Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - "genirq: Introduce generic irq migration for cpu hotunplugged" patch
   merged from tip/irq/for-arm to allow the arm64-specific part to be
   upstreamed via the arm64 tree

 - CPU feature detection reworked to cope with heterogeneous systems
   where CPUs may not have exactly the same features.  The features
   reported by the kernel via internal data structures or ELF_HWCAP are
   delayed until all the CPUs are up (and before user space starts)

 - Support for 16KB pages, with the additional bonus of a 36-bit VA
   space, though the latter only depending on EXPERT

 - Implement native {relaxed, acquire, release} atomics for arm64

 - New ASID allocation algorithm which avoids IPI on roll-over, together
   with TLB invalidation optimisations (using local vs global where
   feasible)

 - KASan support for arm64

 - EFI_STUB clean-up and isolation for the kernel proper (required by
   KASan)

 - copy_{to,from,in}_user optimisations (sharing the memcpy template)

 - perf: moving arm64 to the arm32/64 shared PMU framework

 - L1_CACHE_BYTES increased to 128 to accommodate Cavium hardware

 - Support for the contiguous PTE hint on kernel mapping (16 consecutive
   entries may be able to use a single TLB entry)

 - Generic CONFIG_HZ now used on arm64

 - defconfig updates

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (91 commits)
  arm64/efi: fix libstub build under CONFIG_MODVERSIONS
  ARM64: Enable multi-core scheduler support by default
  arm64/efi: move arm64 specific stub C code to libstub
  arm64: page-align sections for DEBUG_RODATA
  arm64: Fix build with CONFIG_ZONE_DMA=n
  arm64: Fix compat register mappings
  arm64: Increase the max granular size
  arm64: remove bogus TASK_SIZE_64 check
  arm64: make Timer Interrupt Frequency selectable
  arm64/mm: use PAGE_ALIGNED instead of IS_ALIGNED
  arm64: cachetype: fix definitions of ICACHEF_* flags
  arm64: cpufeature: declare enable_cpu_capabilities as static
  genirq: Make the cpuhotplug migration code less noisy
  arm64: Constify hwcap name string arrays
  arm64/kvm: Make use of the system wide safe values
  arm64/debug: Make use of the system wide safe value
  arm64: Move FP/ASIMD hwcap handling to common code
  arm64/HWCAP: Use system wide safe values
  arm64/capabilities: Make use of system wide safe value
  arm64: Delay cpu feature capability checks
  ...

32 files changed, 940 insertions, 536 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index b51f2cc22ca9..12eff928ef8b 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -193,4 +193,15 @@ lr	.req	x30		// link register
 	str	\src, [\tmp, :lo12:\sym]
 	.endm
 
+/*
+ * Annotate a function as position independent, i.e., safe to be called before
+ * the kernel virtual mapping is activated.
+ */
+#define ENDPIPROC(x)			\
+	.globl	__pi_##x;		\
+	.type 	__pi_##x, %function;	\
+	.set	__pi_##x, x;		\
+	.size	__pi_##x, . - x;	\
+	ENDPROC(x)
+
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 1e247ac2601a..f3a3586a421c 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -55,13 +55,42 @@
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
 #define atomic_set(v, i)		WRITE_ONCE(((v)->counter), (i))
+
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_add_return_acquire	atomic_add_return_acquire
+#define atomic_add_return_release	atomic_add_return_release
+#define atomic_add_return		atomic_add_return
+
+#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_sub_return_acquire	atomic_sub_return_acquire
+#define atomic_sub_return_release	atomic_sub_return_release
+#define atomic_sub_return		atomic_sub_return
+
+#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+
+#define atomic_xchg_relaxed(v, new)	xchg_relaxed(&((v)->counter), (new))
+#define atomic_xchg_acquire(v, new)	xchg_acquire(&((v)->counter), (new))
+#define atomic_xchg_release(v, new)	xchg_release(&((v)->counter), (new))
 #define atomic_xchg(v, new)		xchg(&((v)->counter), (new))
+
+#define atomic_cmpxchg_relaxed(v, old, new)				\
+	cmpxchg_relaxed(&((v)->counter), (old), (new))
+#define atomic_cmpxchg_acquire(v, old, new)				\
+	cmpxchg_acquire(&((v)->counter), (old), (new))
+#define atomic_cmpxchg_release(v, old, new)				\
+	cmpxchg_release(&((v)->counter), (old), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
 #define atomic_inc(v)			atomic_add(1, (v))
 #define atomic_dec(v)			atomic_sub(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
 #define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
 #define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 #define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
@@ -75,13 +104,39 @@
 #define ATOMIC64_INIT			ATOMIC_INIT
 #define atomic64_read			atomic_read
 #define atomic64_set			atomic_set
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_add_return_acquire	atomic64_add_return_acquire
+#define atomic64_add_return_release	atomic64_add_return_release
+#define atomic64_add_return		atomic64_add_return
+
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_sub_return_acquire	atomic64_sub_return_acquire
+#define atomic64_sub_return_release	atomic64_sub_return_release
+#define atomic64_sub_return		atomic64_sub_return
+
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
+
+#define atomic64_xchg_relaxed		atomic_xchg_relaxed
+#define atomic64_xchg_acquire		atomic_xchg_acquire
+#define atomic64_xchg_release		atomic_xchg_release
 #define atomic64_xchg			atomic_xchg
+
+#define atomic64_cmpxchg_relaxed	atomic_cmpxchg_relaxed
+#define atomic64_cmpxchg_acquire	atomic_cmpxchg_acquire
+#define atomic64_cmpxchg_release	atomic_cmpxchg_release
 #define atomic64_cmpxchg		atomic_cmpxchg
 
 #define atomic64_inc(v)			atomic64_add(1, (v))
 #define atomic64_dec(v)			atomic64_sub(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
 #define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index b3b5c4ae3800..74d0b8eb0799 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -55,40 +55,47 @@ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v))				\
 }									\
 __LL_SC_EXPORT(atomic_##op);
 
-#define ATOMIC_OP_RETURN(op, asm_op)					\
+#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE int							\
-__LL_SC_PREFIX(atomic_##op##_return(int i, atomic_t *v))		\
+__LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v))		\
 {									\
 	unsigned long tmp;						\
 	int result;							\
 									\
-	asm volatile("// atomic_" #op "_return\n"			\
+	asm volatile("// atomic_" #op "_return" #name "\n"		\
 "	prfm	pstl1strm, %2\n"					\
-"1:	ldxr	%w0, %2\n"						\
+"1:	ld" #acq "xr	%w0, %2\n"					\
 "	" #asm_op "	%w0, %w0, %w3\n"				\
-"	stlxr	%w1, %w0, %2\n"						\
-"	cbnz	%w1, 1b"						\
+"	st" #rel "xr	%w1, %w0, %2\n"					\
+"	cbnz	%w1, 1b\n"						\
+"	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: "Ir" (i)							\
-	: "memory");							\
+	: cl);								\
 									\
-	smp_mb();							\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic_##op##_return);
+__LL_SC_EXPORT(atomic_##op##_return##name);
+
+#define ATOMIC_OPS(...)							\
+	ATOMIC_OP(__VA_ARGS__)						\
+	ATOMIC_OP_RETURN(        , dmb ish,  , l, "memory", __VA_ARGS__)
 
-#define ATOMIC_OPS(op, asm_op)						\
-	ATOMIC_OP(op, asm_op)						\
-	ATOMIC_OP_RETURN(op, asm_op)
+#define ATOMIC_OPS_RLX(...)						\
+	ATOMIC_OPS(__VA_ARGS__)						\
+	ATOMIC_OP_RETURN(_relaxed,        ,  ,  ,         , __VA_ARGS__)\
+	ATOMIC_OP_RETURN(_acquire,        , a,  , "memory", __VA_ARGS__)\
+	ATOMIC_OP_RETURN(_release,        ,  , l, "memory", __VA_ARGS__)
 
-ATOMIC_OPS(add, add)
-ATOMIC_OPS(sub, sub)
+ATOMIC_OPS_RLX(add, add)
+ATOMIC_OPS_RLX(sub, sub)
 
 ATOMIC_OP(and, and)
 ATOMIC_OP(andnot, bic)
 ATOMIC_OP(or, orr)
 ATOMIC_OP(xor, eor)
 
+#undef ATOMIC_OPS_RLX
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -111,40 +118,47 @@ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v))			\
 }									\
 __LL_SC_EXPORT(atomic64_##op);
 
