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

Pull arm64 updates from Will Deacon:
 "Mostly just incremental improvements here:

   - Introduce AT_HWCAP2 for advertising CPU features to userspace

   - Expose SVE2 availability to userspace

   - Support for "data cache clean to point of deep persistence" (DC PODP)

   - Honour "mitigations=off" on the cmdline and advertise status via
     sysfs

   - CPU timer erratum workaround (Neoverse-N1 #1188873)

   - Introduce perf PMU driver for the SMMUv3 performance counters

   - Add config option to disable the kuser helpers page for AArch32 tasks

   - Futex modifications to ensure liveness under contention

   - Rework debug exception handling to seperate kernel and user
     handlers

   - Non-critical fixes and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  Documentation: Add ARM64 to kernel-parameters.rst
  arm64/speculation: Support 'mitigations=' cmdline option
  arm64: ssbs: Don't treat CPUs with SSBS as unaffected by SSB
  arm64: enable generic CPU vulnerabilites support
  arm64: add sysfs vulnerability show for speculative store bypass
  arm64: Fix size of __early_cpu_boot_status
  clocksource/arm_arch_timer: Use arch_timer_read_counter to access stable counters
  clocksource/arm_arch_timer: Remove use of workaround static key
  clocksource/arm_arch_timer: Drop use of static key in arch_timer_reg_read_stable
  clocksource/arm_arch_timer: Direcly assign set_next_event workaround
  arm64: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  watchdog/sbsa: Use arch_timer_read_counter instead of arch_counter_get_cntvct
  ARM: vdso: Remove dependency with the arch_timer driver internals
  arm64: Apply ARM64_ERRATUM_1188873 to Neoverse-N1
  arm64: Add part number for Neoverse N1
  arm64: Make ARM64_ERRATUM_1188873 depend on COMPAT
  arm64: Restrict ARM64_ERRATUM_1188873 mitigation to AArch32
  arm64: mm: Remove pte_unmap_nested()
  arm64: Fix compiler warning from pte_unmap() with -Wunused-but-set-variable
  arm64: compat: Reduce address limit for 64K pages
  ...

29 files changed, 356 insertions, 128 deletions

diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f2a234d6516c..b7bca1ae09e6 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -31,11 +31,23 @@
 #include <clocksource/arm_arch_timer.h>
 
 #if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
-extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_unstable_timer_counter_workaround() \
-	static_branch_unlikely(&arch_timer_read_ool_enabled)
+#define has_erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h);					\
+	})
+
+#define erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h) ? __wa->h : arch_timer_##h;		\
+	})
+
 #else
-#define needs_unstable_timer_counter_workaround()  false
+#define has_erratum_handler(h)			   false
+#define erratum_handler(h)			   (arch_timer_##h)
 #endif
 
 enum arch_timer_erratum_match_type {
@@ -61,23 +73,37 @@ struct arch_timer_erratum_workaround {
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 		timer_unstable_counter_workaround);
 
+/* inline sysreg accessors that make erratum_handler() work */
+static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
+{
+	return read_sysreg(cntp_tval_el0);
+}
+
+static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
+{
+	return read_sysreg(cntv_tval_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntpct_el0(void)
+{
+	return read_sysreg(cntpct_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntvct_el0(void)
+{
+	return read_sysreg(cntvct_el0);
+}
+
 #define arch_timer_reg_read_stable(reg)					\
-({									\
-	u64 _val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *wa;		\
+	({								\
+		u64 _val;						\
+									\
 		preempt_disable_notrace();				\
-		wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (wa && wa->read_##reg)				\
-			_val = wa->read_##reg();			\
-		else							\
-			_val = read_sysreg(reg);			\
+		_val = erratum_handler(read_ ## reg)();			\
 		preempt_enable_notrace();				\
-	} else {							\
-		_val = read_sysreg(reg);				\
-	}								\
-	_val;								\
-})
+									\
+		_val;							\
+	})
 
 /*
  * These register accessors are marked inline so the compiler can
@@ -148,18 +174,67 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	isb();
 }
 
