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

Pull arm64 updates from Will Deacon:
 "It's a bit all over the place this time with no "killer feature" to
  speak of.  Support for mismatched cache line sizes should help people
  seeing whacky JIT failures on some SoCs, and the big.LITTLE perf
  updates have been a long time coming, but a lot of the changes here
  are cleanups.

  We stray outside arch/arm64 in a few areas: the arch/arm/ arch_timer
  workaround is acked by Russell, the DT/OF bits are acked by Rob, the
  arch_timer clocksource changes acked by Marc, CPU hotplug by tglx and
  jump_label by Peter (all CC'd).

  Summary:

   - Support for execute-only page permissions
   - Support for hibernate and DEBUG_PAGEALLOC
   - Support for heterogeneous systems with mismatches cache line sizes
   - Errata workarounds (A53 843419 update and QorIQ A-008585 timer bug)
   - arm64 PMU perf updates, including cpumasks for heterogeneous systems
   - Set UTS_MACHINE for building rpm packages
   - Yet another head.S tidy-up
   - Some cleanups and refactoring, particularly in the NUMA code
   - Lots of random, non-critical fixes across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (100 commits)
  arm64: tlbflush.h: add __tlbi() macro
  arm64: Kconfig: remove SMP dependence for NUMA
  arm64: Kconfig: select OF/ACPI_NUMA under NUMA config
  arm64: fix dump_backtrace/unwind_frame with NULL tsk
  arm/arm64: arch_timer: Use archdata to indicate vdso suitability
  arm64: arch_timer: Work around QorIQ Erratum A-008585
  arm64: arch_timer: Add device tree binding for A-008585 erratum
  arm64: Correctly bounds check virt_addr_valid
  arm64: migrate exception table users off module.h and onto extable.h
  arm64: pmu: Hoist pmu platform device name
  arm64: pmu: Probe default hw/cache counters
  arm64: pmu: add fallback probe table
  MAINTAINERS: Update ARM PMU PROFILING AND DEBUGGING entry
  arm64: Improve kprobes test for atomic sequence
  arm64/kvm: use alternative auto-nop
  arm64: use alternative auto-nop
  arm64: alternative: add auto-nop infrastructure
  arm64: lse: convert lse alternatives NOP padding to use __nops
  arm64: barriers: introduce nops and __nops macros for NOP sequences
  arm64: sysreg: replace open-coded mrs_s/msr_s with {read,write}_sysreg_s
  ...

33 files changed, 481 insertions, 260 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index f43d2c4..44e1d7f 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,4 +1,3 @@
-generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
 generic-y += cputime.h
@@ -10,7 +9,6 @@ generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
-generic-y += ftrace.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -27,12 +25,10 @@ generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
 generic-y += mutex.h
-generic-y += pci.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
-generic-y += sections.h
 generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
@@ -45,7 +41,6 @@ generic-y += swab.h
 generic-y += switch_to.h
 generic-y += termbits.h
 generic-y += termios.h
-generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 5420cb0..e517088 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,7 +12,7 @@
 #ifndef _ASM_ACPI_H
 #define _ASM_ACPI_H
 
-#include <linux/mm.h>
+#include <linux/memblock.h>
 #include <linux/psci.h>
 
 #include <asm/cputype.h>
@@ -32,7 +32,11 @@
 static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 					    acpi_size size)
 {
-	if (!page_is_ram(phys >> PAGE_SHIFT))
+	/*
+	 * EFI's reserve_regions() call adds memory with the WB attribute
+	 * to memblock via early_init_dt_add_memory_arch().
+	 */
+	if (!memblock_is_memory(phys))
 		return ioremap(phys, size);
 
 	return ioremap_cache(phys, size);
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 8746ff6..55101bd 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -2,6 +2,7 @@
 #define __ASM_ALTERNATIVE_H
 
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 
 #ifndef __ASSEMBLY__
 
@@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length);
 .endm
 
 /*
- * Begin an alternative code sequence.
+ * Alternative sequences
+ *
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
+ *
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
  *
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+
+/*
+ * Begin an alternative code sequence.
  */
 .macro alternative_if_not cap
+	.set .Lasm_alt_mode, 0
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
 	.popsection
 661:
 .endm
 
+.macro alternative_if cap
+	.set .Lasm_alt_mode, 1
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+	.align 2	/* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
 /*
- * Provide the alternative code sequence.
- *
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
- *
- * 1. Be exactly the same length (in bytes) as the default code
- *    sequence.
- *
- * 2. Not contain a branch target that is used outside of the
- *    alternative sequence it is defined in (branches into an
- *    alternative sequence are not fixed up).
+ * Provide the other half of the alternative code sequence.
  */
 .macro alternative_else
-662:	.pushsection .altinstr_replacement, "ax"
+662:
+	.if .Lasm_alt_mode==0
+	.pushsection .altinstr_replacement, "ax"
+	.else
+	.popsection
+	.endif
 663:
 .endm
 
@@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length);
  * Complete an alternative code sequence.
  */
 .macro alternative_endif
-664:	.popsection
+664:
+	.if .Lasm_alt_mode==0
+	.popsection
+	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 .endm
 