-#define ATOMIC64_OP_RETURN(op, asm_op)					\
+#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
 __LL_SC_INLINE long							\
-__LL_SC_PREFIX(atomic64_##op##_return(long i, atomic64_t *v))		\
+__LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v))	\
 {									\
 	long result;							\
 	unsigned long tmp;						\
 									\
-	asm volatile("// atomic64_" #op "_return\n"			\
+	asm volatile("// atomic64_" #op "_return" #name "\n"		\
 "	prfm	pstl1strm, %2\n"					\
-"1:	ldxr	%0, %2\n"						\
+"1:	ld" #acq "xr	%0, %2\n"					\
 "	" #asm_op "	%0, %0, %3\n"					\
-"	stlxr	%w1, %0, %2\n"						\
-"	cbnz	%w1, 1b"						\
+"	st" #rel "xr	%w1, %0, %2\n"					\
+"	cbnz	%w1, 1b\n"						\
+"	" #mb								\
 	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
 	: "Ir" (i)							\
-	: "memory");							\
+	: cl);								\
 									\
-	smp_mb();							\
 	return result;							\
 }									\
-__LL_SC_EXPORT(atomic64_##op##_return);
+__LL_SC_EXPORT(atomic64_##op##_return##name);
+
+#define ATOMIC64_OPS(...)						\
+	ATOMIC64_OP(__VA_ARGS__)					\
+	ATOMIC64_OP_RETURN(, dmb ish,  , l, "memory", __VA_ARGS__)
 
-#define ATOMIC64_OPS(op, asm_op)					\
-	ATOMIC64_OP(op, asm_op)						\
-	ATOMIC64_OP_RETURN(op, asm_op)
+#define ATOMIC64_OPS_RLX(...)						\
+	ATOMIC64_OPS(__VA_ARGS__)					\
+	ATOMIC64_OP_RETURN(_relaxed,,  ,  ,         , __VA_ARGS__)	\
+	ATOMIC64_OP_RETURN(_acquire,, a,  , "memory", __VA_ARGS__)	\
+	ATOMIC64_OP_RETURN(_release,,  , l, "memory", __VA_ARGS__)
 
-ATOMIC64_OPS(add, add)
-ATOMIC64_OPS(sub, sub)
+ATOMIC64_OPS_RLX(add, add)
+ATOMIC64_OPS_RLX(sub, sub)
 
 ATOMIC64_OP(and, and)
 ATOMIC64_OP(andnot, bic)
 ATOMIC64_OP(or, orr)
 ATOMIC64_OP(xor, eor)
 
+#undef ATOMIC64_OPS_RLX
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
@@ -172,7 +186,7 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v))
 }
 __LL_SC_EXPORT(atomic64_dec_if_positive);
 
-#define __CMPXCHG_CASE(w, sz, name, mb, rel, cl)			\
+#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl)			\
 __LL_SC_INLINE unsigned long						\
 __LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
 				     unsigned long old,			\
@@ -182,7 +196,7 @@ __LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
 									\
 	asm volatile(							\
 	"	prfm	pstl1strm, %[v]\n"				\
-	"1:	ldxr" #sz "\t%" #w "[oldval], %[v]\n"			\
+	"1:	ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n"		\
 	"	eor	%" #w "[tmp], %" #w "[oldval], %" #w "[old]\n"	\
 	"	cbnz	%" #w "[tmp], 2f\n"				\
 	"	st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n"	\
@@ -199,14 +213,22 @@ __LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr,		\
 }									\
 __LL_SC_EXPORT(__cmpxchg_case_##name);
 
-__CMPXCHG_CASE(w, b,    1,        ,  ,         )
-__CMPXCHG_CASE(w, h,    2,        ,  ,         )
-__CMPXCHG_CASE(w,  ,    4,        ,  ,         )
-__CMPXCHG_CASE( ,  ,    8,        ,  ,         )
-__CMPXCHG_CASE(w, b, mb_1, dmb ish, l, "memory")
-__CMPXCHG_CASE(w, h, mb_2, dmb ish, l, "memory")
-__CMPXCHG_CASE(w,  , mb_4, dmb ish, l, "memory")
-__CMPXCHG_CASE( ,  , mb_8, dmb ish, l, "memory")
+__CMPXCHG_CASE(w, b,     1,        ,  ,  ,         )
+__CMPXCHG_CASE(w, h,     2,        ,  ,  ,         )
+__CMPXCHG_CASE(w,  ,     4,        ,  ,  ,         )
+__CMPXCHG_CASE( ,  ,     8,        ,  ,  ,         )
+__CMPXCHG_CASE(w, b, acq_1,        , a,  , "memory")
+__CMPXCHG_CASE(w, h, acq_2,        , a,  , "memory")
+__CMPXCHG_CASE(w,  , acq_4,        , a,  , "memory")
+__CMPXCHG_CASE( ,  , acq_8,        , a,  , "memory")
+__CMPXCHG_CASE(w, b, rel_1,        ,  , l, "memory")
+__CMPXCHG_CASE(w, h, rel_2,        ,  , l, "memory")
+__CMPXCHG_CASE(w,  , rel_4,        ,  , l, "memory")
+__CMPXCHG_CASE( ,  , rel_8,        ,  , l, "memory")
+__CMPXCHG_CASE(w, b,  mb_1, dmb ish,  , l, "memory")
+__CMPXCHG_CASE(w, h,  mb_2, dmb ish,  , l, "memory")
+__CMPXCHG_CASE(w,  ,  mb_4, dmb ish,  , l, "memory")
+__CMPXCHG_CASE( ,  ,  mb_8, dmb ish,  , l, "memory")
 
 #undef __CMPXCHG_CASE
 
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 55d740e63459..1fce7908e690 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -75,24 +75,32 @@ static inline void atomic_add(int i, atomic_t *v)
 	: "x30");
 }
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
+#define ATOMIC_OP_ADD_RETURN(name, mb, cl...)				\
+static inline int atomic_add_return##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(add_return##name),				\
+	/* LSE atomics */						\
+	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
+	"	add	%w[i], %w[i], w30")				\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: "x30" , ##cl);						\
+									\
+	return w0;							\
+}
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(add_return),
-	/* LSE atomics */
-	"	ldaddal	%w[i], w30, %[v]\n"
-	"	add	%w[i], %w[i], w30")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: "x30", "memory");
+ATOMIC_OP_ADD_RETURN(_relaxed,   )
+ATOMIC_OP_ADD_RETURN(_acquire,  a, "memory")
+ATOMIC_OP_ADD_RETURN(_release,  l, "memory")
+ATOMIC_OP_ADD_RETURN(        , al, "memory")
 
-	return w0;
-}
+#undef ATOMIC_OP_ADD_RETURN
 
 static inline void atomic_and(int i, atomic_t *v)
 {
@@ -128,27 +136,34 @@ static inline void atomic_sub(int i, atomic_t *v)
 	: "x30");
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	register int w0 asm ("w0") = i;
-	register atomic_t *x1 asm ("x1") = v;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(sub_return)
-	"	nop",
-	/* LSE atomics */
-	"	neg	%w[i], %w[i]\n"
-	"	ldaddal	%w[i], w30, %[v]\n"
-	"	add	%w[i], %w[i], w30")
-	: [i] "+r" (w0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: "x30", "memory");
-
-	return w0;
+#define ATOMIC_OP_SUB_RETURN(name, mb, cl...)				\
+static inline int atomic_sub_return##name(int i, atomic_t *v)		\
+{									\
+	register int w0 asm ("w0") = i;					\
+	register atomic_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC(sub_return##name)				\
+	"	nop",							\
+	/* LSE atomics */						\
+	"	neg	%w[i], %w[i]\n"					\
+	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
+	"	add	%w[i], %w[i], w30")				\
+	: [i] "+r" (w0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: "x30" , ##cl);						\
+									\
+	return w0;							\
 }
 
+ATOMIC_OP_SUB_RETURN(_relaxed,   )
+ATOMIC_OP_SUB_RETURN(_acquire,  a, "memory")
+ATOMIC_OP_SUB_RETURN(_release,  l, "memory")
+ATOMIC_OP_SUB_RETURN(        , al, "memory")
+
+#undef ATOMIC_OP_SUB_RETURN
 #undef __LL_SC_ATOMIC
 
 #define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(atomic64_##op)
@@ -201,24 +216,32 @@ static inline void atomic64_add(long i, atomic64_t *v)
 	: "x30");
 }
 
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
+static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(add_return##name),				\
+	/* LSE atomics */						\
+	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
+	"	add	%[i], %[i], x30")				\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(add_return),
-	/* LSE atomics */
-	"	ldaddal	%[i], x30, %[v]\n"
-	"	add	%[i], %[i], x30")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: "x30", "memory");
+ATOMIC64_OP_ADD_RETURN(_relaxed,   )
+ATOMIC64_OP_ADD_RETURN(_acquire,  a, "memory")
+ATOMIC64_OP_ADD_RETURN(_release,  l, "memory")
+ATOMIC64_OP_ADD_RETURN(        , al, "memory")
 
-	return x0;
-}
+#undef ATOMIC64_OP_ADD_RETURN
 
 static inline void atomic64_and(long i, atomic64_t *v)
 {
@@ -254,26 +277,34 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 	: "x30");
 }
 
