These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

70 files changed, 1074 insertions, 759 deletions

diff --git a/kernel/arch/arm/include/asm/Kbuild b/kernel/arch/arm/include/asm/Kbuild
index 3c4596d0c..bd425302c 100644
--- a/kernel/arch/arm/include/asm/Kbuild
+++ b/kernel/arch/arm/include/asm/Kbuild
@@ -12,15 +12,15 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
-generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
+generic-y += msi.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
-generic-y += scatterlist.h
 generic-y += seccomp.h
 generic-y += sections.h
 generic-y += segment.h
diff --git a/kernel/arch/arm/include/asm/arch_gicv3.h b/kernel/arch/arm/include/asm/arch_gicv3.h
new file mode 100644
index 000000000..7da5503c0
--- /dev/null
+++ b/kernel/arch/arm/include/asm/arch_gicv3.h
@@ -0,0 +1,189 @@
+/*
+ * arch/arm/include/asm/arch_gicv3.h
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARCH_GICV3_H
+#define __ASM_ARCH_GICV3_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/io.h>
+#include <asm/barrier.h>
+
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
+#define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm
+
+#define ICC_EOIR1			__ACCESS_CP15(c12, 0, c12, 1)
+#define ICC_DIR				__ACCESS_CP15(c12, 0, c11, 1)
+#define ICC_IAR1			__ACCESS_CP15(c12, 0, c12, 0)
+#define ICC_SGI1R			__ACCESS_CP15_64(0, c12)
+#define ICC_PMR				__ACCESS_CP15(c4, 0, c6, 0)
+#define ICC_CTLR			__ACCESS_CP15(c12, 0, c12, 4)
+#define ICC_SRE				__ACCESS_CP15(c12, 0, c12, 5)
+#define ICC_IGRPEN1			__ACCESS_CP15(c12, 0, c12, 7)
+
+#define ICC_HSRE			__ACCESS_CP15(c12, 4, c9, 5)
+
+#define ICH_VSEIR			__ACCESS_CP15(c12, 4, c9, 4)
+#define ICH_HCR				__ACCESS_CP15(c12, 4, c11, 0)
+#define ICH_VTR				__ACCESS_CP15(c12, 4, c11, 1)
+#define ICH_MISR			__ACCESS_CP15(c12, 4, c11, 2)
+#define ICH_EISR			__ACCESS_CP15(c12, 4, c11, 3)
+#define ICH_ELSR			__ACCESS_CP15(c12, 4, c11, 5)
+#define ICH_VMCR			__ACCESS_CP15(c12, 4, c11, 7)
+
+#define __LR0(x)			__ACCESS_CP15(c12, 4, c12, x)
+#define __LR8(x)			__ACCESS_CP15(c12, 4, c13, x)
+
+#define ICH_LR0				__LR0(0)
+#define ICH_LR1				__LR0(1)
+#define ICH_LR2				__LR0(2)
+#define ICH_LR3				__LR0(3)
+#define ICH_LR4				__LR0(4)
+#define ICH_LR5				__LR0(5)
+#define ICH_LR6				__LR0(6)
+#define ICH_LR7				__LR0(7)
+#define ICH_LR8				__LR8(0)
+#define ICH_LR9				__LR8(1)
+#define ICH_LR10			__LR8(2)
+#define ICH_LR11			__LR8(3)
+#define ICH_LR12			__LR8(4)
+#define ICH_LR13			__LR8(5)
+#define ICH_LR14			__LR8(6)
+#define ICH_LR15			__LR8(7)
+
+/* LR top half */
+#define __LRC0(x)			__ACCESS_CP15(c12, 4, c14, x)
+#define __LRC8(x)			__ACCESS_CP15(c12, 4, c15, x)
+
+#define ICH_LRC0			__LRC0(0)
+#define ICH_LRC1			__LRC0(1)
+#define ICH_LRC2			__LRC0(2)
+#define ICH_LRC3			__LRC0(3)
+#define ICH_LRC4			__LRC0(4)
+#define ICH_LRC5			__LRC0(5)
+#define ICH_LRC6			__LRC0(6)
+#define ICH_LRC7			__LRC0(7)
+#define ICH_LRC8			__LRC8(0)
+#define ICH_LRC9			__LRC8(1)
+#define ICH_LRC10			__LRC8(2)
+#define ICH_LRC11			__LRC8(3)
+#define ICH_LRC12			__LRC8(4)
+#define ICH_LRC13			__LRC8(5)
+#define ICH_LRC14			__LRC8(6)
+#define ICH_LRC15			__LRC8(7)
+
+#define __AP0Rx(x)			__ACCESS_CP15(c12, 4, c8, x)
+#define ICH_AP0R0			__AP0Rx(0)
+#define ICH_AP0R1			__AP0Rx(1)
+#define ICH_AP0R2			__AP0Rx(2)
+#define ICH_AP0R3			__AP0Rx(3)
+
+#define __AP1Rx(x)			__ACCESS_CP15(c12, 4, c9, x)
+#define ICH_AP1R0			__AP1Rx(0)
+#define ICH_AP1R1			__AP1Rx(1)
+#define ICH_AP1R2			__AP1Rx(2)
+#define ICH_AP1R3			__AP1Rx(3)
+
+/* Low-level accessors */
+
+static inline void gic_write_eoir(u32 irq)
+{
+	asm volatile("mcr " __stringify(ICC_EOIR1) : : "r" (irq));
+	isb();
+}
+
+static inline void gic_write_dir(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_DIR) : : "r" (val));
+	isb();
+}
+
+static inline u32 gic_read_iar(void)
+{
+	u32 irqstat;
+
+	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
+	return irqstat;
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_PMR) : : "r" (val));
+}
+
+static inline void gic_write_ctlr(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_CTLR) : : "r" (val));
+	isb();
+}
+
+static inline void gic_write_grpen1(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_IGRPEN1) : : "r" (val));
+	isb();
+}
+
+static inline void gic_write_sgi1r(u64 val)
+{
+	asm volatile("mcrr " __stringify(ICC_SGI1R) : : "r" (val));
+}
+
+static inline u32 gic_read_sre(void)
+{
+	u32 val;
+
+	asm volatile("mrc " __stringify(ICC_SRE) : "=r" (val));
+	return val;
+}
+
+static inline void gic_write_sre(u32 val)
+{
+	asm volatile("mcr " __stringify(ICC_SRE) : : "r" (val));
+	isb();
+}
+
+/*
+ * Even in 32bit systems that use LPAE, there is no guarantee that the I/O
+ * interface provides true 64bit atomic accesses, so using strd/ldrd doesn't
+ * make much sense.
+ * Moreover, 64bit I/O emulation is extremely difficult to implement on
+ * AArch32, since the syndrome register doesn't provide any information for
+ * them.
+ * Consequently, the following IO helpers use 32bit accesses.
+ *
+ * There are only two registers that need 64bit accesses in this driver:
+ * - GICD_IROUTERn, contain the affinity values associated to each interrupt.
+ *   The upper-word (aff3) will always be 0, so there is no need for a lock.
+ * - GICR_TYPER is an ID register and doesn't need atomicity.
+ */
+static inline void gic_write_irouter(u64 val, volatile void __iomem *addr)
+{
+	writel_relaxed((u32)val, addr);
+	writel_relaxed((u32)(val >> 32), addr + 4);
+}
+
+static inline u64 gic_read_typer(const volatile void __iomem *addr)
+{
+	u64 val;
+
+	val = readl_relaxed(addr);
+	val |= (u64)readl_relaxed(addr + 4) << 32;
+	return val;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* !__ASM_ARCH_GICV3_H */
diff --git a/kernel/arch/arm/include/asm/assembler.h b/kernel/arch/arm/include/asm/assembler.h
index 186270b3e..b2bc8e114 100644
--- a/kernel/arch/arm/include/asm/assembler.h
+++ b/kernel/arch/arm/include/asm/assembler.h
@@ -108,33 +108,37 @@
 	.endm
 #endif
 
-	.macro asm_trace_hardirqs_off
+	.macro asm_trace_hardirqs_off, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl	trace_hardirqs_off
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on_cond, cond
+	.macro asm_trace_hardirqs_on, cond=al, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
 	/*
 	 * actually the registers should be pushed and pop'd conditionally, but
 	 * after bl the flags are certainly clobbered
 	 */
+	.if \save
 	stmdb   sp!, {r0-r3, ip, lr}
+	.endif
 	bl\cond	trace_hardirqs_on
+	.if \save
 	ldmia	sp!, {r0-r3, ip, lr}
+	.endif
 #endif
 	.endm
 
-	.macro asm_trace_hardirqs_on
-	asm_trace_hardirqs_on_cond al
-	.endm
-
-	.macro disable_irq
+	.macro disable_irq, save=1
 	disable_irq_notrace
-	asm_trace_hardirqs_off
+	asm_trace_hardirqs_off \save
 	.endm
 
 	.macro enable_irq
@@ -173,11 +177,26 @@
 
 	.macro restore_irqs, oldcpsr
 	tst	\oldcpsr, #PSR_I_BIT
-	asm_trace_hardirqs_on_cond eq
+	asm_trace_hardirqs_on cond=eq
 	restore_irqs_notrace \oldcpsr
 	.endm
 
 /*
+ * Assembly version of "adr rd, BSYM(sym)".  This should only be used to
+ * reference local symbols in the same assembly file which are to be
+ * resolved by the assembler.  Other usage is undefined.
+ */
+	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+	.macro	badr\c, rd, sym
+#ifdef CONFIG_THUMB2_KERNEL
+	adr\c	\rd, \sym + 1
+#else
+	adr\c	\rd, \sym
+#endif
+	.endm
+	.endr
+
+/*
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
@@ -326,7 +345,7 @@
 THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	bne	1f
 	orr	\reg, \reg, #PSR_A_BIT
-	adr	lr, BSYM(2f)
+	badr	lr, 2f
 	msr	spsr_cxsf, \reg
 	__MSR_ELR_HYP(14)
 	__ERET
@@ -430,6 +449,48 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
+	.endm
+
+	.macro	uaccess_save, tmp
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	mrc	p15, 0, \tmp, c3, c0, 0
+	str	\tmp, [sp, #S_FRAME_SIZE]
+#endif
+	.endm
+
+	.macro	uaccess_restore
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	ldr	r0, [sp, #S_FRAME_SIZE]
+	mcr	p15, 0, r0, c3, c0, 0
+#endif
+	.endm
+
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/kernel/arch/arm/include/asm/atomic.h b/kernel/arch/arm/include/asm/atomic.h
index e22c11970..9e10c4567 100644
--- a/kernel/arch/arm/include/asm/atomic.h
+++ b/kernel/arch/arm/include/asm/atomic.h
@@ -27,8 +27,8 @@
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
-#define atomic_read(v)	ACCESS_ONCE((v)->counter)
-#define atomic_set(v,i)	(((v)->counter) = (i))
+#define atomic_read(v)	READ_ONCE((v)->counter)
+#define atomic_set(v,i)	WRITE_ONCE(((v)->counter), (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
 
@@ -57,12 +57,11 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	unsigned long tmp;						\
 	int result;							\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
@@ -75,17 +74,17 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r" (&v->counter), "Ir" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
-static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+
+static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 {
 	int oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -99,10 +98,9 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 		    : "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
@@ -194,6 +192,13 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or,  |=, orr)
+ATOMIC_OP(xor, ^=, eor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -205,8 +210,8 @@ ATOMIC_OPS(sub, -=, sub)
 
 #define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
-#define atomic_inc_return(v)    (atomic_add_return(1, v))
-#define atomic_dec_return(v)    (atomic_sub_return(1, v))
+#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
+#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
@@ -290,12 +295,12 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)				\
-static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
+static inline long long							\
+atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
 {									\
 	long long result;						\
 	unsigned long tmp;						\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
@@ -309,8 +314,6 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 	: "r" (&v->counter), "r" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
@@ -321,17 +324,26 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OP(and, and, and)
+ATOMIC64_OP(andnot, bic, bic)
+ATOMIC64_OP(or,  orr, orr)
+ATOMIC64_OP(xor, eor, eor)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
-					long long new)
+static inline long long
+atomic64_cmpxchg_relaxed(atomic64_t *ptr, long long old, long long new)
 {
 	long long oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -346,17 +358,15 @@ static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 		: "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic64_cmpxchg_relaxed	atomic64_cmpxchg_relaxed
 
-static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+static inline long long atomic64_xchg_relaxed(atomic64_t *ptr, long long new)
 {
 	long long result;
 	unsigned long tmp;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
@@ -368,10 +378,9 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");
 