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+	nops	(662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index fbe0ca3..eaa5bbe 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -20,13 +20,55 @@
 #define __ASM_ARCH_TIMER_H
 
 #include <asm/barrier.h>
+#include <asm/sysreg.h>
 
 #include <linux/bug.h>
 #include <linux/init.h>
+#include <linux/jump_label.h>
 #include <linux/types.h>
 
 #include <clocksource/arm_arch_timer.h>
 
+#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+extern struct static_key_false arch_timer_read_ool_enabled;
+#define needs_fsl_a008585_workaround() \
+	static_branch_unlikely(&arch_timer_read_ool_enabled)
+#else
+#define needs_fsl_a008585_workaround()  false
+#endif
+
+u32 __fsl_a008585_read_cntp_tval_el0(void);
+u32 __fsl_a008585_read_cntv_tval_el0(void);
+u64 __fsl_a008585_read_cntvct_el0(void);
+
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({			\
+	u64 _old, _new;					\
+	int _retries = 200;				\
+							\
+	do {						\
+		_old = read_sysreg(reg);		\
+		_new = read_sysreg(reg);		\
+		_retries--;				\
+	} while (unlikely(_old != _new) && _retries);	\
+							\
+	WARN_ON_ONCE(!_retries);			\
+	_new;						\
+})
+
+#define arch_timer_reg_read_stable(reg) 		\
+({							\
+	u64 _val;					\
+	if (needs_fsl_a008585_workaround())		\
+		_val = __fsl_a008585_read_##reg();	\
+	else						\
+		_val = read_sysreg(reg);		\
+	_val;						\
+})
+
 /*
  * These register accessors are marked inline so the compiler can
  * nicely work out which register we want, and chuck away the rest of
@@ -38,19 +80,19 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("msr cntp_ctl_el0,  %0" : : "r" (val));
+			write_sysreg(val, cntp_ctl_el0);
 			break;
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
+			write_sysreg(val, cntp_tval_el0);
 			break;
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("msr cntv_ctl_el0,  %0" : : "r" (val));
+			write_sysreg(val, cntv_ctl_el0);
 			break;
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
+			write_sysreg(val, cntv_tval_el0);
 			break;
 		}
 	}
@@ -61,48 +103,38 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 static __always_inline
 u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
-	u32 val;
-
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrs %0,  cntp_ctl_el0" : "=r" (val));
-			break;
+			return read_sysreg(cntp_ctl_el0);
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
-			break;
+			return arch_timer_reg_read_stable(cntp_tval_el0);
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrs %0,  cntv_ctl_el0" : "=r" (val));
-			break;
+			return read_sysreg(cntv_ctl_el0);
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
-			break;
+			return arch_timer_reg_read_stable(cntv_tval_el0);
 		}
 	}
 
-	return val;
+	BUG();
 }
 
 static inline u32 arch_timer_get_cntfrq(void)
 {
-	u32 val;
-	asm volatile("mrs %0,   cntfrq_el0" : "=r" (val));
-	return val;
+	return read_sysreg(cntfrq_el0);
 }
 
 static inline u32 arch_timer_get_cntkctl(void)
 {
-	u32 cntkctl;
-	asm volatile("mrs	%0, cntkctl_el1" : "=r" (cntkctl));
-	return cntkctl;
+	return read_sysreg(cntkctl_el1);
 }
 
 static inline void arch_timer_set_cntkctl(u32 cntkctl)
 {
-	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
+	write_sysreg(cntkctl, cntkctl_el1);
 }
 
 static inline u64 arch_counter_get_cntpct(void)
@@ -116,12 +148,8 @@ static inline u64 arch_counter_get_cntpct(void)
 
 static inline u64 arch_counter_get_cntvct(void)
 {
-	u64 cval;
-
 	isb();
-	asm volatile("mrs %0, cntvct_el0" : "=r" (cval));
-
-	return cval;
+	return arch_timer_reg_read_stable(cntvct_el0);
 }
 
 static inline int arch_timer_arch_init(void)
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index d5025c6..28bfe61 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -87,6 +87,15 @@
 	.endm
 
 /*
+ * NOP sequence
+ */
+	.macro	nops, num
+	.rept	\num
+	nop
+	.endr
+	.endm
+
+/*
  * Emit an entry into the exception table
  */
 	.macro		_asm_extable, from, to
@@ -216,11 +225,26 @@ lr	.req	x30		// link register
 	.macro	mmid, rd, rn
 	ldr	\rd, [\rn, #MM_CONTEXT_ID]
 	.endm
+/*
+ * read_ctr - read CTR_EL0. If the system has mismatched
+ * cache line sizes, provide the system wide safe value
+ * from arm64_ftr_reg_ctrel0.sys_val
+ */
+	.macro	read_ctr, reg
+alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+	mrs	\reg, ctr_el0			// read CTR
+	nop
+alternative_else
+	ldr_l	\reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
+alternative_endif
+	.endm
+
 
 /*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ * raw_dcache_line_size - get the minimum D-cache line size on this CPU
+ * from the CTR register.
  */
-	.macro	dcache_line_size, reg, tmp
+	.macro	raw_dcache_line_size, reg, tmp
 	mrs	\tmp, ctr_el0			// read CTR
 	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
 	mov	\reg, #4			// bytes per word
@@ -228,9 +252,20 @@ lr	.req	x30		// link register
 	.endm
 