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
-	register long x0 asm ("x0") = i;
-	register atomic64_t *x1 asm ("x1") = v;
+#define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
+static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
+{									\
+	register long x0 asm ("x0") = i;				\
+	register atomic64_t *x1 asm ("x1") = v;				\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	nop\n"							\
+	__LL_SC_ATOMIC64(sub_return##name)				\
+	"	nop",							\
+	/* LSE atomics */						\
+	"	neg	%[i], %[i]\n"					\
+	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
+	"	add	%[i], %[i], x30")				\
+	: [i] "+r" (x0), [v] "+Q" (v->counter)				\
+	: "r" (x1)							\
+	: "x30" , ##cl);						\
+									\
+	return x0;							\
+}
 
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(sub_return)
-	"	nop",
-	/* LSE atomics */
-	"	neg	%[i], %[i]\n"
-	"	ldaddal	%[i], x30, %[v]\n"
-	"	add	%[i], %[i], x30")
-	: [i] "+r" (x0), [v] "+Q" (v->counter)
-	: "r" (x1)
-	: "x30", "memory");
+ATOMIC64_OP_SUB_RETURN(_relaxed,   )
+ATOMIC64_OP_SUB_RETURN(_acquire,  a, "memory")
+ATOMIC64_OP_SUB_RETURN(_release,  l, "memory")
+ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 
-	return x0;
-}
+#undef ATOMIC64_OP_SUB_RETURN
 
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
@@ -333,14 +364,22 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
 	return x0;							\
 }
 
-__CMPXCHG_CASE(w, b,    1,   )
-__CMPXCHG_CASE(w, h,    2,   )
-__CMPXCHG_CASE(w,  ,    4,   )
-__CMPXCHG_CASE(x,  ,    8,   )
-__CMPXCHG_CASE(w, b, mb_1, al, "memory")
-__CMPXCHG_CASE(w, h, mb_2, al, "memory")
-__CMPXCHG_CASE(w,  , mb_4, al, "memory")
-__CMPXCHG_CASE(x,  , mb_8, al, "memory")
+__CMPXCHG_CASE(w, b,     1,   )
+__CMPXCHG_CASE(w, h,     2,   )
+__CMPXCHG_CASE(w,  ,     4,   )
+__CMPXCHG_CASE(x,  ,     8,   )
+__CMPXCHG_CASE(w, b, acq_1,  a, "memory")
+__CMPXCHG_CASE(w, h, acq_2,  a, "memory")
+__CMPXCHG_CASE(w,  , acq_4,  a, "memory")
+__CMPXCHG_CASE(x,  , acq_8,  a, "memory")
+__CMPXCHG_CASE(w, b, rel_1,  l, "memory")
+__CMPXCHG_CASE(w, h, rel_2,  l, "memory")
+__CMPXCHG_CASE(w,  , rel_4,  l, "memory")
+__CMPXCHG_CASE(x,  , rel_8,  l, "memory")
+__CMPXCHG_CASE(w, b,  mb_1, al, "memory")
+__CMPXCHG_CASE(w, h,  mb_2, al, "memory")
+__CMPXCHG_CASE(w,  ,  mb_4, al, "memory")
+__CMPXCHG_CASE(x,  ,  mb_8, al, "memory")
 
 #undef __LL_SC_CMPXCHG
 #undef __CMPXCHG_CASE
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index bde449936e2f..5082b30bc2c0 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -18,7 +18,7 @@
 
 #include <asm/cachetype.h>
 
-#define L1_CACHE_SHIFT		6
+#define L1_CACHE_SHIFT		7
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
 /*
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index c75b8d027eb1..54efedaf331f 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -115,6 +115,13 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
+static inline void __local_flush_icache_all(void)
+{
+	asm("ic iallu");
+	dsb(nsh);
+	isb();
+}
+
 static inline void __flush_icache_all(void)
 {
 	asm("ic	ialluis");
diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h
index da2fc9e3cedd..f5588692f1d4 100644
--- a/arch/arm64/include/asm/cachetype.h
+++ b/arch/arm64/include/asm/cachetype.h
@@ -34,8 +34,8 @@
 
 #define CTR_L1IP(ctr)	(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
-#define ICACHEF_ALIASING	BIT(0)
-#define ICACHEF_AIVIVT		BIT(1)
+#define ICACHEF_ALIASING	0
+#define ICACHEF_AIVIVT		1
 
 extern unsigned long __icache_flags;
 
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 899e9f1d19e4..9ea611ea69df 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -25,154 +25,151 @@
 #include <asm/barrier.h>
 #include <asm/lse.h>
 
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
-	unsigned long ret, tmp;
-
-	switch (size) {
-	case 1:
-		asm volatile(ARM64_LSE_ATOMIC_INSN(
-		/* LL/SC */
-		"	prfm	pstl1strm, %2\n"
-		"1:	ldxrb	%w0, %2\n"
-		"	stlxrb	%w1, %w3, %2\n"
-		"	cbnz	%w1, 1b\n"
-		"	dmb	ish",
-		/* LSE atomics */
-		"	nop\n"
-		"	nop\n"
-		"	swpalb	%w3, %w0, %2\n"
-		"	nop\n"
-		"	nop")
-			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)
-			: "r" (x)
-			: "memory");
-		break;
-	case 2:
-		asm volatile(ARM64_LSE_ATOMIC_INSN(
-		/* LL/SC */
-		"	prfm	pstl1strm, %2\n"
-		"1:	ldxrh	%w0, %2\n"
-		"	stlxrh	%w1, %w3, %2\n"
-		"	cbnz	%w1, 1b\n"
-		"	dmb	ish",
-		/* LSE atomics */
-		"	nop\n"
-		"	nop\n"
-		"	swpalh	%w3, %w0, %2\n"
-		"	nop\n"
-		"	nop")
-			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr)
-			: "r" (x)
-			: "memory");
-		break;
-	case 4:
-		asm volatile(ARM64_LSE_ATOMIC_INSN(
-		/* LL/SC */
-		"	prfm	pstl1strm, %2\n"
-		"1:	ldxr	%w0, %2\n"
-		"	stlxr	%w1, %w3, %2\n"
-		"	cbnz	%w1, 1b\n"
-		"	dmb	ish",
-		/* LSE atomics */
-		"	nop\n"
-		"	nop\n"
-		"	swpal	%w3, %w0, %2\n"
-		"	nop\n"
-		"	nop")
-			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr)
-			: "r" (x)
-			: "memory");
-		break;
-	case 8:
-		asm volatile(ARM64_LSE_ATOMIC_INSN(
-		/* LL/SC */
-		"	prfm	pstl1strm, %2\n"
-		"1:	ldxr	%0, %2\n"
-		"	stlxr	%w1, %3, %2\n"
-		"	cbnz	%w1, 1b\n"
-		"	dmb	ish",
-		/* LSE atomics */
-		"	nop\n"
-		"	nop\n"
-		"	swpal	%3, %0, %2\n"
-		"	nop\n"
-		"	nop")
-			: "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr)
-			: "r" (x)
-			: "memory");
-		break;
-	default:
-		BUILD_BUG();
-	}
-
-	return ret;
+/*
+ * We need separate acquire parameters for ll/sc and lse, since the full
+ * barrier case is generated as release+dmb for the former and
+ * acquire+release for the latter.
+ */
+#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl)	\
+static inline unsigned long __xchg_case_##name(unsigned long x,		\
+					       volatile void *ptr)	\
+{									\
+	unsigned long ret, tmp;						\
+									\
+	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
+	/* LL/SC */							\
+	"	prfm	pstl1strm, %2\n"				\
+	"1:	ld" #acq "xr" #sz "\t%" #w "0, %2\n"			\
+	"	st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n"		\
+	"	cbnz	%w1, 1b\n"					\
+	"	" #mb,							\
+	/* LSE atomics */						\
+	"	nop\n"							\
+	"	nop\n"							\
+	"	swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n"	\
+	"	nop\n"							\
+	"	" #nop_lse)						\
+	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)			\
+	: "r" (x)							\
+	: cl);								\
+									\
+	return ret;							\
 }
 