-	smp_mb();
-
 	return result;
 }
+#define atomic64_xchg_relaxed		atomic64_xchg_relaxed
 
 static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
@@ -433,11 +442,11 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
diff --git a/kernel/arch/arm/include/asm/barrier.h b/kernel/arch/arm/include/asm/barrier.h
index d2f81e6b8..3ff5642d9 100644
--- a/kernel/arch/arm/include/asm/barrier.h
+++ b/kernel/arch/arm/include/asm/barrier.h
@@ -2,7 +2,6 @@
 #define __ASM_BARRIER_H
 
 #ifndef __ASSEMBLY__
-#include <asm/outercache.h>
 
 #define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");
 
@@ -37,12 +36,20 @@
 #define dmb(x) __asm__ __volatile__ ("" : : : "memory")
 #endif
 
+#ifdef CONFIG_ARM_HEAVY_MB
+extern void (*soc_mb)(void);
+extern void arm_heavy_mb(void);
+#define __arm_heavy_mb(x...) do { dsb(x); arm_heavy_mb(); } while (0)
+#else
+#define __arm_heavy_mb(x...) dsb(x)
+#endif
+
 #ifdef CONFIG_ARCH_HAS_BARRIERS
 #include <mach/barriers.h>
 #elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
-#define mb()		do { dsb(); outer_sync(); } while (0)
+#define mb()		__arm_heavy_mb()
 #define rmb()		dsb()
-#define wmb()		do { dsb(st); outer_sync(); } while (0)
+#define wmb()		__arm_heavy_mb(st)
 #define dma_rmb()	dmb(osh)
 #define dma_wmb()	dmb(oshst)
 #else
@@ -67,12 +74,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
@@ -81,7 +88,7 @@ do {									\
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
-#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_mb__before_atomic()	smp_mb()
 #define smp_mb__after_atomic()	smp_mb()
diff --git a/kernel/arch/arm/include/asm/bitops.h b/kernel/arch/arm/include/asm/bitops.h
index 56380995f..e943e6cee 100644
--- a/kernel/arch/arm/include/asm/bitops.h
+++ b/kernel/arch/arm/include/asm/bitops.h
@@ -35,9 +35,9 @@
 static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p |= mask;
@@ -47,9 +47,9 @@ static inline void ____atomic_set_bit(unsigned int bit, volatile unsigned long *
 static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p &= ~mask;
@@ -59,9 +59,9 @@ static inline void ____atomic_clear_bit(unsigned int bit, volatile unsigned long
 static inline void ____atomic_change_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	*p ^= mask;
@@ -73,9 +73,9 @@ ____atomic_test_and_set_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -90,9 +90,9 @@ ____atomic_test_and_clear_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
@@ -107,9 +107,9 @@ ____atomic_test_and_change_bit(unsigned int bit, volatile unsigned long *p)
 {
 	unsigned long flags;
 	unsigned int res;
-	unsigned long mask = 1UL << (bit & 31);
+	unsigned long mask = BIT_MASK(bit);
 
-	p += bit >> 5;
+	p += BIT_WORD(bit);
 
 	raw_local_irq_save(flags);
 	res = *p;
diff --git a/kernel/arch/arm/include/asm/bug.h b/kernel/arch/arm/include/asm/bug.h
index b274bde24..e7335a921 100644
--- a/kernel/arch/arm/include/asm/bug.h
+++ b/kernel/arch/arm/include/asm/bug.h
@@ -40,6 +40,7 @@ do {								\
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
 		".pushsection __bug_table,\"a\"\n"		\
+		".align 2\n"					\
 		"3:\t.word 1b, 2b\n"				\
 		"\t.hword " #__line ", 0\n"			\
 		".popsection");					\
diff --git a/kernel/arch/arm/include/asm/cacheflush.h b/kernel/arch/arm/include/asm/cacheflush.h
index 2d46862e7..d5525bfc7 100644
--- a/kernel/arch/arm/include/asm/cacheflush.h
+++ b/kernel/arch/arm/include/asm/cacheflush.h
@@ -140,8 +140,6 @@ extern struct cpu_cache_fns cpu_cache;
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-#define dmac_map_area			cpu_cache.dma_map_area
-#define dmac_unmap_area			cpu_cache.dma_unmap_area
 #define dmac_flush_range		cpu_cache.dma_flush_range
 
 #else
@@ -161,8 +159,6 @@ extern void __cpuc_flush_dcache_area(void *, size_t);
  * is visible to DMA, or data written by DMA to system memory is
  * visible to the CPU.
  */
-extern void dmac_map_area(const void *, size_t, int);
-extern void dmac_unmap_area(const void *, size_t, int);
 extern void dmac_flush_range(const void *, const void *);
 
 #endif
@@ -482,10 +478,17 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
 	      "r9","r10","lr","memory" )
 
+#ifdef CONFIG_MMU
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
+#else
+static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_x(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
+#endif
 
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
@@ -499,4 +502,21 @@ static inline void set_kernel_text_ro(void) { }
 void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
 			     void *kaddr, unsigned long len);
 
+/**
+ * secure_flush_area - ensure coherency across the secure boundary
+ * @addr: virtual address
+ * @size: size of region
+ *
+ * Ensure that the specified area of memory is coherent across the secure
+ * boundary from the non-secure side.  This is used when calling secure
+ * firmware where the secure firmware does not ensure coherency.
+ */
+static inline void secure_flush_area(const void *addr, size_t size)
+{
+	phys_addr_t phys = __pa(addr);
+
+	__cpuc_flush_dcache_area((void *)addr, size);
+	outer_flush_range(phys, phys + size);
+}
+
 #endif
diff --git a/kernel/arch/arm/include/asm/cmpxchg.h b/kernel/arch/arm/include/asm/cmpxchg.h
index 2386e9745..97882f9ba 100644
--- a/kernel/arch/arm/include/asm/cmpxchg.h
+++ b/kernel/arch/arm/include/asm/cmpxchg.h
@@ -35,11 +35,11 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	unsigned int tmp;
 #endif
 
-	smp_mb();
 	prefetchw((const void *)ptr);
 
 	switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
+#ifndef CONFIG_CPU_V6 /* MIN ARCH >= V6K */
 	case 1:
 		asm volatile("@	__xchg1\n"
 		"1:	ldrexb	%0, [%3]\n"
@@ -50,6 +50,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 			: "r" (x), "r" (ptr)
 			: "memory", "cc");
 		break;
+	case 2:
+		asm volatile("@	__xchg2\n"
+		"1:	ldrexh	%0, [%3]\n"
+		"	strexh	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#endif
 	case 4:
 		asm volatile("@	__xchg4\n"
 		"1:	ldrex	%0, [%3]\n"
@@ -94,16 +105,18 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		break;
 #endif
 	default:
+		/* Cause a link-time error, the xchg() size is not supported */
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
-	smp_mb();
 
 	return ret;
 }
 
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+#define xchg_relaxed(ptr, x) ({						\
+	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
+				   sizeof(*(ptr)));			\
+})
 
 #include <asm-generic/cmpxchg-local.h>
 
@@ -114,23 +127,25 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 #error "SMP is not supported on this platform"
 #endif
 
+#define xchg xchg_relaxed
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
  */
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
+#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))
 
-#ifndef CONFIG_SMP
 #include <asm-generic/cmpxchg.h>
-#endif
 
 #else	/* min ARCH >= ARMv6 */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 extern void __bad_cmpxchg(volatile void *ptr, int size);
 
 /*
@@ -191,23 +206,12 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return oldval;
 }
 
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	unsigned long ret;
-
-	smp_mb();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
-					  (unsigned long)(o),		\
-					  (unsigned long)(n),		\
-					  sizeof(*(ptr))))
+#define cmpxchg_relaxed(ptr,o,n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg((ptr),				\
+				      (unsigned long)(o),		\
+				      (unsigned long)(n),		\
+				      sizeof(*(ptr)));			\
+})
 
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
 					    unsigned long old,
@@ -229,6 +233,13 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	return ret;
 }
 
+#define cmpxchg_local(ptr, o, n) ({					\
+	(__typeof(*ptr))__cmpxchg_local((ptr),				\
+				        (unsigned long)(o),		\
+				        (unsigned long)(n),		\
+				        sizeof(*(ptr)));		\
+})
+
 static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 					     unsigned long long old,
 					     unsigned long long new)
@@ -254,36 +265,13 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 	return oldval;
 }
 
-static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
-						unsigned long long old,
-						unsigned long long new)
-{
-	unsigned long long ret;
-
-	smp_mb();
-	ret = __cmpxchg64(ptr, old, new);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg_local(ptr,o,n)						\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
-				       (unsigned long)(o),		\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
-
-#define cmpxchg64(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
-
-#define cmpxchg64_relaxed(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+#define cmpxchg64_relaxed(ptr, o, n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg64((ptr),				\
 					(unsigned long long)(o),	\
-					(unsigned long long)(n)))
+					(unsigned long long)(n));	\
+})
 
-#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
+#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/kernel/arch/arm/include/asm/dma-mapping.h b/kernel/arch/arm/include/asm/dma-mapping.h
index b52101d37..ccb3aa646 100644
--- a/kernel/arch/arm/include/asm/dma-mapping.h
+++ b/kernel/arch/arm/include/asm/dma-mapping.h
@@ -8,13 +8,12 @@
 #include <linux/dma-attrs.h>
 #include <linux/dma-debug.h>
 
-#include <asm-generic/dma-coherent.h>
 #include <asm/memory.h>
 
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~0)
+#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 extern struct dma_map_ops arm_dma_ops;
 extern struct dma_map_ops arm_coherent_dma_ops;
 
@@ -39,12 +38,15 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
+#define HAVE_ARCH_DMA_SUPPORTED 1
+extern int dma_supported(struct device *dev, u64 mask);
 
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	return get_dma_ops(dev)->set_dma_mask(dev, 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
@@ -167,32 +169,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline void dma_mark_clean(void *addr, size_t size) { }
 
-/*
- * DMA errors are defined by all-bits-set in the DMA address.
- */
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	debug_dma_mapping_error(dev, dma_addr);
-	return dma_addr == DMA_ERROR_CODE;
-}
-
-/*
- * Dummy noncoherent implementation.  We don't provide a dma_cache_sync
- * function so drivers using this API are highlighted with build warnings.
- */
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *handle, gfp_t gfp)
-{
-	return NULL;
-}
-
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t handle)
-{
-}
-
-extern int dma_supported(struct device *dev, u64 mask);
-
 extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
 
 /**
@@ -209,21 +185,6 @@ extern int arm_dma_set_mask(struct device *dev, u64 dma_mask);
 extern void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 			   gfp_t gfp, struct dma_attrs *attrs);
 
-#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL)
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *cpu_addr;
-	BUG_ON(!ops);
-
-	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
-	return cpu_addr;
-}
-
 /**
  * arm_dma_free - free memory allocated by arm_dma_alloc
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -241,19 +202,6 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size,
 extern void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 			 dma_addr_t handle, struct dma_attrs *attrs);
 
-#define dma_free_coherent(d, s, c, h) dma_free_attrs(d, s, c, h, NULL)
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle,
-				     struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-
-	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free(dev, size, cpu_addr, dma_handle, attrs);
-}
-
 /**
  * arm_dma_mmap - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
diff --git a/kernel/arch/arm/include/asm/dma.h b/kernel/arch/arm/include/asm/dma.h
index 99084431d..bb4fa67da 100644
--- a/kernel/arch/arm/include/asm/dma.h
+++ b/kernel/arch/arm/include/asm/dma.h
@@ -19,7 +19,7 @@
  * It should not be re-used except for that purpose.
  */
 #include <linux/spinlock.h>
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
 
 #include <mach/isa-dma.h>
 
diff --git a/kernel/arch/arm/include/asm/domain.h b/kernel/arch/arm/include/asm/domain.h
index 6ddbe4464..fc8ba1663 100644
--- a/kernel/arch/arm/include/asm/domain.h
+++ b/kernel/arch/arm/include/asm/domain.h
@@ -12,6 +12,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/barrier.h>
+#include <asm/thread_info.h>
 #endif
 
 /*
@@ -34,15 +35,14 @@
  */
 #ifndef CONFIG_IO_36
 #define DOMAIN_KERNEL	0
-#define DOMAIN_TABLE	0
 #define DOMAIN_USER	1
 #define DOMAIN_IO	2
 #else
 #define DOMAIN_KERNEL	2
-#define DOMAIN_TABLE	2
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
+#define DOMAIN_VECTORS	3
 
