diff --git a/Documentation/devicetree/bindings/arm/l2cc.txt b/Documentation/devicetree/bindings/arm/l2cc.txt
index 2251dcc..06c88a4 100644
--- a/Documentation/devicetree/bindings/arm/l2cc.txt
+++ b/Documentation/devicetree/bindings/arm/l2cc.txt
@@ -67,6 +67,12 @@
   disable if zero.
 - arm,prefetch-offset : Override prefetch offset value. Valid values are
   0-7, 15, 23, and 31.
+- arm,shared-override : The default behavior of the pl310 cache controller with
+  respect to the shareable attribute is to transform "normal memory
+  non-cacheable transactions" into "cacheable no allocate" (for reads) or
+  "write through no write allocate" (for writes).
+  On systems where this may cause DMA buffer corruption, this property must be
+  specified to indicate that such transforms are precluded.
 - prefetch-data : Data prefetch. Value: <0> (forcibly disable), <1>
   (forcibly enable), property absent (retain settings set by firmware)
 - prefetch-instr : Instruction prefetch. Value: <0> (forcibly disable),
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1c50210..3458828 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -188,6 +188,9 @@
 config ARCH_HAS_BANDGAP
 	bool
 
+config FIX_EARLYCON_MEM
+	def_bool y if MMU
+
 config GENERIC_HWEIGHT
 	bool
 	default y
@@ -1700,6 +1703,21 @@
 	  consumed by page tables.  Setting this option will allow
 	  user-space 2nd level page tables to reside in high memory.
 
+config CPU_SW_DOMAIN_PAN
+	bool "Enable use of CPU domains to implement privileged no-access"
+	depends on MMU && !ARM_LPAE
+	default y
+	help
+	  Increase kernel security by ensuring that normal kernel accesses
+	  are unable to access userspace addresses.  This can help prevent
+	  use-after-free bugs becoming an exploitable privilege escalation
+	  by ensuring that magic values (such as LIST_POISON) will always
+	  fault when dereferenced.
+
+	  CPUs with low-vector mappings use a best-efforts implementation.
+	  Their lower 1MB needs to remain accessible for the vectors, but
+	  the remainder of userspace will become appropriately inaccessible.
+
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
 	depends on PERF_EVENTS
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 92e54d7..2b25b60 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -65,14 +65,10 @@
 	return !mcpm_wait_for_cpu_powerdown(pcpu, pcluster);
 }
 
-static int mcpm_cpu_disable(unsigned int cpu)
+static bool mcpm_cpu_can_disable(unsigned int cpu)
 {
-	/*
-	 * We assume all CPUs may be shut down.
-	 * This would be the hook to use for eventual Secure
-	 * OS migration requests as described in the PSCI spec.
-	 */
-	return 0;
+	/* We assume all CPUs may be shut down. */
+	return true;
 }
 
 static void mcpm_cpu_die(unsigned int cpu)
@@ -92,7 +88,7 @@
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
 	.cpu_kill		= mcpm_cpu_kill,
-	.cpu_disable		= mcpm_cpu_disable,
+	.cpu_can_disable	= mcpm_cpu_can_disable,
 	.cpu_die		= mcpm_cpu_die,
 #endif
 };
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 83c5019..517ef6d 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -12,7 +12,6 @@
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
-generic-y += mcs_spinlock.h
 generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 4abe572..7bbf325 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/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
@@ -173,7 +177,7 @@
 
 	.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
 
@@ -445,6 +449,53 @@
 #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
+
+	.macro	uaccess_save_and_disable, tmp
+	uaccess_save \tmp
+	uaccess_disable \tmp
+	.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/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 6c2327e..3d8f1d3 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/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
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 5638099..e943e6c 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/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_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_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 @@
 {
 	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 @@
 {
 	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 @@
 {
 	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/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 4812cda..d5525bf 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -140,8 +140,6 @@
  * 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 @@
  * 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
@@ -506,4 +502,21 @@
 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/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index b52101d..a68b9d8 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -14,7 +14,7 @@
 #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;
 
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 6ddbe44..e878129 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -34,15 +34,14 @@
  */
 #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
@@ -55,11 +54,46 @@
 #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));
+
+	return domain;
+}
+
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
@@ -68,17 +102,16 @@
 	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/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 0415eae..58cfe9f 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/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 @@
 	__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/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 5eed828..6795368 100644
--- a/arch/arm/include/asm/futex.h
+++ b/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 @@
 	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 @@
 	: "=&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 @@
 #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_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 @@
 		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 @@
 	: "+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/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index a3c24cd..cab07f6 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -158,8 +158,6 @@
 #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/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index 563b92f..c2bf24f 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -129,21 +129,4 @@
 
 #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/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5e68278..d0131ee 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/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/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 2f3ac1b..ef35665 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -74,7 +74,6 @@
 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);
@@ -105,6 +104,7 @@
 #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
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index 993e522..f908071 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -107,4 +107,13 @@
 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/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index c99e259..12ebfcc 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -10,7 +10,9 @@
  * 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
 
 /*
@@ -22,6 +24,7 @@
 
 #define switch_to(prev,next,last)					\
 do {									\
+	__complete_pending_tlbi();					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index bd32ede..d0a1119 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -74,9 +74,6 @@
 	.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)
@@ -136,22 +133,18 @@
 