 /*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
+ * dcache_line_size - get the safe D-cache line size across all CPUs
  */
-	.macro	icache_line_size, reg, tmp
+	.macro	dcache_line_size, reg, tmp
+	read_ctr	\tmp
+	ubfm		\tmp, \tmp, #16, #19	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
+/*
+ * raw_icache_line_size - get the minimum I-cache line size on this CPU
+ * from the CTR register.
+ */
+	.macro	raw_icache_line_size, reg, tmp
 	mrs	\tmp, ctr_el0			// read CTR
 	and	\tmp, \tmp, #0xf		// cache line size encoding
 	mov	\reg, #4			// bytes per word
@@ -238,6 +273,16 @@ lr	.req	x30		// link register
 	.endm
 
 /*
+ * icache_line_size - get the safe I-cache line size across all CPUs
+ */
+	.macro	icache_line_size, reg, tmp
+	read_ctr	\tmp
+	and		\tmp, \tmp, #0xf	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
+/*
  * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index b5890be..7457ce0 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -86,8 +86,8 @@ static inline int atomic_add_return##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(add_return##name),				\
+	__LL_SC_ATOMIC(add_return##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
 	"	add	%w[i], %w[i], w30")				\
@@ -112,8 +112,8 @@ static inline void atomic_and(int i, atomic_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(and),
+	__LL_SC_ATOMIC(and)
+	__nops(1),
 	/* LSE atomics */
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]")
@@ -130,8 +130,8 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(fetch_and##name),				\
+	__LL_SC_ATOMIC(fetch_and##name)					\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]")			\
@@ -156,8 +156,8 @@ static inline void atomic_sub(int i, atomic_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(sub),
+	__LL_SC_ATOMIC(sub)
+	__nops(1),
 	/* LSE atomics */
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]")
@@ -174,9 +174,8 @@ static inline int atomic_sub_return##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
 	__LL_SC_ATOMIC(sub_return##name)				\
-	"	nop",							\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
@@ -203,8 +202,8 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(fetch_sub##name),				\
+	__LL_SC_ATOMIC(fetch_sub##name)					\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]")			\
@@ -284,8 +283,8 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(add_return##name),				\
+	__LL_SC_ATOMIC64(add_return##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
 	"	add	%[i], %[i], x30")				\
@@ -310,8 +309,8 @@ static inline void atomic64_and(long i, atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(and),
+	__LL_SC_ATOMIC64(and)
+	__nops(1),
 	/* LSE atomics */
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]")
@@ -328,8 +327,8 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(fetch_and##name),				\
+	__LL_SC_ATOMIC64(fetch_and##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]")			\
@@ -354,8 +353,8 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(sub),
+	__LL_SC_ATOMIC64(sub)
+	__nops(1),
 	/* LSE atomics */
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]")
@@ -372,9 +371,8 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
 	__LL_SC_ATOMIC64(sub_return##name)				\
-	"	nop",							\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
@@ -401,8 +399,8 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(fetch_sub##name),				\
+	__LL_SC_ATOMIC64(fetch_sub##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]")			\
@@ -426,13 +424,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
 	__LL_SC_ATOMIC64(dec_if_positive)
-	"	nop\n"
-	"	nop\n"
-	"	nop\n"
-	"	nop\n"
-	"	nop",
+	__nops(6),
 	/* LSE atomics */
 	"1:	ldr	x30, %[v]\n"
 	"	subs	%[ret], x30, #1\n"
@@ -464,9 +457,8 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-		__LL_SC_CMPXCHG(name)					\
-	"	nop",							\
+	__LL_SC_CMPXCHG(name)						\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	mov	" #w "30, %" #w "[old]\n"			\
 	"	cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n"		\
@@ -517,10 +509,8 @@ static inline long __cmpxchg_double##name(unsigned long old1,		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	"	nop\n"							\
-	"	nop\n"							\
-	__LL_SC_CMPXCHG_DBL(name),					\
+	__LL_SC_CMPXCHG_DBL(name)					\
+	__nops(3),							\
 	/* LSE atomics */						\
 	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 4eea7f6..4e0497f 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,9 @@
 
 #ifndef __ASSEMBLY__
 
+#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
+#define nops(n)		asm volatile(__nops(n))
+
 #define sev()		asm volatile("sev" : : : "memory")
 #define wfe()		asm volatile("wfe" : : : "memory")
 #define wfi()		asm volatile("wfi" : : : "memory")
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index c64268d..2e5fb97 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -68,6 +68,7 @@
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_poc(void *addr, size_t len);
 extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
@@ -85,7 +86,7 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
  */
 extern void __dma_map_area(const void *, size_t, int);
 extern void __dma_unmap_area(const void *, size_t, int);
-extern void __dma_flush_range(const void *, const void *);
+extern void __dma_flush_area(const void *, size_t);
 
