From dc50eab76b709d68175a358d6e23a5a3890764d3 Mon Sep 17 00:00:00 2001
From: Daniel Baumann <daniel.baumann@progress-linux.org>
Date: Sat, 18 May 2024 19:39:57 +0200
Subject: Merging upstream version 6.7.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
---
 arch/arm64/include/asm/Kbuild               |  2 +-
 arch/arm64/include/asm/alternative-macros.h | 12 ++--
 arch/arm64/include/asm/arch_gicv3.h         |  8 +++
 arch/arm64/include/asm/archrandom.h         |  2 +-
 arch/arm64/include/asm/cacheflush.h         |  2 +-
 arch/arm64/include/asm/cpu.h                |  6 --
 arch/arm64/include/asm/cpucaps.h            | 67 ++++++++++++++++++++
 arch/arm64/include/asm/cpufeature.h         | 98 +++++++++++++----------------
 arch/arm64/include/asm/cputype.h            |  4 ++
 arch/arm64/include/asm/crash_core.h         | 10 +++
 arch/arm64/include/asm/fpsimd.h             | 38 +++++++++--
 arch/arm64/include/asm/hwcap.h              |  3 +
 arch/arm64/include/asm/irq.h                |  3 +
 arch/arm64/include/asm/irq_work.h           |  2 -
 arch/arm64/include/asm/irqflags.h           | 20 +++---
 arch/arm64/include/asm/jump_label.h         |  4 +-
 arch/arm64/include/asm/kprobes.h            |  2 -
 arch/arm64/include/asm/kvm_arm.h            |  4 +-
 arch/arm64/include/asm/kvm_emulate.h        | 19 +++---
 arch/arm64/include/asm/kvm_host.h           | 63 ++++++++++++++-----
 arch/arm64/include/asm/kvm_hyp.h            |  7 +--
 arch/arm64/include/asm/kvm_mmu.h            | 47 ++++++++++----
 arch/arm64/include/asm/kvm_nested.h         |  3 +-
 arch/arm64/include/asm/lse.h                |  9 +--
 arch/arm64/include/asm/mmu.h                |  2 +-
 arch/arm64/include/asm/mmu_context.h        | 28 +++++----
 arch/arm64/include/asm/module.h             |  3 +-
 arch/arm64/include/asm/mte.h                |  4 +-
 arch/arm64/include/asm/pgtable-prot.h       |  6 +-
 arch/arm64/include/asm/pgtable.h            | 34 ++++++----
 arch/arm64/include/asm/smp.h                |  4 +-
 arch/arm64/include/asm/spectre.h            |  2 +-
 arch/arm64/include/asm/stage2_pgtable.h     |  4 +-
 arch/arm64/include/asm/syscall_wrapper.h    |  1 -
 arch/arm64/include/asm/sysreg.h             | 45 +++++++++++++
 arch/arm64/include/asm/tlb.h                |  5 +-
 arch/arm64/include/asm/tlbflush.h           | 15 +++--
 arch/arm64/include/asm/traps.h              | 54 +++++++++++++++-
 arch/arm64/include/asm/unistd.h             |  2 +-
 arch/arm64/include/asm/unistd32.h           | 12 +++-
 arch/arm64/include/asm/vectors.h            |  2 +-
 arch/arm64/include/uapi/asm/hwcap.h         |  3 +
 arch/arm64/include/uapi/asm/kvm.h           | 32 ++++++++++
 43 files changed, 494 insertions(+), 199 deletions(-)
 create mode 100644 arch/arm64/include/asm/cpucaps.h
 create mode 100644 arch/arm64/include/asm/crash_core.h

(limited to 'arch/arm64/include')

diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 5c8ee5a54..4b6d2d520 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -6,5 +6,5 @@ generic-y += qspinlock.h
 generic-y += parport.h
 generic-y += user.h
 
-generated-y += cpucaps.h
+generated-y += cpucap-defs.h
 generated-y += sysreg-defs.h
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 94b486192..d328f549b 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -226,10 +226,10 @@ alternative_endif
 static __always_inline bool
 alternative_has_cap_likely(const unsigned long cpucap)
 {
-	compiletime_assert(cpucap < ARM64_NCAPS,
-			   "cpucap must be < ARM64_NCAPS");
+	if (!cpucap_is_possible(cpucap))
+		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE_CB("b	%l[l_no]", %[cpucap], alt_cb_patch_nops)
 	:
 	: [cpucap] "i" (cpucap)
@@ -244,10 +244,10 @@ l_no:
 static __always_inline bool
 alternative_has_cap_unlikely(const unsigned long cpucap)
 {
-	compiletime_assert(cpucap < ARM64_NCAPS,
-			   "cpucap must be < ARM64_NCAPS");
+	if (!cpucap_is_possible(cpucap))
+		return false;
 
