed with 32-bit regs     */	\
-		/* only, and gcc is good at that.                    */	\
-		{							\
-			unsigned int __res0 = __res;			\
-			unsigned int __b0 = __b;			\
-			__r -= __res0 * __b0;				\
-		}							\
-		/* BUG_ON(__r >= __b || __res * __b + __r != n); */	\
-		n = __res;						\
-	}								\
-	__r;								\
-})
-
-/* our own fls implementation to make sure constant propagation is fine */
-#define __div64_fls(bits)						\
-({									\
-	unsigned int __left = (bits), __nr = 0;				\
-	if (__left & 0xffff0000) __nr += 16, __left >>= 16;		\
-	if (__left & 0x0000ff00) __nr +=  8, __left >>=  8;		\
-	if (__left & 0x000000f0) __nr +=  4, __left >>=  4;		\
-	if (__left & 0x0000000c) __nr +=  2, __left >>=  2;		\
-	if (__left & 0x00000002) __nr +=  1;				\
-	__nr;								\
-})
+
+#define __div64_const32_is_OK (__GNUC__ >= 4)
+
+static inline uint64_t __arch_xprod_64(uint64_t m, uint64_t n, bool bias)
+{
+	unsigned long long res;
+	unsigned int tmp = 0;
+
+	if (!bias) {
+		asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"
+			"mov	%Q0, #0"
+			: "=&r" (res)
+			: "r" (m), "r" (n)
+			: "cc");
+	} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		res = m;
+		asm (	"umlal	%Q0, %R0, %Q1, %Q2\n\t"
+			"mov	%Q0, #0"
+			: "+&r" (res)
+			: "r" (m), "r" (n)
+			: "cc");
+	} else {
+		asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"
+			"cmn	%Q0, %Q1\n\t"
+			"adcs	%R0, %R0, %R1\n\t"
+			"adc	%Q0, %3, #0"
+			: "=&r" (res)
+			: "r" (m), "r" (n), "r" (tmp)
+			: "cc");
+	}
+
+	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
+		asm (	"umlal	%R0, %Q0, %R1, %Q2\n\t"
+			"umlal	%R0, %Q0, %Q1, %R2\n\t"
+			"mov	%R0, #0\n\t"
+			"umlal	%Q0, %R0, %R1, %R2"
+			: "+&r" (res)
+			: "r" (m), "r" (n)
+			: "cc");
+	} else {
+		asm (	"umlal	%R0, %Q0, %R2, %Q3\n\t"
+			"umlal	%R0, %1, %Q2, %R3\n\t"
+			"mov	%R0, #0\n\t"
+			"adds	%Q0, %1, %Q0\n\t"
+			"adc	%R0, %R0, #0\n\t"
+			"umlal	%Q0, %R0, %R2, %R3"
+			: "+&r" (res), "+&r" (tmp)
+			: "r" (m), "r" (n)
+			: "cc");
+	}
+
+	return res;
+}
+#define __arch_xprod_64 __arch_xprod_64
+
+#include <asm-generic/div64.h>
 
 #endif
 
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index ccb3aa646..6ad1ceda6 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -41,13 +41,6 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 #define HAVE_ARCH_DMA_SUPPORTED 1
 extern int dma_supported(struct device *dev, u64 mask);
 