-static inline u64 arch_counter_get_cntpct(void)
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static inline u64 __arch_counter_get_cntpct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntpct_el0);
+	cnt = read_sysreg(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntvct_stable(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntvct_el0);
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
+static inline u64 __arch_counter_get_cntvct(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = read_sysreg(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+#undef arch_counter_enforce_ordering
+
 static inline int arch_timer_arch_init(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index c5308d01e228..039fbd822ec6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -407,10 +407,14 @@ alternative_endif
 	.ifc	\op, cvap
 	sys	3, c7, c12, 1, \kaddr	// dc cvap
 	.else
+	.ifc	\op, cvadp
+	sys	3, c7, c13, 1, \kaddr	// dc cvadp
+	.else
 	dc	\op, \kaddr
 	.endif
 	.endif
 	.endif
+	.endif
 	add	\kaddr, \kaddr, \tmp1
 	cmp	\kaddr, \size
 	b.lo	9998b
@@ -442,8 +446,8 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */
 	.macro	reset_pmuserenr_el0, tmpreg
-	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	\tmpreg, \tmpreg, #8, #4
+	mrs	\tmpreg, id_aa64dfr0_el1
+	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	\tmpreg, #1			// Skip if no PMU present
 	b.lt	9000f
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f66bb04fdf2d..85b6bedbcc68 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/kasan-checks.h>
+
 #define __nops(n)	".rept	" #n "\nnop\n.endr\n"
 #define nops(n)		asm volatile(__nops(n))
 
@@ -72,31 +74,33 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
 
 #define __smp_store_release(p, v)					\
 do {									\
+	typeof(p) __p = (p);						\
 	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) }; 			\
+		{ .__val = (__force typeof(*p)) (v) };			\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_write(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u8 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u16 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u32 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u64 *)__u.__c)		\
 				: "memory");				\
 		break;							\
@@ -106,27 +110,29 @@ do {									\
 #define __smp_load_acquire(p)						\
 ({									\
 	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_read(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
 			: "=r" (*(__u8 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
 			: "=r" (*(__u16 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
 			: "=r" (*(__u32 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
 			: "=r" (*(__u64 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	}								\
 	__u.__val;							\
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index 2945fe6cd863..d84294064e6a 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -11,6 +11,8 @@
 
 /*
  * #imm16 values used for BRK instruction generation
+ * 0x004: for installing kprobes
+ * 0x005: for installing uprobes
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -18,10 +20,13 @@
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
  */
+#define KPROBES_BRK_IMM			0x004
+#define UPROBES_BRK_IMM			0x005
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
 #define BUG_BRK_IMM			0x800
 #define KASAN_BRK_IMM			0x900
+#define KASAN_BRK_MASK			0x0ff
 
 #endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f6a76e43f39e..defdc67d9ab4 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -61,7 +61,8 @@
 #define ARM64_HAS_GENERIC_AUTH_ARCH		40
 #define ARM64_HAS_GENERIC_AUTH_IMP_DEF		41
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
+#define ARM64_HAS_DCPODP			43
 
-#define ARM64_NCAPS				43
+#define ARM64_NCAPS				44
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e505e1fbd2b9..f210bcf096f7 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -14,15 +14,8 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
-/*
- * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
- * in the kernel and for user space to keep track of which optional features
- * are supported by the current system. So let's map feature 'x' to HWCAP_x.
- * Note that HWCAP_x constants are bit fields so we need to take the log.
- */
-
-#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
-#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+#define MAX_CPU_FEATURES	64
+#define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
 
@@ -399,11 +392,13 @@ extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 	for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
 
 bool this_cpu_has_cap(unsigned int cap);
+void cpu_set_feature(unsigned int num);
+bool cpu_have_feature(unsigned int num);
+unsigned long cpu_get_elf_hwcap(void);
+unsigned long cpu_get_elf_hwcap2(void);
 
-static inline bool cpu_have_feature(unsigned int num)
-{
-	return elf_hwcap & (1UL << num);
-}
+#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
+#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
 /* System capability check for constant caps */
 static inline bool __cpus_have_const_cap(int num)
@@ -638,11 +633,7 @@ static inline int arm64_get_ssbd_state(void)
 #endif
 }
 
-#ifdef CONFIG_ARM64_SSBD
 void arm64_set_ssbd_mitigation(bool state);
-#else
-static inline void arm64_set_ssbd_mitigation(bool state) {}
-#endif
 