 /*
  * Copy user data from/to a page which is mapped into a different
diff --git a/arch/arm64/include/asm/clocksource.h b/arch/arm64/include/asm/clocksource.h
new file mode 100644
index 0000000..0b350a7
--- /dev/null
+++ b/arch/arm64/include/asm/clocksource.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+	bool vdso_direct;	/* Usable for direct VDSO access? */
+};
+
+#endif
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index bd86a79..91b26d2 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -43,10 +43,8 @@ static inline unsigned long __xchg_case_##name(unsigned long x,		\
 	"	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"							\
+		__nops(3)						\
 	"	" #nop_lse)						\
 	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)			\
 	: "r" (x)							\
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 7099f26..758d74f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_CPUFEATURE_H
 #define __ASM_CPUFEATURE_H
 
+#include <linux/jump_label.h>
+
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
@@ -37,8 +39,9 @@
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
 #define ARM64_HYP_OFFSET_LOW			14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
 
-#define ARM64_NCAPS				15
+#define ARM64_NCAPS				16
 
 #ifndef __ASSEMBLY__
 
@@ -63,7 +66,7 @@ struct arm64_ftr_bits {
 	enum ftr_type	type;
 	u8		shift;
 	u8		width;
-	s64		safe_val; /* safe value for discrete features */
+	s64		safe_val; /* safe value for FTR_EXACT features */
 };
 
 /*
@@ -72,13 +75,14 @@ struct arm64_ftr_bits {
  * @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;
+	const char			*name;
+	u64				strict_mask;
+	u64				sys_val;
+	const struct arm64_ftr_bits	*ftr_bits;
 };
 
+extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
+
 /* scope of capability check */
 enum {
 	SCOPE_SYSTEM,
@@ -109,6 +113,7 @@ struct arm64_cpu_capabilities {
 };
 
 extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
 
 bool this_cpu_has_cap(unsigned int cap);
 
@@ -121,16 +126,21 @@ static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
-	return test_bit(num, cpu_hwcaps);
+	if (__builtin_constant_p(num))
+		return static_branch_unlikely(&cpu_hwcap_keys[num]);
+	else
+		return test_bit(num, cpu_hwcaps);
 }
 
 static inline void cpus_set_cap(unsigned int num)
 {
-	if (num >= ARM64_NCAPS)
+	if (num >= ARM64_NCAPS) {
 		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
 			num, ARM64_NCAPS);
-	else
+	} else {
 		__set_bit(num, cpu_hwcaps);
+		static_branch_enable(&cpu_hwcap_keys[num]);
+	}
 }
 
 static inline int __attribute_const__
@@ -157,7 +167,7 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
 	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
 }
 
-static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
 }
@@ -170,7 +180,7 @@ cpuid_feature_extract_field(u64 features, int field, bool sign)
 		cpuid_feature_extract_unsigned_field(features, field);
 }
 
-static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
 {
 	return (s64)cpuid_feature_extract_field(val, ftrp->shift, ftrp->sign);
 }
@@ -193,11 +203,11 @@ void __init setup_cpu_features(void);
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
-void check_local_cpu_errata(void);
-void __init enable_errata_workarounds(void);
+void check_local_cpu_capabilities(void);
 
-void verify_local_cpu_errata(void);
-void verify_local_cpu_capabilities(void);
+void update_cpu_errata_workarounds(void);
+void __init enable_errata_workarounds(void);
+void verify_local_cpu_errata_workarounds(void);
 
 u64 read_system_reg(u32 id);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 9d9fd4b..26a68dd 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -93,11 +93,7 @@
 
 #include <asm/sysreg.h>
 
-#define read_cpuid(reg) ({						\
-	u64 __val;							\
-	asm("mrs_s	%0, " __stringify(SYS_ ## reg) : "=r" (__val));	\
-	__val;								\
-})
+#define read_cpuid(reg)			read_sysreg_s(SYS_ ## reg)
 
 /*
  * The CPU ID never changes at run time, so we might as well tell the
diff --git a/arch/arm64/include/asm/dcc.h b/arch/arm64/include/asm/dcc.h
index 65e0190..836b056 100644
--- a/arch/arm64/include/asm/dcc.h
+++ b/arch/arm64/include/asm/dcc.h
@@ -21,21 +21,16 @@
 #define __ASM_DCC_H
 
 #include <asm/barrier.h>
+#include <asm/sysreg.h>
 
 static inline u32 __dcc_getstatus(void)
 {
-	u32 ret;
-
-	asm volatile("mrs %0, mdccsr_el0" : "=r" (ret));
-
-	return ret;
+	return read_sysreg(mdccsr_el0);
 }
 
 static inline char __dcc_getchar(void)
 {
-	char c;
-
-	asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c));
+	char c = read_sysreg(dbgdtrrx_el0);
 	isb();
 
 	return c;
@@ -47,8 +42,7 @@ static inline void __dcc_putchar(char c)
 	 * The typecast is to make absolutely certain that 'c' is
 	 * zero-extended.
 	 */
-	asm volatile("msr dbgdtrtx_el0, %0"
-			: : "r" ((unsigned long)(unsigned char)c));
+	write_sysreg((unsigned char)c, dbgdtrtx_el0);
 	isb();
 }
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index f772e15..d14c478 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -78,6 +78,23 @@
 