 /*
  * Domain types
@@ -55,30 +55,65 @@
 #define DOMAIN_MANAGER	1
 #endif
 
-#define domain_val(dom,type)	((type) << (2*(dom)))
+#define domain_mask(dom)	((3) << (2 * (dom)))
+#define domain_val(dom,type)	((type) << (2 * (dom)))
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#else
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#endif
+
+#define __DACR_DEFAULT \
+	domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)
+
+#define DACR_UACCESS_DISABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+#define DACR_UACCESS_ENABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_CPU_USE_DOMAINS
+static inline unsigned int get_domain(void)
+{
+	unsigned int domain;
+
+	asm(
+	"mrc	p15, 0, %0, c3, c0	@ get domain"
+	 : "=r" (domain)
+	 : "m" (current_thread_info()->cpu_domain));
+
+	return domain;
+}
+
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
-	  : : "r" (val));
+	  : : "r" (val) : "memory");
 	isb();
 }
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define modify_domain(dom,type)					\
 	do {							\
-	struct thread_info *thread = current_thread_info();	\
-	unsigned int domain = thread->cpu_domain;		\
-	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
-	thread->cpu_domain = domain | domain_val(dom, type);	\
-	set_domain(thread->cpu_domain);				\
+		unsigned int domain = get_domain();		\
+		domain &= ~domain_mask(dom);			\
+		domain = domain | domain_val(dom, type);	\
+		set_domain(domain);				\
 	} while (0)
 
 #else
-static inline void set_domain(unsigned val) { }
 static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 
diff --git a/kernel/arch/arm/include/asm/edac.h b/kernel/arch/arm/include/asm/edac.h
index 0df7a2c1f..5189fa819 100644
--- a/kernel/arch/arm/include/asm/edac.h
+++ b/kernel/arch/arm/include/asm/edac.h
@@ -18,11 +18,12 @@
 #define ASM_EDAC_H
 /*
  * ECC atomic, DMA, SMP and interrupt safe scrub function.
- * Implements the per arch atomic_scrub() that EDAC use for software
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
  * ECC scrubbing.  It reads memory and then writes back the original
  * value, allowing the hardware to detect and correct memory errors.
  */
-static inline void atomic_scrub(void *va, u32 size)
+
+static inline void edac_atomic_scrub(void *va, u32 size)
 {
 #if __LINUX_ARM_ARCH__ >= 6
 	unsigned int *virt_addr = va;
diff --git a/kernel/arch/arm/include/asm/entry-macro-multi.S b/kernel/arch/arm/include/asm/entry-macro-multi.S
index 469a2b30f..609184f52 100644
--- a/kernel/arch/arm/include/asm/entry-macro-multi.S
+++ b/kernel/arch/arm/include/asm/entry-macro-multi.S
@@ -10,7 +10,7 @@
 	@
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
 	@
-	adrne	lr, BSYM(1b)
+	badrne	lr, 1b
 	bne	asm_do_IRQ
 
 #ifdef CONFIG_SMP
@@ -23,7 +23,7 @@
 	ALT_SMP(test_for_ipi r0, r2, r6, lr)
 	ALT_UP_B(9997f)
 	movne	r1, sp
-	adrne	lr, BSYM(1b)
+	badrne	lr, 1b
 	bne	do_IPI
 #endif
 9997:
diff --git a/kernel/arch/arm/include/asm/firmware.h b/kernel/arch/arm/include/asm/firmware.h
index 89aefe10d..34c1d96ef 100644
--- a/kernel/arch/arm/include/asm/firmware.h
+++ b/kernel/arch/arm/include/asm/firmware.h
@@ -34,6 +34,10 @@ struct firmware_ops {
 	 */
 	int (*set_cpu_boot_addr)(int cpu, unsigned long boot_addr);
 	/*
+	 * Gets boot address of specified physical CPU
+	 */
+	int (*get_cpu_boot_addr)(int cpu, unsigned long *boot_addr);
+	/*
 	 * Boots specified physical CPU
 	 */
 	int (*cpu_boot)(int cpu);
diff --git a/kernel/arch/arm/include/asm/fixmap.h b/kernel/arch/arm/include/asm/fixmap.h
index 0415eae1d..58cfe9f1a 100644
--- a/kernel/arch/arm/include/asm/fixmap.h
+++ b/kernel/arch/arm/include/asm/fixmap.h
@@ -6,9 +6,13 @@
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
 #include <asm/kmap_types.h>
+#include <asm/pgtable.h>
 
 enum fixed_addresses {
-	FIX_KMAP_BEGIN,
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_permanent_fixed_addresses,
+
+	FIX_KMAP_BEGIN = __end_of_permanent_fixed_addresses,
 	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
 
 	/* Support writing RO kernel text via kprobes, jump labels, etc. */
@@ -18,7 +22,16 @@ enum fixed_addresses {
 	__end_of_fixed_addresses
 };
 
+#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)
+
+/* 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
+
 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>
 
diff --git a/kernel/arch/arm/include/asm/futex.h b/kernel/arch/arm/include/asm/futex.h
index 5eed82809..6795368ad 100644
--- a/kernel/arch/arm/include/asm/futex.h
+++ b/kernel/arch/arm/include/asm/futex.h
@@ -22,8 +22,11 @@
 #ifdef CONFIG_SMP
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags;				\
 	smp_mb();						\
 	prefetchw(uaddr);					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -34,12 +37,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret;
 	u32 val;
 
@@ -49,6 +55,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	smp_mb();
 	/* Prefetching cannot fault */
 	prefetchw(uaddr);
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -61,6 +68,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "=&r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 	smp_mb();
 
 	*uval = val;
@@ -73,6 +81,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags = uaccess_save_and_enable();	\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -81,12 +91,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret = 0;
 	u32 val;
 
@@ -94,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	preempt_disable();
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -103,6 +117,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 
 	*uval = val;
 	preempt_enable();
diff --git a/kernel/arch/arm/include/asm/glue-cache.h b/kernel/arch/arm/include/asm/glue-cache.h
index a3c24cd5b..cab07f693 100644
--- a/kernel/arch/arm/include/asm/glue-cache.h
+++ b/kernel/arch/arm/include/asm/glue-cache.h
@@ -158,8 +158,6 @@ static inline void nop_dma_unmap_area(const void *s, size_t l, int f) { }
 #define __cpuc_coherent_user_range	__glue(_CACHE,_coherent_user_range)
 #define __cpuc_flush_dcache_area	__glue(_CACHE,_flush_kern_dcache_area)
 
-#define dmac_map_area			__glue(_CACHE,_dma_map_area)
-#define dmac_unmap_area			__glue(_CACHE,_dma_unmap_area)
 #define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
 #endif
 
diff --git a/kernel/arch/arm/include/asm/hardware/arm_timer.h b/kernel/arch/arm/include/asm/hardware/arm_timer.h
deleted file mode 100644
index d6030ff59..000000000
--- a/kernel/arch/arm/include/asm/hardware/arm_timer.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef __ASM_ARM_HARDWARE_ARM_TIMER_H
-#define __ASM_ARM_HARDWARE_ARM_TIMER_H
-
-/*
- * ARM timer implementation, found in Integrator, Versatile and Realview
- * platforms.  Not all platforms support all registers and bits in these
- * registers, so we mark them with A for Integrator AP, C for Integrator
- * CP, V for Versatile and R for Realview.
- *
- * Integrator AP has 16-bit timers, Integrator CP, Versatile and Realview
- * can have 16-bit or 32-bit selectable via a bit in the control register.
- *
- * Every SP804 contains two identical timers.
- */
-#define TIMER_1_BASE	0x00
-#define TIMER_2_BASE	0x20
-
-#define TIMER_LOAD	0x00			/* ACVR rw */
-#define TIMER_VALUE	0x04			/* ACVR ro */
-#define TIMER_CTRL	0x08			/* ACVR rw */
-#define TIMER_CTRL_ONESHOT	(1 << 0)	/*  CVR */
-#define TIMER_CTRL_32BIT	(1 << 1)	/*  CVR */
-#define TIMER_CTRL_DIV1		(0 << 2)	/* ACVR */
-#define TIMER_CTRL_DIV16	(1 << 2)	/* ACVR */
-#define TIMER_CTRL_DIV256	(2 << 2)	/* ACVR */
-#define TIMER_CTRL_IE		(1 << 5)	/*   VR */
-#define TIMER_CTRL_PERIODIC	(1 << 6)	/* ACVR */
-#define TIMER_CTRL_ENABLE	(1 << 7)	/* ACVR */
-
-#define TIMER_INTCLR	0x0c			/* ACVR wo */
-#define TIMER_RIS	0x10			/*  CVR ro */
-#define TIMER_MIS	0x14			/*  CVR ro */
-#define TIMER_BGLOAD	0x18			/*  CVR rw */
-
-#endif
diff --git a/kernel/arch/arm/include/asm/hardware/cache-uniphier.h b/kernel/arch/arm/include/asm/hardware/cache-uniphier.h
new file mode 100644
index 000000000..102e3fbe1
--- /dev/null
+++ b/kernel/arch/arm/include/asm/hardware/cache-uniphier.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __CACHE_UNIPHIER_H
+#define __CACHE_UNIPHIER_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_CACHE_UNIPHIER
+int uniphier_cache_init(void);
+int uniphier_cache_l2_is_enabled(void);
+void uniphier_cache_l2_touch_range(unsigned long start, unsigned long end);
+void uniphier_cache_l2_set_locked_ways(u32 way_mask);
+#else
+static inline int uniphier_cache_init(void)
+{
+	return -ENODEV;
+}
+
+static inline int uniphier_cache_l2_is_enabled(void)
+{
+	return 0;
+}
+
+static inline void uniphier_cache_l2_touch_range(unsigned long start,
+						 unsigned long end)
+{
+}
+
+static inline void uniphier_cache_l2_set_locked_ways(u32 way_mask)
+{
+}
+#endif
+
+#endif /* __CACHE_UNIPHIER_H */
diff --git a/kernel/arch/arm/include/asm/hardware/it8152.h b/kernel/arch/arm/include/asm/hardware/it8152.h
index d36a73d7c..076777ff3 100644
--- a/kernel/arch/arm/include/asm/hardware/it8152.h
+++ b/kernel/arch/arm/include/asm/hardware/it8152.h
@@ -106,7 +106,7 @@ extern void __iomem *it8152_base_address;
 struct pci_dev;
 struct pci_sys_data;
 
-extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc);
+extern void it8152_irq_demux(struct irq_desc *desc);
 extern void it8152_init_irq(void);
 extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
 extern int it8152_pci_setup(int nr, struct pci_sys_data *sys);
diff --git a/kernel/arch/arm/include/asm/hardware/timer-sp.h b/kernel/arch/arm/include/asm/hardware/timer-sp.h
deleted file mode 100644
index bb28af7c3..000000000
--- a/kernel/arch/arm/include/asm/hardware/timer-sp.h
+++ /dev/null
@@ -1,23 +0,0 @@
-struct clk;
-
-void __sp804_clocksource_and_sched_clock_init(void __iomem *,
-					      const char *, struct clk *, int);
-void __sp804_clockevents_init(void __iomem *, unsigned int,
-			      struct clk *, const char *);
-
-static inline void sp804_clocksource_init(void __iomem *base, const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 0);
-}
-
-static inline void sp804_clocksource_and_sched_clock_init(void __iomem *base,
-							  const char *name)
-{
-	__sp804_clocksource_and_sched_clock_init(base, name, NULL, 1);
-}
-
-static inline void sp804_clockevents_init(void __iomem *base, unsigned int irq, const char *name)
-{
-	__sp804_clockevents_init(base, irq, NULL, name);
-
-}
diff --git a/kernel/arch/arm/include/asm/highmem.h b/kernel/arch/arm/include/asm/highmem.h
index 535579511..0a0e2d178 100644
--- a/kernel/arch/arm/include/asm/highmem.h
+++ b/kernel/arch/arm/include/asm/highmem.h
@@ -68,7 +68,6 @@ extern void kunmap(struct page *page);
 extern void *kmap_atomic(struct page *page);
 extern void __kunmap_atomic(void *kvaddr);
 extern void *kmap_atomic_pfn(unsigned long pfn);
-extern struct page *kmap_atomic_to_page(const void *ptr);
 #endif
 
 #endif
diff --git a/kernel/arch/arm/include/asm/hugetlb.h b/kernel/arch/arm/include/asm/hugetlb.h
index 1f1b1cd11..7d26f6c4f 100644
--- a/kernel/arch/arm/include/asm/hugetlb.h
+++ b/kernel/arch/arm/include/asm/hugetlb.h
@@ -53,10 +53,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
-{
-}
-
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
@@ -67,15 +63,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte)
 	return pte_wrprotect(pte);
 }
 