-#define xchg(ptr,x) \
-({ \
-	__typeof__(*(ptr)) __ret; \
-	__ret = (__typeof__(*(ptr))) \
-		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \
-	__ret; \
+__XCHG_CASE(w, b,     1,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w, h,     2,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w,  ,     4,        ,    ,  ,  ,  ,         )
+__XCHG_CASE( ,  ,     8,        ,    ,  ,  ,  ,         )
+__XCHG_CASE(w, b, acq_1,        ,    , a, a,  , "memory")
+__XCHG_CASE(w, h, acq_2,        ,    , a, a,  , "memory")
+__XCHG_CASE(w,  , acq_4,        ,    , a, a,  , "memory")
+__XCHG_CASE( ,  , acq_8,        ,    , a, a,  , "memory")
+__XCHG_CASE(w, b, rel_1,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w, h, rel_2,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w,  , rel_4,        ,    ,  ,  , l, "memory")
+__XCHG_CASE( ,  , rel_8,        ,    ,  ,  , l, "memory")
+__XCHG_CASE(w, b,  mb_1, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE(w, h,  mb_2, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE(w,  ,  mb_4, dmb ish, nop,  , a, l, "memory")
+__XCHG_CASE( ,  ,  mb_8, dmb ish, nop,  , a, l, "memory")
+
+#undef __XCHG_CASE
+
+#define __XCHG_GEN(sfx)							\
+static inline unsigned long __xchg##sfx(unsigned long x,		\
+					volatile void *ptr,		\
+					int size)			\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __xchg_case##sfx##_1(x, ptr);			\
+	case 2:								\
+		return __xchg_case##sfx##_2(x, ptr);			\
+	case 4:								\
+		return __xchg_case##sfx##_4(x, ptr);			\
+	case 8:								\
+		return __xchg_case##sfx##_8(x, ptr);			\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
+}
+
+__XCHG_GEN()
+__XCHG_GEN(_acq)
+__XCHG_GEN(_rel)
+__XCHG_GEN(_mb)
+
+#undef __XCHG_GEN
+
+#define __xchg_wrapper(sfx, ptr, x)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__ret = (__typeof__(*(ptr)))					\
+		__xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret;								\
 })
 
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		return __cmpxchg_case_1(ptr, (u8)old, new);
-	case 2:
-		return __cmpxchg_case_2(ptr, (u16)old, new);
-	case 4:
-		return __cmpxchg_case_4(ptr, old, new);
-	case 8:
-		return __cmpxchg_case_8(ptr, old, new);
-	default:
-		BUILD_BUG();
-	}
-
-	unreachable();
+/* xchg */
+#define xchg_relaxed(...)	__xchg_wrapper(    , __VA_ARGS__)
+#define xchg_acquire(...)	__xchg_wrapper(_acq, __VA_ARGS__)
+#define xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
+#define xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
+
+#define __CMPXCHG_GEN(sfx)						\
+static inline unsigned long __cmpxchg##sfx(volatile void *ptr,		\
+					   unsigned long old,		\
+					   unsigned long new,		\
+					   int size)			\
+{									\
+	switch (size) {							\
+	case 1:								\
+		return __cmpxchg_case##sfx##_1(ptr, (u8)old, new);	\
+	case 2:								\
+		return __cmpxchg_case##sfx##_2(ptr, (u16)old, new);	\
+	case 4:								\
+		return __cmpxchg_case##sfx##_4(ptr, old, new);		\
+	case 8:								\
+		return __cmpxchg_case##sfx##_8(ptr, old, new);		\
+	default:							\
+		BUILD_BUG();						\
+	}								\
+									\
+	unreachable();							\
 }
 
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		return __cmpxchg_case_mb_1(ptr, (u8)old, new);
-	case 2:
-		return __cmpxchg_case_mb_2(ptr, (u16)old, new);
-	case 4:
-		return __cmpxchg_case_mb_4(ptr, old, new);
-	case 8:
-		return __cmpxchg_case_mb_8(ptr, old, new);
-	default:
-		BUILD_BUG();
-	}
-
-	unreachable();
-}
+__CMPXCHG_GEN()
+__CMPXCHG_GEN(_acq)
+__CMPXCHG_GEN(_rel)
+__CMPXCHG_GEN(_mb)
 
-#define cmpxchg(ptr, o, n) \
-({ \
-	__typeof__(*(ptr)) __ret; \
-	__ret = (__typeof__(*(ptr))) \
-		__cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \
-			     sizeof(*(ptr))); \
-	__ret; \
-})
+#undef __CMPXCHG_GEN
 
-#define cmpxchg_local(ptr, o, n) \
-({ \
-	__typeof__(*(ptr)) __ret; \
-	__ret = (__typeof__(*(ptr))) \
-		__cmpxchg((ptr), (unsigned long)(o), \
-			  (unsigned long)(n), sizeof(*(ptr))); \
-	__ret; \
+#define __cmpxchg_wrapper(sfx, ptr, o, n)				\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	__ret = (__typeof__(*(ptr)))					\
+		__cmpxchg##sfx((ptr), (unsigned long)(o),		\
+				(unsigned long)(n), sizeof(*(ptr)));	\
+	__ret;								\
 })
 
+/* cmpxchg */
+#define cmpxchg_relaxed(...)	__cmpxchg_wrapper(    , __VA_ARGS__)
+#define cmpxchg_acquire(...)	__cmpxchg_wrapper(_acq, __VA_ARGS__)
+#define cmpxchg_release(...)	__cmpxchg_wrapper(_rel, __VA_ARGS__)
+#define cmpxchg(...)		__cmpxchg_wrapper( _mb, __VA_ARGS__)
+#define cmpxchg_local		cmpxchg_relaxed
+
+/* cmpxchg64 */
+#define cmpxchg64_relaxed	cmpxchg_relaxed
+#define cmpxchg64_acquire	cmpxchg_acquire
+#define cmpxchg64_release	cmpxchg_release
+#define cmpxchg64		cmpxchg
+#define cmpxchg64_local		cmpxchg_local
+
+/* cmpxchg_double */
 #define system_has_cmpxchg_double()     1
 
 #define __cmpxchg_double_check(ptr1, ptr2)					\
@@ -202,6 +199,7 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret; \
 })
 
+/* this_cpu_cmpxchg */
 #define _protect_cmpxchg_local(pcp, o, n)			\
 ({								\
 	typeof(*raw_cpu_ptr(&(pcp))) __ret;			\
@@ -227,9 +225,4 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
 	__ret;								\
 })
 
-#define cmpxchg64(ptr,o,n)		cmpxchg((ptr),(o),(n))
-#define cmpxchg64_local(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
-
-#define cmpxchg64_relaxed(ptr,o,n)	cmpxchg_local((ptr),(o),(n))
-
 #endif	/* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 8e797b2fcc01..b5e9cee4b5f8 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -63,4 +63,8 @@ DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
 void cpuinfo_store_cpu(void);
 void __init cpuinfo_store_boot_cpu(void);
 
+void __init init_cpu_features(struct cpuinfo_arm64 *info);
+void update_cpu_features(int cpu, struct cpuinfo_arm64 *info,
+				 struct cpuinfo_arm64 *boot);
+
 #endif /* __ASM_CPU_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index dbc78d2b8cc6..11d5bb0fdd54 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -10,6 +10,7 @@
 #define __ASM_CPUFEATURE_H
 
 #include <asm/hwcap.h>
+#include <asm/sysreg.h>
 
 /*
  * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
@@ -35,11 +36,42 @@
 
 #include <linux/kernel.h>
 
+/* CPU feature register tracking */
+enum ftr_type {
+	FTR_EXACT,	/* Use a predefined safe value */
+	FTR_LOWER_SAFE,	/* Smaller value is safe */
+	FTR_HIGHER_SAFE,/* Bigger value is safe */
+};
+
+#define FTR_STRICT	true	/* SANITY check strict matching required */
+#define FTR_NONSTRICT	false	/* SANITY check ignored */
+
+struct arm64_ftr_bits {
+	bool		strict;	  /* CPU Sanity check: strict matching required ? */
+	enum ftr_type	type;
+	u8		shift;
+	u8		width;
+	s64		safe_val; /* safe value for discrete features */
+};
+
+/*
+ * @arm64_ftr_reg - Feature register
+ * @strict_mask		Bits which should match across all CPUs for sanity.
+ * @sys_val		Safe value across the CPUs (system view)
+ */
+struct arm64_ftr_reg {
+	u32			sys_id;
+	const char		*name;
+	u64			strict_mask;
+	u64			sys_val;
+	struct arm64_ftr_bits	*ftr_bits;
+};
+
 struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
 	bool (*matches)(const struct arm64_cpu_capabilities *);
-	void (*enable)(void);
+	void (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
 			u32 midr_model;
@@ -47,8 +79,11 @@ struct arm64_cpu_capabilities {
 		};
 
 		struct {	/* Feature register checking */
+			u32 sys_reg;
 			int field_pos;
 			int min_field_value;
+			int hwcap_type;
+			unsigned long hwcap;
 		};
 	};
 };
@@ -76,19 +111,59 @@ static inline void cpus_set_cap(unsigned int num)
 		__set_bit(num, cpu_hwcaps);
 }
 
-static inline int __attribute_const__ cpuid_feature_extract_field(u64 features,
-								  int field)
+static inline int __attribute_const__
+cpuid_feature_extract_field_width(u64 features, int field, int width)
+{
+	return (s64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline int __attribute_const__
+cpuid_feature_extract_field(u64 features, int field)
+{
+	return cpuid_feature_extract_field_width(features, field, 4);
+}
+
+static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+{
+	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
+}
+
+static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+{
+	return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+}
+
+static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
 {
-	return (s64)(features << (64 - 4 - field)) >> (64 - 4);
+	return cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL_SHIFT) == 0x1 ||
+		cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1;
 }
 
+void __init setup_cpu_features(void);
 