-/*
- * Note that while the generic code provides dummy dma_{alloc,free}_noncoherent
- * implementations, we don't provide a dma_cache_sync function so drivers using
- * this API are highlighted with build warnings.
- */
-#include <asm-generic/dma-mapping-common.h>
-
 #ifdef __arch_page_to_dma
 #error Please update to __arch_pfn_to_dma
 #endif
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
new file mode 100644
index 000000000..e0eea72de
--- /dev/null
+++ b/arch/arm/include/asm/efi.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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_ARM_EFI_H
+#define __ASM_ARM_EFI_H
+
+#include <asm/cacheflush.h>
+#include <asm/cachetype.h>
+#include <asm/early_ioremap.h>
+#include <asm/fixmap.h>
+#include <asm/highmem.h>
+#include <asm/mach/map.h>
+#include <asm/mmu_context.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_EFI
+void efi_init(void);
+
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+
+#define efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+	efi_status_t __s;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__s = __f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+	__s;								\
+})
+
+#define __efi_call_virt(f, ...)						\
+({									\
+	efi_##f##_t *__f;						\
+									\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
+	__f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
+})
+
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	check_and_switch_context(mm, NULL);
+}
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
+#else
+#define efi_init()
+#endif /* CONFIG_EFI */
+
+/* arch specific definitions used by the stub code */
+
+#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
+
+/*
+ * A reasonable upper bound for the uncompressed kernel size is 32 MBytes,
+ * so we will reserve that amount of memory. We have no easy way to tell what
+ * the actuall size of code + data the uncompressed kernel will use.
+ * If this is insufficient, the decompressor will relocate itself out of the
+ * way before performing the decompression.
+ */
+#define MAX_UNCOMP_KERNEL_SIZE	SZ_32M
+
+/*
+ * The kernel zImage should preferably be located between 32 MB and 128 MB
+ * from the base of DRAM. The min address leaves space for a maximal size
+ * uncompressed image, and the max address is due to how the zImage decompressor
+ * picks a destination address.
+ */
+#define ZIMAGE_OFFSET_LIMIT	SZ_128M
+#define MIN_ZIMAGE_OFFSET	MAX_UNCOMP_KERNEL_SIZE
+#define MAX_FDT_OFFSET		ZIMAGE_OFFSET_LIMIT
+
+#endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 58cfe9f1a..5c17d2dec 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -19,20 +19,47 @@ enum fixed_addresses {
 	FIX_TEXT_POKE0,
 	FIX_TEXT_POKE1,
 
-	__end_of_fixed_addresses
+	__end_of_fixmap_region,
+
+	/*
+	 * Share the kmap() region with early_ioremap(): this is guaranteed
+	 * not to clash since early_ioremap() is only available before
+	 * paging_init(), and kmap() only after.
+	 */
+#define NR_FIX_BTMAPS		32
+#define FIX_BTMAPS_SLOTS	7
+#define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
+	__end_of_early_ioremap_region
 };
 
+static const enum fixed_addresses __end_of_fixed_addresses =
+	__end_of_fixmap_region > __end_of_early_ioremap_region ?
+	__end_of_fixmap_region : __end_of_early_ioremap_region;
+
 #define FIXMAP_PAGE_COMMON	(L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY)
 
 #define FIXMAP_PAGE_NORMAL	(FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK)
+#define FIXMAP_PAGE_RO		(FIXMAP_PAGE_NORMAL | L_PTE_RDONLY)
 
 /* Used by set_fixmap_(io|nocache), both meant for mapping a device */
 #define FIXMAP_PAGE_IO		(FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED)
 #define FIXMAP_PAGE_NOCACHE	FIXMAP_PAGE_IO
 
+#define __early_set_fixmap	__set_fixmap
+
+#ifdef CONFIG_MMU
+
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot);
 void __init early_fixmap_init(void);
 
 #include <asm-generic/fixmap.h>
 
+#else
+
+static inline void early_fixmap_init(void) { }
+
+#endif
 #endif
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index fe3ea776d..3d7351c84 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	8
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index dc641ddf0..e22089fb4 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -19,6 +19,7 @@
 #ifndef __ARM_KVM_ARM_H__
 #define __ARM_KVM_ARM_H__
 
+#include <linux/const.h>
 #include <linux/types.h>
 
 /* Hyp Configuration Register (HCR) bits */
@@ -132,10 +133,9 @@
  * space.
  */
 #define KVM_PHYS_SHIFT	(40)
-#define KVM_PHYS_SIZE	(1ULL << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1ULL)
-#define PTRS_PER_S2_PGD	(1ULL << (KVM_PHYS_SHIFT - 30))
-#define S2_PGD_ORDER	get_order(PTRS_PER_S2_PGD * sizeof(pgd_t))
+#define KVM_PHYS_SIZE	(_AC(1, ULL) << KVM_PHYS_SHIFT)
+#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - _AC(1, ULL))
+#define PTRS_PER_S2_PGD	(_AC(1, ULL) << (KVM_PHYS_SHIFT - 30))
 