 /*
  * 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_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		7	/* seccomp syscall filtering active */
+
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 74b17d0..8cc85a4 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -50,6 +50,35 @@
 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 @@
 		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 @@
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +255,7 @@
 		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 @@
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,20 +333,23 @@
 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 @@
 	: "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 @@
 #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 @@
 #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 @@
 	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 @@
 	: "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 @@
 #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 +490,46 @@
 
 
 #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)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+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 +562,7 @@
 	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/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 5e5a51a..f89811f 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -97,9 +97,9 @@
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index cb4fb1e..3e1c26e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -435,7 +444,7 @@
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
@@ -770,6 +784,8 @@
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index b48dd4f..30a7228 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -24,35 +24,55 @@
 
 
 	.align	5
+#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
 /*
- * This is the fast syscall return path.  We do as little as
- * possible here, and this includes saving r0 back into the SVC
- * stack.
+ * This is the fast syscall return path.  We do as little as possible here,
+ * such as avoiding writing r0 to the stack.  We only use this path if we
+ * have tracing and context tracking disabled - the overheads from those
+ * features make this path too inefficient.
  */
 ret_fast_syscall:
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK
-	bne	__sys_trace_return
-	tst	r1, #_TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
 	bne	fast_work_pending
-	asm_trace_hardirqs_on
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
-	ct_user_enter
 
 	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
 
-/*
- * Ok, we need to do extra processing, enter the slow path.
- */
+	/* Ok, we need to do extra processing, enter the slow path. */
 fast_work_pending:
 	str	r0, [sp, #S_R0+S_OFF]!		@ returned r0
-work_pending:
+	/* fall through to work_pending */
+#else
+/*
+ * The "replacement" ret_fast_syscall for when tracing or context tracking
+ * is enabled.  As we will need to call out to some C functions, we save
+ * r0 first to avoid needing to save registers around each C function call.
+ */
+ret_fast_syscall:
+ UNWIND(.fnstart	)
+ UNWIND(.cantunwind	)
+	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
+	disable_irq_notrace			@ disable interrupts
+	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
+	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	beq	no_work_pending
+ UNWIND(.fnend		)
+ENDPROC(ret_fast_syscall)
+
+	/* Slower path - fall through to work_pending */
+#endif
+
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	__sys_trace_return_nosave
+slow_work_pending:
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
 	bl	do_work_pending
@@ -65,16 +85,19 @@
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.
+ * IRQs may be enabled here, so always disable them.  Note that we use the
+ * "notrace" version to avoid calling into the tracing code unnecessarily.
+ * do_work_pending() will update this state if necessary.
  */
 ENTRY(ret_to_user)
 ret_slow_syscall:
-	disable_irq				@ disable interrupts
+	disable_irq_notrace			@ disable interrupts
 ENTRY(ret_to_user_from_irq)
 	ldr	r1, [tsk, #TI_FLAGS]
 	tst	r1, #_TIF_WORK_MASK
-	bne	work_pending
+	bne	slow_work_pending
 no_work_pending:
-	asm_trace_hardirqs_on
+	asm_trace_hardirqs_on save = 0
 
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
@@ -174,6 +197,8 @@
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -252,6 +277,12 @@
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
+__sys_trace_return_nosave:
+	enable_irq_notrace
+	mov	r0, sp
+	bl	syscall_trace_exit
+	b	ret_slow_syscall
+
 	.align	5
 #ifdef CONFIG_ALIGNMENT_TRAP
 	.type	__cr_alignment, #object
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045a..0d22ad2 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,10 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +226,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +259,9 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +271,27 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +309,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.endm
-
-#ifdef CONFIG_CPU_V7M
-	/*
-	 * Note we don't need to do clrex here as clearing the local monitor is
-	 * part of each exception entry and exit sequence.
-	 */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.if	\offset
 	add	sp, #\offset
 	.endif
 	v7m_exception_slow_exit ret_r0 = \fast
-	.endm
-#else	/* ifdef CONFIG_CPU_V7M */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +336,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29e2991..04286fd 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -464,10 +464,7 @@
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 350f188..b96c8ed 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -39,6 +39,7 @@
 #include <linux/export.h>
 
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/outercache.h>
 #include <asm/exception.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 54272e0..7d5379c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -795,8 +795,10 @@
 
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0 && irq_is_percpu(irq))
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		cpumask_setall(&pmu->supported_cpus);
 		return 0;
+	}
 
 	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f192a2a..a3089ba 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -91,13 +91,6 @@
 	ledtrig_cpu(CPU_LED_IDLE_END);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-void arch_cpu_idle_dead(void)
-{
-	cpu_die();
-}
-#endif
-
 void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
@@ -129,12 +122,36 @@
 	buf[4] = '\0';
 