-void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
+void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void check_local_cpu_errata(void);
-void check_local_cpu_features(void);
-bool cpu_supports_mixed_endian_el0(void);
-bool system_supports_mixed_endian_el0(void);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void verify_local_cpu_capabilities(void);
+#else
+static inline void verify_local_cpu_capabilities(void)
+{
+}
+#endif
+
+u64 read_system_reg(u32 id);
+
+static inline bool cpu_supports_mixed_endian_el0(void)
+{
+	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
+}
+
+static inline bool system_supports_mixed_endian_el0(void)
+{
+	return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
+}
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 100a3d1b17c8..1a5949364ed0 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,15 +75,6 @@
 
 #define CAVIUM_CPU_PART_THUNDERX	0x0A1
 
-#define ID_AA64MMFR0_BIGENDEL0_SHIFT	16
-#define ID_AA64MMFR0_BIGENDEL0_MASK	(0xf << ID_AA64MMFR0_BIGENDEL0_SHIFT)
-#define ID_AA64MMFR0_BIGENDEL0(mmfr0)	\
-	(((mmfr0) & ID_AA64MMFR0_BIGENDEL0_MASK) >> ID_AA64MMFR0_BIGENDEL0_SHIFT)
-#define ID_AA64MMFR0_BIGEND_SHIFT	8
-#define ID_AA64MMFR0_BIGEND_MASK	(0xf << ID_AA64MMFR0_BIGEND_SHIFT)
-#define ID_AA64MMFR0_BIGEND(mmfr0)	\
-	(((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
-
 #ifndef __ASSEMBLY__
 
 /*
@@ -115,12 +106,6 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 {
 	return read_cpuid(CTR_EL0);
 }
-
-static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
-{
-	return (ID_AA64MMFR0_BIGEND(mmfr0) == 0x1) ||
-		(ID_AA64MMFR0_BIGENDEL0(mmfr0) == 0x1);
-}
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 8b9884c726ad..309704544d22 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -17,6 +17,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
+#include <linux/sizes.h>
 #include <asm/boot.h>
 #include <asm/page.h>
 
@@ -55,11 +56,7 @@ enum fixed_addresses {
 	 * Temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
 	 */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define NR_FIX_BTMAPS		4
-#else
-#define NR_FIX_BTMAPS		64
-#endif
+#define NR_FIX_BTMAPS		(SZ_256K / PAGE_SIZE)
 #define FIX_BTMAPS_SLOTS	7
 #define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 4c47cb2fbb52..e54415ec6935 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -17,6 +17,7 @@
 #define __ASM_HW_BREAKPOINT_H
 
 #include <asm/cputype.h>
+#include <asm/cpufeature.h>
 
 #ifdef __KERNEL__
 
@@ -137,13 +138,17 @@ extern struct pmu perf_ops_bp;
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
-	return ((read_cpuid(ID_AA64DFR0_EL1) >> 12) & 0xf) + 1;
+	return 1 +
+		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+						ID_AA64DFR0_BRPS_SHIFT);
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
-	return ((read_cpuid(ID_AA64DFR0_EL1) >> 20) & 0xf) + 1;
+	return 1 +
+		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+						ID_AA64DFR0_WRPS_SHIFT);
 }
 
 #endif	/* __KERNEL__ */
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 0ad735166d9f..400b80b49595 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -52,6 +52,14 @@
 extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
 #endif
 
+enum {
+	CAP_HWCAP = 1,
+#ifdef CONFIG_COMPAT
+	CAP_COMPAT_HWCAP,
+	CAP_COMPAT_HWCAP2,
+#endif
+};
+
 extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index bbb251b14746..09169296c3cc 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,7 +7,6 @@
 
 struct pt_regs;
 
-extern void migrate_irqs(void);
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 static inline void acpi_irq_init(void)
diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h
new file mode 100644
index 000000000000..2774fa384c47
--- /dev/null
+++ b/arch/arm64/include/asm/kasan.h
@@ -0,0 +1,38 @@
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+#include <linux/linkage.h>
+#include <asm/memory.h>
+
+/*
+ * KASAN_SHADOW_START: beginning of the kernel virtual addresses.
+ * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses.
+ */
+#define KASAN_SHADOW_START      (VA_START)
+#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1UL << (VA_BITS - 3)))
+
+/*
+ * This value is used to map an address to the corresponding shadow
+ * address by the following formula:
+ *     shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET;
+ *
+ * (1 << 61) shadow addresses - [KASAN_SHADOW_OFFSET,KASAN_SHADOW_END]
+ * cover all 64-bits of virtual addresses. So KASAN_SHADOW_OFFSET
+ * should satisfy the following equation:
+ *      KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - (1ULL << 61)
+ */
+#define KASAN_SHADOW_OFFSET     (KASAN_SHADOW_END - (1ULL << (64 - 3)))
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+
+#else
+static inline void kasan_init(void) { }
+#endif
+
+#endif
+#endif
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
new file mode 100644
index 000000000000..a459714ee29e
--- /dev/null
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -0,0 +1,83 @@
+/*
+ * Kernel page table mapping
+ *
+ * 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_KERNEL_PGTABLE_H
+#define __ASM_KERNEL_PGTABLE_H
+
+
+/*
+ * The linear mapping and the start of memory are both 2M aligned (per
+ * the arm64 booting.txt requirements). Hence we can use section mapping
+ * with 4K (section size = 2M) but not with 16K (section size = 32M) or
+ * 64K (section size = 512M).
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define ARM64_SWAPPER_USES_SECTION_MAPS 1
+#else
+#define ARM64_SWAPPER_USES_SECTION_MAPS 0
+#endif
+
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
+ * map the kernel. With the 64K page configuration, swapper and idmap need to
+ * map to pte level. The swapper also maps the FDT (see __create_page_tables
+ * for more information). Note that the number of ID map translation levels
+ * could be increased on the fly if system RAM is out of reach for the default
+ * VA range, so pages required to map highest possible PA are reserved in all
+ * cases.
+ */
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
+#define IDMAP_PGTABLE_LEVELS	(ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT) - 1)
+#else
+#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS)
+#define IDMAP_PGTABLE_LEVELS	(ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT))
+#endif
+
+#define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
+#define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
+
+/* Initial memory map size */
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_BLOCK_SHIFT	SECTION_SHIFT
+#define SWAPPER_BLOCK_SIZE	SECTION_SIZE
+#define SWAPPER_TABLE_SHIFT	PUD_SHIFT
+#else
+#define SWAPPER_BLOCK_SHIFT	PAGE_SHIFT
+#define SWAPPER_BLOCK_SIZE	PAGE_SIZE
+#define SWAPPER_TABLE_SHIFT	PMD_SHIFT
+#endif
+
+/* The size of the initial kernel direct mapping */
+#define SWAPPER_INIT_MAP_SIZE	(_AC(1, UL) << SWAPPER_TABLE_SHIFT)
+
+/*
+ * Initial memory map attributes.
+ */
+#define SWAPPER_PTE_FLAGS	(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
+#define SWAPPER_PMD_FLAGS	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
+
+#if ARM64_SWAPPER_USES_SECTION_MAPS
+#define SWAPPER_MM_MMUFLAGS	(PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
+#else
+#define SWAPPER_MM_MMUFLAGS	(PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS)
+#endif
+
+
+#endif	/* __ASM_KERNEL_PGTABLE_H */
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 67027c611dbd..853953cd1f08 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -42,12 +42,14 @@
  * PAGE_OFFSET - the virtual address of the start of the kernel image (top
  *		 (VA_BITS - 1))
  * VA_BITS - the maximum number of bits for virtual addresses.
+ * VA_START - the first kernel virtual address.
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 128MB of the kernel text.
  */
 #define VA_BITS			(CONFIG_ARM64_VA_BITS)
+#define VA_START		(UL(0xffffffffffffffff) << VA_BITS)
 #define PAGE_OFFSET		(UL(0xffffffffffffffff) << (VA_BITS - 1))
 #define MODULES_END		(PAGE_OFFSET)
 #define MODULES_VADDR		(MODULES_END - SZ_64M)
@@ -68,10 +70,6 @@
 
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
 
-#if TASK_SIZE_64 > MODULES_VADDR
-#error Top of 64-bit user space clashes with start of module space
-#endif
-
 /*
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 030208767185..990124a67eeb 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -17,15 +17,16 @@
 #define __ASM_MMU_H
 
 typedef struct {
-	unsigned int id;
-	raw_spinlock_t id_lock;
-	void *vdso;
+	atomic64_t	id;
+	void		*vdso;
 } mm_context_t;
 
-#define INIT_MM_CONTEXT(name) \
-	.context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock),
-
-#define ASID(mm)	((mm)->context.id & 0xffff)
+/*
+ * This macro is only used by the TLBI code, which cannot race with an
+ * ASID change and therefore doesn't need to reload the counter using
+ * atomic64_read.
+ */
+#define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
 extern void paging_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 8ec41e5f56f0..c0e87898ba96 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -28,13 +28,6 @@
 #include <asm/cputype.h>
 #include <asm/pgtable.h>
 