 /* Virtualization Translation Control Register (VTCR) bits */
 #define VTCR_SH0	(3 << 12)
@@ -162,17 +162,17 @@
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
-#define VTTBR_VMID_SHIFT  (48LLU)
-#define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_VMID_SHIFT  _AC(48, ULL)
+#define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 
 /* Hyp Syndrome Register (HSR) bits */
 #define HSR_EC_SHIFT	(26)
-#define HSR_EC		(0x3fU << HSR_EC_SHIFT)
-#define HSR_IL		(1U << 25)
+#define HSR_EC		(_AC(0x3f, UL) << HSR_EC_SHIFT)
+#define HSR_IL		(_AC(1, UL) << 25)
 #define HSR_ISS		(HSR_IL - 1)
 #define HSR_ISV_SHIFT	(24)
-#define HSR_ISV		(1U << HSR_ISV_SHIFT)
+#define HSR_ISV		(_AC(1, UL) << HSR_ISV_SHIFT)
 #define HSR_SRT_SHIFT	(16)
 #define HSR_SRT_MASK	(0xf << HSR_SRT_SHIFT)
 #define HSR_FSC		(0x3f)
@@ -180,9 +180,9 @@
 #define HSR_SSE		(1 << 21)
 #define HSR_WNR		(1 << 6)
 #define HSR_CV_SHIFT	(24)
-#define HSR_CV		(1U << HSR_CV_SHIFT)
+#define HSR_CV		(_AC(1, UL) << HSR_CV_SHIFT)
 #define HSR_COND_SHIFT	(20)
-#define HSR_COND	(0xfU << HSR_COND_SHIFT)
+#define HSR_COND	(_AC(0xf, UL) << HSR_COND_SHIFT)
 
 #define FSC_FAULT	(0x04)
 #define FSC_ACCESS	(0x08)
@@ -210,13 +210,13 @@
 #define HSR_EC_DABT	(0x24)
 #define HSR_EC_DABT_HYP	(0x25)
 
-#define HSR_WFI_IS_WFE		(1U << 0)
+#define HSR_WFI_IS_WFE		(_AC(1, UL) << 0)
 
-#define HSR_HVC_IMM_MASK	((1UL << 16) - 1)
+#define HSR_HVC_IMM_MASK	((_AC(1, UL) << 16) - 1)
 
-#define HSR_DABT_S1PTW		(1U << 7)
-#define HSR_DABT_CM		(1U << 8)
-#define HSR_DABT_EA		(1U << 9)
+#define HSR_DABT_S1PTW		(_AC(1, UL) << 7)
+#define HSR_DABT_CM		(_AC(1, UL) << 8)
+#define HSR_DABT_EA		(_AC(1, UL) << 9)
 
 #define kvm_arm_exception_type	\
 	{0, "RESET" }, 		\
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 6692982c9..f9f27792d 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -150,6 +150,12 @@ struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
 	u32 halt_attempted_poll;
 	u32 halt_wakeup;
+	u32 hvc_exit_stat;
+	u64 wfe_exit_stat;
+	u64 wfi_exit_stat;
+	u64 mmio_exit_user;
+	u64 mmio_exit_kernel;
+	u64 exits;
 };
 
 int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init);
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 405aa1883..a520b7987 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
 }
 
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
+					       kvm_pfn_t pfn,
 					       unsigned long size,
 					       bool ipa_uncached)
 {
@@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte)
 static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
 {
 	unsigned long size = PMD_SIZE;
-	pfn_t pfn = pmd_pfn(pmd);
+	kvm_pfn_t pfn = pmd_pfn(pmd);
 
 	while (size) {
 		void *va = kmap_atomic_pfn(pfn);
@@ -279,6 +280,11 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
 				       pgd_t *merged_hyp_pgd,
 				       unsigned long hyp_idmap_start) { }
 
+static inline unsigned int kvm_get_vmid_bits(void)
+{
+	return 8;
+}
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index f98c7f32c..9b7c328fb 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -42,6 +42,8 @@ enum {
 extern void iotable_init(struct map_desc *, int);
 extern void vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller);
+extern void create_mapping_late(struct mm_struct *mm, struct map_desc *md,
+				bool ng);
 
 #ifdef CONFIG_DEBUG_LL
 extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr);
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 9b32f76bb..432ce8176 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -26,7 +26,7 @@ void __check_vmalloc_seq(struct mm_struct *mm);
 #ifdef CONFIG_CPU_HAS_ASID
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 #ifdef CONFIG_ARM_ERRATA_798181
 void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h
new file mode 100644
index 000000000..8435ff591
--- /dev/null
+++ b/arch/arm/include/asm/paravirt.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM_PARAVIRT_H
+#define _ASM_ARM_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a745a2a53..dc46398bc 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -88,7 +88,6 @@
 
 #define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
 #define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
-#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
 #define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
 #define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
 