 #ifndef CONFIG_CPU_V7M
-	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		isa_modes[isa_mode(regs)],
-		get_fs() == get_ds() ? "kernel" : "user");
+	{
+		unsigned int domain = get_domain();
+		const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		/*
+		 * Get the domain register for the parent context. In user
+		 * mode, we don't save the DACR, so lets use what it should
+		 * be. For other modes, we place it after the pt_regs struct.
+		 */
+		if (user_mode(regs))
+			domain = DACR_UACCESS_ENABLE;
+		else
+			domain = *(unsigned int *)(regs + 1);
+#endif
+
+		if ((domain & domain_mask(DOMAIN_USER)) ==
+		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+			segment = "none";
+		else if (get_fs() == get_ds())
+			segment = "kernel";
+		else
+			segment = "user";
+
+		printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
+			buf, interrupts_enabled(regs) ? "n" : "ff",
+			fast_interrupts_enabled(regs) ? "n" : "ff",
+			processor_modes[processor_mode(regs)],
+			isa_modes[isa_mode(regs)], segment);
+	}
 #else
 	printk("xPSR: %08lx\n", regs->ARM_cpsr);
 #endif
@@ -146,10 +163,9 @@
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac;
+			unsigned int transbase, dac = get_domain();
 			asm("mrc p15, 0, %0, c2, c0\n\t"
-			    "mrc p15, 0, %1, c3, c0\n"
-			    : "=r" (transbase), "=r" (dac));
+			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
 			  	transbase, dac);
 		}
@@ -210,6 +226,14 @@
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+	/*
+	 * Copy the initial value of the domain access control register
+	 * from the current thread: thread->addr_limit will have been
+	 * copied from the current thread via setup_thread_stack() in
+	 * kernel/fork.c
+	 */
+	thread->cpu_domain = get_domain();
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 36c18b7..e2ecee6 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -37,6 +37,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
+#include <asm/fixmap.h>
 #include <asm/procinfo.h>
 #include <asm/psci.h>
 #include <asm/sections.h>
@@ -954,6 +955,9 @@
 	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = cmd_line;
 
+	if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM))
+		early_fixmap_init();
+
 	parse_early_param();
 
 #ifdef CONFIG_MMU
@@ -1015,7 +1019,7 @@
 
 	for_each_possible_cpu(cpu) {
 		struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu);
-		cpuinfo->cpu.hotpluggable = 1;
+		cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu);
 		register_cpu(&cpuinfo->cpu, cpu);
 	}
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 423663e..b6cda06 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -562,6 +562,12 @@
 asmlinkage int
 do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
+	/*
+	 * The assembly code enters us with IRQs off, but it hasn't
+	 * informed the tracing code of that for efficiency reasons.
+	 * Update the trace code with the current status.
+	 */
+	trace_hardirqs_off();
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 3d6b782..ba0063c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -175,13 +175,26 @@
 	if (smp_ops.cpu_disable)
 		return smp_ops.cpu_disable(cpu);
 
+	return 0;
+}
+
+int platform_can_hotplug_cpu(unsigned int cpu)
+{
+	/* cpu_die must be specified to support hotplug */
+	if (!smp_ops.cpu_die)
+		return 0;
+
+	if (smp_ops.cpu_can_disable)
+		return smp_ops.cpu_can_disable(cpu);
+
 	/*
 	 * By default, allow disabling all CPUs except the first one,
 	 * since this is special on a lot of platforms, e.g. because
 	 * of clock tick interrupts.
 	 */
-	return cpu == 0 ? -EPERM : 0;
+	return cpu != 0;
 }
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -253,7 +266,7 @@
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void __ref cpu_die(void)
+void arch_cpu_idle_dead(void)
 {
 	unsigned int cpu = smp_processor_id();
 
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 1361756..5b26e7e 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -141,11 +141,14 @@
 
 	while (1) {
 		unsigned long temp;
+		unsigned int __ua_flags;
 
+		__ua_flags = uaccess_save_and_enable();
 		if (type == TYPE_SWPB)
 			__user_swpb_asm(*data, address, res, temp);
 		else
 			__user_swp_asm(*data, address, res, temp);
+		uaccess_restore(__ua_flags);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d358226..969f9d9 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -870,7 +870,6 @@
 	kuser_init(vectors_base);
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
-	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 1710fd7..970d6c0 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -12,14 +12,14 @@
 
 		.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
 ENTRY(__clear_user_std)
-WEAK(__clear_user)
+WEAK(arm_clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,7 +44,7 @@
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
-ENDPROC(__clear_user)
+ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
 		.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a235b9..1512beb 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -89,11 +89,11 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(arm_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(arm_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 9648b06..caf5019 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -93,11 +93,11 @@
 	.text
 
 ENTRY(__copy_to_user_std)
-WEAK(__copy_to_user)
+WEAK(arm_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(arm_copy_to_user)
 ENDPROC(__copy_to_user_std)
 
 	.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1d0957e..1712f13 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -17,6 +17,19 @@
 
 		.text
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		.macro	save_regs
+		mrc	p15, 0, ip, c3, c0, 0
+		stmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		uaccess_enable ip
+		.endm
+
+		.macro	load_regs
+		ldmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		mcr	p15, 0, ip, c3, c0, 0
+		ret	lr
+		.endm
+#else
 		.macro	save_regs
 		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
@@ -24,6 +37,7 @@
 		.macro	load_regs
 		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
+#endif
 
 		.macro	load1b,	reg1
 		ldrusr	\reg1, r0, 1
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 4b39af2..d72b909 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -136,7 +136,7 @@
 }
 
 unsigned long
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	/*
 	 * This test is stubbed out of the main function above to keep
@@ -190,7 +190,7 @@
 	return n;
 }
 