 #define ESR_ELx_IL		(UL(1) << 25)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+
+/* ISS field definitions shared by different classes */
+#define ESR_ELx_WNR		(UL(1) << 6)
+
+/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_EA		(UL(1) << 9)
+#define ESR_ELx_S1PTW		(UL(1) << 7)
+
+/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
+#define ESR_ELx_FSC		(0x3F)
+#define ESR_ELx_FSC_TYPE	(0x3C)
+#define ESR_ELx_FSC_EXTABT	(0x10)
+#define ESR_ELx_FSC_ACCESS	(0x08)
+#define ESR_ELx_FSC_FAULT	(0x04)
+#define ESR_ELx_FSC_PERM	(0x0C)
+
+/* ISS field definitions for Data Aborts */
 #define ESR_ELx_ISV		(UL(1) << 24)
 #define ESR_ELx_SAS_SHIFT	(22)
 #define ESR_ELx_SAS		(UL(3) << ESR_ELx_SAS_SHIFT)
@@ -86,16 +103,9 @@
 #define ESR_ELx_SRT_MASK	(UL(0x1F) << ESR_ELx_SRT_SHIFT)
 #define ESR_ELx_SF 		(UL(1) << 15)
 #define ESR_ELx_AR 		(UL(1) << 14)
-#define ESR_ELx_EA 		(UL(1) << 9)
 #define ESR_ELx_CM 		(UL(1) << 8)
-#define ESR_ELx_S1PTW 		(UL(1) << 7)
-#define ESR_ELx_WNR		(UL(1) << 6)
-#define ESR_ELx_FSC		(0x3F)
-#define ESR_ELx_FSC_TYPE	(0x3C)
-#define ESR_ELx_FSC_EXTABT	(0x10)
-#define ESR_ELx_FSC_ACCESS	(0x08)
-#define ESR_ELx_FSC_FAULT	(0x04)
-#define ESR_ELx_FSC_PERM	(0x0C)
+
+/* ISS field definitions for exceptions taken in to Hyp */
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -109,6 +119,62 @@
 	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
 	 ((imm) & 0xffff))
 
+/* ISS field definitions for System instruction traps */
+#define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
+#define ESR_ELx_SYS64_ISS_RES0_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT)
+#define ESR_ELx_SYS64_ISS_DIR_MASK	0x1
+#define ESR_ELx_SYS64_ISS_DIR_READ	0x1
+#define ESR_ELx_SYS64_ISS_DIR_WRITE	0x0
+
+#define ESR_ELx_SYS64_ISS_RT_SHIFT	5
+#define ESR_ELx_SYS64_ISS_RT_MASK	(UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRM_SHIFT	1
+#define ESR_ELx_SYS64_ISS_CRM_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRN_SHIFT	10
+#define ESR_ELx_SYS64_ISS_CRN_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP1_SHIFT	14
+#define ESR_ELx_SYS64_ISS_OP1_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP2_SHIFT	17
+#define ESR_ELx_SYS64_ISS_OP2_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP0_SHIFT	20
+#define ESR_ELx_SYS64_ISS_OP0_MASK	(UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT)
+#define ESR_ELx_SYS64_ISS_SYS_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+					 ESR_ELx_SYS64_ISS_OP1_MASK | \
+					 ESR_ELx_SYS64_ISS_OP2_MASK | \
+					 ESR_ELx_SYS64_ISS_CRN_MASK | \
+					 ESR_ELx_SYS64_ISS_CRM_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \
+					(((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \
+					 ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \
+					 ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \
+					 ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \
+					 ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_SYS64_ISS_SYS_OP_MASK	(ESR_ELx_SYS64_ISS_SYS_MASK | \
+					 ESR_ELx_SYS64_ISS_DIR_MASK)
+/*
+ * User space cache operations have the following sysreg encoding
+ * in System instructions.
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0)
+ */
+#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
+#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU	5
+
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+						 ESR_ELx_SYS64_ISS_OP1_MASK | \
+						 ESR_ELx_SYS64_ISS_OP2_MASK | \
+						 ESR_ELx_SYS64_ISS_CRN_MASK | \
+						 ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
+				(ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
+				 ESR_ELx_SYS64_ISS_DIR_WRITE)
+
+#define ESR_ELx_SYS64_ISS_SYS_CTR	ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
+#define ESR_ELx_SYS64_ISS_SYS_CTR_READ	(ESR_ELx_SYS64_ISS_SYS_CTR | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 115ea2a..9510ace 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -18,6 +18,7 @@
 
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 #include <asm/virt.h>
 
 #ifdef __KERNEL__
@@ -98,18 +99,18 @@ static inline void decode_ctrl_reg(u32 reg,
 #define AARCH64_DBG_REG_WCR	(AARCH64_DBG_REG_WVR + ARM_MAX_WRP)
 
 /* Debug register names. */
-#define AARCH64_DBG_REG_NAME_BVR	"bvr"
-#define AARCH64_DBG_REG_NAME_BCR	"bcr"
-#define AARCH64_DBG_REG_NAME_WVR	"wvr"
-#define AARCH64_DBG_REG_NAME_WCR	"wcr"
+#define AARCH64_DBG_REG_NAME_BVR	bvr
+#define AARCH64_DBG_REG_NAME_BCR	bcr
+#define AARCH64_DBG_REG_NAME_WVR	wvr
+#define AARCH64_DBG_REG_NAME_WCR	wcr
 