@@ -232,13 +231,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
-#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp);
-#endif
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
@@ -246,9 +238,9 @@ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 
 PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
 PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean,   &= ~L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h
index b4c6d9936..e1b825dfa 100644
--- a/arch/arm/include/asm/psci.h
+++ b/arch/arm/include/asm/psci.h
@@ -14,7 +14,7 @@
 #ifndef __ASM_ARM_PSCI_H
 #define __ASM_ARM_PSCI_H
 
-extern struct smp_operations psci_smp_ops;
+extern const struct smp_operations psci_smp_ops;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI)
 bool psci_smp_available(void);
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index e0adb9f1b..3613d7e9f 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -25,4 +25,10 @@ extern int arm_add_memory(u64 start, u64 size);
 extern void early_print(const char *str, ...);
 extern void dump_machine_table(void);
 
+#ifdef CONFIG_ATAGS_PROC
+extern void save_atags(const struct tag *tags);
+#else
+static inline void save_atags(const struct tag *tags) { }
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h
index 712b50e0a..d769972db 100644
--- a/arch/arm/include/asm/xen/hypercall.h
+++ b/arch/arm/include/asm/xen/hypercall.h
@@ -35,6 +35,7 @@
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
+#include <xen/interface/platform.h>
 
 long privcmd_call(unsigned call, unsigned long a1,
 		unsigned long a2, unsigned long a3,
@@ -49,6 +50,12 @@ int HYPERVISOR_memory_op(unsigned int cmd, void *arg);
 int HYPERVISOR_physdev_op(int cmd, void *arg);
 int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
 int HYPERVISOR_tmem_op(void *arg);
+int HYPERVISOR_platform_op_raw(void *arg);
+static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
+{
+	op->interface_version = XENPF_INTERFACE_VERSION;
+	return HYPERVISOR_platform_op_raw(op);
+}
 int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr);
 
 static inline int
diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h
index 50066006e..75d596862 100644
--- a/arch/arm/include/asm/xen/interface.h
+++ b/arch/arm/include/asm/xen/interface.h
@@ -27,6 +27,8 @@
 		(hnd).p = val;				\
 	} while (0)
 
+#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op
+
 #ifndef __ASSEMBLY__
 /* Explicitly size integers that represent pfns in the interface with
  * Xen so that we can have one ABI that works for 32 and 64 bit guests.
@@ -76,6 +78,7 @@ struct pvclock_wall_clock {
 	u32   version;
 	u32   sec;
 	u32   nsec;
+	u32   sec_hi;
 } __attribute__((__packed__));
 #endif
 
diff --git a/arch/arm/include/debug/dc21285.S b/arch/arm/include/debug/dc21285.S
new file mode 100644
index 000000000..02247f313
--- /dev/null
+++ b/arch/arm/include/debug/dc21285.S
@@ -0,0 +1,42 @@
+/* arch/arm/mach-footbridge/include/mach/debug-macro.S
+ *
+ * Debugging macro include header
+ *
+ *  Copyright (C) 1994-1999 Russell King
+ *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
+ *
+ * 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.
+ *
+*/
+
+#include <asm/hardware/dec21285.h>
+
+#include <mach/hardware.h>
+	/* For EBSA285 debugging */
+		.equ	dc21285_high, ARMCSR_BASE & 0xff000000
+		.equ	dc21285_low,  ARMCSR_BASE & 0x00ffffff
+
+		.macro	addruart, rp, rv, tmp
+		.if	dc21285_low
+		mov	\rp, #dc21285_low
+		.else
+		mov	\rp, #0
+		.endif
+		orr	\rv, \rp, #dc21285_high
+		orr	\rp, \rp, #0x42000000
+		.endm
+
+		.macro	senduart,rd,rx
+		str	\rd, [\rx, #0x160]	@ UARTDR
+		.endm
+
+		.macro	busyuart,rd,rx
+1001:		ldr	\rd, [\rx, #0x178]	@ UARTFLG
+		tst	\rd, #1 << 3
+		bne	1001b
+		.endm
+
+		.macro	waituart,rd,rx
+		.endm
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index ede692ffa..5dd2528e9 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -417,6 +417,7 @@
 #define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
 #define __NR_membarrier			(__NR_SYSCALL_BASE+389)
 #define __NR_mlock2			(__NR_SYSCALL_BASE+390)
+#define __NR_copy_file_range		(__NR_SYSCALL_BASE+391)
 
 /*
  * The following SWIs are ARM private.