-#define MAX_ASID_BITS	16
-
-extern unsigned int cpu_last_asid;
-
-void __init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void __new_context(struct mm_struct *mm);
-
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 static inline void contextidr_thread_switch(struct task_struct *next)
 {
@@ -77,96 +70,38 @@ static inline bool __cpu_uses_extended_idmap(void)
 		unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)));
 }
 
-static inline void __cpu_set_tcr_t0sz(u64 t0sz)
-{
-	unsigned long tcr;
-
-	if (__cpu_uses_extended_idmap())
-		asm volatile (
-		"	mrs	%0, tcr_el1	;"
-		"	bfi	%0, %1, %2, %3	;"
-		"	msr	tcr_el1, %0	;"
-		"	isb"
-		: "=&r" (tcr)
-		: "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
-}
-
-/*
- * Set TCR.T0SZ to the value appropriate for activating the identity map.
- */
-static inline void cpu_set_idmap_tcr_t0sz(void)
-{
-	__cpu_set_tcr_t0sz(idmap_t0sz);
-}
-
 /*
  * Set TCR.T0SZ to its default value (based on VA_BITS)
  */
 static inline void cpu_set_default_tcr_t0sz(void)
 {
-	__cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS));
-}
-
-static inline void switch_new_context(struct mm_struct *mm)
-{
-	unsigned long flags;
-
-	__new_context(mm);
+	unsigned long tcr;
 
-	local_irq_save(flags);
-	cpu_switch_mm(mm->pgd, mm);
-	local_irq_restore(flags);
-}
+	if (!__cpu_uses_extended_idmap())
+		return;
 
-static inline void check_and_switch_context(struct mm_struct *mm,
-					    struct task_struct *tsk)
-{
-	/*
-	 * Required during context switch to avoid speculative page table
-	 * walking with the wrong TTBR.
-	 */
-	cpu_set_reserved_ttbr0();
-
-	if (!((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS))
-		/*
-		 * The ASID is from the current generation, just switch to the
-		 * new pgd. This condition is only true for calls from
-		 * context_switch() and interrupts are already disabled.
-		 */
-		cpu_switch_mm(mm->pgd, mm);
-	else if (irqs_disabled())
-		/*
-		 * Defer the new ASID allocation until after the context
-		 * switch critical region since __new_context() cannot be
-		 * called with interrupts disabled.
-		 */
-		set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM);
-	else
-		/*
-		 * That is a direct call to switch_mm() or activate_mm() with
-		 * interrupts enabled and a new context.
-		 */
-		switch_new_context(mm);
+	asm volatile (
+	"	mrs	%0, tcr_el1	;"
+	"	bfi	%0, %1, %2, %3	;"
+	"	msr	tcr_el1, %0	;"
+	"	isb"
+	: "=&r" (tcr)
+	: "r"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
 }
 
-#define init_new_context(tsk,mm)	(__init_new_context(tsk,mm),0)
+/*
+ * It would be nice to return ASIDs back to the allocator, but unfortunately
+ * that introduces a race with a generation rollover where we could erroneously
+ * free an ASID allocated in a future generation. We could workaround this by
+ * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap),
+ * but we'd then need to make sure that we didn't dirty any TLBs afterwards.
+ * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you
+ * take CPU migration into account.
+ */
 #define destroy_context(mm)		do { } while(0)
+void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define finish_arch_post_lock_switch \
-	finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
-{
-	if (test_and_clear_thread_flag(TIF_SWITCH_MM)) {
-		struct mm_struct *mm = current->mm;
-		unsigned long flags;
-
-		__new_context(mm);
-
-		local_irq_save(flags);
-		cpu_switch_mm(mm->pgd, mm);
-		local_irq_restore(flags);
-	}
-}
+#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
@@ -194,6 +129,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	unsigned int cpu = smp_processor_id();
 
+	if (prev == next)
+		return;
+
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
 	 * active for kernel addresses in TTBR1. Just set the reserved TTBR0.
@@ -203,8 +141,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		return;
 	}
 
-	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
-		check_and_switch_context(next, tsk);
+	check_and_switch_context(next, cpu);
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 7d9c7e4a424b..9b2f5a9d019d 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -20,31 +20,22 @@
 #define __ASM_PAGE_H
 
 /* PAGE_SHIFT determines the page size */
+/* CONT_SHIFT determines the number of pages which can be tracked together  */
 #ifdef CONFIG_ARM64_64K_PAGES
 #define PAGE_SHIFT		16
+#define CONT_SHIFT		5
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define PAGE_SHIFT		14
+#define CONT_SHIFT		7
 #else
 #define PAGE_SHIFT		12
+#define CONT_SHIFT		4
 #endif
-#define PAGE_SIZE		(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_SIZE		(_AC(1, UL) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
-/*
- * The idmap and swapper page tables need some space reserved in the kernel
- * image. Both require pgd, pud (4 levels only) and pmd tables to (section)
- * map the kernel. With the 64K page configuration, swapper and idmap need to
- * map to pte level. The swapper also maps the FDT (see __create_page_tables
- * for more information). Note that the number of ID map translation levels
- * could be increased on the fly if system RAM is out of reach for the default
- * VA range, so 3 pages are reserved in all cases.
- */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS)
-#else
-#define SWAPPER_PGTABLE_LEVELS	(CONFIG_PGTABLE_LEVELS - 1)
-#endif
-
-#define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(3 * PAGE_SIZE)
+#define CONT_SIZE		(_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT))
+#define CONT_MASK		(~(CONT_SIZE-1))
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 76420568d66a..c15053902942 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -27,6 +27,7 @@
 #define check_pgt_cache()		do { } while (0)
 
 #define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
 
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index 24154b055835..d6739e836f7b 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -16,13 +16,46 @@
 #ifndef __ASM_PGTABLE_HWDEF_H
 #define __ASM_PGTABLE_HWDEF_H
 
+/*
+ * Number of page-table levels required to address 'va_bits' wide
+ * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT)
+ * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence:
+ *
+ *  levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3))
+ *
+ * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d))
+ *
+ * We cannot include linux/kernel.h which defines DIV_ROUND_UP here
+ * due to build issues. So we open code DIV_ROUND_UP here:
+ *
+ *	((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3))
+ *
+ * which gets simplified as :
+ */
+#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3))
+
+/*
+ * Size mapped by an entry at level n ( 0 <= n <= 3)
+ * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits
+ * in the final page. The maximum number of translation levels supported by
+ * the architecture is 4. Hence, starting at at level n, we have further
+ * ((4 - n) - 1) levels of translation excluding the offset within the page.
+ * So, the total number of bits mapped by an entry at level n is :
+ *
+ *  ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT
+ *
+ * Rearranging it a bit we get :
+ *   (4 - n) * (PAGE_SHIFT - 3) + 3
+ */
+#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n)	((PAGE_SHIFT - 3) * (4 - (n)) + 3)
+
 #define PTRS_PER_PTE		(1 << (PAGE_SHIFT - 3))
 
 /*
  * PMD_SHIFT determines the size a level 2 page table entry can map.
  */
 #if CONFIG_PGTABLE_LEVELS > 2
-#define PMD_SHIFT		((PAGE_SHIFT - 3) * 2 + 3)
+#define PMD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
 #define PMD_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
 #define PTRS_PER_PMD		PTRS_PER_PTE
@@ -32,7 +65,7 @@
  * PUD_SHIFT determines the size a level 1 page table entry can map.
  */
 #if CONFIG_PGTABLE_LEVELS > 3
-#define PUD_SHIFT		((PAGE_SHIFT - 3) * 3 + 3)
+#define PUD_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
 #define PUD_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_MASK		(~(PUD_SIZE-1))
 #define PTRS_PER_PUD		PTRS_PER_PTE
@@ -42,7 +75,7 @@
  * PGDIR_SHIFT determines the size a top-level page table entry can map
  * (depending on the configuration, this level can be 0, 1 or 2).
  */
-#define PGDIR_SHIFT		((PAGE_SHIFT - 3) * CONFIG_PGTABLE_LEVELS + 3)
+#define PGDIR_SHIFT		ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS)
 #define PGDIR_SIZE		(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE-1))
 #define PTRS_PER_PGD		(1 << (VA_BITS - PGDIR_SHIFT))
@@ -55,6 +88,13 @@
 #define SECTION_MASK		(~(SECTION_SIZE-1))
 
 /*
+ * Contiguous page definitions.
+ */
+#define CONT_PTES		(_AC(1, UL) << CONT_SHIFT)
+/* the the numerical offset of the PTE within a range of CONT_PTES */
+#define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
+
+/*
  * Hardware page table definitions.
  *
  * Level 1 descriptor (PUD).
@@ -83,6 +123,7 @@
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)
 #define PMD_SECT_AF		(_AT(pmdval_t, 1) << 10)
 #define PMD_SECT_NG		(_AT(pmdval_t, 1) << 11)
+#define PMD_SECT_CONT		(_AT(pmdval_t, 1) << 52)
 #define PMD_SECT_PXN		(_AT(pmdval_t, 1) << 53)
 #define PMD_SECT_UXN		(_AT(pmdval_t, 1) << 54)
 