 /* Accessor macros for the debug registers. */
 #define AARCH64_DBG_READ(N, REG, VAL) do {\
-	asm volatile("mrs %0, dbg" REG #N "_el1" : "=r" (VAL));\
+	VAL = read_sysreg(dbg##REG##N##_el1);\
 } while (0)
 
 #define AARCH64_DBG_WRITE(N, REG, VAL) do {\
-	asm volatile("msr dbg" REG #N "_el1, %0" :: "r" (VAL));\
+	write_sysreg(VAL, dbg##REG##N##_el1);\
 } while (0)
 
 struct task_struct;
@@ -141,8 +142,6 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task)
 }
 #endif
 
-extern struct pmu perf_ops_bp;
-
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 1dbaa90..bc85366 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -246,7 +246,8 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 { return (val); }
 
-__AARCH64_INSN_FUNCS(adr_adrp,	0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adr,	0x9F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
@@ -318,6 +319,11 @@ __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
 bool aarch64_insn_is_nop(u32 insn);
 bool aarch64_insn_is_branch_imm(u32 insn);
 
+static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+{
+	return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+}
+
 int aarch64_insn_read(void *addr, u32 *insnp);
 int aarch64_insn_write(void *addr, u32 insn);
 enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
@@ -398,6 +404,9 @@ int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
+s32 aarch64_insn_adrp_get_offset(u32 insn);
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
+
 bool aarch32_insn_is_wide(u32 insn);
 
 #define A32_RN_OFFSET	16
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 9b6e408..0bba427 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -40,25 +40,25 @@
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
-	asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writew __raw_writew
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
-	asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
-	asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writeq __raw_writeq
 static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
-	asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_readb __raw_readb
@@ -184,17 +184,6 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
 #define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
 #include <asm-generic/io.h>
 
 /*
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b6bb834..dff1098 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -99,14 +99,10 @@
 .macro kern_hyp_va	reg
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	and     \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else
-	nop
-alternative_endif
-alternative_if_not ARM64_HYP_OFFSET_LOW
-	nop
-alternative_else
+alternative_else_nop_endif
+alternative_if ARM64_HYP_OFFSET_LOW
 	and     \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_endif
+alternative_else_nop_endif
 .endm
 
 #else
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 31b7322..ba62df8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -214,7 +214,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
 #define __page_to_voff(kaddr)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
@@ -222,11 +222,15 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
 
-#define virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+#define _virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
 					   + PHYS_OFFSET) >> PAGE_SHIFT)
 #endif
 #endif
 
+#define _virt_addr_is_linear(kaddr)	(((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(kaddr)		(_virt_addr_is_linear(kaddr) && \
+					 _virt_addr_valid(kaddr))
+
 #include <asm-generic/memory_model.h>
 
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index b1892a0..a501853 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -27,22 +27,17 @@
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
 #include <asm/pgtable.h>
+#include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
-#ifdef CONFIG_PID_IN_CONTEXTIDR
-static inline void contextidr_thread_switch(struct task_struct *next)
-{
-	asm(
-	"	msr	contextidr_el1, %0\n"
-	"	isb"
-	:
-	: "r" (task_pid_nr(next)));
-}
-#else
 static inline void contextidr_thread_switch(struct task_struct *next)
 {
+	if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
+		return;
+
+	write_sysreg(task_pid_nr(next), contextidr_el1);
+	isb();
 }
-#endif
 
 /*
  * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
@@ -51,11 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
 {
 	unsigned long ttbr = virt_to_phys(empty_zero_page);
 
-	asm(
-	"	msr	ttbr0_el1, %0			// set TTBR0\n"
-	"	isb"
-	:
-	: "r" (ttbr));
+	write_sysreg(ttbr, ttbr0_el1);
+	isb();
 }
 
 /*
@@ -81,13 +73,11 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 	if (!__cpu_uses_extended_idmap())
 		return;
 
-	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));
+	tcr = read_sysreg(tcr_el1);
+	tcr &= ~TCR_T0SZ_MASK;
+	tcr |= t0sz << TCR_T0SZ_OFFSET;
+	write_sysreg(tcr, tcr_el1);
+	isb();
 }
 
 #define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS))
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index c3ae239..eb0c2bd 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -208,6 +208,7 @@
 #define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_T1SZ_OFFSET)
 #define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
 #define TCR_TxSZ_WIDTH		6
+#define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
 
 #define TCR_IRGN0_SHIFT		8
 #define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 39f5252..2142c77 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -70,12 +70,13 @@
 #define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_COPY
 #define __P011  PAGE_COPY
-#define __P100  PAGE_READONLY_EXEC
+#define __P100  PAGE_EXECONLY
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_COPY_EXEC
 #define __P111  PAGE_COPY_EXEC
@@ -84,7 +85,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_READONLY_EXEC
+#define __S100  PAGE_EXECONLY
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e20bd43..ffbb9a5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -73,7 +73,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #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))
-#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
+#define pte_ng(pte)		(!!(pte_val(pte) & PTE_NG))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -84,8 +84,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_global(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID)
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 
@@ -155,6 +155,16 @@ static inline pte_t pte_mknoncont(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
+static inline pte_t pte_clear_rdonly(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+}
+
+static inline pte_t pte_mkpresent(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_VALID));
+}
+
 static inline pmd_t pmd_mkcont(pmd_t pmd)
 {
 	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
@@ -168,7 +178,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
 	 * or update_mmu_cache() have the necessary barriers.
 	 */
-	if (pte_valid_not_user(pte)) {
+	if (pte_valid_global(pte)) {
 		dsb(ishst);
 		isb();
 	}
@@ -202,7 +212,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
-		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+		if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte))
 			__sync_icache_dcache(pte, addr);
 	}
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ace0a96..df2e53d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -37,7 +37,6 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
-#ifdef __KERNEL__
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
@@ -49,7 +48,6 @@
 