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5f1437099b99..2602bae334fb 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -89,6 +89,7 @@
 #define ARM_CPU_PART_CORTEX_A35		0xD04
 #define ARM_CPU_PART_CORTEX_A55		0xD05
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -118,6 +119,7 @@
 #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
 #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index a44cf5225429..0679f781696d 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -65,12 +65,9 @@
 #define CACHE_FLUSH_IS_SAFE		1
 
 /* kprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_MASK		0xFFFF
-#define BRK64_ESR_KPROBES	0x0004
-#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
 /* uprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_UPROBES	0x0005
-#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
@@ -94,18 +91,24 @@ struct step_hook {
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
 };
 
-void register_step_hook(struct step_hook *hook);
-void unregister_step_hook(struct step_hook *hook);
+void register_user_step_hook(struct step_hook *hook);
+void unregister_user_step_hook(struct step_hook *hook);
+
+void register_kernel_step_hook(struct step_hook *hook);
+void unregister_kernel_step_hook(struct step_hook *hook);
 
 struct break_hook {
 	struct list_head node;
-	u32 esr_val;
-	u32 esr_mask;
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	u16 imm;
+	u16 mask; /* These bits are ignored when comparing with imm */
 };
 
-void register_break_hook(struct break_hook *hook);
-void unregister_break_hook(struct break_hook *hook);
+void register_user_break_hook(struct break_hook *hook);
+void unregister_user_break_hook(struct break_hook *hook);
+
+void register_kernel_break_hook(struct break_hook *hook);
+void unregister_kernel_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 6adc1a90e7e6..355d120b78cb 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -214,10 +214,10 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 	set_thread_flag(TIF_32BIT);					\
  })
 #define COMPAT_ARCH_DLINFO
-extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
-				      int uses_interp);
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+					  int uses_interp);
 #define compat_arch_setup_additional_pages \
-					aarch32_setup_vectors_page
+					aarch32_setup_additional_pages
 
 #endif /* CONFIG_COMPAT */
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 52233f00d53d..0e27fe91d5ea 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -156,9 +156,7 @@
 				 ESR_ELx_WFx_ISS_WFI)
 
 /* BRK instruction trap from AArch64 state */
-#define ESR_ELx_VAL_BRK64(imm)					\
-	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
-	 ((imm) & 0xffff))
+#define ESR_ELx_BRK64_ISS_COMMENT_MASK	0xffff
 
 /* ISS field definitions for System instruction traps */
 #define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
@@ -198,9 +196,10 @@
 /*
  * User space cache operations have the following sysreg encoding
  * in System instructions.
- * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 14 }, WRITE (L=0)
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0)
  */
 #define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVADP	13
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAP	12
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index c7e1a7837706..a56efb5626fa 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -23,26 +23,34 @@
 
 #include <asm/errno.h>
 
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
 	uaccess_enable();						\
 	asm volatile(							\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
 "2:	stlxr	%w0, %w3, %2\n"						\
-"	cbnz	%w0, 1b\n"						\
-"	dmb	ish\n"							\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w7\n"						\
 "3:\n"									\
+"	dmb	ish\n"							\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
-"4:	mov	%w0, %w5\n"						\
+"4:	mov	%w0, %w6\n"						\
 "	b	3b\n"							\
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
-	: "r" (oparg), "Ir" (-EFAULT)					\
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN)			\
 	: "memory");							\
 	uaccess_disable();						\
 } while (0)
@@ -57,23 +65,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w3, %w4",
+		__futex_atomic_op("mov	%w3, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w3, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w3, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w3, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w3, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:
@@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
 	u32 val, tmp;
 	u32 __user *uaddr;
 
@@ -104,24 +113,30 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
-"	sub	%w3, %w1, %w4\n"
-"	cbnz	%w3, 3f\n"
-"2:	stlxr	%w3, %w5, %2\n"
-"	cbnz	%w3, 1b\n"
-"	dmb	ish\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w8\n"
 "3:\n"
+"	dmb	ish\n"
+"4:\n"
 "	.pushsection .fixup,\"ax\"\n"
-"4:	mov	%w0, %w6\n"
-"	b	3b\n"
+"5:	mov	%w0, %w7\n"
+"	b	4b\n"
 "	.popsection\n"
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 4b)
-	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
-	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
 	: "memory");
 	uaccess_disable();
 
-	*uval = val;
+	if (!ret)
+		*uval = val;
+
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 400b80b49595..b4bfb6672168 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -17,6 +17,7 @@
 #define __ASM_HWCAP_H
 