@@ -105,6 +146,7 @@
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
 #define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
+#define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 571ca0ed4f05..f3acf421ded4 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -41,7 +41,14 @@
  *	fixed mappings and modules
  */
 #define VMEMMAP_SIZE		ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
-#define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
+
+#ifndef CONFIG_KASAN
+#define VMALLOC_START		(VA_START)
+#else
+#include <asm/kasan.h>
+#define VMALLOC_START		(KASAN_SHADOW_END + SZ_64K)
+#endif
+
 #define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
@@ -74,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
+#define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
 #define PAGE_HYP		__pgprot(_PAGE_DEFAULT | PTE_HYP)
 #define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
@@ -142,6 +150,7 @@ extern struct page *empty_zero_page;
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
+#define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -204,6 +213,16 @@ static inline pte_t pte_mkspecial(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_SPECIAL));
 }
 
+static inline pte_t pte_mkcont(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_CONT));
+}
+
+static inline pte_t pte_mknoncont(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_CONT));
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
@@ -648,14 +667,17 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB for user mappings, so make sure that
-	 * the page table write is visible.
+	 * We don't do anything here, so there's a very small chance of
+	 * us retaking a user fault which we just fixed up. The alternative
+	 * is doing a dsb(ishst), but that penalises the fastpath.
 	 */
-	dsb(ishst);
 }
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
+#define kc_vaddr_to_offset(v)	((v) & ~VA_START)
+#define kc_offset_to_vaddr(o)	((o) | VA_START)
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_PGTABLE_H */
diff --git a/arch/arm64/include/asm/pmu.h b/arch/arm64/include/asm/pmu.h
deleted file mode 100644
index b7710a59672c..000000000000
--- a/arch/arm64/include/asm/pmu.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Based on arch/arm/include/asm/pmu.h
- *
- * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
- * Copyright (C) 2012 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_PMU_H
-#define __ASM_PMU_H
-
-#ifdef CONFIG_HW_PERF_EVENTS
-
-/* 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;
-
-	/*
-	 * 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.
-	 */
-	unsigned long           *used_mask;
-
-	/*
-	 * Hardware lock to serialize accesses to PMU registers. Needed for the
-	 * read/modify/write sequences.
-	 */
-	raw_spinlock_t		pmu_lock;
-};
-
-struct arm_pmu {
-	struct pmu		pmu;
-	cpumask_t		active_irqs;
-	int			*irq_affinity;
-	const char		*name;
-	irqreturn_t		(*handle_irq)(int irq_num, void *dev);
-	void			(*enable)(struct hw_perf_event *evt, int idx);
-	void			(*disable)(struct hw_perf_event *evt, int idx);
-	int			(*get_event_idx)(struct pmu_hw_events *hw_events,
-						 struct hw_perf_event *hwc);
-	int			(*set_event_filter)(struct hw_perf_event *evt,
-						    struct perf_event_attr *attr);
-	u32			(*read_counter)(int idx);
-	void			(*write_counter)(int idx, u32 val);
-	void			(*start)(void);
-	void			(*stop)(void);
-	void			(*reset)(void *);
-	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	*(*get_hw_events)(void);
-};
-
-#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
-
-int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type);
-
-u64 armpmu_event_update(struct perf_event *event,
-			struct hw_perf_event *hwc,
-			int idx);
-
-int armpmu_event_set_period(struct perf_event *event,
-			    struct hw_perf_event *hwc,
-			    int idx);
-
-#endif /* CONFIG_HW_PERF_EVENTS */
-#endif /* __ASM_PMU_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 98f32355dc97..4acb7ca94fcd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x)
 
 #endif
 
-void cpu_enable_pan(void);
+void cpu_enable_pan(void *__unused);
 
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 536274ed292e..e9e5467e0bf4 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -83,14 +83,14 @@
 #define compat_sp	regs[13]
 #define compat_lr	regs[14]
 #define compat_sp_hyp	regs[15]
-#define compat_sp_irq	regs[16]
-#define compat_lr_irq	regs[17]
-#define compat_sp_svc	regs[18]
-#define compat_lr_svc	regs[19]
-#define compat_sp_abt	regs[20]
-#define compat_lr_abt	regs[21]
-#define compat_sp_und	regs[22]
-#define compat_lr_und	regs[23]
+#define compat_lr_irq	regs[16]
+#define compat_sp_irq	regs[17]
+#define compat_lr_svc	regs[18]
+#define compat_sp_svc	regs[19]
+#define compat_lr_abt	regs[20]
+#define compat_sp_abt	regs[21]
+#define compat_lr_und	regs[22]
+#define compat_sp_und	regs[23]
 #define compat_r8_fiq	regs[24]
 #define compat_r9_fiq	regs[25]
 #define compat_r10_fiq	regs[26]
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index 64d2d4884a9d..2eb714c4639f 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -36,17 +36,33 @@ extern __kernel_size_t strnlen(const char *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *, const void *, __kernel_size_t);
+extern void *__memcpy(void *, const void *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMMOVE
 extern void *memmove(void *, const void *, __kernel_size_t);
+extern void *__memmove(void *, const void *, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCHR
 extern void *memchr(const void *, int, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *, int, __kernel_size_t);
+extern void *__memset(void *, int, __kernel_size_t);
 
 #define __HAVE_ARCH_MEMCMP
 extern int memcmp(const void *, const void *, size_t);
 
+
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+/*
+ * For files that are not instrumented (e.g. mm/slub.c) we
+ * should use not instrumented version of mem* functions.
+ */
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memmove(dst, src, len) __memmove(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+#endif
+
 #endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a7f3d4b2514d..d48ab5b41f52 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -22,9 +22,6 @@
 
 #include <asm/opcodes.h>
 
-#define SCTLR_EL1_CP15BEN	(0x1 << 5)
-#define SCTLR_EL1_SED		(0x1 << 8)
-
 /*
  * ARMv8 ARM reserves the following encoding for system registers:
  * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
@@ -38,12 +35,162 @@
 #define sys_reg(op0, op1, crn, crm, op2) \
 	((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
 
-#define REG_PSTATE_PAN_IMM                     sys_reg(0, 0, 4, 0, 4)
-#define SCTLR_EL1_SPAN                         (1 << 23)
+#define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
+#define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
+#define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
+
+#define SYS_ID_PFR0_EL1			sys_reg(3, 0, 0, 1, 0)
+#define SYS_ID_PFR1_EL1			sys_reg(3, 0, 0, 1, 1)
+#define SYS_ID_DFR0_EL1			sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_MMFR0_EL1		sys_reg(3, 0, 0, 1, 4)
+#define SYS_ID_MMFR1_EL1		sys_reg(3, 0, 0, 1, 5)
+#define SYS_ID_MMFR2_EL1		sys_reg(3, 0, 0, 1, 6)
+#define SYS_ID_MMFR3_EL1		sys_reg(3, 0, 0, 1, 7)
+
+#define SYS_ID_ISAR0_EL1		sys_reg(3, 0, 0, 2, 0)
+#define SYS_ID_ISAR1_EL1		sys_reg(3, 0, 0, 2, 1)
+#define SYS_ID_ISAR2_EL1		sys_reg(3, 0, 0, 2, 2)
+#define SYS_ID_ISAR3_EL1		sys_reg(3, 0, 0, 2, 3)
+#define SYS_ID_ISAR4_EL1		sys_reg(3, 0, 0, 2, 4)
+#define SYS_ID_ISAR5_EL1		sys_reg(3, 0, 0, 2, 5)
+#define SYS_ID_MMFR4_EL1		sys_reg(3, 0, 0, 2, 6)
+
+#define SYS_MVFR0_EL1			sys_reg(3, 0, 0, 3, 0)
+#define SYS_MVFR1_EL1			sys_reg(3, 0, 0, 3, 1)
+#define SYS_MVFR2_EL1			sys_reg(3, 0, 0, 3, 2)
+
+#define SYS_ID_AA64PFR0_EL1		sys_reg(3, 0, 0, 4, 0)
+#define SYS_ID_AA64PFR1_EL1		sys_reg(3, 0, 0, 4, 1)
+
+#define SYS_ID_AA64DFR0_EL1		sys_reg(3, 0, 0, 5, 0)
+#define SYS_ID_AA64DFR1_EL1		sys_reg(3, 0, 0, 5, 1)
+
+#define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
+#define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
+
+#define SYS_ID_AA64MMFR0_EL1		sys_reg(3, 0, 0, 7, 0)
+#define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
+
+#define SYS_CNTFRQ_EL0			sys_reg(3, 3, 14, 0, 0)
+#define SYS_CTR_EL0			sys_reg(3, 3, 0, 0, 1)
+#define SYS_DCZID_EL0			sys_reg(3, 3, 0, 0, 7)
+
+#define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
 