-unsigned long __clear_user(void __user *addr, unsigned long n)
+unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
 	if (n < 64)
diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c
index 04c9daf..7db5870 100644
--- a/arch/arm/mach-mmp/pm-pxa910.c
+++ b/arch/arm/mach-mmp/pm-pxa910.c
@@ -18,6 +18,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <asm/mach-types.h>
+#include <asm/outercache.h>
 #include <mach/hardware.h>
 #include <mach/cputype.h>
 #include <mach/addr-map.h>
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index ecc04ff..8427997 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -29,6 +29,7 @@
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
 	select OMAP_INTERCONNECT
+	select OMAP_INTERCONNECT_BARRIER
 	select PL310_ERRATA_588369 if CACHE_L2X0
 	select PL310_ERRATA_727915 if CACHE_L2X0
 	select PM_OPP if PM
@@ -46,6 +47,7 @@
 	select HAVE_ARM_TWD if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT_BARRIER
 
 config SOC_AM33XX
 	bool "TI AM33XX"
@@ -70,6 +72,7 @@
 	select HAVE_ARM_ARCH_TIMER
 	select IRQ_CROSSBAR
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT_BARRIER
 
 config ARCH_OMAP2PLUS
 	bool
@@ -91,6 +94,10 @@
 	help
 	  Systems based on OMAP2, OMAP3, OMAP4 or OMAP5
 
+config OMAP_INTERCONNECT_BARRIER
+	bool
+	select ARM_HEAVY_MB
+	
 
 if ARCH_OMAP2PLUS
 
diff --git a/arch/arm/mach-omap2/common.c b/arch/arm/mach-omap2/common.c
index eae6a0e..484cdad 100644
--- a/arch/arm/mach-omap2/common.c
+++ b/arch/arm/mach-omap2/common.c
@@ -30,4 +30,5 @@
 void __init omap_reserve(void)
 {
 	omap_secure_ram_reserve_memblock();
+	omap_barrier_reserve_memblock();
 }
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index cf3cf22..82f88b4 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -189,6 +189,15 @@
 }
 #endif
 
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
+void omap_barrier_reserve_memblock(void);
+void omap_barriers_init(void);
+#else
+static inline void omap_barrier_reserve_memblock(void)
+{
+}
+#endif
+
 /* This gets called from mach-omap2/io.c, do not call this */
 void __init omap2_set_globals_tap(u32 class, void __iomem *tap);
 
diff --git a/arch/arm/mach-omap2/include/mach/barriers.h b/arch/arm/mach-omap2/include/mach/barriers.h
deleted file mode 100644
index 1c582a8..0000000
--- a/arch/arm/mach-omap2/include/mach/barriers.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * OMAP memory barrier header.
- *
- * Copyright (C) 2011 Texas Instruments, Inc.
- *  Santosh Shilimkar <santosh.shilimkar@ti.com>
- *  Richard Woodruff <r-woodruff2@ti.com>
- *
- * 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, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef __MACH_BARRIERS_H
-#define __MACH_BARRIERS_H
-
-#include <asm/outercache.h>
-
-extern void omap_bus_sync(void);
-
-#define rmb()		dsb()
-#define wmb()		do { dsb(); outer_sync(); omap_bus_sync(); } while (0)
-#define mb()		wmb()
-
-#endif	/* __MACH_BARRIERS_H */
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 820dde8..7743e367 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -306,6 +306,7 @@
 void __init omap4_map_io(void)
 {
 	iotable_init(omap44xx_io_desc, ARRAY_SIZE(omap44xx_io_desc));
+	omap_barriers_init();
 }
 #endif
 
@@ -313,6 +314,7 @@
 void __init omap5_map_io(void)
 {
 	iotable_init(omap54xx_io_desc, ARRAY_SIZE(omap54xx_io_desc));
+	omap_barriers_init();
 }
 #endif
 /*
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 16350ee..949696b 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -51,6 +51,127 @@
 