 extern phys_addr_t arm64_dma_phys_limit;
 #define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
-#endif /* __KERNEL__ */
 
 struct debug_info {
 	/* Have we suspended stepping by a debugger? */
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
new file mode 100644
index 0000000..4e7e706
--- /dev/null
+++ b/arch/arm64/include/asm/sections.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2016 ARM Limited
+ *
+ * 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_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __alt_instructions[], __alt_instructions_end[];
+extern char __exception_text_start[], __exception_text_end[];
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+extern char __hyp_text_start[], __hyp_text_end[];
+extern char __idmap_text_start[], __idmap_text_end[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
+
+#endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 89206b5..cae331d 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -66,8 +66,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	nop\n"
-"	nop\n",
+	__nops(2),
 	/* LSE atomics */
 "	mov	%w1, %w0\n"
 "	cas	%w0, %w0, %2\n"
@@ -99,9 +98,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	/* LSE atomics */
 "	mov	%w2, %w5\n"
 "	ldadda	%w2, %w0, %3\n"
-"	nop\n"
-"	nop\n"
-"	nop\n"
+	__nops(3)
 	)
 
 	/* Did we get the lock? */
@@ -165,8 +162,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	"	stlrh	%w1, %0",
 	/* LSE atomics */
 	"	mov	%w1, #1\n"
-	"	nop\n"
-	"	staddlh	%w1, %0")
+	"	staddlh	%w1, %0\n"
+	__nops(1))
 	: "=Q" (lock->owner), "=&r" (tmp)
 	:
 	: "memory");
@@ -212,7 +209,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	"	cbnz	%w0, 1b\n"
 	"	stxr	%w0, %w2, %1\n"
 	"	cbnz	%w0, 2b\n"
-	"	nop",
+	__nops(1),
 	/* LSE atomics */
 	"1:	mov	%w0, wzr\n"
 	"2:	casa	%w0, %w2, %1\n"
@@ -241,8 +238,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	/* LSE atomics */
 	"	mov	%w0, wzr\n"
 	"	casa	%w0, %w2, %1\n"
-	"	nop\n"
-	"	nop")
+	__nops(2))
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -290,8 +286,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	"	add	%w0, %w0, #1\n"
 	"	tbnz	%w0, #31, 1b\n"
 	"	stxr	%w1, %w0, %2\n"
-	"	nop\n"
-	"	cbnz	%w1, 2b",
+	"	cbnz	%w1, 2b\n"
+	__nops(1),
 	/* LSE atomics */
 	"1:	wfe\n"
 	"2:	ldxr	%w0, %2\n"
@@ -317,9 +313,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 1b",
 	/* LSE atomics */
 	"	movn	%w0, #0\n"
-	"	nop\n"
-	"	nop\n"
-	"	staddl	%w0, %2")
+	"	staddl	%w0, %2\n"
+	__nops(2))
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
 	: "memory");
@@ -344,7 +339,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	"	tbnz	%w1, #31, 1f\n"
 	"	casa	%w0, %w1, %2\n"
 	"	sbc	%w1, %w1, %w0\n"
-	"	nop\n"
+	__nops(1)
 	"1:")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index 024d623..b8a313f 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -47,4 +47,7 @@ int swsusp_arch_resume(void);
 int arch_hibernation_header_save(void *addr, unsigned int max_size);
 int arch_hibernation_header_restore(void *addr);
 
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
 #endif
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index cc06794..e8d46e8 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -100,6 +100,7 @@
 /* SCTLR_EL1 specific flags. */
 #define SCTLR_EL1_UCI		(1 << 26)
 #define SCTLR_EL1_SPAN		(1 << 23)
+#define SCTLR_EL1_UCT		(1 << 15)
 #define SCTLR_EL1_SED		(1 << 8)
 #define SCTLR_EL1_CP15BEN	(1 << 5)
 
@@ -253,16 +254,6 @@ asm(
 "	.endm\n"
 );
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
-	val &= ~clear;
-	val |= set;
-	asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
 /*
  * Unlike read_cpuid, calls to read_sysreg are never expected to be
  * optimized away or replaced with synthetic values.
@@ -273,12 +264,41 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
 	__val;							\
 })
 
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
 #define write_sysreg(v, r) do {					\
 	u64 __val = (u64)v;					\
-	asm volatile("msr " __stringify(r) ", %0"		\
-		     : : "r" (__val));				\
+	asm volatile("msr " __stringify(r) ", %x0"		\
+		     : : "rZ" (__val));				\
+} while (0)
+
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({						\
+	u64 __val;							\
+	asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val));	\
+	__val;								\
+})
+
+#define write_sysreg_s(v, r) do {					\
+	u64 __val = (u64)v;						\
+	asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val));	\
 } while (0)
 