 #define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
 				     (!!x)<<8 | 0x1f)
 
+/* SCTLR_EL1 */
+#define SCTLR_EL1_CP15BEN	(0x1 << 5)
+#define SCTLR_EL1_SED		(0x1 << 8)
+#define SCTLR_EL1_SPAN		(0x1 << 23)
+
+
+/* id_aa64isar0 */
+#define ID_AA64ISAR0_RDM_SHIFT		28
+#define ID_AA64ISAR0_ATOMICS_SHIFT	20
+#define ID_AA64ISAR0_CRC32_SHIFT	16
+#define ID_AA64ISAR0_SHA2_SHIFT		12
+#define ID_AA64ISAR0_SHA1_SHIFT		8
+#define ID_AA64ISAR0_AES_SHIFT		4
+
+/* id_aa64pfr0 */
+#define ID_AA64PFR0_GIC_SHIFT		24
+#define ID_AA64PFR0_ASIMD_SHIFT		20
+#define ID_AA64PFR0_FP_SHIFT		16
+#define ID_AA64PFR0_EL3_SHIFT		12
+#define ID_AA64PFR0_EL2_SHIFT		8
+#define ID_AA64PFR0_EL1_SHIFT		4
+#define ID_AA64PFR0_EL0_SHIFT		0
+
+#define ID_AA64PFR0_FP_NI		0xf
+#define ID_AA64PFR0_FP_SUPPORTED	0x0
+#define ID_AA64PFR0_ASIMD_NI		0xf
+#define ID_AA64PFR0_ASIMD_SUPPORTED	0x0
+#define ID_AA64PFR0_EL1_64BIT_ONLY	0x1
+#define ID_AA64PFR0_EL0_64BIT_ONLY	0x1
+
+/* id_aa64mmfr0 */
+#define ID_AA64MMFR0_TGRAN4_SHIFT	28
+#define ID_AA64MMFR0_TGRAN64_SHIFT	24
+#define ID_AA64MMFR0_TGRAN16_SHIFT	20
+#define ID_AA64MMFR0_BIGENDEL0_SHIFT	16
+#define ID_AA64MMFR0_SNSMEM_SHIFT	12
+#define ID_AA64MMFR0_BIGENDEL_SHIFT	8
+#define ID_AA64MMFR0_ASID_SHIFT		4
+#define ID_AA64MMFR0_PARANGE_SHIFT	0
+
+#define ID_AA64MMFR0_TGRAN4_NI		0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED	0x0
+#define ID_AA64MMFR0_TGRAN64_NI		0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED	0x0
+#define ID_AA64MMFR0_TGRAN16_NI		0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED	0x1
+
+/* id_aa64mmfr1 */
+#define ID_AA64MMFR1_PAN_SHIFT		20
+#define ID_AA64MMFR1_LOR_SHIFT		16
+#define ID_AA64MMFR1_HPD_SHIFT		12
+#define ID_AA64MMFR1_VHE_SHIFT		8
+#define ID_AA64MMFR1_VMIDBITS_SHIFT	4
+#define ID_AA64MMFR1_HADBS_SHIFT	0
+
+/* id_aa64dfr0 */
+#define ID_AA64DFR0_CTX_CMPS_SHIFT	28
+#define ID_AA64DFR0_WRPS_SHIFT		20
+#define ID_AA64DFR0_BRPS_SHIFT		12
+#define ID_AA64DFR0_PMUVER_SHIFT	8
+#define ID_AA64DFR0_TRACEVER_SHIFT	4
+#define ID_AA64DFR0_DEBUGVER_SHIFT	0
+
+#define ID_ISAR5_RDM_SHIFT		24
+#define ID_ISAR5_CRC32_SHIFT		16
+#define ID_ISAR5_SHA2_SHIFT		12
+#define ID_ISAR5_SHA1_SHIFT		8
+#define ID_ISAR5_AES_SHIFT		4
+#define ID_ISAR5_SEVL_SHIFT		0
+
+#define MVFR0_FPROUND_SHIFT		28
+#define MVFR0_FPSHVEC_SHIFT		24
+#define MVFR0_FPSQRT_SHIFT		20
+#define MVFR0_FPDIVIDE_SHIFT		16
+#define MVFR0_FPTRAP_SHIFT		12
+#define MVFR0_FPDP_SHIFT		8
+#define MVFR0_FPSP_SHIFT		4
+#define MVFR0_SIMD_SHIFT		0
+
+#define MVFR1_SIMDFMAC_SHIFT		28
+#define MVFR1_FPHP_SHIFT		24
+#define MVFR1_SIMDHP_SHIFT		20
+#define MVFR1_SIMDSP_SHIFT		16
+#define MVFR1_SIMDINT_SHIFT		12
+#define MVFR1_SIMDLS_SHIFT		8
+#define MVFR1_FPDNAN_SHIFT		4
+#define MVFR1_FPFTZ_SHIFT		0
+
+
+#define ID_AA64MMFR0_TGRAN4_SHIFT	28
+#define ID_AA64MMFR0_TGRAN64_SHIFT	24
+#define ID_AA64MMFR0_TGRAN16_SHIFT	20
+
+#define ID_AA64MMFR0_TGRAN4_NI		0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED	0x0
+#define ID_AA64MMFR0_TGRAN64_NI		0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED	0x0
+#define ID_AA64MMFR0_TGRAN16_NI		0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED	0x1
+
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN4_SUPPORTED
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN16_SUPPORTED
+#elif defined(CONFIG_ARM64_64K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT	ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED	ID_AA64MMFR0_TGRAN64_SUPPORTED
+#endif
+
 #ifdef __ASSEMBLY__
 
 	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index dcd06d18a42a..90c7ff233735 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -23,8 +23,10 @@
 
 #include <linux/compiler.h>
 
-#ifndef CONFIG_ARM64_64K_PAGES
+#ifdef CONFIG_ARM64_4K_PAGES
 #define THREAD_SIZE_ORDER	2
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define THREAD_SIZE_ORDER	0
 #endif
 
 #define THREAD_SIZE		16384
@@ -111,7 +113,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_RESTORE_SIGMASK	20
 #define TIF_SINGLESTEP		21
 #define TIF_32BIT		22	/* 32bit process */
-#define TIF_SWITCH_MM		23	/* deferred switch_mm */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index d6e6b6660380..ffdaea7954bb 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,17 +37,21 @@ static inline void __tlb_remove_table(void *_table)
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	if (tlb->fullmm) {
-		flush_tlb_mm(tlb->mm);
-	} else {
-		struct vm_area_struct vma = { .vm_mm = tlb->mm, };
-		/*
-		 * The intermediate page table levels are already handled by
-		 * the __(pte|pmd|pud)_free_tlb() functions, so last level
-		 * TLBI is sufficient here.
-		 */
-		__flush_tlb_range(&vma, tlb->start, tlb->end, true);
-	}
+	struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+
+	/*
+	 * The ASID allocator will either invalidate the ASID or mark
+	 * it as used.
+	 */
+	if (tlb->fullmm)
+		return;
+
+	/*
+	 * The intermediate page table levels are already handled by
+	 * the __(pte|pmd|pud)_free_tlb() functions, so last level
+	 * TLBI is sufficient here.
+	 */
+	__flush_tlb_range(&vma, tlb->start, tlb->end, true);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 7bd2da021658..b460ae28e346 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -63,6 +63,14 @@
  *		only require the D-TLB to be invalidated.
  *		- kaddr - Kernel virtual memory address
  */
+static inline void local_flush_tlb_all(void)
+{
+	dsb(nshst);
+	asm("tlbi	vmalle1");
+	dsb(nsh);
+	isb();
+}
+
 static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
@@ -73,7 +81,7 @@ static inline void flush_tlb_all(void)
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
 {
-	unsigned long asid = (unsigned long)ASID(mm) << 48;
+	unsigned long asid = ASID(mm) << 48;
 
 	dsb(ishst);
 	asm("tlbi	aside1is, %0" : : "r" (asid));
@@ -83,8 +91,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
-	unsigned long addr = uaddr >> 12 |
-		((unsigned long)ASID(vma->vm_mm) << 48);
+	unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
 
 	dsb(ishst);
 	asm("tlbi	vale1is, %0" : : "r" (addr));
@@ -101,7 +108,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
 				     bool last_level)
 {
-	unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48;
+	unsigned long asid = ASID(vma->vm_mm) << 48;
 	unsigned long addr;
 
 	if ((end - start) > MAX_TLB_RANGE) {
@@ -154,9 +161,8 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 				       unsigned long uaddr)
 {
-	unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48);
+	unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
 
-	dsb(ishst);
 	asm("tlbi	vae1is, %0" : : "r" (addr));
 	dsb(ish);
 }