 #define IRQ_LOCALTIMER		29
 
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
+
+/* Used to implement memory barrier on DRAM path */
+#define OMAP4_DRAM_BARRIER_VA			0xfe600000
+
+static void __iomem *dram_sync, *sram_sync;
+static phys_addr_t dram_sync_paddr;
+static u32 dram_sync_size;
+
+/*
+ * The OMAP4 bus structure contains asynchrnous bridges which can buffer
+ * data writes from the MPU. These asynchronous bridges can be found on
+ * paths between the MPU to EMIF, and the MPU to L3 interconnects.
+ *
+ * We need to be careful about re-ordering which can happen as a result
+ * of different accesses being performed via different paths, and
+ * therefore different asynchronous bridges.
+ */
+
+/*
+ * OMAP4 interconnect barrier which is called for each mb() and wmb().
+ * This is to ensure that normal paths to DRAM (normal memory, cacheable
+ * accesses) are properly synchronised with writes to DMA coherent memory
+ * (normal memory, uncacheable) and device writes.
+ *
+ * The mb() and wmb() barriers only operate only on the MPU->MA->EMIF
+ * path, as we need to ensure that data is visible to other system
+ * masters prior to writes to those system masters being seen.
+ *
+ * Note: the SRAM path is not synchronised via mb() and wmb().
+ */
+static void omap4_mb(void)
+{
+	if (dram_sync)
+		writel_relaxed(0, dram_sync);
+}
+
+/*
+ * OMAP4 Errata i688 - asynchronous bridge corruption when entering WFI.
+ *
+ * If a data is stalled inside asynchronous bridge because of back
+ * pressure, it may be accepted multiple times, creating pointer
+ * misalignment that will corrupt next transfers on that data path until
+ * next reset of the system. No recovery procedure once the issue is hit,
+ * the path remains consistently broken.
+ *
+ * Async bridges can be found on paths between MPU to EMIF and MPU to L3
+ * interconnects.
+ *
+ * This situation can happen only when the idle is initiated by a Master
+ * Request Disconnection (which is trigged by software when executing WFI
+ * on the CPU).
+ *
+ * The work-around for this errata needs all the initiators connected
+ * through an async bridge to ensure that data path is properly drained
+ * before issuing WFI. This condition will be met if one Strongly ordered
+ * access is performed to the target right before executing the WFI.
+ *
+ * In MPU case, L3 T2ASYNC FIFO and DDR T2ASYNC FIFO needs to be drained.
+ * IO barrier ensure that there is no synchronisation loss on initiators
+ * operating on both interconnect port simultaneously.
+ *
+ * This is a stronger version of the OMAP4 memory barrier below, and
+ * operates on both the MPU->MA->EMIF path but also the MPU->OCP path
+ * as well, and is necessary prior to executing a WFI.
+ */
+void omap_interconnect_sync(void)
+{
+	if (dram_sync && sram_sync) {
+		writel_relaxed(readl_relaxed(dram_sync), dram_sync);
+		writel_relaxed(readl_relaxed(sram_sync), sram_sync);
+		isb();
+	}
+}
+
+static int __init omap4_sram_init(void)
+{
+	struct device_node *np;
+	struct gen_pool *sram_pool;
+
+	np = of_find_compatible_node(NULL, NULL, "ti,omap4-mpu");
+	if (!np)
+		pr_warn("%s:Unable to allocate sram needed to handle errata I688\n",
+			__func__);
+	sram_pool = of_gen_pool_get(np, "sram", 0);
+	if (!sram_pool)
+		pr_warn("%s:Unable to get sram pool needed to handle errata I688\n",
+			__func__);
+	else
+		sram_sync = (void *)gen_pool_alloc(sram_pool, PAGE_SIZE);
+
+	return 0;
+}
+omap_arch_initcall(omap4_sram_init);
+
+/* Steal one page physical memory for barrier implementation */
+void __init omap_barrier_reserve_memblock(void)
+{
+	dram_sync_size = ALIGN(PAGE_SIZE, SZ_1M);
+	dram_sync_paddr = arm_memblock_steal(dram_sync_size, SZ_1M);
+}
+
+void __init omap_barriers_init(void)
+{
+	struct map_desc dram_io_desc[1];
+
+	dram_io_desc[0].virtual = OMAP4_DRAM_BARRIER_VA;
+	dram_io_desc[0].pfn = __phys_to_pfn(dram_sync_paddr);
+	dram_io_desc[0].length = dram_sync_size;
+	dram_io_desc[0].type = MT_MEMORY_RW_SO;
+	iotable_init(dram_io_desc, ARRAY_SIZE(dram_io_desc));
+	dram_sync = (void __iomem *) dram_io_desc[0].virtual;
+
+	pr_info("OMAP4: Map %pa to %p for dram barrier\n",
+		&dram_sync_paddr, dram_sync);
+
+	soc_mb = omap4_mb;
+}
+
+#endif
+
 void gic_dist_disable(void)
 {
 	if (gic_dist_base_addr)
diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S
index ad1bb94..9b09d85 100644
--- a/arch/arm/mach-omap2/sleep44xx.S
+++ b/arch/arm/mach-omap2/sleep44xx.S
@@ -333,14 +333,12 @@
 
 #endif	/* defined(CONFIG_SMP) && defined(CONFIG_PM) */
 
-ENTRY(omap_bus_sync)
-	ret	lr
-ENDPROC(omap_bus_sync)
-
 ENTRY(omap_do_wfi)
 	stmfd	sp!, {lr}
+#ifdef CONFIG_OMAP_INTERCONNECT_BARRIER
 	/* Drain interconnect write buffers. */
-	bl omap_bus_sync
+	bl	omap_interconnect_sync
+#endif
 