-	asm_volatile_goto(
+	asm goto(
 	ALTERNATIVE("nop", "b	%l[l_yes]", %[cpucap])
 	:
 	: [cpucap] "i" (cpucap)
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 01281a533..5f1726116 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -79,6 +79,14 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
 	return 0x3ff;
 }
 
+static u64 __maybe_unused gic_read_iar(void)
+{
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_CAVIUM_23154))
+		return gic_read_iar_cavium_thunderx();
+	else
+		return gic_read_iar_common();
+}
+
 static inline void gic_write_ctlr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_CTLR_EL1);
diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h
index b0abc64f8..ecdb3cfcd 100644
--- a/arch/arm64/include/asm/archrandom.h
+++ b/arch/arm64/include/asm/archrandom.h
@@ -63,7 +63,7 @@ static __always_inline bool __cpu_has_rng(void)
 {
 	if (unlikely(!system_capabilities_finalized() && !preemptible()))
 		return this_cpu_has_cap(ARM64_HAS_RNG);
-	return cpus_have_const_cap(ARM64_HAS_RNG);
+	return alternative_has_cap_unlikely(ARM64_HAS_RNG);
 }
 
 static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d115451ed..fefac75fa 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -132,7 +132,7 @@ void flush_dcache_folio(struct folio *);
 
 static __always_inline void icache_inval_all_pou(void)
 {
-	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+	if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC))
 		return;
 
 	asm("ic	ialluis");
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index e749838b9..f3034099f 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -63,12 +63,6 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64smfr0;
 
 	struct cpuinfo_32bit	aarch32;
-
-	/* pseudo-ZCR for recording maximum ZCR_EL1 LEN value: */
-	u64		reg_zcr;
-
-	/* pseudo-SMCR for recording maximum SMCR_EL1 LEN value: */
-	u64		reg_smcr;
 };
 
 DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data);
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
new file mode 100644
index 000000000..270680e2b
--- /dev/null
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_CPUCAPS_H
+#define __ASM_CPUCAPS_H
+
+#include <asm/cpucap-defs.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+/*
+ * Check whether a cpucap is possible at compiletime.
+ */
+static __always_inline bool
+cpucap_is_possible(const unsigned int cap)
+{
+	compiletime_assert(__builtin_constant_p(cap),
+			   "cap must be a constant");
+	compiletime_assert(cap < ARM64_NCAPS,
+			   "cap must be < ARM64_NCAPS");
+
+	switch (cap) {
+	case ARM64_HAS_PAN:
+		return IS_ENABLED(CONFIG_ARM64_PAN);
+	case ARM64_HAS_EPAN:
+		return IS_ENABLED(CONFIG_ARM64_EPAN);
+	case ARM64_SVE:
+		return IS_ENABLED(CONFIG_ARM64_SVE);
+	case ARM64_SME:
+	case ARM64_SME2:
+	case ARM64_SME_FA64:
+		return IS_ENABLED(CONFIG_ARM64_SME);
+	case ARM64_HAS_CNP:
+		return IS_ENABLED(CONFIG_ARM64_CNP);
+	case ARM64_HAS_ADDRESS_AUTH:
+	case ARM64_HAS_GENERIC_AUTH:
+		return IS_ENABLED(CONFIG_ARM64_PTR_AUTH);
+	case ARM64_HAS_GIC_PRIO_MASKING:
+		return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI);
+	case ARM64_MTE:
+		return IS_ENABLED(CONFIG_ARM64_MTE);
+	case ARM64_BTI:
+		return IS_ENABLED(CONFIG_ARM64_BTI);
+	case ARM64_HAS_TLB_RANGE:
+		return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
+	case ARM64_UNMAP_KERNEL_AT_EL0:
+		return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
+	case ARM64_WORKAROUND_843419:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419);
+	case ARM64_WORKAROUND_1742098:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_1742098);
+	case ARM64_WORKAROUND_2645198:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198);
+	case ARM64_WORKAROUND_2658417:
+		return IS_ENABLED(CONFIG_ARM64_ERRATUM_2658417);
+	case ARM64_WORKAROUND_CAVIUM_23154:
+		return IS_ENABLED(CONFIG_CAVIUM_ERRATUM_23154);
+	case ARM64_WORKAROUND_NVIDIA_CARMEL_CNP:
+		return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM);
+	case ARM64_WORKAROUND_REPEAT_TLBI:
+		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
+	}
+
+	return true;
+}
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 5bba39376..f6d416fe4 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -23,6 +23,7 @@
 #include <linux/bug.h>
 #include <linux/jump_label.h>
 #include <linux/kernel.h>
+#include <linux/cpumask.h>
 