 #include <uapi/asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #define COMPAT_HWCAP_HALF	(1 << 1)
 #define COMPAT_HWCAP_THUMB	(1 << 2)
@@ -40,11 +41,67 @@
 #define COMPAT_HWCAP2_CRC32	(1 << 4)
 
 #ifndef __ASSEMBLY__
+#include <linux/log2.h>
+
+/*
+ * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
+ * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
+ * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
+ * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ *
+ * Hwcaps should be set and tested within the kernel via the
+ * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
+ * of KERNEL_HWCAP_{feature}.
+ */
+#define __khwcap_feature(x)		const_ilog2(HWCAP_ ## x)
+#define KERNEL_HWCAP_FP			__khwcap_feature(FP)
+#define KERNEL_HWCAP_ASIMD		__khwcap_feature(ASIMD)
+#define KERNEL_HWCAP_EVTSTRM		__khwcap_feature(EVTSTRM)
+#define KERNEL_HWCAP_AES		__khwcap_feature(AES)
+#define KERNEL_HWCAP_PMULL		__khwcap_feature(PMULL)
+#define KERNEL_HWCAP_SHA1		__khwcap_feature(SHA1)
+#define KERNEL_HWCAP_SHA2		__khwcap_feature(SHA2)
+#define KERNEL_HWCAP_CRC32		__khwcap_feature(CRC32)
+#define KERNEL_HWCAP_ATOMICS		__khwcap_feature(ATOMICS)
+#define KERNEL_HWCAP_FPHP		__khwcap_feature(FPHP)
+#define KERNEL_HWCAP_ASIMDHP		__khwcap_feature(ASIMDHP)
+#define KERNEL_HWCAP_CPUID		__khwcap_feature(CPUID)
+#define KERNEL_HWCAP_ASIMDRDM		__khwcap_feature(ASIMDRDM)
+#define KERNEL_HWCAP_JSCVT		__khwcap_feature(JSCVT)
+#define KERNEL_HWCAP_FCMA		__khwcap_feature(FCMA)
+#define KERNEL_HWCAP_LRCPC		__khwcap_feature(LRCPC)
+#define KERNEL_HWCAP_DCPOP		__khwcap_feature(DCPOP)
+#define KERNEL_HWCAP_SHA3		__khwcap_feature(SHA3)
+#define KERNEL_HWCAP_SM3		__khwcap_feature(SM3)
+#define KERNEL_HWCAP_SM4		__khwcap_feature(SM4)
+#define KERNEL_HWCAP_ASIMDDP		__khwcap_feature(ASIMDDP)
+#define KERNEL_HWCAP_SHA512		__khwcap_feature(SHA512)
+#define KERNEL_HWCAP_SVE		__khwcap_feature(SVE)
+#define KERNEL_HWCAP_ASIMDFHM		__khwcap_feature(ASIMDFHM)
+#define KERNEL_HWCAP_DIT		__khwcap_feature(DIT)
+#define KERNEL_HWCAP_USCAT		__khwcap_feature(USCAT)
+#define KERNEL_HWCAP_ILRCPC		__khwcap_feature(ILRCPC)
+#define KERNEL_HWCAP_FLAGM		__khwcap_feature(FLAGM)
+#define KERNEL_HWCAP_SSBS		__khwcap_feature(SSBS)
+#define KERNEL_HWCAP_SB			__khwcap_feature(SB)
+#define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
+#define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
+
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
+#define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
+#define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
+#define KERNEL_HWCAP_SVEPMULL		__khwcap2_feature(SVEPMULL)
+#define KERNEL_HWCAP_SVEBITPERM		__khwcap2_feature(SVEBITPERM)
+#define KERNEL_HWCAP_SVESHA3		__khwcap2_feature(SVESHA3)
+#define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
+
 /*
  * This yields a mask that user programs can use to figure out what
  * instruction set this cpu supports.
  */
-#define ELF_HWCAP		(elf_hwcap)
+#define ELF_HWCAP		cpu_get_elf_hwcap()
+#define ELF_HWCAP2		cpu_get_elf_hwcap2()
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
@@ -60,6 +117,5 @@ enum {
 #endif
 };
 
-extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 43d8366c1e87..629963189085 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -43,7 +43,7 @@ static inline void arch_local_irq_enable(void)
 	asm volatile(ALTERNATIVE(
 		"msr	daifclr, #2		// arch_local_irq_enable\n"
 		"nop",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ",%0\n"
+		__msr_s(SYS_ICC_PMR_EL1, "%0")
 		"dsb	sy",
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
@@ -55,7 +55,7 @@ static inline void arch_local_irq_disable(void)
 {
 	asm volatile(ALTERNATIVE(
 		"msr	daifset, #2		// arch_local_irq_disable",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ", %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" ((unsigned long) GIC_PRIO_IRQOFF)
@@ -86,7 +86,7 @@ static inline unsigned long arch_local_save_flags(void)
 			"mov	%0, %1\n"
 			"nop\n"
 			"nop",
-			"mrs_s	%0, " __stringify(SYS_ICC_PMR_EL1) "\n"
+			__mrs_s("%0", SYS_ICC_PMR_EL1)
 			"ands	%1, %1, " __stringify(PSR_I_BIT) "\n"
 			"csel	%0, %0, %2, eq",
 			ARM64_HAS_IRQ_PRIO_MASKING)
@@ -116,7 +116,7 @@ static inline void arch_local_irq_restore(unsigned long flags)
 	asm volatile(ALTERNATIVE(
 			"msr	daif, %0\n"
 			"nop",
-			"msr_s	" __stringify(SYS_ICC_PMR_EL1) ", %0\n"
+			__msr_s(SYS_ICC_PMR_EL1, "%0")
 			"dsb	sy",
 			ARM64_HAS_IRQ_PRIO_MASKING)
 		: "+r" (flags)
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index d5a44cf859e9..21721fbf44e7 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -54,8 +54,6 @@ void arch_remove_kprobe(struct kprobe *);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);
-int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
-int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
 void kretprobe_trampoline(void);
 void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4da765f2cca5..c3060833b7a5 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -30,7 +30,7 @@
 	({								\
 		u64 reg;						\
 		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
-					 "mrs_s %0, " __stringify(r##vh),\
+					 __mrs_s("%0", r##vh),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 			     : "=r" (reg));				\
 		reg;							\
@@ -40,7 +40,7 @@
 	do {								\
 		u64 __val = (u64)(v);					\
 		asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
-					 "msr_s " __stringify(r##vh) ", %x0",\
+					 __msr_s(r##vh, "%x0"),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 					 : : "rZ" (__val));		\
 	} while (0)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 290195168bb3..2cb8248fa2c8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -302,7 +302,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
+#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)__get_free_page(PGALLOC_GFP);
+	struct page *page;
+
+	page = alloc_page(PGALLOC_GFP);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	return page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
 	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmdp));
 	free_page((unsigned long)pmdp);
 }
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index de70c1eabf33..2c41b04708fe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -478,6 +478,8 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 	return __pmd_to_phys(pmd);
 }
 
+static inline void pte_unmap(pte_t *pte) { }
+
 /* Find an entry in the third-level page table. */
 #define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -485,9 +487,6 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
 
 #define pte_set_fixmap(addr)		((pte_t *)set_fixmap_offset(FIX_PTE, addr))
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 15d49515efdd..d328540cb85e 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_POINTER_AUTH_H
 #define __ASM_POINTER_AUTH_H
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5d9ce62bdebd..fcd0e691b1ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -57,7 +57,15 @@
 #define TASK_SIZE_64		(UL(1) << vabits_user)
 
 #ifdef CONFIG_COMPAT
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
 #define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ec60174c8c18..b2de32939ada 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -305,6 +305,28 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->regs[0];
 }
 
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note that this chooses the most likely register mapping. In very rare
+ * cases this may not return correct data, for example, if one of the
+ * function parameters is 16 bytes or bigger. In such cases, we cannot
+ * get access the parameter correctly and the register assignment of
+ * subsequent parameters will be shifted.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						     unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+	if (n < NR_REG_ARGUMENTS)
+		return pt_regs_read_reg(regs, n);
+	return 0;
+}
+
 /* We must avoid circular header include via sched.h */
 struct task_struct;
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index ffe47d766c25..63e0b92a5fbb 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_SDEI_H
 #define __ASM_SDEI_H
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index 81abea0b7650..58e288aaf0ba 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -20,8 +20,6 @@
 #ifdef CONFIG_COMPAT
 #include <linux/compat.h>
 
-#define AARCH32_KERN_SIGRET_CODE_OFFSET	0x500
-
 int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
 		       struct pt_regs *regs);
 int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 5412fa40825e..915809e4ac32 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -119,7 +119,7 @@ static inline pud_t *stage2_pud_offset(struct kvm *kvm,
 static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
 {
 	if (kvm_stage2_has_pud(kvm))
-		pud_free(NULL, pud);
+		free_page((unsigned long)pud);
 }
 
 static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
@@ -192,7 +192,7 @@ static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
 static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
 {
 	if (kvm_stage2_has_pmd(kvm))
-		pmd_free(NULL, pmd);
+		free_page((unsigned long)pmd);
 }
 
 static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5b267dec6194..3f7b917e8f3a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -606,6 +606,20 @@
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 
+/* id_aa64zfr0 */
+#define ID_AA64ZFR0_SM4_SHIFT		40
+#define ID_AA64ZFR0_SHA3_SHIFT		32
+#define ID_AA64ZFR0_BITPERM_SHIFT	16
+#define ID_AA64ZFR0_AES_SHIFT		4
+#define ID_AA64ZFR0_SVEVER_SHIFT	0
+
+#define ID_AA64ZFR0_SM4			0x1
+#define ID_AA64ZFR0_SHA3		0x1
+#define ID_AA64ZFR0_BITPERM		0x1
+#define ID_AA64ZFR0_AES			0x1
+#define ID_AA64ZFR0_AES_PMULL		0x2
+#define ID_AA64ZFR0_SVEVER_SVE2		0x1
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
@@ -746,20 +760,39 @@
 #include <linux/build_bug.h>
 #include <linux/types.h>
 
-asm(
-"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
-"	.equ	.L__reg_num_x\\num, \\num\n"
-"	.endr\n"
+#define __DEFINE_MRS_MSR_S_REGNUM				\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+"	.equ	.L__reg_num_x\\num, \\num\n"			\
+"	.endr\n"						\
 "	.equ	.L__reg_num_xzr, 31\n"
-"\n"
-"	.macro	mrs_s, rt, sreg\n"
-	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MRS_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	mrs_s, rt, sreg\n"				\
+	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-"\n"
-"	.macro	msr_s, sreg, rt\n"
-	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MSR_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	msr_s, sreg, rt\n"				\
+	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-);
+
+#define UNDEFINE_MRS_S						\
+"	.purgem	mrs_s\n"
+
+#define UNDEFINE_MSR_S						\
+"	.purgem	msr_s\n"
+
+#define __mrs_s(v, r)						\
+	DEFINE_MRS_S						\
+"	mrs_s " v ", " __stringify(r) "\n"			\
+	UNDEFINE_MRS_S
+
+#define __msr_s(r, v)						\
+	DEFINE_MSR_S						\
+"	msr_s " __stringify(r) ", " v "\n"			\
+	UNDEFINE_MSR_S
 
 /*
  * Unlike read_cpuid, calls to read_sysreg are never expected to be
@@ -787,13 +820,13 @@ asm(
  */
 #define read_sysreg_s(r) ({						\
 	u64 __val;							\
-	asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val));	\
+	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
 	__val;								\
 })
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)(v);						\
-	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
+	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
 } while (0)
 
 /*
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 32693f34f431..fca95424e873 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -41,7 +41,6 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 			   int sig, int code, const char *name);
 
 struct mm_struct;
-extern void show_pte(unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 37603b5616a5..a287189ca8b4 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -63,7 +63,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_remove_table(tlb, virt_to_page(pmdp));
+	struct page *page = virt_to_page(pmdp);
+
+	pgtable_pmd_page_dtor(page);
+	tlb_remove_table(tlb, page);
 }
 #endif
 
diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
index 2b9a63771eda..f89263c8e11a 100644
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ b/arch/arm64/include/asm/vdso_datapage.h
@@ -38,6 +38,7 @@ struct vdso_data {
 	__u32 tz_minuteswest;	/* Whacky timezone stuff */
 	__u32 tz_dsttime;
 	__u32 use_syscall;
+	__u32 hrtimer_res;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
index 0b5ec6e08c10..0a12115d9638 100644
--- a/arch/arm64/include/asm/vmap_stack.h
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_VMAP_STACK_H
 #define __ASM_VMAP_STACK_H