 	/*
 	 * Execute an ISB instruction to ensure that all of the
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index d99d08e..83e94c9 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -16,6 +16,7 @@
 #include <linux/of_platform.h>
 #include <linux/io.h>
 #include <linux/rtc/sirfsoc_rtciobrg.h>
+#include <asm/outercache.h>
 #include <asm/suspend.h>
 #include <asm/hardware/cache-l2x0.h>
 
diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h
index 476092b..8d27ec5 100644
--- a/arch/arm/mach-shmobile/common.h
+++ b/arch/arm/mach-shmobile/common.h
@@ -13,7 +13,7 @@
 extern void shmobile_smp_sleep(void);
 extern void shmobile_smp_hook(unsigned int cpu, unsigned long fn,
 			      unsigned long arg);
-extern int shmobile_smp_cpu_disable(unsigned int cpu);
+extern bool shmobile_smp_cpu_can_disable(unsigned int cpu);
 extern void shmobile_boot_scu(void);
 extern void shmobile_smp_scu_prepare_cpus(unsigned int max_cpus);
 extern void shmobile_smp_scu_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c
index 3923e09..b23378f 100644
--- a/arch/arm/mach-shmobile/platsmp.c
+++ b/arch/arm/mach-shmobile/platsmp.c
@@ -31,8 +31,8 @@
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int shmobile_smp_cpu_disable(unsigned int cpu)
+bool shmobile_smp_cpu_can_disable(unsigned int cpu)
 {
-	return 0; /* Hotplug of any CPU is supported */
+	return true; /* Hotplug of any CPU is supported */
 }
 #endif
diff --git a/arch/arm/mach-shmobile/smp-r8a7790.c b/arch/arm/mach-shmobile/smp-r8a7790.c
index 930f45c..947e437 100644
--- a/arch/arm/mach-shmobile/smp-r8a7790.c
+++ b/arch/arm/mach-shmobile/smp-r8a7790.c
@@ -64,7 +64,7 @@
 	.smp_prepare_cpus	= r8a7790_smp_prepare_cpus,
 	.smp_boot_secondary	= shmobile_smp_apmu_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-r8a7791.c b/arch/arm/mach-shmobile/smp-r8a7791.c
index 5e2d1db7..b2508c0 100644
--- a/arch/arm/mach-shmobile/smp-r8a7791.c
+++ b/arch/arm/mach-shmobile/smp-r8a7791.c
@@ -58,7 +58,7 @@
 	.smp_prepare_cpus	= r8a7791_smp_prepare_cpus,
 	.smp_boot_secondary	= r8a7791_smp_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_apmu_cpu_die,
 	.cpu_kill		= shmobile_smp_apmu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-shmobile/smp-sh73a0.c b/arch/arm/mach-shmobile/smp-sh73a0.c
index 2106d6b..ae7c764 100644
--- a/arch/arm/mach-shmobile/smp-sh73a0.c
+++ b/arch/arm/mach-shmobile/smp-sh73a0.c
@@ -68,7 +68,7 @@
 	.smp_prepare_cpus	= sh73a0_smp_prepare_cpus,
 	.smp_boot_secondary	= sh73a0_boot_secondary,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable		= shmobile_smp_cpu_disable,
+	.cpu_can_disable	= shmobile_smp_cpu_can_disable,
 	.cpu_die		= shmobile_smp_scu_cpu_die,
 	.cpu_kill		= shmobile_smp_scu_cpu_kill,
 #endif
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index 7557bed..780bd13 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -8,6 +8,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 
+#include <asm/outercache.h>
 #include <asm/hardware/cache-l2x0.h>
 
 #include "db8500-regs.h"
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 7c6b976..df7537f 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -883,6 +883,7 @@
 
 config OUTER_CACHE_SYNC
 	bool
+	select ARM_HEAVY_MB
 	help
 	  The outer cache has a outer_cache_fns.sync function pointer
 	  that can be used to drain the write buffer of the outer cache.
@@ -1031,6 +1032,9 @@
 	  This option allows the use of custom mandatory barriers
 	  included via the mach/barriers.h file.
 
+config ARM_HEAVY_MB
+	bool
+
 config ARCH_SUPPORTS_BIG_ENDIAN
 	bool
 	help
diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S
index 54473cd4..b3b31e3 100644
--- a/arch/arm/mm/abort-ev4.S
+++ b/arch/arm/mm/abort-ev4.S
@@ -19,6 +19,7 @@
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	ldr	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
 	tst	r3, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index a0908d4..a6a381a 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -21,8 +21,10 @@
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable user access
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ check write
 	orreq	r1, r1, #1 << 11
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index 4006b7a..00ab011 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -24,7 +24,9 @@
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
-	do_ldrd_abort tmp=ip, insn=r3
+	uaccess_disable ip			@ disable userspace access
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8c48c5c..8801a15 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,16 +26,18 @@
 	ldr	ip, =0x4107b36
 	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
 	teq	ip, r3, lsr #4			@ r0 ARM1136?
-	bne	do_DataAbort
+	bne	1f
 	tst	r5, #PSR_J_BIT			@ Java?
 	tsteq	r5, #PSR_T_BIT			@ Thumb?
-	bne	do_DataAbort
+	bne	1f
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	1f				@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
+1:	uaccess_disable ip			@ disable userspace access
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 4812ad0..e8d0e08 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -15,6 +15,7 @@
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+	uaccess_disable ip			@ disable userspace access
 