 /*
  * CPU feature register tracking
@@ -380,6 +381,7 @@ struct arm64_cpu_capabilities {
 	 * method is robust against being called multiple times.
 	 */
 	const struct arm64_cpu_capabilities *match_list;
+	const struct cpumask *cpus;
 };
 
 static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
@@ -438,6 +440,11 @@ unsigned long cpu_get_elf_hwcap2(void);
 #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
 #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
+static __always_inline bool boot_capabilities_finalized(void)
+{
+	return alternative_has_cap_likely(ARM64_ALWAYS_BOOT);
+}
+
 static __always_inline bool system_capabilities_finalized(void)
 {
 	return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM);
@@ -450,6 +457,8 @@ static __always_inline bool system_capabilities_finalized(void)
  */
 static __always_inline bool cpus_have_cap(unsigned int num)
 {
+	if (__builtin_constant_p(num) && !cpucap_is_possible(num))
+		return false;
 	if (num >= ARM64_NCAPS)
 		return false;
 	return arch_test_bit(num, system_cpucaps);
@@ -458,55 +467,37 @@ static __always_inline bool cpus_have_cap(unsigned int num)
 /*
  * Test for a capability without a runtime check.
  *
- * Before capabilities are finalized, this returns false.
- * After capabilities are finalized, this is patched to avoid a runtime check.
+ * Before boot capabilities are finalized, this will BUG().
+ * After boot capabilities are finalized, this is patched to avoid a runtime
+ * check.
  *
  * @num must be a compile-time constant.
  */
-static __always_inline bool __cpus_have_const_cap(int num)
+static __always_inline bool cpus_have_final_boot_cap(int num)
 {
-	if (num >= ARM64_NCAPS)
-		return false;
-	return alternative_has_cap_unlikely(num);
+	if (boot_capabilities_finalized())
+		return alternative_has_cap_unlikely(num);
+	else
+		BUG();
 }
 
 /*
  * Test for a capability without a runtime check.
  *
- * Before capabilities are finalized, this will BUG().
- * After capabilities are finalized, this is patched to avoid a runtime check.
+ * Before system capabilities are finalized, this will BUG().
+ * After system capabilities are finalized, this is patched to avoid a runtime
+ * check.
  *
  * @num must be a compile-time constant.
  */
 static __always_inline bool cpus_have_final_cap(int num)
 {
 	if (system_capabilities_finalized())
-		return __cpus_have_const_cap(num);
+		return alternative_has_cap_unlikely(num);
 	else
 		BUG();
 }
 
-/*
- * Test for a capability, possibly with a runtime check for non-hyp code.
- *
- * For hyp code, this behaves the same as cpus_have_final_cap().
- *
- * For non-hyp code:
- * Before capabilities are finalized, this behaves as cpus_have_cap().
- * After capabilities are finalized, this is patched to avoid a runtime check.
- *
- * @num must be a compile-time constant.
- */
-static __always_inline bool cpus_have_const_cap(int num)
-{
-	if (is_hyp_code())
-		return cpus_have_final_cap(num);
-	else if (system_capabilities_finalized())
-		return __cpus_have_const_cap(num);
-	else
-		return cpus_have_cap(num);
-}
-
 static inline int __attribute_const__
 cpuid_feature_extract_signed_field_width(u64 features, int field, int width)
 {
@@ -626,7 +617,9 @@ static inline bool id_aa64pfr1_mte(u64 pfr1)
 	return val >= ID_AA64PFR1_EL1_MTE_MTE2;
 }
 
-void __init setup_cpu_features(void);
+void __init setup_system_features(void);
+void __init setup_user_features(void);
+
 void check_local_cpu_capabilities(void);
 
 u64 read_sanitised_ftr_reg(u32 id);
@@ -735,13 +728,12 @@ static inline bool system_supports_mixed_endian(void)
 
 static __always_inline bool system_supports_fpsimd(void)
 {
-	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
+	return alternative_has_cap_likely(ARM64_HAS_FPSIMD);
 }
 
 static inline bool system_uses_hw_pan(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PAN) &&
-		cpus_have_const_cap(ARM64_HAS_PAN);
+	return alternative_has_cap_unlikely(ARM64_HAS_PAN);
 }
 
 static inline bool system_uses_ttbr0_pan(void)
@@ -752,26 +744,22 @@ static inline bool system_uses_ttbr0_pan(void)
 
 static __always_inline bool system_supports_sve(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SVE) &&
-		cpus_have_const_cap(ARM64_SVE);
+	return alternative_has_cap_unlikely(ARM64_SVE);
 }
 
 static __always_inline bool system_supports_sme(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME);
+	return alternative_has_cap_unlikely(ARM64_SME);
 }
 
 static __always_inline bool system_supports_sme2(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME2);
+	return alternative_has_cap_unlikely(ARM64_SME2);
 }
 
 static __always_inline bool system_supports_fa64(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_SME) &&
-		cpus_have_const_cap(ARM64_SME_FA64);
+	return alternative_has_cap_unlikely(ARM64_SME_FA64);
 }
 
 static __always_inline bool system_supports_tpidr2(void)
@@ -781,20 +769,17 @@ static __always_inline bool system_supports_tpidr2(void)
 
 static __always_inline bool system_supports_cnp(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_CNP) &&
-		cpus_have_const_cap(ARM64_HAS_CNP);
+	return alternative_has_cap_unlikely(ARM64_HAS_CNP);
 }
 
 static inline bool system_supports_address_auth(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH);
+	return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH);
 }
 
 static inline bool system_supports_generic_auth(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
-		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
+	return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH);
 }
 
 static inline bool system_has_full_ptr_auth(void)
@@ -804,14 +789,12 @@ static inline bool system_has_full_ptr_auth(void)
 
 static __always_inline bool system_uses_irq_prio_masking(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
-	       cpus_have_const_cap(ARM64_HAS_GIC_PRIO_MASKING);
+	return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
 }
 
 static inline bool system_supports_mte(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_MTE) &&
-		cpus_have_const_cap(ARM64_MTE);
+	return alternative_has_cap_unlikely(ARM64_MTE);
 }
 
 static inline bool system_has_prio_mask_debugging(void)
@@ -822,13 +805,18 @@ static inline bool system_has_prio_mask_debugging(void)
 
 static inline bool system_supports_bti(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+	return cpus_have_final_cap(ARM64_BTI);
+}
+
+static inline bool system_supports_bti_kernel(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) &&
+		cpus_have_final_boot_cap(ARM64_BTI);
 }
 
 static inline bool system_supports_tlb_range(void)
 {
-	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
-		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+	return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE);
 }
 
 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 7c7493cb5..52f076afe 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -61,6 +61,7 @@
 #define ARM_CPU_IMP_HISI		0x48
 #define ARM_CPU_IMP_APPLE		0x61
 #define ARM_CPU_IMP_AMPERE		0xC0
+#define ARM_CPU_IMP_MICROSOFT		0x6D
 
 #define ARM_CPU_PART_AEM_V8		0xD0F
 #define ARM_CPU_PART_FOUNDATION		0xD00
@@ -135,6 +136,8 @@
 
 #define AMPERE_CPU_PART_AMPERE1		0xAC3
 
+#define MICROSOFT_CPU_PART_AZURE_COBALT_100	0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
 #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
 #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -193,6 +196,7 @@
 #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
 #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
 #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
+#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
 
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
diff --git a/arch/arm64/include/asm/crash_core.h b/arch/arm64/include/asm/crash_core.h
new file mode 100644
index 000000000..9f5c8d339
--- /dev/null
+++ b/arch/arm64/include/asm/crash_core.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ARM64_CRASH_CORE_H
+#define _ARM64_CRASH_CORE_H
+
+/* Current arm64 boot protocol requires 2MB alignment */
+#define CRASH_ALIGN                     SZ_2M
+
+#define CRASH_ADDR_LOW_MAX              arm64_dma_phys_limit
+#define CRASH_ADDR_HIGH_MAX             (PHYS_MASK + 1)
+#endif
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 8df46f186..7780d343e 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -32,6 +32,32 @@
 #define VFP_STATE_SIZE		((32 * 8) + 4)
 #endif
 
+static inline unsigned long cpacr_save_enable_kernel_sve(void)
+{
+	unsigned long old = read_sysreg(cpacr_el1);
+	unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN;
+
+	write_sysreg(old | set, cpacr_el1);
+	isb();
+	return old;
+}
+
+static inline unsigned long cpacr_save_enable_kernel_sme(void)
+{
+	unsigned long old = read_sysreg(cpacr_el1);
+	unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN;
+
+	write_sysreg(old | set, cpacr_el1);
+	isb();
+	return old;
+}
+
+static inline void cpacr_restore(unsigned long cpacr)
+{
+	write_sysreg(cpacr, cpacr_el1);
+	isb();
+}
+
 /*
  * When we defined the maximum SVE vector length we defined the ABI so
  * that the maximum vector length included all the reserved for future
@@ -123,12 +149,12 @@ extern void sme_save_state(void *state, int zt);
 extern void sme_load_state(void const *state, int zt);
 
 struct arm64_cpu_capabilities;
-extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
-extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused);
 
-extern u64 read_zcr_features(void);
 extern u64 read_smcr_features(void);
 
 /*
@@ -360,6 +386,7 @@ extern void sme_alloc(struct task_struct *task, bool flush);
 extern unsigned int sme_get_vl(void);
 extern int sme_set_current_vl(unsigned long arg);
 extern int sme_get_current_vl(void);
+extern void sme_suspend_exit(void);
 
 /*
  * Return how many bytes of memory are required to store the full SME
@@ -395,6 +422,7 @@ static inline int sme_max_vl(void) { return 0; }
 static inline int sme_max_virtualisable_vl(void) { return 0; }
 static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
 static inline int sme_get_current_vl(void) { return -EINVAL; }
+static inline void sme_suspend_exit(void) { }
 
 static inline size_t sme_state_size(struct task_struct const *task)
 {
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 521267478..cd71e09ea 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -139,6 +139,9 @@
 #define KERNEL_HWCAP_SME_F16F16		__khwcap2_feature(SME_F16F16)
 #define KERNEL_HWCAP_MOPS		__khwcap2_feature(MOPS)
 #define KERNEL_HWCAP_HBC		__khwcap2_feature(HBC)
+#define KERNEL_HWCAP_SVE_B16B16		__khwcap2_feature(SVE_B16B16)
+#define KERNEL_HWCAP_LRCPC3		__khwcap2_feature(LRCPC3)
+#define KERNEL_HWCAP_LSE128		__khwcap2_feature(LSE128)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index fac08e18b..50ce8b697 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -6,6 +6,9 @@
 
 #include <asm-generic/irq.h>
 
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu);
+#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
+
 struct pt_regs;
 
 int set_handle_irq(void (*handle_irq)(struct pt_regs *));
diff --git a/arch/arm64/include/asm/irq_work.h b/arch/arm64/include/asm/irq_work.h
index 81bbfa3a0..a1020285e 100644
--- a/arch/arm64/include/asm/irq_work.h
+++ b/arch/arm64/include/asm/irq_work.h
@@ -2,8 +2,6 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-extern void arch_irq_work_raise(void);
-
 static inline bool arch_irq_work_has_interrupt(void)
 {
 	return true;
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 1f31ec146..0a7186a93 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -21,12 +21,6 @@
  * exceptions should be unmasked.
  */
 
-static __always_inline bool __irqflags_uses_pmr(void)
-{
-	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
-	       alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING);
-}
-
 static __always_inline void __daif_local_irq_enable(void)
 {
 	barrier();
@@ -49,7 +43,7 @@ static __always_inline void __pmr_local_irq_enable(void)
 
 static inline void arch_local_irq_enable(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_enable();
 	} else {
 		__daif_local_irq_enable();
@@ -77,7 +71,7 @@ static __always_inline void __pmr_local_irq_disable(void)
 
 static inline void arch_local_irq_disable(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_disable();
 	} else {
 		__daif_local_irq_disable();
@@ -99,7 +93,7 @@ static __always_inline unsigned long __pmr_local_save_flags(void)
  */
 static inline unsigned long arch_local_save_flags(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_save_flags();
 	} else {
 		return __daif_local_save_flags();
@@ -118,7 +112,7 @@ static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags)
 
 static inline bool arch_irqs_disabled_flags(unsigned long flags)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled_flags(flags);
 	} else {
 		return __daif_irqs_disabled_flags(flags);
@@ -137,7 +131,7 @@ static __always_inline bool __pmr_irqs_disabled(void)
 
 static inline bool arch_irqs_disabled(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_irqs_disabled();
 	} else {
 		return __daif_irqs_disabled();
@@ -169,7 +163,7 @@ static __always_inline unsigned long __pmr_local_irq_save(void)
 
 static inline unsigned long arch_local_irq_save(void)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		return __pmr_local_irq_save();
 	} else {
 		return __daif_local_irq_save();
@@ -196,7 +190,7 @@ static __always_inline void __pmr_local_irq_restore(unsigned long flags)
  */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	if (__irqflags_uses_pmr()) {
+	if (system_uses_irq_prio_masking()) {
 		__pmr_local_irq_restore(flags);
 	} else {
 		__daif_local_irq_restore(flags);
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 48ddc0f45..6aafbb789 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop					\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
@@ -35,7 +35,7 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
 		 "	.pushsection	__jump_table, \"aw\"	\n\t"
 		 "	.align		3			\n\t"
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 05cd82eec..be7a3680d 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -37,8 +37,6 @@ struct kprobe_ctlblk {
 
 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);
 void __kretprobe_trampoline(void);
 void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 1095c6647..b85f46a73 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -102,7 +102,9 @@
 #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
-#define HCRX_GUEST_FLAGS (HCRX_EL2_SMPME | HCRX_EL2_TCR2En)
+#define HCRX_GUEST_FLAGS \
+	(HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \
+	 (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0))
 #define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En)
 
 /* TCR_EL2 Registers bits */
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 3d6725ff0..78a550537 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -54,6 +54,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu);
 int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2);
 int kvm_inject_nested_irq(struct kvm_vcpu *vcpu);
 
+static inline bool vcpu_has_feature(const struct kvm_vcpu *vcpu, int feature)
+{
+	return test_bit(feature, vcpu->kvm->arch.vcpu_features);
+}
+
 #if defined(__KVM_VHE_HYPERVISOR__) || defined(__KVM_NVHE_HYPERVISOR__)
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
@@ -62,7 +67,7 @@ static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 #else
 static __always_inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu)
 {
-	return test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features);
+	return vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT);
 }
 #endif
 
@@ -71,14 +76,14 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 	vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS;
 	if (has_vhe() || has_hvhe())
 		vcpu->arch.hcr_el2 |= HCR_E2H;
-	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN)) {
+	if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) {
 		/* route synchronous external abort exceptions to EL2 */
 		vcpu->arch.hcr_el2 |= HCR_TEA;
 		/* trap error record accesses */
 		vcpu->arch.hcr_el2 |= HCR_TERR;
 	}
 
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB)) {
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) {
 		vcpu->arch.hcr_el2 |= HCR_FWB;
 	} else {
 		/*
@@ -465,7 +470,7 @@ static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 
 static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 {
-	return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
+	return __vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
 }
 
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
@@ -565,12 +570,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)
 
-
-static inline bool vcpu_has_feature(struct kvm_vcpu *vcpu, int feature)
-{
-	return test_bit(feature, vcpu->arch.features);
-}
-
 static __always_inline void kvm_write_cptr_el2(u64 val)
 {
 	if (has_vhe() || has_hvhe())
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index af06ccb7e..824f29f04 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -78,7 +78,7 @@ extern unsigned int __ro_after_init kvm_sve_max_vl;
 int __init kvm_arm_init_sve(void);
 
 u32 __attribute_const__ kvm_target_cpu(void);
-int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
+void kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 struct kvm_hyp_memcache {
@@ -158,6 +158,16 @@ struct kvm_s2_mmu {
 	phys_addr_t	pgd_phys;
 	struct kvm_pgtable *pgt;
 
+	/*
+	 * VTCR value used on the host. For a non-NV guest (or a NV
+	 * guest that runs in a context where its own S2 doesn't
+	 * apply), its T0SZ value reflects that of the IPA size.
+	 *
+	 * For a shadow S2 MMU, T0SZ reflects the PARange exposed to
+	 * the guest.
+	 */
+	u64	vtcr;
+
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
@@ -202,12 +212,34 @@ struct kvm_protected_vm {
 	struct kvm_hyp_memcache teardown_mc;
 };
 
+struct kvm_mpidr_data {
+	u64			mpidr_mask;
+	DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx);
+};
+
+static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr)
+{
+	unsigned long mask = data->mpidr_mask;
+	u64 aff = mpidr & MPIDR_HWID_BITMASK;
+	int nbits, bit, bit_idx = 0;
+	u16 index = 0;
+
+	/*
+	 * If this looks like RISC-V's BEXT or x86's PEXT
+	 * instructions, it isn't by accident.
+	 */
+	nbits = fls(mask);
+	for_each_set_bit(bit, &mask, nbits) {
+		index |= (aff & BIT(bit)) >> (bit - bit_idx);
+		bit_idx++;
+	}
+
+	return index;
+}
+
 struct kvm_arch {
 	struct kvm_s2_mmu mmu;
 
-	/* VTCR_EL2 value for this VM */
-	u64    vtcr;
-
 	/* Interrupt controller */
 	struct vgic_dist	vgic;
 
@@ -239,15 +271,16 @@ struct kvm_arch {
 #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET			5
 	/* Timer PPIs made immutable */
 #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE		6
-	/* SMCCC filter initialized for the VM */
-#define KVM_ARCH_FLAG_SMCCC_FILTER_CONFIGURED		7
 	/* Initial ID reg values loaded */
-#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		8
+#define KVM_ARCH_FLAG_ID_REGS_INITIALIZED		7
 	unsigned long flags;
 
 	/* VM-wide vCPU feature set */
 	DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES);
 
+	/* MPIDR to vcpu index mapping, optional */
+	struct kvm_mpidr_data *mpidr_data;
+
 	/*
 	 * VM-wide PMU filter, implemented as a bitmap and big enough for
 	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
@@ -257,6 +290,9 @@ struct kvm_arch {
 
 	cpumask_var_t supported_cpus;
 
+	/* PMCR_EL0.N value for the guest */
+	u8 pmcr_n;
+
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
 	struct maple_tree smccc_filter;
@@ -574,9 +610,6 @@ struct kvm_vcpu_arch {
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
-	/* feature flags */
-	DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES);
-
 	/* Virtual SError ESR to restore when HCR_EL2.VSE is set */
 	u64 vsesr_el2;
 
@@ -1025,7 +1058,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
@@ -1052,7 +1085,7 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 
 static inline bool kvm_system_needs_idmapped_vectors(void)
 {
-	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
+	return cpus_have_final_cap(ARM64_SPECTRE_V3A);
 }
 
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
@@ -1078,6 +1111,8 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 			       struct kvm_arm_copy_mte_tags *copy_tags);
 int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm,
 				    struct kvm_arm_counter_offset *offset);
+int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
+					struct reg_mask_range *range);
 
 /* Guest/host FPSIMD coordination helpers */
 int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
@@ -1109,8 +1144,8 @@ static inline bool kvm_set_pmuserenr(u64 val)
 }
 #endif
 
-void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu);
-void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu);
+void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu);
 
 int __init kvm_set_ipa_limit(void);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 66efd67ea..145ce73fc 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -93,6 +93,8 @@ void __timer_disable_traps(struct kvm_vcpu *vcpu);
 void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt);
 #else
+void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu);
+void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu);
 void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt);
 void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt);
@@ -111,11 +113,6 @@ void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
 void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
 void __sve_restore_state(void *sve_pffr, u32 *fpsr);
 
-#ifndef __KVM_NVHE_HYPERVISOR__
-void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
-void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
-#endif
-
 u64 __guest_enter(struct kvm_vcpu *vcpu);
 
 bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 96a80e8f6..49e0d4b36 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -150,9 +150,9 @@ static __always_inline unsigned long __kern_hyp_va(unsigned long v)
  */
 #define KVM_PHYS_SHIFT	(40)
 
-#define kvm_phys_shift(kvm)		VTCR_EL2_IPA(kvm->arch.vtcr)
-#define kvm_phys_size(kvm)		(_AC(1, ULL) << kvm_phys_shift(kvm))
-#define kvm_phys_mask(kvm)		(kvm_phys_size(kvm) - _AC(1, ULL))
+#define kvm_phys_shift(mmu)		VTCR_EL2_IPA((mmu)->vtcr)
+#define kvm_phys_size(mmu)		(_AC(1, ULL) << kvm_phys_shift(mmu))
+#define kvm_phys_mask(mmu)		(kvm_phys_size(mmu) - _AC(1, ULL))
 
 #include <asm/kvm_pgtable.h>
 #include <asm/stage2_pgtable.h>
@@ -218,22 +218,47 @@ static inline void __clean_dcache_guest_page(void *va, size_t size)
 	 * faulting in pages. Furthermore, FWB implies IDC, so cleaning to
 	 * PoU is not required either in this case.
 	 */
-	if (cpus_have_const_cap(ARM64_HAS_STAGE2_FWB))
+	if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
 		return;
 
 	kvm_flush_dcache_to_poc(va, size);
 }
 
+static inline size_t __invalidate_icache_max_range(void)
+{
+	u8 iminline;
+	u64 ctr;
+
+	asm volatile(ALTERNATIVE_CB("movz %0, #0\n"
+				    "movk %0, #0, lsl #16\n"
+				    "movk %0, #0, lsl #32\n"
+				    "movk %0, #0, lsl #48\n",
+				    ARM64_ALWAYS_SYSTEM,
+				    kvm_compute_final_ctr_el0)
+		     : "=r" (ctr));
+
+	iminline = SYS_FIELD_GET(CTR_EL0, IminLine, ctr) + 2;
+	return MAX_DVM_OPS << iminline;
+}
+
 static inline void __invalidate_icache_guest_page(void *va, size_t size)
 {
-	if (icache_is_aliasing()) {
-		/* any kind of VIPT cache */
+	/*
+	 * VPIPT I-cache maintenance must be done from EL2. See comment in the
+	 * nVHE flavor of __kvm_tlb_flush_vmid_ipa().
+	 */
+	if (icache_is_vpipt() && read_sysreg(CurrentEL) != CurrentEL_EL2)
+		return;
+
+	/*
+	 * Blow the whole I-cache if it is aliasing (i.e. VIPT) or the
+	 * invalidation range exceeds our arbitrary limit on invadations by
+	 * cache line.
+	 */
+	if (icache_is_aliasing() || size > __invalidate_icache_max_range())
 		icache_inval_all_pou();
-	} else if (read_sysreg(CurrentEL) != CurrentEL_EL1 ||
-		   !icache_is_vpipt()) {
-		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
+	else
 		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
-	}
 }
 