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+	u32 val;
+
+	val = read_sysreg(sctlr_el1);
+	val &= ~clear;
+	val |= set;
+	write_sysreg(val, sctlr_el1);
+}
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 57f110b..bc81243 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -56,12 +56,6 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 	__show_ratelimited;						\
 })
 
-#define UDBG_UNDEFINED	(1 << 0)
-#define UDBG_SYSCALL	(1 << 1)
-#define UDBG_BADABORT	(1 << 2)
-#define UDBG_SEGV	(1 << 3)
-#define UDBG_BUS	(1 << 4)
-
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index abd64bd..e9ea5a6 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -75,6 +75,9 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
 /*
  * struct thread_info can be accessed directly via sp_el0.
+ *
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
  */
 static inline struct thread_info *current_thread_info(void)
 {
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b460ae2..deab523 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -25,6 +25,24 @@
 #include <asm/cputype.h>
 
 /*
+ * Raw TLBI operations.
+ *
+ * Where necessary, use the __tlbi() macro to avoid asm()
+ * boilerplate. Drivers and most kernel code should use the TLB
+ * management routines in preference to the macro below.
+ *
+ * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
+ * on whether a particular TLBI operation takes an argument or
+ * not. The macros handles invoking the asm with or without the
+ * register argument as appropriate.
+ */
+#define __TLBI_0(op, arg)		asm ("tlbi " #op)
+#define __TLBI_1(op, arg)		asm ("tlbi " #op ", %0" : : "r" (arg))
+#define __TLBI_N(op, arg, n, ...)	__TLBI_##n(op, arg)
+
+#define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)
+
+/*
  *	TLB Management
  *	==============
  *
@@ -66,7 +84,7 @@
 static inline void local_flush_tlb_all(void)
 {
 	dsb(nshst);
-	asm("tlbi	vmalle1");
+	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 }
@@ -74,7 +92,7 @@ static inline void local_flush_tlb_all(void)
 static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
-	asm("tlbi	vmalle1is");
+	__tlbi(vmalle1is);
 	dsb(ish);
 	isb();
 }
@@ -84,7 +102,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	unsigned long asid = ASID(mm) << 48;
 
 	dsb(ishst);
-	asm("tlbi	aside1is, %0" : : "r" (asid));
+	__tlbi(aside1is, asid);
 	dsb(ish);
 }
 
@@ -94,7 +112,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
 
 	dsb(ishst);
-	asm("tlbi	vale1is, %0" : : "r" (addr));
+	__tlbi(vale1is, addr);
 	dsb(ish);
 }
 
@@ -122,9 +140,9 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
 		if (last_level)
-			asm("tlbi vale1is, %0" : : "r"(addr));
+			__tlbi(vale1is, addr);
 		else
-			asm("tlbi vae1is, %0" : : "r"(addr));
+			__tlbi(vae1is, addr);
 	}
 	dsb(ish);
 }
@@ -149,7 +167,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
-		asm("tlbi vaae1is, %0" : : "r"(addr));
+		__tlbi(vaae1is, addr);
 	dsb(ish);
 	isb();
 }
@@ -163,7 +181,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 {
 	unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
 
-	asm("tlbi	vae1is, %0" : : "r" (addr));
+	__tlbi(vae1is, addr);
 	dsb(ish);
 }
 
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 9cd03f3..02e9035 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -19,6 +19,7 @@
 #define __ASM_TRAP_H
 
 #include <linux/list.h>
+#include <asm/sections.h>
 
 struct pt_regs;
 
@@ -39,9 +40,6 @@ void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static inline int __in_irqentry_text(unsigned long ptr)
 {
-	extern char __irqentry_text_start[];
-	extern char __irqentry_text_end[];
-
 	return ptr >= (unsigned long)&__irqentry_text_start &&
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
@@ -54,8 +52,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 
 static inline int in_exception_text(unsigned long ptr)
 {
-	extern char __exception_text_start[];
-	extern char __exception_text_end[];
 	int in;
 
 	in = ptr >= (unsigned long)&__exception_text_start &&
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 1788545..fea1073 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -45,6 +45,8 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
 
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
@@ -75,10 +77,7 @@ static inline bool is_hyp_mode_mismatched(void)
 
 static inline bool is_kernel_in_hyp_mode(void)
 {
-	u64 el;
-
-	asm("mrs %0, CurrentEL" : "=r" (el));
-	return el == CurrentEL_EL2;
+	return read_sysreg(CurrentEL) == CurrentEL_EL2;
 }
 
 #ifdef CONFIG_ARM64_VHE
@@ -87,14 +86,6 @@ extern void verify_cpu_run_el(void);
 static inline void verify_cpu_run_el(void) {}
 #endif
 
-/* The section containing the hypervisor idmap text */
-extern char __hyp_idmap_text_start[];
-extern char __hyp_idmap_text_end[];
-
-/* The section containing the hypervisor text */
-extern char __hyp_text_start[];
-extern char __hyp_text_end[];
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */