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

Pull arm64 updates from Catalin Marinas:

 - struct thread_info moved off-stack (also touching
   include/linux/thread_info.h and include/linux/restart_block.h)

 - cpus_have_cap() reworked to avoid __builtin_constant_p() for static
   key use (also touching drivers/irqchip/irq-gic-v3.c)

 - uprobes support (currently only for native 64-bit tasks)

 - Emulation of kernel Privileged Access Never (PAN) using TTBR0_EL1
   switching to a reserved page table

 - CPU capacity information passing via DT or sysfs (used by the
   scheduler)

 - support for systems without FP/SIMD (IOW, kernel avoids touching
   these registers; there is no soft-float ABI, nor kernel emulation for
   AArch64 FP/SIMD)

 - handling of hardware watchpoint with unaligned addresses, varied
   lengths and offsets from base

 - use of the page table contiguous hint for kernel mappings

 - hugetlb fixes for sizes involving the contiguous hint

 - remove unnecessary I-cache invalidation in flush_cache_range()

 - CNTHCTL_EL2 access fix for CPUs with VHE support (ARMv8.1)

 - boot-time checks for writable+executable kernel mappings

 - simplify asm/opcodes.h and avoid including the 32-bit ARM counterpart
   and make the arm64 kernel headers self-consistent (Xen headers patch
   merged separately)

 - Workaround for broken .inst support in certain binutils versions

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (60 commits)
  arm64: Disable PAN on uaccess_enable()
  arm64: Work around broken .inst when defective gas is detected
  arm64: Add detection code for broken .inst support in binutils
  arm64: Remove reference to asm/opcodes.h
  arm64: Get rid of asm/opcodes.h
  arm64: smp: Prevent raw_smp_processor_id() recursion
  arm64: head.S: Fix CNTHCTL_EL2 access on VHE system
  arm64: Remove I-cache invalidation from flush_cache_range()
  arm64: Enable HIBERNATION in defconfig
  arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN
  arm64: xen: Enable user access before a privcmd hvc call
  arm64: Handle faults caused by inadvertent user access with PAN enabled
  arm64: Disable TTBR0_EL1 during normal kernel execution
  arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1
  arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
  arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
  arm64: Update the synchronous external abort fault description
  selftests: arm64: add test for unaligned/inexact watchpoint handling
  arm64: Allow hw watchpoint of length 3,5,6 and 7
  arm64: hw_breakpoint: Handle inexact watchpoint addresses
  ...

28 files changed, 511 insertions, 127 deletions

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index b4ab238a59ec..8365a84c2640 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += bugs.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 28bfe6132eb6..446f6c46d4b1 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -41,6 +41,15 @@
 	msr	daifclr, #2
 	.endm
 
+	.macro	save_and_disable_irq, flags
+	mrs	\flags, daif
+	msr	daifset, #2
+	.endm
+
+	.macro	restore_irq, flags
+	msr	daif, \flags
+	.endm
+
 /*
  * Enable and disable debug exceptions.
  */
@@ -202,14 +211,25 @@ lr	.req	x30		// link register
 	.endm
 
 	/*
+	 * @dst: Result of per_cpu(sym, smp_processor_id())
 	 * @sym: The name of the per-cpu variable
-	 * @reg: Result of per_cpu(sym, smp_processor_id())
 	 * @tmp: scratch register
 	 */
-	.macro this_cpu_ptr, sym, reg, tmp
-	adr_l	\reg, \sym
+	.macro adr_this_cpu, dst, sym, tmp
+	adr_l	\dst, \sym
 	mrs	\tmp, tpidr_el1
-	add	\reg, \reg, \tmp
+	add	\dst, \dst, \tmp
+	.endm
+
+	/*
+	 * @dst: Result of READ_ONCE(per_cpu(sym, smp_processor_id()))
+	 * @sym: The name of the per-cpu variable
+	 * @tmp: scratch register
+	 */
+	.macro ldr_this_cpu dst, sym, tmp
+	adr_l	\dst, \sym
+	mrs	\tmp, tpidr_el1
+	ldr	\dst, [\dst, \tmp]
 	.endm
 
 /*
@@ -395,4 +415,24 @@ alternative_endif
 	movk	\reg, :abs_g0_nc:\val
 	.endm
 
+/*
+ * Return the current thread_info.
+ */
+	.macro	get_thread_info, rd
+	mrs	\rd, sp_el0
+	.endm
+
+/*
+ * Errata workaround post TTBR0_EL1 update.
+ */
+	.macro	post_ttbr0_update_workaround
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
+	ic	iallu
+	dsb	nsh
+	isb
+alternative_else_nop_endif
+#endif
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 2e5fb976a572..5a2a6ee65f65 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -65,12 +65,12 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
-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);
+extern void sync_icache_aliases(void *kaddr, unsigned long len);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
@@ -81,6 +81,11 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 {
 }
 
+static inline void flush_cache_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end)
+{
+}
+
 /*
  * Cache maintenance functions used by the DMA API. No to be used directly.
  */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 87b446535185..4174f09678c4 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -34,7 +34,8 @@
 #define ARM64_HAS_32BIT_EL0			13
 #define ARM64_HYP_OFFSET_LOW			14
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
+#define ARM64_HAS_NO_FPSIMD			16
 
-#define ARM64_NCAPS				16
+#define ARM64_NCAPS				17
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 0bc0b1de90c4..b4989df48670 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -9,8 +9,6 @@
 #ifndef __ASM_CPUFEATURE_H
 #define __ASM_CPUFEATURE_H
 
-#include <linux/jump_label.h>
-
 #include <asm/cpucaps.h>
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
@@ -27,6 +25,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bug.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 
 /* CPU feature register tracking */
@@ -104,14 +104,19 @@ static inline bool cpu_have_feature(unsigned int num)
 	return elf_hwcap & (1UL << num);
 }
 
+/* System capability check for constant caps */
+static inline bool cpus_have_const_cap(int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
 static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
-	if (__builtin_constant_p(num))
-		return static_branch_unlikely(&cpu_hwcap_keys[num]);
-	else
-		return test_bit(num, cpu_hwcaps);
+	return test_bit(num, cpu_hwcaps);
 }
 
 static inline void cpus_set_cap(unsigned int num)
@@ -200,7 +205,7 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 
 static inline bool system_supports_32bit_el0(void)
 {
-	return cpus_have_cap(ARM64_HAS_32BIT_EL0);
+	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
 }
 
 static inline bool system_supports_mixed_endian_el0(void)
@@ -208,6 +213,17 @@ static inline bool system_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
 }
 
+static inline bool system_supports_fpsimd(void)
+{
+	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
+}
+
+static inline bool system_uses_ttbr0_pan(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
+		!cpus_have_cap(ARM64_HAS_PAN);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
new file mode 100644
index 000000000000..f2bcbe2d9889
--- /dev/null
+++ b/arch/arm64/include/asm/current.h
@@ -0,0 +1,22 @@
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+	return (struct task_struct *)read_sysreg(sp_el0);
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
+
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index b71420a12f26..a44cf5225429 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -68,6 +68,9 @@
 #define BRK64_ESR_MASK		0xFFFF
 #define BRK64_ESR_KPROBES	0x0004
 #define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+/* uprobes BRK opcodes with ESR encoding  */
+#define BRK64_ESR_UPROBES	0x0005
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 771b3f0bc757..0b6b1633017f 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_EFI_H
 #define _ASM_EFI_H
 
+#include <asm/cpufeature.h>
 #include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/neon.h>
@@ -78,7 +79,30 @@ static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 
 static inline void efi_set_pgd(struct mm_struct *mm)
 {
-	switch_mm(NULL, mm, NULL);
+	__switch_mm(mm);
+
+	if (system_uses_ttbr0_pan()) {
+		if (mm != current->active_mm) {
+			/*
+			 * Update the current thread's saved ttbr0 since it is
+			 * restored as part of a return from exception. Set
+			 * the hardware TTBR0_EL1 using cpu_switch_mm()
+			 * directly to enable potential errata workarounds.
+			 */
+			update_saved_ttbr0(current, mm);
+			cpu_switch_mm(mm->pgd, mm);
+		} else {
+			/*
+			 * Defer the switch to the current thread's TTBR0_EL1
+			 * until uaccess_enable(). Restore the current
+			 * thread's saved ttbr0 corresponding to its active_mm
+			 * (if different from init_mm).
+			 */
+			cpu_set_reserved_ttbr0();
+			if (current->active_mm != &init_mm)
+				update_saved_ttbr0(current, current->active_mm);
+		}
+	}
 }
 
 void efi_virtmap_load(void);
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index a55384f4a5d7..5d1700425efe 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -138,7 +138,11 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  */
 #define ELF_PLAT_INIT(_r, load_addr)	(_r)->regs[0] = 0
 
-#define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);
+#define SET_PERSONALITY(ex)						\
+({									\
+	clear_bit(TIF_32BIT, &current->mm->context.flags);		\
+	clear_thread_flag(TIF_32BIT);					\
+})
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
@@ -183,7 +187,11 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 					 ((x)->e_flags & EF_ARM_EABI_MASK))
 
 #define compat_start_thread		compat_start_thread
-#define COMPAT_SET_PERSONALITY(ex)	set_thread_flag(TIF_32BIT);
+#define COMPAT_SET_PERSONALITY(ex)					\
+({									\
+	set_bit(TIF_32BIT, &current->mm->context.flags);		\
+	set_thread_flag(TIF_32BIT);					\
+ })
 #define COMPAT_ARCH_DLINFO
 extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
 				      int uses_interp);
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index f2585cdd32c2..85c4a8981d47 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -21,15 +21,12 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 
-#include <asm/alternative.h>
-#include <asm/cpufeature.h>
 #include <asm/errno.h>
-#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
+do {									\
+	uaccess_enable();						\
 	asm volatile(							\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
@@ -44,11 +41,11 @@
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "memory")
+	: "memory");							\
+	uaccess_disable();						\
+} while (0)
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -118,8 +115,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	uaccess_enable();
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -134,10 +131,10 @@ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	.popsection\n"
 	_ASM_EXTABLE(1b, 4b)
 	_ASM_EXTABLE(2b, 4b)
-ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
+	uaccess_disable();
 
 	*uval = val;
 	return ret;
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9510ace570e2..b6b167ac082b 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -77,7 +77,11 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Lengths */
 #define ARM_BREAKPOINT_LEN_1	0x1
 #define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_3	0x7
 #define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_5	0x1f
+#define ARM_BREAKPOINT_LEN_6	0x3f
+#define ARM_BREAKPOINT_LEN_7	0x7f
 #define ARM_BREAKPOINT_LEN_8	0xff
 
 /* Kernel stepping */
@@ -119,7 +123,7 @@ struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-				  int *gen_len, int *gen_type);
+				  int *gen_len, int *gen_type, int *offset);
 extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 7e51d1b57c0c..7803343e5881 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -19,6 +19,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
+#include <asm/pgtable.h>
 #include <asm/sparsemem.h>
 
 /*
@@ -54,6 +55,12 @@
 #define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+#define RESERVED_TTBR0_SIZE	(PAGE_SIZE)
+#else
+#define RESERVED_TTBR0_SIZE	(0)
+#endif
+
 /* Initial memory map size */
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_BLOCK_SHIFT	SECTION_SHIFT
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 8d9fce037b2f..47619411f0ff 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -19,6 +19,7 @@
 typedef struct {
 	atomic64_t	id;
 	void		*vdso;
+	unsigned long	flags;
 } mm_context_t;
 
 /*
@@ -34,7 +35,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot, bool allow_block_mappings);
+			       pgprot_t prot, bool page_mappings_only);
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 
 #endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a50185375f09..0363fe80455c 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -23,6 +23,7 @@
 #include <linux/sched.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
@@ -103,7 +104,7 @@ static inline void cpu_uninstall_idmap(void)
 	local_flush_tlb_all();
 	cpu_set_default_tcr_t0sz();
 
-	if (mm != &init_mm)
+	if (mm != &init_mm && !system_uses_ttbr0_pan())
 		cpu_switch_mm(mm->pgd, mm);
 }
 
@@ -163,20 +164,26 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
 
-/*
- * This is the actual mm switch as far as the scheduler
- * is concerned.  No registers are touched.  We avoid
- * calling the CPU specific function when the mm hasn't
- * actually changed.
- */
-static inline void
-switch_mm(struct mm_struct *prev, struct mm_struct *next,
-	  struct task_struct *tsk)
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
 {
-	unsigned int cpu = smp_processor_id();
+	if (system_uses_ttbr0_pan()) {
+		BUG_ON(mm->pgd == swapper_pg_dir);
+		task_thread_info(tsk)->ttbr0 =
+			virt_to_phys(mm->pgd) | ASID(mm) << 48;
+	}
+}
+#else
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
+{
+}
+#endif
 
-	if (prev == next)
-		return;
+static inline void __switch_mm(struct mm_struct *next)
+{
+	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
@@ -190,8 +197,26 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	check_and_switch_context(next, cpu);
 }
 
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+	if (prev != next)
+		__switch_mm(next);
+
+	/*
+	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
+	 * value may have not been initialised yet (activate_mm caller) or the
+	 * ASID has changed since the last run (following the context switch
+	 * of another thread of the same process). Avoid setting the reserved
+	 * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+	 */
+	if (next != &init_mm)
+		update_saved_ttbr0(tsk, next);
+}
+
 #define deactivate_mm(tsk,mm)	do { } while (0)
-#define activate_mm(prev,next)	switch_mm(prev, next, NULL)
+#define activate_mm(prev,next)	switch_mm(prev, next, current)
 
 void verify_cpu_asid_bits(void);
 
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index 13ce4cc18e26..ad4cdc966c0f 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -9,8 +9,9 @@
  */
 
 #include <linux/types.h>
+#include <asm/fpsimd.h>
 
-#define cpu_has_neon()		(1)
+#define cpu_has_neon()		system_supports_fpsimd()
 
 #define kernel_neon_begin()	kernel_neon_begin_partial(32)
 
diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h
deleted file mode 100644
index 123f45d92cd1..000000000000
--- a/arch/arm64/include/asm/opcodes.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN
-#endif
-
-#include <../../arm/include/asm/opcodes.h>
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 5394c8405e66..3bd498e4de4c 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#include <asm/stack_pointer.h>
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -101,16 +103,16 @@ static inline unsigned long __percpu_read(void *ptr, int size)
 
 	switch (size) {
 	case 1:
-		ret = ACCESS_ONCE(*(u8 *)ptr);
+		ret = READ_ONCE(*(u8 *)ptr);
 		break;
 	case 2:
-		ret = ACCESS_ONCE(*(u16 *)ptr);
+		ret = READ_ONCE(*(u16 *)ptr);
 		break;
 	case 4:
-		ret = ACCESS_ONCE(*(u32 *)ptr);
+		ret = READ_ONCE(*(u32 *)ptr);
 		break;
 	case 8:
-		ret = ACCESS_ONCE(*(u64 *)ptr);
+		ret = READ_ONCE(*(u64 *)ptr);
 		break;
 	default:
 		BUILD_BUG();
@@ -123,16 +125,16 @@ static inline void __percpu_write(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
-		ACCESS_ONCE(*(u8 *)ptr) = (u8)val;
+		WRITE_ONCE(*(u8 *)ptr, (u8)val);
 		break;
 	case 2:
-		ACCESS_ONCE(*(u16 *)ptr) = (u16)val;
+		WRITE_ONCE(*(u16 *)ptr, (u16)val);
 		break;
 	case 4:
-		ACCESS_ONCE(*(u32 *)ptr) = (u32)val;
+		WRITE_ONCE(*(u32 *)ptr, (u32)val);
 		break;
 	case 8:
-		ACCESS_ONCE(*(u64 *)ptr) = (u64)val;
+		WRITE_ONCE(*(u64 *)ptr, (u64)val);
 		break;
 	default:
 		BUILD_BUG();
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 38b6a2b49d68..8d5cbec17d80 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -17,6 +17,8 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
+#include <asm/stack_pointer.h>
+
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
 
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
index 5af574d632fa..6a5b28904c33 100644
--- a/arch/arm64/include/asm/probes.h
+++ b/arch/arm64/include/asm/probes.h
@@ -15,21 +15,22 @@
 #ifndef _ARM_PROBES_H
 #define _ARM_PROBES_H
 
-#include <asm/opcodes.h>
-
-struct kprobe;
-struct arch_specific_insn;
-
-typedef u32 kprobe_opcode_t;
-typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
 
 /* architecture specific copy of original instruction */
-struct arch_specific_insn {
-	kprobe_opcode_t *insn;
+struct arch_probe_insn {
+	probe_opcode_t *insn;
 	pstate_check_t *pstate_cc;
-	kprobes_handler_t *handler;
+	probes_handler_t *handler;
 	/* restore address after step xol */
 	unsigned long restore;
 };
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
 
 #endif
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
index 07b8ed037dee..6afd8476c60c 100644
--- a/arch/arm64/include/asm/ptdump.h
+++ b/arch/arm64/include/asm/ptdump.h
@@ -16,9 +16,10 @@
 #ifndef __ASM_PTDUMP_H
 #define __ASM_PTDUMP_H
 
-#ifdef CONFIG_ARM64_PTDUMP
+#ifdef CONFIG_ARM64_PTDUMP_CORE
 
 #include <linux/mm_types.h>
+#include <linux/seq_file.h>
 
 struct addr_marker {
 	unsigned long start_address;
@@ -29,16 +30,25 @@ struct ptdump_info {
 	struct mm_struct		*mm;
 	const struct addr_marker	*markers;
 	unsigned long			base_addr;
-	unsigned long			max_addr;
 };
 
-int ptdump_register(struct ptdump_info *info, const char *name);
-
+void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
+#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name);
 #else
-static inline int ptdump_register(struct ptdump_info *info, const char *name)
+static inline int ptdump_debugfs_register(struct ptdump_info *info,
+					const char *name)
 {
 	return 0;
 }
-#endif /* CONFIG_ARM64_PTDUMP */
+#endif
+void ptdump_check_wx(void);
+#endif /* CONFIG_ARM64_PTDUMP_CORE */
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx()	ptdump_check_wx()
+#else
+#define debug_checkwx()	do { } while (0)
+#endif
 
 #endif /* __ASM_PTDUMP_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ada08b5b036d..513daf050e84 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -217,6 +217,14 @@ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
 
 #include <asm-generic/ptrace.h>
 
+#define procedure_link_pointer(regs)	((regs)->regs[30])
+
+static inline void procedure_link_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	procedure_link_pointer(regs) = val;
+}
+
 #undef profile_pc
 extern unsigned long profile_pc(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 022644704a93..d050d720a1b4 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -29,11 +29,22 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/percpu.h>
+
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
+
+/*
+ * We don't use this_cpu_read(cpu_number) as that has implicit writes to
+ * preempt_count, and associated (compiler) barriers, that we'd like to avoid
+ * the expense of. If we're preemptible, the value can be stale at use anyway.
+ * And we can't use this_cpu_ptr() either, as that winds up recursing back
+ * here under CONFIG_DEBUG_PREEMPT=y.
+ */
+#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number))
 
 struct seq_file;
 
@@ -73,6 +84,7 @@ asmlinkage void secondary_start_kernel(void);
  */
 struct secondary_data {
 	void *stack;
+	struct task_struct *task;
 	long status;
 };
 
diff --git a/arch/arm64/include/asm/stack_pointer.h b/arch/arm64/include/asm/stack_pointer.h
new file mode 100644
index 000000000000..ffcdf742cddf
--- /dev/null
+++ b/arch/arm64/include/asm/stack_pointer.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_STACK_POINTER_H
+#define __ASM_STACK_POINTER_H
+
+/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+#endif /* __ASM_STACK_POINTER_H */
diff --git a/arch/arm64/include/asm/suspend.h b/arch/arm64/include/asm/suspend.h
index b8a313fd7a09..de5600f40adf 100644
--- a/arch/arm64/include/asm/suspend.h
+++ b/arch/arm64/include/asm/suspend.h
@@ -1,7 +1,7 @@
 #ifndef __ASM_SUSPEND_H
 #define __ASM_SUSPEND_H
 
-#define NR_CTX_REGS 10
+#define NR_CTX_REGS 12
 #define NR_CALLEE_SAVED_REGS 12
 
 /*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 6c80b3699cb8..98ae03f8eedd 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -22,8 +22,6 @@
 
 #include <linux/stringify.h>
 
-#include <asm/opcodes.h>
-
 /*
  * ARMv8 ARM reserves the following encoding for system registers:
  * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
@@ -37,6 +35,33 @@
 #define sys_reg(op0, op1, crn, crm, op2) \
 	((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
 
+#ifndef CONFIG_BROKEN_GAS_INST
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x)			.inst (x)
+#else
+#define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
+#endif
+
+#else  /* CONFIG_BROKEN_GAS_INST */
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+#define __INSTR_BSWAP(x)		(x)
+#else  /* CONFIG_CPU_BIG_ENDIAN */
+#define __INSTR_BSWAP(x)		((((x) << 24) & 0xff000000)	| \
+					 (((x) <<  8) & 0x00ff0000)	| \
+					 (((x) >>  8) & 0x0000ff00)	| \
+					 (((x) >> 24) & 0x000000ff))
+#endif	/* CONFIG_CPU_BIG_ENDIAN */
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x)			.long __INSTR_BSWAP(x)
+#else  /* __ASSEMBLY__ */
+#define __emit_inst(x)			".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* CONFIG_BROKEN_GAS_INST */
+
 #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)
@@ -81,10 +106,10 @@
 #define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
 #define REG_PSTATE_UAO_IMM		sys_reg(0, 0, 4, 0, 3)
 
-#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
-				     (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __inst_arm(0xd5000000 | REG_PSTATE_UAO_IMM |\
-				     (!!x)<<8 | 0x1f)
+#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM |	\
+				      (!!x)<<8 | 0x1f)
+#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM |	\
+				      (!!x)<<8 | 0x1f)
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_EE    (1 << 25)
@@ -228,11 +253,11 @@
 	.equ	.L__reg_num_xzr, 31
 
 	.macro	mrs_s, rt, sreg
-	.inst	0xd5200000|(\sreg)|(.L__reg_num_\rt)
+	 __emit_inst(0xd5200000|(\sreg)|(.L__reg_num_\rt))
 	.endm
 
 	.macro	msr_s, sreg, rt
-	.inst	0xd5000000|(\sreg)|(.L__reg_num_\rt)
+	__emit_inst(0xd5000000|(\sreg)|(.L__reg_num_\rt))
 	.endm
 
 #else
@@ -246,11 +271,11 @@ asm(
 "	.equ	.L__reg_num_xzr, 31\n"
 "\n"
 "	.macro	mrs_s, rt, sreg\n"
-"	.inst	0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n"
+	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
 "	.endm\n"
 "\n"
 "	.macro	msr_s, sreg, rt\n"
-"	.inst	0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n"
+	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
 "	.endm\n"
 );
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index e9ea5a6bd449..46c3b93cf865 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -36,58 +36,31 @@
 
 struct task_struct;
 
+#include <asm/stack_pointer.h>
 #include <asm/types.h>
 
 typedef unsigned long mm_segment_t;
 
 /*
  * low level task data that entry.S needs immediate access to.
- * __switch_to() assumes cpu_context follows immediately after cpu_domain.
  */
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	mm_segment_t		addr_limit;	/* address limit */
-	struct task_struct	*task;		/* main task structure */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	u64			ttbr0;		/* saved TTBR0_EL1 */
+#endif
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
-	int			cpu;		/* cpu */
 };
 
 #define INIT_THREAD_INFO(tsk)						\
 {									\
-	.task		= &tsk,						\
-	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
-/*
- * how to get the current stack pointer from C
- */
-register unsigned long current_stack_pointer asm ("sp");
-
-/*
- * how to get the thread information struct from C
- */
-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)
-{
-	unsigned long sp_el0;
-
-	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
-
-	return (struct thread_info *)sp_el0;
-}
-
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(tsk->thread.cpu_context.pc))
 #define thread_saved_sp(tsk)	\
@@ -112,6 +85,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
@@ -132,10 +106,12 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
+				 _TIF_UPROBE)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 55d0adbf6509..d26750ca6e06 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -18,6 +18,12 @@
 #ifndef __ASM_UACCESS_H
 #define __ASM_UACCESS_H
 
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
 /*
  * User space memory access functions
  */
@@ -26,10 +32,8 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/ptrace.h>
-#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -120,6 +124,99 @@ static inline void set_fs(mm_segment_t fs)
 	"	.popsection\n"
 
 /*
+ * User access enabling/disabling.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void __uaccess_ttbr0_disable(void)
+{
+	unsigned long ttbr;
+
+	/* reserved_ttbr0 placed at the end of swapper_pg_dir */
+	ttbr = read_sysreg(ttbr1_el1) + SWAPPER_DIR_SIZE;
+	write_sysreg(ttbr, ttbr0_el1);
+	isb();
+}
+
+static inline void __uaccess_ttbr0_enable(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable interrupts to avoid preemption between reading the 'ttbr0'
+	 * variable and the MSR. A context switch could trigger an ASID
+	 * roll-over and an update of 'ttbr0'.
+	 */
+	local_irq_save(flags);
+	write_sysreg(current_thread_info()->ttbr0, ttbr0_el1);
+	isb();
+	local_irq_restore(flags);
+}
+
+static inline bool uaccess_ttbr0_disable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_disable();
+	return true;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_enable();
+	return true;
+}
+#else
+static inline bool uaccess_ttbr0_disable(void)
+{
+	return false;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	return false;
+}
+#endif
+
+#define __uaccess_disable(alt)						\
+do {									\
+	if (!uaccess_ttbr0_disable())					\
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt,		\
+				CONFIG_ARM64_PAN));			\
+} while (0)
+
+#define __uaccess_enable(alt)						\
+do {									\
+	if (!uaccess_ttbr0_enable())					\
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt,		\
+				CONFIG_ARM64_PAN));			\
+} while (0)
+
+static inline void uaccess_disable(void)
+{
+	__uaccess_disable(ARM64_HAS_PAN);
+}
+
+static inline void uaccess_enable(void)
+{
+	__uaccess_enable(ARM64_HAS_PAN);
+}
+
+/*
+ * These functions are no-ops when UAO is present.
+ */
+static inline void uaccess_disable_not_uao(void)
+{
+	__uaccess_disable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+static inline void uaccess_enable_not_uao(void)
+{
+	__uaccess_enable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+/*
  * The "__xxx" versions of the user access functions do not verify the address
  * space - it must have been done previously with a separate "access_ok()"
  * call.
@@ -146,8 +243,7 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr),  \
@@ -168,9 +264,8 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
+	uaccess_disable_not_uao();					\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __get_user(x, ptr)						\
@@ -215,8 +310,7 @@ do {									\
 do {									\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr),	\
@@ -237,8 +331,7 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_disable_not_uao();					\
 } while (0)
 
 #define __put_user(x, ptr)						\
@@ -331,4 +424,66 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+#else	/* __ASSEMBLY__ */
+
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
+	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1
+	get_thread_info \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+	uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif	/* __ASSEMBLY__ */
+
 #endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
new file mode 100644
index 000000000000..8d004073d0e8
--- /dev/null
+++ b/arch/arm64/include/asm/uprobes.h
@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
+#include <asm/probes.h>
+
+#define MAX_UINSN_BYTES		AARCH64_INSN_SIZE
+
+#define UPROBE_SWBP_INSN	BRK64_OPCODE_UPROBES
+#define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	bool simulate;
+};
+
+#endif