 	/*
 	 * V6 code adjusts the returned DFSR.
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index f398258..6d8e8e3 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -26,6 +26,7 @@
 #endif
 	bne	.data_thumb_abort
 	ldr	r8, [r4]			@ read arm instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
 	and	r7, r8, #15 << 24
@@ -155,6 +156,7 @@
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 11			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 8			@ yes
 	and	r7, r8, #15 << 12
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 2cbf68e..4509bee 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -13,6 +13,7 @@
 	tst	\psr, #PSR_T_BIT
 	beq	not_thumb
 	ldrh	\tmp, [\pc]			@ Read aborted Thumb instruction
+	uaccess_disable ip			@ disable userspace access
 	and	\tmp, \tmp, # 0xfe00		@ Mask opcode field
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes
@@ -29,12 +30,9 @@
  *   [7:4] == 1101
  *    [20] == 0
  */
-	.macro	do_ldrd_abort, tmp, insn
-	tst	\insn, #0x0e100000		@ [27:25,20] == 0
-	bne	not_ldrd
-	and	\tmp, \insn, #0x000000f0	@ [7:4] == 1101
-	cmp	\tmp, #0x000000d0
-	beq	do_DataAbort
-not_ldrd:
+	.macro	teq_ldrd, tmp, insn
+	mov	\tmp, #0x0e100000
+	orr	\tmp, #0x000000f0
+	and	\tmp, \insn, \tmp
+	teq	\tmp, #0x000000d0
 	.endm
-
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 097181e..5c1b7a7 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -368,7 +368,6 @@
 	struct device_node *node;
 	void __iomem *base;
 	bool l2_wt_override = false;
-	struct resource res;
 
 #if defined(CONFIG_CACHE_FEROCEON_L2_WRITETHROUGH)
 	l2_wt_override = true;
@@ -376,10 +375,7 @@
 
 	node = of_find_matching_node(NULL, feroceon_ids);
 	if (node && of_device_is_compatible(node, "marvell,kirkwood-cache")) {
-		if (of_address_to_resource(node, 0, &res))
-			return -ENODEV;
-
-		base = ioremap(res.start, resource_size(&res));
+		base = of_iomap(node, 0);
 		if (!base)
 			return -ENOMEM;
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 71b3d33..493692d 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1171,6 +1171,11 @@
 		}
 	}
 
+	if (of_property_read_bool(np, "arm,shared-override")) {
+		*aux_val |= L2C_AUX_CTRL_SHARED_OVERRIDE;
+		*aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE;
+	}
+
 	prefetch = l2x0_saved_regs.prefetch_ctrl;
 
 	ret = of_property_read_u32(np, "arm,double-linefill", &val);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index cba12f3..9f509b2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -39,6 +39,7 @@
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
 
+#include "dma.h"
 #include "mm.h"
 
 /*
@@ -648,14 +649,18 @@
 	size = PAGE_ALIGN(size);
 	want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs);
 
-	if (is_coherent || nommu())
+	if (nommu())
+		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (dev_get_cma_area(dev) && (gfp & __GFP_WAIT))
+		addr = __alloc_from_contiguous(dev, size, prot, &page,
+					       caller, want_vaddr);
+	else if (is_coherent)
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!dev_get_cma_area(dev))
-		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller, want_vaddr);
 	else
-		addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr);
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page,
+					    caller, want_vaddr);
 
 	if (page)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
@@ -683,13 +688,12 @@
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
 		return memory;
 
-	return __dma_alloc(dev, size, handle, gfp, prot, true,
+	return __dma_alloc(dev, size, handle, gfp, PAGE_KERNEL, true,
 			   attrs, __builtin_return_address(0));
 }
 
@@ -753,12 +757,12 @@
 
 	size = PAGE_ALIGN(size);
 
-	if (is_coherent || nommu()) {
+	if (nommu()) {
 		__dma_free_buffer(page, size);
-	} else if (__free_from_pool(cpu_addr, size)) {
+	} else if (!is_coherent && __free_from_pool(cpu_addr, size)) {
 		return;
 	} else if (!dev_get_cma_area(dev)) {
-		if (want_vaddr)
+		if (want_vaddr && !is_coherent)
 			__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
diff --git a/arch/arm/mm/dma.h b/arch/arm/mm/dma.h
new file mode 100644
index 0000000..70ea6852
--- /dev/null
+++ b/arch/arm/mm/dma.h
@@ -0,0 +1,32 @@
+#ifndef DMA_H
+#define DMA_H
+
+#include <asm/glue-cache.h>
+
+#ifndef MULTI_CACHE
+#define dmac_map_area			__glue(_CACHE,_dma_map_area)
+#define dmac_unmap_area 		__glue(_CACHE,_dma_unmap_area)
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * 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);
+
+#else
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the 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
+
+#endif
+
+#endif
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 34b66af..1ec8e75 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -21,6 +21,21 @@
 
 #include "mm.h"
 
+#ifdef CONFIG_ARM_HEAVY_MB
+void (*soc_mb)(void);
+
+void arm_heavy_mb(void)
+{
+#ifdef CONFIG_OUTER_CACHE_SYNC
+	if (outer_cache.sync)
+		outer_cache.sync();
+#endif
+	if (soc_mb)
+		soc_mb();
+}
+EXPORT_SYMBOL(arm_heavy_mb);
+#endif
+
 #ifdef CONFIG_CPU_CACHE_VIPT
 
 static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index ee8dfa7..9df5f09 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -79,7 +79,7 @@
 
 	type = kmap_atomic_idx_push();
 