-static inline int arch_prepare_hugepage(struct page *page)
-{
-	return 0;
-}
-
-static inline void arch_release_hugepage(struct page *page)
-{
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/kernel/arch/arm/include/asm/hw_irq.h b/kernel/arch/arm/include/asm/hw_irq.h
index af79da40a..9beb92914 100644
--- a/kernel/arch/arm/include/asm/hw_irq.h
+++ b/kernel/arch/arm/include/asm/hw_irq.h
@@ -11,12 +11,6 @@ static inline void ack_bad_irq(int irq)
 	pr_crit("unexpected IRQ trap at vector %02x\n", irq);
 }
 
-void set_irq_flags(unsigned int irq, unsigned int flags);
-
-#define IRQF_VALID	(1 << 0)
-#define IRQF_PROBE	(1 << 1)
-#define IRQF_NOAUTOEN	(1 << 2)
-
 #define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
 
 #endif
diff --git a/kernel/arch/arm/include/asm/io.h b/kernel/arch/arm/include/asm/io.h
index db58deb00..485982084 100644
--- a/kernel/arch/arm/include/asm/io.h
+++ b/kernel/arch/arm/include/asm/io.h
@@ -23,6 +23,7 @@
 
 #ifdef __KERNEL__
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/blk_types.h>
 #include <asm/byteorder.h>
@@ -73,17 +74,16 @@ void __raw_readsl(const volatile void __iomem *addr, void *data, int longlen);
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr)
-		     : "r" (val));
+		     : : "Q" (*(volatile u16 __force *)addr), "r" (val));
 }
 
 #define __raw_readw __raw_readw
 static inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
-	asm volatile("ldrh %1, %0"
-		     : "+Q" (*(volatile u16 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrh %0, %1"
+		     : "=r" (val)
+		     : "Q" (*(volatile u16 __force *)addr));
 	return val;
 }
 #endif
@@ -92,25 +92,23 @@ static inline u16 __raw_readw(const volatile void __iomem *addr)
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u8 __force *)addr), "r" (val));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
 	asm volatile("str %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr)
-		     : "r" (val));
+		     : : "Qo" (*(volatile u32 __force *)addr), "r" (val));
 }
 
 #define __raw_readb __raw_readb
 static inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile("ldrb %1, %0"
-		     : "+Qo" (*(volatile u8 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldrb %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u8 __force *)addr));
 	return val;
 }
 
@@ -118,9 +116,9 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 static inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile("ldr %1, %0"
-		     : "+Qo" (*(volatile u32 __force *)addr),
-		       "=r" (val));
+	asm volatile("ldr %0, %1"
+		     : "=r" (val)
+		     : "Qo" (*(volatile u32 __force *)addr));
 	return val;
 }
 
@@ -142,16 +140,11 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
@@ -319,24 +312,95 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 #define writesw(p,d,l)		__raw_writesw(p,d,l)
 #define writesl(p,d,l)		__raw_writesl(p,d,l)
 
+#ifndef __ARMBE__
+static inline void memset_io(volatile void __iomem *dst, unsigned c,
+	size_t count)
+{
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
+}
+#define memset_io(dst,c,count) memset_io(dst,c,count)
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
+	size_t count)
+{
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
+}
+#define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
+
+static inline void memcpy_toio(volatile void __iomem *to, const void *from,
+	size_t count)
+{
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
+}
+#define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
+
+#else
 #define memset_io(c,v,l)	_memset_io(c,(v),(l))
 #define memcpy_fromio(a,c,l)	_memcpy_fromio((a),c,(l))
 #define memcpy_toio(c,a,l)	_memcpy_toio(c,(a),(l))
+#endif
 
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
+ *
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
+ *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
  *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros
diff --git a/kernel/arch/arm/include/asm/irq.h b/kernel/arch/arm/include/asm/irq.h
index 53c15dec7..1bd9510de 100644
--- a/kernel/arch/arm/include/asm/irq.h
+++ b/kernel/arch/arm/include/asm/irq.h
@@ -35,6 +35,16 @@ extern void (*handle_arch_irq)(struct pt_regs *);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 #endif
 
+#ifdef CONFIG_SMP
+extern void arch_trigger_all_cpu_backtrace(bool);
+#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x)
+#endif
+
+static inline int nr_legacy_irqs(void)
+{
+	return NR_IRQS_LEGACY;
+}
+
 #endif
 
 #endif
diff --git a/kernel/arch/arm/include/asm/irqflags.h b/kernel/arch/arm/include/asm/irqflags.h
index 3b763d665..e6b70d9d0 100644
--- a/kernel/arch/arm/include/asm/irqflags.h
+++ b/kernel/arch/arm/include/asm/irqflags.h
@@ -20,6 +20,7 @@
 
 #if __LINUX_ARM_ARCH__ >= 6
 
+#define arch_local_irq_save arch_local_irq_save
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags;
@@ -31,6 +32,7 @@ static inline unsigned long arch_local_irq_save(void)
 	return flags;
 }
 
+#define arch_local_irq_enable arch_local_irq_enable
 static inline void arch_local_irq_enable(void)
 {
 	asm volatile(
@@ -40,6 +42,7 @@ static inline void arch_local_irq_enable(void)
 		: "memory", "cc");
 }
 
+#define arch_local_irq_disable arch_local_irq_disable
 static inline void arch_local_irq_disable(void)
 {
 	asm volatile(
@@ -51,11 +54,20 @@ static inline void arch_local_irq_disable(void)
 
 #define local_fiq_enable()  __asm__("cpsie f	@ __stf" : : : "memory", "cc")
 #define local_fiq_disable() __asm__("cpsid f	@ __clf" : : : "memory", "cc")
+
+#ifndef CONFIG_CPU_V7M
+#define local_abt_enable()  __asm__("cpsie a	@ __sta" : : : "memory", "cc")
+#define local_abt_disable() __asm__("cpsid a	@ __cla" : : : "memory", "cc")
+#else
+#define local_abt_enable()	do { } while (0)
+#define local_abt_disable()	do { } while (0)
+#endif
 #else
 
 /*
  * Save the current interrupt enable state & disable IRQs
  */
+#define arch_local_irq_save arch_local_irq_save
 static inline unsigned long arch_local_irq_save(void)
 {
 	unsigned long flags, temp;
@@ -73,6 +85,7 @@ static inline unsigned long arch_local_irq_save(void)
 /*
  * Enable IRQs
  */
+#define arch_local_irq_enable arch_local_irq_enable
 static inline void arch_local_irq_enable(void)
 {
 	unsigned long temp;
@@ -88,6 +101,7 @@ static inline void arch_local_irq_enable(void)
 /*
  * Disable IRQs
  */
+#define arch_local_irq_disable arch_local_irq_disable
 static inline void arch_local_irq_disable(void)
 {
 	unsigned long temp;
@@ -130,11 +144,14 @@ static inline void arch_local_irq_disable(void)
 	: "memory", "cc");					\
 	})
 
+#define local_abt_enable()	do { } while (0)
+#define local_abt_disable()	do { } while (0)
 #endif
 
 /*
  * Save the current interrupt enable state.
  */
+#define arch_local_save_flags arch_local_save_flags
 static inline unsigned long arch_local_save_flags(void)
 {
 	unsigned long flags;
@@ -147,6 +164,7 @@ static inline unsigned long arch_local_save_flags(void)
 /*
  * restore saved IRQ & FIQ state
  */
+#define arch_local_irq_restore arch_local_irq_restore
 static inline void arch_local_irq_restore(unsigned long flags)
 {
 	asm volatile(
@@ -156,10 +174,13 @@ static inline void arch_local_irq_restore(unsigned long flags)
 		: "memory", "cc");
 }
 
+#define arch_irqs_disabled_flags arch_irqs_disabled_flags
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return flags & IRQMASK_I_BIT;
 }
 
+#include <asm-generic/irqflags.h>
+
 #endif /* ifdef __KERNEL__ */
 #endif /* ifndef __ASM_ARM_IRQFLAGS_H */
diff --git a/kernel/arch/arm/include/asm/jump_label.h b/kernel/arch/arm/include/asm/jump_label.h
index 5f337dc5c..34f7b6980 100644
--- a/kernel/arch/arm/include/asm/jump_label.h
+++ b/kernel/arch/arm/include/asm/jump_label.h
@@ -4,23 +4,32 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <asm/unified.h>
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#ifdef CONFIG_THUMB2_KERNEL
-#define JUMP_LABEL_NOP	"nop.w"
-#else
-#define JUMP_LABEL_NOP	"nop"
-#endif
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 WASM(nop) "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
-		 JUMP_LABEL_NOP "\n\t"
+		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (key) :  : l_yes);
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes:
diff --git a/kernel/arch/arm/include/asm/kvm_arm.h b/kernel/arch/arm/include/asm/kvm_arm.h
index d995821f1..dc641ddf0 100644
--- a/kernel/arch/arm/include/asm/kvm_arm.h
+++ b/kernel/arch/arm/include/asm/kvm_arm.h
@@ -218,4 +218,24 @@
 #define HSR_DABT_CM		(1U << 8)
 #define HSR_DABT_EA		(1U << 9)
 
+#define kvm_arm_exception_type	\
+	{0, "RESET" }, 		\
+	{1, "UNDEFINED" },	\
+	{2, "SOFTWARE" },	\
+	{3, "PREF_ABORT" },	\
+	{4, "DATA_ABORT" },	\
+	{5, "IRQ" },		\
+	{6, "FIQ" },		\
+	{7, "HVC" }
+
+#define HSRECN(x) { HSR_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+	HSRECN(UNKNOWN), HSRECN(WFI), HSRECN(CP15_32), HSRECN(CP15_64), \
+	HSRECN(CP14_MR), HSRECN(CP14_LS), HSRECN(CP_0_13), HSRECN(CP10_ID), \
+	HSRECN(JAZELLE), HSRECN(BXJ), HSRECN(CP14_64), HSRECN(SVC_HYP), \
+	HSRECN(HVC), HSRECN(SMC), HSRECN(IABT), HSRECN(IABT_HYP), \
+	HSRECN(DABT), HSRECN(DABT_HYP)
+
+
 #endif /* __ARM_KVM_ARM_H__ */
diff --git a/kernel/arch/arm/include/asm/kvm_asm.h b/kernel/arch/arm/include/asm/kvm_asm.h
index 25410b2d8..194c91b61 100644
--- a/kernel/arch/arm/include/asm/kvm_asm.h
+++ b/kernel/arch/arm/include/asm/kvm_asm.h
@@ -23,7 +23,7 @@
 #define c0_MPIDR	1	/* MultiProcessor ID Register */
 #define c0_CSSELR	2	/* Cache Size Selection Register */
 #define c1_SCTLR	3	/* System Control Register */
-#define c1_ACTLR	4	/* Auxilliary Control Register */
+#define c1_ACTLR	4	/* Auxiliary Control Register */
 #define c1_CPACR	5	/* Coprocessor Access Control */
 #define c2_TTBR0	6	/* Translation Table Base Register 0 */
 #define c2_TTBR0_high	7	/* TTBR0 top 32 bits */
diff --git a/kernel/arch/arm/include/asm/kvm_emulate.h b/kernel/arch/arm/include/asm/kvm_emulate.h
index a9c80a2ea..3095df091 100644
--- a/kernel/arch/arm/include/asm/kvm_emulate.h
+++ b/kernel/arch/arm/include/asm/kvm_emulate.h
@@ -28,6 +28,18 @@
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
 
+static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
+					 u8 reg_num)
+{
+	return *vcpu_reg(vcpu, reg_num);
+}
+
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	*vcpu_reg(vcpu, reg_num) = val;
+}
+
 bool kvm_condition_valid(struct kvm_vcpu *vcpu);
 void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
diff --git a/kernel/arch/arm/include/asm/kvm_host.h b/kernel/arch/arm/include/asm/kvm_host.h
index d71607c16..6692982c9 100644
--- a/kernel/arch/arm/include/asm/kvm_host.h
+++ b/kernel/arch/arm/include/asm/kvm_host.h
@@ -29,21 +29,18 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
-#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
-#else
-#define KVM_MAX_VCPUS 0
-#endif
-
 #define KVM_USER_MEM_SLOTS 32
 #define KVM_PRIVATE_MEM_SLOTS 4
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_VCPU_MAX_FEATURES 2
 
 #include <kvm/arm_vgic.h>
 
+#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
+
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -129,7 +126,10 @@ struct kvm_vcpu_arch {
 	 * here.
 	 */
 
-	/* Don't run the guest on this vcpu */
+	/* vcpu power-off state */
+	bool power_off;
+
+	 /* Don't run the guest (internal implementation need) */
 	bool pause;
 
 	/* IO related fields */
@@ -148,6 +148,7 @@ struct kvm_vm_stat {
 
 struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 };
 
@@ -218,11 +219,6 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
-static inline void vgic_arch_setup(const struct vgic_params *vgic)
-{
-	BUG_ON(vgic->type != VGIC_V2);
-}
-
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
@@ -236,4 +232,9 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 
+static inline void kvm_arm_init_debug(void) {}
+static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+
 #endif /* __ARM_KVM_HOST_H__ */
diff --git a/kernel/arch/arm/include/asm/mach/arch.h b/kernel/arch/arm/include/asm/mach/arch.h
index 0406cb3f1..5c1ad11aa 100644
--- a/kernel/arch/arm/include/asm/mach/arch.h
+++ b/kernel/arch/arm/include/asm/mach/arch.h
@@ -47,11 +47,11 @@ struct machine_desc {
 	unsigned		l2c_aux_val;	/* L2 cache aux value	*/
 	unsigned		l2c_aux_mask;	/* L2 cache aux mask	*/
 	void			(*l2c_write_sec)(unsigned long, unsigned);
-	struct smp_operations	*smp;		/* SMP operations	*/
+	const struct smp_operations	*smp;	/* SMP operations	*/
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
 	void			(*dt_fixup)(void);
-	void			(*init_meminfo)(void);
+	long long		(*pv_fixup)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_early)(void);
diff --git a/kernel/arch/arm/include/asm/mach/irq.h b/kernel/arch/arm/include/asm/mach/irq.h
index 2092ee1e1..de4634b51 100644
--- a/kernel/arch/arm/include/asm/mach/irq.h
+++ b/kernel/arch/arm/include/asm/mach/irq.h
@@ -23,10 +23,10 @@ extern int show_fiq_list(struct seq_file *, int);
 /*
  * This is for easy migration, but should be changed in the source
  */
-#define do_bad_IRQ(irq,desc)				\
+#define do_bad_IRQ(desc)				\
 do {							\
 	raw_spin_lock(&desc->lock);			\
-	handle_bad_irq(irq, desc);			\
+	handle_bad_irq(desc);				\
 	raw_spin_unlock(&desc->lock);			\
 } while(0)
 
diff --git a/kernel/arch/arm/include/asm/mach/pci.h b/kernel/arch/arm/include/asm/mach/pci.h
index 28b9bb359..0070e8520 100644
--- a/kernel/arch/arm/include/asm/mach/pci.h
+++ b/kernel/arch/arm/include/asm/mach/pci.h
@@ -19,9 +19,7 @@ struct pci_bus;
 struct device;
 
 struct hw_pci {
-#ifdef CONFIG_PCI_MSI
 	struct msi_controller *msi_ctrl;
-#endif
 	struct pci_ops	*ops;
 	int		nr_controllers;
 	void		**private_data;
@@ -42,9 +40,6 @@ struct hw_pci {
  * Per-controller structure
  */
 struct pci_sys_data {
-#ifdef CONFIG_PCI_MSI
-	struct msi_controller *msi_ctrl;
-#endif
 	struct list_head node;
 	int		busnr;		/* primary bus number			*/
 	u64		mem_offset;	/* bus->cpu memory mapping offset	*/
@@ -57,12 +52,6 @@ struct pci_sys_data {
 	u8		(*swizzle)(struct pci_dev *, u8 *);
 					/* IRQ mapping				*/
 	int		(*map_irq)(const struct pci_dev *, u8, u8);
-					/* Resource alignement requirements	*/
-	resource_size_t (*align_resource)(struct pci_dev *dev,
-					  const struct resource *res,
-					  resource_size_t start,
-					  resource_size_t size,
-					  resource_size_t align);
 	void		*private_data;	/* platform controller private data	*/
 };
 
diff --git a/kernel/arch/arm/include/asm/mcpm.h b/kernel/arch/arm/include/asm/mcpm.h
index 50b378f59..acd4983d9 100644
--- a/kernel/arch/arm/include/asm/mcpm.h
+++ b/kernel/arch/arm/include/asm/mcpm.h
@@ -137,17 +137,12 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
 /**
  * mcpm_cpu_suspend - bring the calling CPU in a suspended state
  *
- * @expected_residency: duration in microseconds the CPU is expected
- *			to remain suspended, or 0 if unknown/infinity.
- *
- * The calling CPU is suspended.  The expected residency argument is used
- * as a hint by the platform specific backend to implement the appropriate
- * sleep state level according to the knowledge it has on wake-up latency
- * for the given hardware.
+ * The calling CPU is suspended.  This is similar to mcpm_cpu_power_down()
+ * except for possible extra platform specific configuration steps to allow
+ * an asynchronous wake-up e.g. with a pending interrupt.
  *
  * If this CPU is found to be the "last man standing" in the cluster
- * then the cluster may be prepared for power-down too, if the expected
- * residency makes it worthwhile.
+ * then the cluster may be prepared for power-down too.
  *
  * This must be called with interrupts disabled.
  *
@@ -157,7 +152,7 @@ int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
  * This will return if mcpm_platform_register() has not been called
  * previously in which case the caller should take appropriate action.
  */
-void mcpm_cpu_suspend(u64 expected_residency);
+void mcpm_cpu_suspend(void);
 
 /**
  * mcpm_cpu_powered_up - housekeeping workafter a CPU has been powered up
@@ -234,12 +229,6 @@ struct mcpm_platform_ops {
 	void (*cpu_is_up)(unsigned int cpu, unsigned int cluster);
 	void (*cluster_is_up)(unsigned int cluster);
 	int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
-
-	/* deprecated callbacks */
-	int (*power_up)(unsigned int cpu, unsigned int cluster);
-	void (*power_down)(void);
-	void (*suspend)(u64);
-	void (*powered_up)(void);
 };
 
 /**
@@ -251,35 +240,6 @@ struct mcpm_platform_ops {
  */
 int __init mcpm_platform_register(const struct mcpm_platform_ops *ops);
 
-/* Synchronisation structures for coordinating safe cluster setup/teardown: */
-
-/*
- * When modifying this structure, make sure you update the MCPM_SYNC_ defines
- * to match.
- */
-struct mcpm_sync_struct {
-	/* individual CPU states */
-	struct {
-		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
-	} cpus[MAX_CPUS_PER_CLUSTER];
-
-	/* cluster state */
-	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
-
-	/* inbound-side state */
-	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
-};
-
-struct sync_struct {
-	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
-};
-
-void __mcpm_cpu_going_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster);
-void __mcpm_outbound_leave_critical(unsigned int cluster, int state);
-bool __mcpm_outbound_enter_critical(unsigned int this_cpu, unsigned int cluster);
-int __mcpm_cluster_state(unsigned int cluster);
-
 /**
  * mcpm_sync_init - Initialize the cluster synchronization support
  *
@@ -318,6 +278,29 @@ int __init mcpm_loopback(void (*cache_disable)(void));
 
 void __init mcpm_smp_set_ops(void);
 
+/*
+ * Synchronisation structures for coordinating safe cluster setup/teardown.
+ * This is private to the MCPM core code and shared between C and assembly.
+ * When modifying this structure, make sure you update the MCPM_SYNC_ defines
+ * to match.
+ */
+struct mcpm_sync_struct {
+	/* individual CPU states */
+	struct {
+		s8 cpu __aligned(__CACHE_WRITEBACK_GRANULE);
+	} cpus[MAX_CPUS_PER_CLUSTER];
+
+	/* cluster state */
+	s8 cluster __aligned(__CACHE_WRITEBACK_GRANULE);
+
+	/* inbound-side state */
+	s8 inbound __aligned(__CACHE_WRITEBACK_GRANULE);
+};
+
+struct sync_struct {
+	struct mcpm_sync_struct clusters[MAX_NR_CLUSTERS];
+};
+
 #else
 
 /* 
diff --git a/kernel/arch/arm/include/asm/memory.h b/kernel/arch/arm/include/asm/memory.h
index 184def0e1..c79b57bf7 100644
--- a/kernel/arch/arm/include/asm/memory.h
+++ b/kernel/arch/arm/include/asm/memory.h
@@ -18,8 +18,6 @@
 #include <linux/types.h>
 #include <linux/sizes.h>
 
-#include <asm/cache.h>
-
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
 #endif
@@ -78,10 +76,12 @@
  */
 #define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
  * Allow 16MB-aligned ioremap pages
  */
 #define IOREMAP_MAX_ORDER	24
+#endif
 
 #else /* CONFIG_MMU */
 
@@ -121,32 +121,12 @@
 #endif
 
 /*
- * Convert a physical address to a Page Frame Number and back
- */
-#define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
-#define	__pfn_to_phys(pfn)	((phys_addr_t)(pfn) << PAGE_SHIFT)
-
-/*
  * Convert a page to/from a physical address
  */
 #define page_to_phys(page)	(__pfn_to_phys(page_to_pfn(page)))
 #define phys_to_page(phys)	(pfn_to_page(__phys_to_pfn(phys)))
 
 /*
- * Minimum guaranted alignment in pgd_alloc().  The page table pointers passed
- * around in head.S and proc-*.S are shifted by this amount, in order to
- * leave spare high bits for systems with physical address extension.  This
- * does not fully accomodate the 40-bit addressing capability of ARM LPAE, but
- * gives us about 38-bits or so.
- */
-#ifdef CONFIG_ARM_LPAE
-#define ARCH_PGD_SHIFT		L1_CACHE_SHIFT
-#else
-#define ARCH_PGD_SHIFT		0
-#endif
-#define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
-
-/*
  * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
  * memory.  This is used for XIP and NoMMU kernels, and on platforms that don't
  * have CONFIG_ARM_PATCH_PHYS_VIRT. Assembly code must always use
@@ -291,7 +271,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
 extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
 
@@ -302,7 +282,7 @@ extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
  */
 static inline phys_addr_t __virt_to_idmap(unsigned long x)
 {
-	if (arch_virt_to_idmap)
+	if (IS_ENABLED(CONFIG_MMU) && arch_virt_to_idmap)
 		return arch_virt_to_idmap(x);
 	else
 		return __virt_to_phys(x);
diff --git a/kernel/arch/arm/include/asm/module.h b/kernel/arch/arm/include/asm/module.h
index ed690c49e..e358b7966 100644
--- a/kernel/arch/arm/include/asm/module.h
+++ b/kernel/arch/arm/include/asm/module.h
@@ -16,11 +16,21 @@ enum {
 	ARM_SEC_UNLIKELY,
 	ARM_SEC_MAX,
 };
+#endif
 
 struct mod_arch_specific {
+#ifdef CONFIG_ARM_UNWIND
 	struct unwind_table *unwind[ARM_SEC_MAX];
-};
 #endif
+#ifdef CONFIG_ARM_MODULE_PLTS
+	struct elf32_shdr   *core_plt;
+	struct elf32_shdr   *init_plt;
+	int		    core_plt_count;
+	int		    init_plt_count;
+#endif
+};
+
+u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val);
 
 /*
  * Add the ARM architecture version to the version magic string
diff --git a/kernel/arch/arm/include/asm/outercache.h b/kernel/arch/arm/include/asm/outercache.h
index 563b92fc2..c2bf24f40 100644
--- a/kernel/arch/arm/include/asm/outercache.h
+++ b/kernel/arch/arm/include/asm/outercache.h
@@ -129,21 +129,4 @@ static inline void outer_resume(void) { }
 
 #endif
 
-#ifdef CONFIG_OUTER_CACHE_SYNC
-/**
- * outer_sync - perform a sync point for outer cache
- *
- * Ensure that all outer cache operations are complete and any store
- * buffers are drained.
- */
-static inline void outer_sync(void)
-{
-	if (outer_cache.sync)
-		outer_cache.sync();
-}
-#else
-static inline void outer_sync(void)
-{ }
-#endif
-
 #endif	/* __ASM_OUTERCACHE_H */
diff --git a/kernel/arch/arm/include/asm/pci.h b/kernel/arch/arm/include/asm/pci.h
index 585dc33a7..a5635444c 100644
--- a/kernel/arch/arm/include/asm/pci.h
+++ b/kernel/arch/arm/include/asm/pci.h
@@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus)
  */
 #define PCI_DMA_BUS_IS_PHYS     (1)
 
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#endif
-
 #define HAVE_PCI_MMAP
 extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
                                enum pci_mmap_state mmap_state, int write_combine);
diff --git a/kernel/arch/arm/include/asm/perf_event.h b/kernel/arch/arm/include/asm/perf_event.h
index d9cf138fd..4f9dec489 100644
--- a/kernel/arch/arm/include/asm/perf_event.h
+++ b/kernel/arch/arm/include/asm/perf_event.h
@@ -19,4 +19,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
 #endif
 
+#define perf_arch_fetch_caller_regs(regs, __ip) { \
+	(regs)->ARM_pc = (__ip); \
+	(regs)->ARM_fp = (unsigned long) __builtin_frame_address(0); \
+	(regs)->ARM_sp = current_stack_pointer; \
+	(regs)->ARM_cpsr = SVC_MODE; \
+}
+
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/kernel/arch/arm/include/asm/pgtable-2level-hwdef.h b/kernel/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5e68278e9..d0131ee6f 100644
--- a/kernel/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/kernel/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -23,6 +23,7 @@
 #define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_DOMAIN_MASK		PMD_DOMAIN(0x0f)
 #define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
 /*
  *   - section
diff --git a/kernel/arch/arm/include/asm/pgtable-2level.h b/kernel/arch/arm/include/asm/pgtable-2level.h
index bfd662e49..aeddd28b3 100644
--- a/kernel/arch/arm/include/asm/pgtable-2level.h
+++ b/kernel/arch/arm/include/asm/pgtable-2level.h
@@ -129,7 +129,36 @@
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
diff --git a/kernel/arch/arm/include/asm/pgtable.h b/kernel/arch/arm/include/asm/pgtable.h
index f40354198..348caabb7 100644
--- a/kernel/arch/arm/include/asm/pgtable.h
+++ b/kernel/arch/arm/include/asm/pgtable.h
@@ -43,7 +43,7 @@
  */
 #define VMALLOC_OFFSET		(8*1024*1024)
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#define VMALLOC_END		0xff000000UL
+#define VMALLOC_END		0xff800000UL
 
 #define LIBRARY_TEXT_START	0x0c000000
 
diff --git a/kernel/arch/arm/include/asm/pmu.h b/kernel/arch/arm/include/asm/pmu.h
deleted file mode 100644
index 675e4ab79..000000000
--- a/kernel/arch/arm/include/asm/pmu.h
+++ /dev/null
@@ -1,163 +0,0 @@
-/*
- *  linux/arch/arm/include/asm/pmu.h
- *
- *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
- *
- * 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 __ARM_PMU_H__
-#define __ARM_PMU_H__
-
-#include <linux/interrupt.h>
-#include <linux/perf_event.h>
-
-#include <asm/cputype.h>
-
-/*
- * struct arm_pmu_platdata - ARM PMU platform data
- *
- * @handle_irq: an optional handler which will be called from the
- *	interrupt and passed the address of the low level handler,
- *	and can be used to implement any platform specific handling
- *	before or after calling it.
- * @runtime_resume: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_get().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called once.
- * @runtime_suspend: an optional handler which will be called by the
- *	runtime PM framework following a call to pm_runtime_put().
- *	Note that if pm_runtime_get() is called more than once in
- *	succession this handler will only be called following the
- *	final call to pm_runtime_put() that actually disables the
- *	hardware.
- */
-struct arm_pmu_platdata {
-	irqreturn_t (*handle_irq)(int irq, void *dev,
-				  irq_handler_t pmu_handler);
-	int (*runtime_resume)(struct device *dev);
-	int (*runtime_suspend)(struct device *dev);
-};
-
-#ifdef CONFIG_HW_PERF_EVENTS
-
-/*
- * The ARMv7 CPU PMU supports up to 32 event counters.
- */
-#define ARMPMU_MAX_HWEVENTS		32
-
-#define HW_OP_UNSUPPORTED		0xFFFF
-#define C(_x)				PERF_COUNT_HW_CACHE_##_x
-#define CACHE_OP_UNSUPPORTED		0xFFFF
-
-#define PERF_MAP_ALL_UNSUPPORTED					\
-	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
-
-#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
-[0 ... C(MAX) - 1] = {							\
-	[0 ... C(OP_MAX) - 1] = {					\
-		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
-	},								\
-}
-
-/* The events for a given PMU register set. */
-struct pmu_hw_events {
-	/*
-	 * The events that are active on the PMU for the given index.
-	 */
-	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
-
-	/*
-	 * A 1 bit for an index indicates that the counter is being used for
-	 * an event. A 0 means that the counter can be used.
-	 */
-	DECLARE_BITMAP(used_mask, ARMPMU_MAX_HWEVENTS);
-
-	/*
-	 * Hardware lock to serialize accesses to PMU registers. Needed for the
-	 * read/modify/write sequences.
-	 */
-	raw_spinlock_t		pmu_lock;
-
-	/*
-	 * When using percpu IRQs, we need a percpu dev_id. Place it here as we
-	 * already have to allocate this struct per cpu.
-	 */
-	struct arm_pmu		*percpu_pmu;
-};
-
-struct arm_pmu {
-	struct pmu	pmu;
-	cpumask_t	active_irqs;
-	int		*irq_affinity;
-	char		*name;
-	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
-	void		(*enable)(struct perf_event *event);
-	void		(*disable)(struct perf_event *event);
-	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
-					 struct perf_event *event);
-	void		(*clear_event_idx)(struct pmu_hw_events *hw_events,
-					 struct perf_event *event);
-	int		(*set_event_filter)(struct hw_perf_event *evt,
-					    struct perf_event_attr *attr);
-	u32		(*read_counter)(struct perf_event *event);
-	void		(*write_counter)(struct perf_event *event, u32 val);
-	void		(*start)(struct arm_pmu *);
-	void		(*stop)(struct arm_pmu *);
-	void		(*reset)(void *);
-	int		(*request_irq)(struct arm_pmu *, irq_handler_t handler);
-	void		(*free_irq)(struct arm_pmu *);
-	int		(*map_event)(struct perf_event *event);
-	int		num_events;
-	atomic_t	active_events;
-	struct mutex	reserve_mutex;
-	u64		max_period;
-	struct platform_device	*plat_device;
-	struct pmu_hw_events	__percpu *hw_events;
-	struct notifier_block	hotplug_nb;
-};
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-extern const struct dev_pm_ops armpmu_dev_pm_ops;
-
-int armpmu_register(struct arm_pmu *armpmu, int type);
-
-u64 armpmu_event_update(struct perf_event *event);
-
-int armpmu_event_set_period(struct perf_event *event);
-
-int armpmu_map_event(struct perf_event *event,
-		     const unsigned (*event_map)[PERF_COUNT_HW_MAX],
-		     const unsigned (*cache_map)[PERF_COUNT_HW_CACHE_MAX]
-						[PERF_COUNT_HW_CACHE_OP_MAX]
-						[PERF_COUNT_HW_CACHE_RESULT_MAX],
-		     u32 raw_event_mask);
-
-struct pmu_probe_info {
-	unsigned int cpuid;
-	unsigned int mask;
-	int (*init)(struct arm_pmu *);
-};
-
-#define PMU_PROBE(_cpuid, _mask, _fn)	\
-{					\
-	.cpuid = (_cpuid),		\
-	.mask = (_mask),		\
-	.init = (_fn),			\
-}
-
-#define ARM_PMU_PROBE(_cpuid, _fn) \
-	PMU_PROBE(_cpuid, ARM_CPU_PART_MASK, _fn)
-
-#define ARM_PMU_XSCALE_MASK	((0xff << 24) | ARM_CPU_XSCALE_ARCH_MASK)
-
-#define XSCALE_PMU_PROBE(_version, _fn) \
-	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
-
-#endif /* CONFIG_HW_PERF_EVENTS */
-
-#endif /* __ARM_PMU_H__ */
diff --git a/kernel/arch/arm/include/asm/proc-fns.h b/kernel/arch/arm/include/asm/proc-fns.h
index 5324c1112..8877ad5ff 100644
--- a/kernel/arch/arm/include/asm/proc-fns.h
+++ b/kernel/arch/arm/include/asm/proc-fns.h
@@ -125,13 +125,6 @@ extern void cpu_resume(void);
 		ttbr;						\
 	})
 
-#define cpu_set_ttbr(nr, val)					\
-	do {							\
-		u64 ttbr = val;					\
-		__asm__("mcrr	p15, " #nr ", %Q0, %R0, c2"	\
-			: : "r" (ttbr));			\
-	} while (0)
-
 #define cpu_get_pgd()	\
 	({						\
 		u64 pg = cpu_get_ttbr(0);		\
diff --git a/kernel/arch/arm/include/asm/psci.h b/kernel/arch/arm/include/asm/psci.h
index c25ef3ec6..b4c6d9936 100644
--- a/kernel/arch/arm/include/asm/psci.h
+++ b/kernel/arch/arm/include/asm/psci.h
@@ -14,34 +14,11 @@
 #ifndef __ASM_ARM_PSCI_H
 #define __ASM_ARM_PSCI_H
 
-#define PSCI_POWER_STATE_TYPE_STANDBY		0
-#define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
-
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
-
-struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
-	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
-	int (*migrate)(unsigned long cpuid);
-	int (*affinity_info)(unsigned long target_affinity,
-			unsigned long lowest_affinity_level);
-	int (*migrate_info_type)(void);
-};
-
-extern struct psci_operations psci_ops;
 extern struct smp_operations psci_smp_ops;
 
-#ifdef CONFIG_ARM_PSCI
-int psci_init(void);
+#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI)
 bool psci_smp_available(void);
 #else
-static inline int psci_init(void) { return 0; }
 static inline bool psci_smp_available(void) { return false; }
 #endif
 
diff --git a/kernel/arch/arm/include/asm/smp.h b/kernel/arch/arm/include/asm/smp.h
index 18f5a5541..3d6dc8b46 100644
--- a/kernel/arch/arm/include/asm/smp.h
+++ b/kernel/arch/arm/include/asm/smp.h
@@ -61,7 +61,7 @@ asmlinkage void secondary_start_kernel(void);
 struct secondary_data {
 	union {
 		unsigned long mpu_rgn_szr;
-		unsigned long pgdir;
+		u64 pgdir;
 	};
 	unsigned long swapper_pg_dir;
 	void *stack;
@@ -69,11 +69,11 @@ struct secondary_data {
 extern struct secondary_data secondary_data;
 extern volatile int pen_release;
 extern void secondary_startup(void);
+extern void secondary_startup_arm(void);
 
 extern int __cpu_disable(void);
 
 extern void __cpu_die(unsigned int cpu);
-extern void cpu_die(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
@@ -104,6 +104,7 @@ struct smp_operations {
 #ifdef CONFIG_HOTPLUG_CPU
 	int  (*cpu_kill)(unsigned int cpu);
 	void (*cpu_die)(unsigned int cpu);
+	bool  (*cpu_can_disable)(unsigned int cpu);
 	int  (*cpu_disable)(unsigned int cpu);
 #endif
 #endif
@@ -111,7 +112,7 @@ struct smp_operations {
 
 struct of_cpu_method {
 	const char *method;
-	struct smp_operations *ops;
+	const struct smp_operations *ops;
 };
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
@@ -121,6 +122,6 @@ struct of_cpu_method {
 /*
  * set platform specific SMP operations
  */
-extern void smp_set_ops(struct smp_operations *);
+extern void smp_set_ops(const struct smp_operations *);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/kernel/arch/arm/include/asm/smp_plat.h b/kernel/arch/arm/include/asm/smp_plat.h
index 993e5224d..f9080717f 100644
--- a/kernel/arch/arm/include/asm/smp_plat.h
+++ b/kernel/arch/arm/include/asm/smp_plat.h
@@ -107,4 +107,13 @@ static inline u32 mpidr_hash_size(void)
 extern int platform_can_secondary_boot(void);
 extern int platform_can_cpu_hotplug(void);
 
+#ifdef CONFIG_HOTPLUG_CPU
+extern int platform_can_hotplug_cpu(unsigned int cpu);
+#else
+static inline int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/kernel/arch/arm/include/asm/suspend.h b/kernel/arch/arm/include/asm/suspend.h
index cd20029bc..6c7182f32 100644
--- a/kernel/arch/arm/include/asm/suspend.h
+++ b/kernel/arch/arm/include/asm/suspend.h
@@ -7,6 +7,7 @@ struct sleep_save_sp {
 };
 
 extern void cpu_resume(void);
+extern void cpu_resume_arm(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
 #endif
diff --git a/kernel/arch/arm/include/asm/switch_to.h b/kernel/arch/arm/include/asm/switch_to.h
index f3e3d800c..c96208460 100644
--- a/kernel/arch/arm/include/asm/switch_to.h
+++ b/kernel/arch/arm/include/asm/switch_to.h
@@ -17,7 +17,9 @@ switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
  * CPU.
  */
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
-#define finish_arch_switch(prev)	dsb(ish)
+#define __complete_pending_tlbi()	dsb(ish)
+#else
+#define __complete_pending_tlbi()
 #endif
 
 /*
@@ -29,6 +31,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 
 #define switch_to(prev,next,last)					\
 do {									\
+	__complete_pending_tlbi();					\
 	switch_kmaps(prev, next);					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
diff --git a/kernel/arch/arm/include/asm/system_info.h b/kernel/arch/arm/include/asm/system_info.h
index 720ea0320..3860cbd40 100644
--- a/kernel/arch/arm/include/asm/system_info.h
+++ b/kernel/arch/arm/include/asm/system_info.h
@@ -17,6 +17,7 @@
 
 /* information about the system we're running on */
 extern unsigned int system_rev;
+extern const char *system_serial;
 extern unsigned int system_serial_low;
 extern unsigned int system_serial_high;
 extern unsigned int mem_fclk_21285;
diff --git a/kernel/arch/arm/include/asm/thread_info.h b/kernel/arch/arm/include/asm/thread_info.h
index b5a616376..1f36a4ecc 100644
--- a/kernel/arch/arm/include/asm/thread_info.h
+++ b/kernel/arch/arm/include/asm/thread_info.h
@@ -25,7 +25,6 @@
 struct task_struct;
 
 #include <asm/types.h>
-#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 
@@ -75,9 +74,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -137,23 +133,19 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 
 /*
  * thread information flags:
- *  TIF_SYSCALL_TRACE	- syscall trace active
- *  TIF_SYSCAL_AUDIT	- syscall auditing active
- *  TIF_SIGPENDING	- signal pending
- *  TIF_NEED_RESCHED	- rescheduling necessary
- *  TIF_NOTIFY_RESUME	- callback before returning to user
  *  TIF_USEDFPU		- FPU was used by this task this quantum (SMP)
  *  TIF_POLLING_NRFLAG	- true if poll_idle() is polling TIF_NEED_RESCHED
  */
-#define TIF_SIGPENDING		0
-#define TIF_NEED_RESCHED	1
+#define TIF_SIGPENDING		0	/* signal pending */
+#define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
-#define TIF_NEED_RESCHED_LAZY	3
-#define TIF_UPROBE		7
-#define TIF_SYSCALL_TRACE	8
-#define TIF_SYSCALL_AUDIT	9
-#define TIF_SYSCALL_TRACEPOINT	10
-#define TIF_SECCOMP		11	/* seccomp syscall filtering active */
+#define TIF_UPROBE		3	/* breakpointed or singlestepping */
+#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
+#define TIF_NEED_RESCHED_LAZY	7
+
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
@@ -178,7 +170,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_NEED_RESCHED_LAZY)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/kernel/arch/arm/include/asm/topology.h b/kernel/arch/arm/include/asm/topology.h
index 2fe85fff5..370f7a732 100644
--- a/kernel/arch/arm/include/asm/topology.h
+++ b/kernel/arch/arm/include/asm/topology.h
@@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_physical_package_id(cpu)	(cpu_topology[cpu].socket_id)
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
-#define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/kernel/arch/arm/include/asm/uaccess.h b/kernel/arch/arm/include/asm/uaccess.h
index 74b17d09e..35c9db857 100644
--- a/kernel/arch/arm/include/asm/uaccess.h
+++ b/kernel/arch/arm/include/asm/uaccess.h
@@ -50,6 +50,35 @@ struct exception_table_entry
 extern int fixup_exception(struct pt_regs *regs);
 
 /*
+ * These two functions allow hooking accesses to userspace to increase
+ * system integrity by ensuring that the kernel can not inadvertantly
+ * perform such accesses (eg, via list poison values) which could then
+ * be exploited for priviledge escalation.
+ */
+static inline unsigned int uaccess_save_and_enable(void)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	unsigned int old_domain = get_domain();
+
+	/* Set the current domain access to permit user accesses */
+	set_domain((old_domain & ~domain_mask(DOMAIN_USER)) |
+		   domain_val(DOMAIN_USER, DOMAIN_CLIENT));
+
+	return old_domain;
+#else
+	return 0;
+#endif
+}
+
+static inline void uaccess_restore(unsigned int flags)
+{
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/* Restore the user access mask */
+	set_domain(flags);
+#endif
+}
+
+/*
  * These two are intentionally not defined anywhere - if the kernel
  * code generates any references to them, that's a bug.
  */
@@ -165,6 +194,7 @@ extern int __get_user_64t_4(void *);
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -192,6 +222,7 @@ extern int __get_user_64t_4(void *);
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +255,7 @@ extern int __put_user_8(void *, unsigned long long);
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			__put_user_x(__r2, __p, __e, __l, 1);		\
@@ -239,6 +271,7 @@ extern int __put_user_8(void *, unsigned long long);
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,20 +333,23 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
+	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
+	uaccess_restore(__ua_flags);					\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
-#define __get_user_asm_byte(x, addr, err)			\
+#define __get_user_asm(x, addr, err, instr)			\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(ldrb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -329,6 +365,9 @@ do {									\
 	: "r" (addr), "i" (-EFAULT)				\
 	: "cc")
 
+#define __get_user_asm_byte(x, addr, err)			\
+	__get_user_asm(x, addr, err, ldrb)
+
 #ifndef __ARMEB__
 #define __get_user_asm_half(x, __gu_addr, err)			\
 ({								\
@@ -348,22 +387,7 @@ do {									\
 #endif
 
 #define __get_user_asm_word(x, addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(ldr) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	mov	%1, #0\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
+	__get_user_asm(x, addr, err, ldr)
 
 #define __put_user(x, ptr)						\
 ({									\
@@ -381,9 +405,11 @@ do {									\
 #define __put_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	unsigned int __ua_flags;					\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
 	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
@@ -391,11 +417,12 @@ do {									\
 	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
 	default: __put_user_bad();					\
 	}								\
+	uaccess_restore(__ua_flags);					\
 } while (0)
 
-#define __put_user_asm_byte(x, __pu_addr, err)			\
+#define __put_user_asm(x, __pu_addr, err, instr)		\
 	__asm__ __volatile__(					\
-	"1:	" TUSER(strb) "	%1,[%2],#0\n"			\
+	"1:	" TUSER(instr) " %1, [%2], #0\n"		\
 	"2:\n"							\
 	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
@@ -410,6 +437,9 @@ do {									\
 	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
 	: "cc")
 
+#define __put_user_asm_byte(x, __pu_addr, err)			\
+	__put_user_asm(x, __pu_addr, err, strb)
+
 #ifndef __ARMEB__
 #define __put_user_asm_half(x, __pu_addr, err)			\
 ({								\
@@ -427,21 +457,7 @@ do {									\
 #endif
 
 #define __put_user_asm_word(x, __pu_addr, err)			\
-	__asm__ __volatile__(					\
-	"1:	" TUSER(str) "	%1,[%2],#0\n"			\
-	"2:\n"							\
-	"	.pushsection .text.fixup,\"ax\"\n"		\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	b	2b\n"					\
-	"	.popsection\n"					\
-	"	.pushsection __ex_table,\"a\"\n"		\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.popsection"					\
-	: "+r" (err)						\
-	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
-	: "cc")
+	__put_user_asm(x, __pu_addr, err, str)
 
 #ifndef __ARMEB__
 #define	__reg_oper0	"%R2"
@@ -474,11 +490,50 @@ do {									\
 
 
 #ifdef CONFIG_MMU
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+arm_copy_from_user(void *to, const void __user *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_from_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+__copy_to_user_std(void __user *to, const void *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+#ifndef CONFIG_UACCESS_WITH_MEMCPY
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+#else
+	return arm_copy_to_user(to, from, n);
+#endif
+}
+
+extern unsigned long __must_check
+arm_clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+__clear_user_std(void __user *addr, unsigned long n);
+
+static inline unsigned long __must_check
+__clear_user(void __user *addr, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_clear_user(addr, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
 #else
 #define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
@@ -511,6 +566,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
+/* These are from lib/ code, and use __get_user() and friends */
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
 extern __must_check long strlen_user(const char __user *str);
diff --git a/kernel/arch/arm/include/asm/unified.h b/kernel/arch/arm/include/asm/unified.h
index 200f9a7cd..a91ae4996 100644
--- a/kernel/arch/arm/include/asm/unified.h
+++ b/kernel/arch/arm/include/asm/unified.h
@@ -45,7 +45,6 @@
 #define THUMB(x...)	x
 #ifdef __ASSEMBLY__
 #define W(instr)	instr.w
-#define BSYM(sym)	sym + 1
 #else
 #define WASM(instr)	#instr ".w"
 #endif
@@ -59,7 +58,6 @@
 #define THUMB(x...)
 #ifdef __ASSEMBLY__
 #define W(instr)	instr
-#define BSYM(sym)	sym
 #else
 #define WASM(instr)	#instr
 #endif
diff --git a/kernel/arch/arm/include/asm/unistd.h b/kernel/arch/arm/include/asm/unistd.h
index 32640c431..7b84657fb 100644
--- a/kernel/arch/arm/include/asm/unistd.h
+++ b/kernel/arch/arm/include/asm/unistd.h
@@ -19,14 +19,7 @@
  * This may need to be greater than __NR_last_syscall+1 in order to
  * account for the padding in the syscall table
  */
-#define __NR_syscalls  (388)
-
-/*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-#define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
+#define __NR_syscalls  (392)
 
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/kernel/arch/arm/include/asm/vfp.h b/kernel/arch/arm/include/asm/vfp.h
index ee5f30842..22e414056 100644
--- a/kernel/arch/arm/include/asm/vfp.h
+++ b/kernel/arch/arm/include/asm/vfp.h
@@ -5,6 +5,9 @@
  * First, the standard VFP set.
  */
 
+#ifndef __ASM_VFP_H
+#define __ASM_VFP_H
+
 #define FPSID			cr0
 #define FPSCR			cr1
 #define MVFR1			cr6
@@ -87,3 +90,9 @@
 #define VFPOPDESC_UNUSED_BIT	(24)
 #define VFPOPDESC_UNUSED_MASK	(0xFF << VFPOPDESC_UNUSED_BIT)
 #define VFPOPDESC_OPDESC_MASK	(~(VFPOPDESC_LENGTH_MASK | VFPOPDESC_UNUSED_MASK))
+
+#ifndef __ASSEMBLY__
+void vfp_disable(void);
+#endif
+
+#endif /* __ASM_VFP_H */
diff --git a/kernel/arch/arm/include/asm/xen/events.h b/kernel/arch/arm/include/asm/xen/events.h
index 8b1f37bfe..71e473d05 100644
--- a/kernel/arch/arm/include/asm/xen/events.h
+++ b/kernel/arch/arm/include/asm/xen/events.h
@@ -20,4 +20,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs)
 							    atomic64_t,	\
 							    counter), (val))
 
+/* Rebind event channel is supported by default */
+static inline bool xen_support_evtchn_rebind(void)
+{
+	return true;
+}
+
 #endif /* _ASM_ARM_XEN_EVENTS_H */
diff --git a/kernel/arch/arm/include/asm/xen/hypervisor.h b/kernel/arch/arm/include/asm/xen/hypervisor.h
index 1317ee40f..95251512e 100644
--- a/kernel/arch/arm/include/asm/xen/hypervisor.h
+++ b/kernel/arch/arm/include/asm/xen/hypervisor.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_ARM_XEN_HYPERVISOR_H
 #define _ASM_ARM_XEN_HYPERVISOR_H
 
+#include <linux/init.h>
+
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
@@ -18,4 +20,20 @@ static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 
 extern struct dma_map_ops *xen_dma_ops;
 
+#ifdef CONFIG_XEN
+void __init xen_early_init(void);
+#else
+static inline void xen_early_init(void) { return; }
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+static inline void xen_arch_register_cpu(int num)
+{
+}
+
+static inline void xen_arch_unregister_cpu(int num)
+{
+}
+#endif
+
 #endif /* _ASM_ARM_XEN_HYPERVISOR_H */
diff --git a/kernel/arch/arm/include/asm/xen/page-coherent.h b/kernel/arch/arm/include/asm/xen/page-coherent.h
index efd562412..9408a994c 100644
--- a/kernel/arch/arm/include/asm/xen/page-coherent.h
+++ b/kernel/arch/arm/include/asm/xen/page-coherent.h
@@ -35,11 +35,22 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	bool local = PFN_DOWN(dev_addr) == page_to_pfn(page);
-	/* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise
-	 * is a foreign page grant-mapped in dom0. If the page is local we
-	 * can safely call the native dma_ops function, otherwise we call
-	 * the xen specific function. */
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
 	if (local)
 		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 	else
@@ -51,10 +62,14 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		struct dma_attrs *attrs)
 {
 	unsigned long pfn = PFN_DOWN(handle);
-	/* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will
-	 * always return false. If the page is local we can safely call the
-	 * native dma_ops function, otherwise we call the xen specific
-	 * function. */
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
 	if (pfn_valid(pfn)) {
 		if (__generic_dma_ops(hwdev)->unmap_page)
 			__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
diff --git a/kernel/arch/arm/include/asm/xen/page.h b/kernel/arch/arm/include/asm/xen/page.h
index 0b579b2f4..415dbc6e4 100644
--- a/kernel/arch/arm/include/asm/xen/page.h
+++ b/kernel/arch/arm/include/asm/xen/page.h
@@ -12,10 +12,6 @@
 #include <xen/interface/grant_table.h>
 
 #define phys_to_machine_mapping_valid(pfn) (1)
-#define mfn_to_virt(m)			(__va(mfn_to_pfn(m) << PAGE_SHIFT))
-
-#define pte_mfn	    pte_pfn
-#define mfn_pte	    pfn_pte
 
 /* Xen machine address */
 typedef struct xmaddr {
@@ -32,10 +28,33 @@ typedef struct xpaddr {
 
 #define INVALID_P2M_ENTRY      (~0UL)
 
+/*
+ * The pseudo-physical frame (pfn) used in all the helpers is always based
+ * on Xen page granularity (i.e 4KB).
+ *
+ * A Linux page may be split across multiple non-contiguous Xen page so we
+ * have to keep track with frame based on 4KB page granularity.
+ *
+ * PV drivers should never make a direct usage of those helpers (particularly
+ * pfn_to_gfn and gfn_to_pfn).
+ */
+
 unsigned long __pfn_to_mfn(unsigned long pfn);
 extern struct rb_root phys_to_mach;
 
-static inline unsigned long pfn_to_mfn(unsigned long pfn)
+/* Pseudo-physical <-> Guest conversion */
+static inline unsigned long pfn_to_gfn(unsigned long pfn)
+{
+	return pfn;
+}
+
+static inline unsigned long gfn_to_pfn(unsigned long gfn)
+{
+	return gfn;
+}
+
+/* Pseudo-physical <-> BUS conversion */
+static inline unsigned long pfn_to_bfn(unsigned long pfn)
 {
 	unsigned long mfn;
 
@@ -48,33 +67,21 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn)
 	return pfn;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long bfn_to_pfn(unsigned long bfn)
 {
-	return mfn;
+	return bfn;
 }
 
-#define mfn_to_local_pfn(mfn) mfn_to_pfn(mfn)
-
-static inline xmaddr_t phys_to_machine(xpaddr_t phys)
-{
-	unsigned offset = phys.paddr & ~PAGE_MASK;
-	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
-}
+#define bfn_to_local_pfn(bfn)	bfn_to_pfn(bfn)
 
-static inline xpaddr_t machine_to_phys(xmaddr_t machine)
-{
-	unsigned offset = machine.maddr & ~PAGE_MASK;
-	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
-}
-/* VIRT <-> MACHINE conversion */
-#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
-#define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
-#define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
+/* VIRT <-> GUEST conversion */
+#define virt_to_gfn(v)		(pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT))
+#define gfn_to_virt(m)		(__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT))
 
+/* Only used in PV code. But ARM guests are always HVM. */
 static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
 {
-	/* TODO: assuming it is mapped in the kernel 1:1 */
-	return virt_to_machine(vaddr);
+	BUG();
 }
 
 /* TODO: this shouldn't be here but it is because the frontend drivers
@@ -108,8 +115,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_unmap(cookie) iounmap((cookie))
 
 bool xen_arch_need_swiotlb(struct device *dev,
-			   unsigned long pfn,
-			   unsigned long mfn);
+			   phys_addr_t phys,
+			   dma_addr_t dev_addr);
 unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/kernel/arch/arm/include/debug/8250.S b/kernel/arch/arm/include/debug/8250.S
index 7a2baf913..7f7446f6f 100644
--- a/kernel/arch/arm/include/debug/8250.S
+++ b/kernel/arch/arm/include/debug/8250.S
@@ -16,11 +16,14 @@
 
 #ifdef CONFIG_DEBUG_UART_8250_WORD
 		.macro	store, rd, rx:vararg
+	 ARM_BE8(rev \rd, \rd)
 		str	\rd, \rx
+	 ARM_BE8(rev \rd, \rd)
 		.endm
 
 		.macro	load, rd, rx:vararg
 		ldr	\rd, \rx
+	ARM_BE8(rev \rd, \rd)
 		.endm
 #else
 		.macro	store, rd, rx:vararg
diff --git a/kernel/arch/arm/include/debug/at91.S b/kernel/arch/arm/include/debug/at91.S
index c3c45e628..43243be94 100644
--- a/kernel/arch/arm/include/debug/at91.S
+++ b/kernel/arch/arm/include/debug/at91.S
@@ -9,29 +9,22 @@
  *
 */
 
-#if defined(CONFIG_AT91_DEBUG_LL_DBGU0)
-#define AT91_DBGU 0xfffff200 /* AT91_BASE_DBGU0 */
-#elif defined(CONFIG_AT91_DEBUG_LL_DBGU1)
-#define AT91_DBGU 0xffffee00 /* AT91_BASE_DBGU1 */
-#else
-/* On sama5d4, use USART3 as low level serial console */
-#define AT91_DBGU 0xfc00c000 /* SAMA5D4_BASE_USART3 */
-#endif
-
 #ifdef CONFIG_MMU
 #define AT91_IO_P2V(x) ((x) - 0x01000000)
 #else
 #define AT91_IO_P2V(x) (x)
 #endif
 
+#define CONFIG_DEBUG_UART_VIRT AT91_IO_P2V(CONFIG_DEBUG_UART_PHYS)
+
 #define AT91_DBGU_SR		(0x14)	/* Status Register */
 #define AT91_DBGU_THR		(0x1c)	/* Transmitter Holding Register */
 #define AT91_DBGU_TXRDY		(1 << 1)	/* Transmitter Ready */
 #define AT91_DBGU_TXEMPTY	(1 << 9)	/* Transmitter Empty */
 
 	.macro	addruart, rp, rv, tmp
-	ldr	\rp, =AT91_DBGU				@ System peripherals (phys address)
-	ldr	\rv, =AT91_IO_P2V(AT91_DBGU)		@ System peripherals (virt address)
+	ldr	\rp, =CONFIG_DEBUG_UART_PHYS		@ System peripherals (phys address)
+	ldr	\rv, =CONFIG_DEBUG_UART_VIRT		@ System peripherals (virt address)
 	.endm
 
 	.macro	senduart,rd,rx
diff --git a/kernel/arch/arm/include/debug/efm32.S b/kernel/arch/arm/include/debug/efm32.S
index 2265a1992..660fa1e4b 100644
--- a/kernel/arch/arm/include/debug/efm32.S
+++ b/kernel/arch/arm/include/debug/efm32.S
@@ -16,7 +16,7 @@
 
 #define	UARTn_TXDATA		0x0034
 
-		.macro	addruart, rx, tmp
+		.macro	addruart, rx, tmp, tmp2
 		ldr	\rx, =(CONFIG_DEBUG_UART_PHYS)
 
 		/*
diff --git a/kernel/arch/arm/include/debug/imx-uart.h b/kernel/arch/arm/include/debug/imx-uart.h
index 032a316eb..bce58e975 100644
--- a/kernel/arch/arm/include/debug/imx-uart.h
+++ b/kernel/arch/arm/include/debug/imx-uart.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ * Copyright (C) 2012-2015 Freescale Semiconductor, Inc.
  *
  * 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
@@ -90,6 +90,27 @@
 #define IMX6SX_UART_BASE_ADDR(n) IMX6SX_UART##n##_BASE_ADDR
 #define IMX6SX_UART_BASE(n)	IMX6SX_UART_BASE_ADDR(n)
 
+#define IMX6UL_UART1_BASE_ADDR	0x02020000
+#define IMX6UL_UART2_BASE_ADDR	0x021e8000
+#define IMX6UL_UART3_BASE_ADDR	0x021ec000
+#define IMX6UL_UART4_BASE_ADDR	0x021f0000
+#define IMX6UL_UART5_BASE_ADDR	0x021f4000
+#define IMX6UL_UART6_BASE_ADDR	0x021fc000
+#define IMX6UL_UART7_BASE_ADDR	0x02018000
+#define IMX6UL_UART8_BASE_ADDR	0x02024000
+#define IMX6UL_UART_BASE_ADDR(n) IMX6UL_UART##n##_BASE_ADDR
+#define IMX6UL_UART_BASE(n)	IMX6UL_UART_BASE_ADDR(n)
+
+#define IMX7D_UART1_BASE_ADDR	0x30860000
+#define IMX7D_UART2_BASE_ADDR	0x30890000
+#define IMX7D_UART3_BASE_ADDR	0x30880000
+#define IMX7D_UART4_BASE_ADDR	0x30a60000
+#define IMX7D_UART5_BASE_ADDR	0x30a70000
+#define IMX7D_UART6_BASE_ADDR	0x30a80000
+#define IMX7D_UART7_BASE_ADDR	0x30a90000
+#define IMX7D_UART_BASE_ADDR(n) IMX7D_UART##n##_BASE_ADDR
+#define IMX7D_UART_BASE(n)	IMX7D_UART_BASE_ADDR(n)
+
 #define IMX_DEBUG_UART_BASE(soc) soc##_UART_BASE(CONFIG_DEBUG_IMX_UART_PORT)
 
 #ifdef CONFIG_DEBUG_IMX1_UART
@@ -114,6 +135,11 @@
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SL)
 #elif defined(CONFIG_DEBUG_IMX6SX_UART)
 #define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6SX)
+#elif defined(CONFIG_DEBUG_IMX6UL_UART)
+#define UART_PADDR	IMX_DEBUG_UART_BASE(IMX6UL)
+#elif defined(CONFIG_DEBUG_IMX7D_UART)
+#define UART_PADDR	IMX_DEBUG_UART_BASE(IMX7D)
+
 #endif
 
 #endif /* __DEBUG_IMX_UART_H */
diff --git a/kernel/arch/arm/include/debug/pl01x.S b/kernel/arch/arm/include/debug/pl01x.S
index 92ef808a2..f7d8323ce 100644
--- a/kernel/arch/arm/include/debug/pl01x.S
+++ b/kernel/arch/arm/include/debug/pl01x.S
@@ -12,6 +12,13 @@
 */
 #include <linux/amba/serial.h>
 
+#ifdef CONFIG_DEBUG_ZTE_ZX
+#undef UART01x_DR
+#undef UART01x_FR
+#define UART01x_DR     0x04
+#define UART01x_FR     0x14
+#endif
+
 #ifdef CONFIG_DEBUG_UART_PHYS
 		.macro	addruart, rp, rv, tmp
 		ldr	\rp, =CONFIG_DEBUG_UART_PHYS
diff --git a/kernel/arch/arm/include/debug/zynq.S b/kernel/arch/arm/include/debug/zynq.S
index bd13dedbd..de86b9247 100644
--- a/kernel/arch/arm/include/debug/zynq.S
+++ b/kernel/arch/arm/include/debug/zynq.S
@@ -38,7 +38,7 @@
 		.endm
 
 		.macro	senduart,rd,rx
-		str	\rd, [\rx, #UART_FIFO_OFFSET]	@ TXDATA
+		strb	\rd, [\rx, #UART_FIFO_OFFSET]	@ TXDATA
 		.endm
 
 		.macro	waituart,rd,rx
diff --git a/kernel/arch/arm/include/uapi/asm/unistd.h b/kernel/arch/arm/include/uapi/asm/unistd.h
index 0c3f5a0da..ede692ffa 100644
--- a/kernel/arch/arm/include/uapi/asm/unistd.h
+++ b/kernel/arch/arm/include/uapi/asm/unistd.h
@@ -414,6 +414,9 @@
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
 #define __NR_execveat			(__NR_SYSCALL_BASE+387)
+#define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
+#define __NR_membarrier			(__NR_SYSCALL_BASE+389)
+#define __NR_mlock2			(__NR_SYSCALL_BASE+390)
 
 /*
  * The following SWIs are ARM private.