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
@@ -106,7 +106,7 @@
 
 	if (kvaddr >= (void *)FIXADDR_START) {
 		type = kmap_atomic_idx();
-		idx = type + KM_TYPE_NR * smp_processor_id();
+		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
@@ -138,7 +138,7 @@
 		return page_address(page);
 
 	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR * smp_processor_id();
+	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 870838a..7cd1514 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -291,13 +291,13 @@
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_HIGH_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_USER | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
@@ -357,6 +357,47 @@
 }
 EXPORT_SYMBOL(get_mem_type);
 
+static pte_t *(*pte_offset_fixmap)(pmd_t *dir, unsigned long addr);
+
+static pte_t bm_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+	__aligned(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE) __initdata;
+
+static pte_t * __init pte_offset_early_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return &bm_pte[pte_index(addr)];
+}
+
+static pte_t *pte_offset_late_fixmap(pmd_t *dir, unsigned long addr)
+{
+	return pte_offset_kernel(dir, addr);
+}
+
+static inline pmd_t * __init fixmap_pmd(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	pud_t *pud = pud_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
+
+	return pmd;
+}
+
+void __init early_fixmap_init(void)
+{
+	pmd_t *pmd;
+
+	/*
+	 * The early fixmap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+	BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT)
+		     != FIXADDR_TOP >> PMD_SHIFT);
+
+	pmd = fixmap_pmd(FIXADDR_TOP);
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+
+	pte_offset_fixmap = pte_offset_early_fixmap;
+}
+
 /*
  * To avoid TLB flush broadcasts, this uses local_flush_tlb_kernel_range().
  * As a result, this can only be called with preemption disabled, as under
@@ -365,7 +406,7 @@
 void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 {
 	unsigned long vaddr = __fix_to_virt(idx);
-	pte_t *pte = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
+	pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr);
 
 	/* Make sure fixmap region does not exceed available allocation. */
 	BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
@@ -855,7 +896,7 @@
 	}
 
 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET &&
+	    md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START &&
 	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n",
 			(long long)__pfn_to_phys((u64)md->pfn), md->virtual);
@@ -1219,10 +1260,10 @@
 
 /*
  * Set up the device mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_START, we will remove any debug device mappings.
- * This means you have to be careful how you debug this function, or any
- * called function.  This means you can't use any function or debugging
- * method which may touch any device, otherwise the kernel _will_ crash.
+ * mappings above VMALLOC_START, except early fixmap, we might remove debug
+ * device mappings.  This means earlycon can be used to debug this function
+ * Any other function or debugging method which may touch any device _will_
+ * crash the kernel.
  */
 static void __init devicemaps_init(const struct machine_desc *mdesc)
 {
@@ -1237,7 +1278,10 @@
 
 	early_trap_init(vectors);
 
-	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
+	/*
+	 * Clear page table except top pmd used by early fixmaps
+	 */
+	for (addr = VMALLOC_START; addr < (FIXADDR_TOP & PMD_MASK); addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
@@ -1489,6 +1533,35 @@
 
 #endif
 
+static void __init early_fixmap_shutdown(void)
+{
+	int i;
+	unsigned long va = fix_to_virt(__end_of_permanent_fixed_addresses - 1);
+
+	pte_offset_fixmap = pte_offset_late_fixmap;
+	pmd_clear(fixmap_pmd(va));
+	local_flush_tlb_kernel_page(va);
+
+	for (i = 0; i < __end_of_permanent_fixed_addresses; i++) {
+		pte_t *pte;
+		struct map_desc map;
+
+		map.virtual = fix_to_virt(i);
+		pte = pte_offset_early_fixmap(pmd_off_k(map.virtual), map.virtual);
+
+		/* Only i/o device mappings are supported ATM */
+		if (pte_none(*pte) ||
+		    (pte_val(*pte) & L_PTE_MT_MASK) != L_PTE_MT_DEV_SHARED)
+			continue;
+
+		map.pfn = pte_pfn(*pte);
+		map.type = MT_DEVICE;
+		map.length = PAGE_SIZE;
+
+		create_mapping(&map);
+	}
+}
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
@@ -1502,6 +1575,7 @@
 	map_lowmem();
 	memblock_set_current_limit(arm_lowmem_limit);
 	dma_contiguous_remap();
+	early_fixmap_shutdown();
 	devicemaps_init(mdesc);
 	kmap_init();
 	tcm_init();
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a3681f1..e683db1 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -84,6 +84,16 @@
 		if (!new_pte)
 			goto no_pte;
 
+#ifndef CONFIG_ARM_LPAE
+		/*
+		 * Modify the PTE pointer to have the correct domain.  This
+		 * needs to be the vectors domain to avoid the low vectors
+		 * being unmapped.
+		 */
+		pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
+		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
+#endif
+
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 1bd6f9c..29e6850 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/qcom_scm.h>
 
-#include <asm/outercache.h>
 #include <asm/cacheflush.h>
 
 #include "qcom_scm.h"
@@ -219,8 +218,7 @@
 	 * Flush the command buffer so that the secure world sees
 	 * the correct data.
 	 */
-	__cpuc_flush_dcache_area((void *)cmd, cmd->len);
-	outer_flush_range(cmd_addr, cmd_addr + cmd->len);
+	secure_flush_area(cmd, cmd->len);
 
 	ret = smc(cmd_addr);
 	if (ret < 0)