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
@@ -299,7 +324,7 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
 static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
 					  struct kvm_arch *arch)
 {
-	write_sysreg(arch->vtcr, vtcr_el2);
+	write_sysreg(mmu->vtcr, vtcr_el2);
 	write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
 
 	/*
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index fa23cc9c2..6cec8e9c6 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -2,13 +2,14 @@
 #ifndef __ARM64_KVM_NESTED_H
 #define __ARM64_KVM_NESTED_H
 
+#include <asm/kvm_emulate.h>
 #include <linux/kvm_host.h>
 
 static inline bool vcpu_has_nv(const struct kvm_vcpu *vcpu)
 {
 	return (!__is_defined(__KVM_NVHE_HYPERVISOR__) &&
 		cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) &&
-		test_bit(KVM_ARM_VCPU_HAS_EL2, vcpu->arch.features));
+		vcpu_has_feature(vcpu, KVM_ARM_VCPU_HAS_EL2));
 }
 
 extern bool __check_nv_sr_forward(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h
index cbbcdc35c..3129a5819 100644
--- a/arch/arm64/include/asm/lse.h
+++ b/arch/arm64/include/asm/lse.h
@@ -16,14 +16,9 @@
 #include <asm/atomic_lse.h>
 #include <asm/cpucaps.h>
 
-static __always_inline bool system_uses_lse_atomics(void)
-{
-	return alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS);
-}
-
 #define __lse_ll_sc_body(op, ...)					\
 ({									\
-	system_uses_lse_atomics() ?					\
+	alternative_has_cap_likely(ARM64_HAS_LSE_ATOMICS) ?		\
 		__lse_##op(__VA_ARGS__) :				\
 		__ll_sc_##op(__VA_ARGS__);				\
 })
@@ -34,8 +29,6 @@ static __always_inline bool system_uses_lse_atomics(void)
 
 #else	/* CONFIG_ARM64_LSE_ATOMICS */
 
-static inline bool system_uses_lse_atomics(void) { return false; }
-
 #define __lse_ll_sc_body(op, ...)		__ll_sc_##op(__VA_ARGS__)
 
 #define ARM64_LSE_ATOMIC_INSN(llsc, lse)	llsc
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 94b68850c..2fcf51231 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -57,7 +57,7 @@ typedef struct {
 
 static inline bool arm64_kernel_unmapped_at_el0(void)
 {
-	return cpus_have_const_cap(ARM64_UNMAP_KERNEL_AT_EL0);
+	return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0);
 }
 
 extern void arm64_memblock_init(void);
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index a6fb32542..9ce420050 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -152,7 +152,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
  * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
  * avoiding the possibility of conflicting TLB entries being allocated.
  */
-static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp)
 {
 	typedef void (ttbr_replace_func)(phys_addr_t);
 	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
@@ -162,17 +162,8 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
 	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
 
-	if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) {
-		/*
-		 * cpu_replace_ttbr1() is used when there's a boot CPU
-		 * up (i.e. cpufeature framework is not up yet) and
-		 * latter only when we enable CNP via cpufeature's
-		 * enable() callback.
-		 * Also we rely on the system_cpucaps bit being set before
-		 * calling the enable() function.
-		 */
+	if (cnp)
 		ttbr1 |= TTBR_CNP_BIT;
-	}
 
 	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
 
@@ -189,6 +180,21 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
 	cpu_uninstall_idmap();
 }
 
+static inline void cpu_enable_swapper_cnp(void)
+{
+	__cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true);
+}
+
+static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
+{
+	/*
+	 * Only for early TTBR1 replacement before cpucaps are finalized and
+	 * before we've decided whether to use CNP.
+	 */
+	WARN_ON(system_capabilities_finalized());
+	__cpu_replace_ttbr1(pgdp, idmap, false);
+}
+
 /*
  * It would be nice to return ASIDs back to the allocator, but unfortunately
  * that introduces a race with a generation rollover where we could erroneously
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index bfa6638b4..79550b22b 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -44,8 +44,7 @@ struct plt_entry {
 
 static inline bool is_forbidden_offset_for_adrp(void *place)
 {
-	return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) &&
-	       cpus_have_const_cap(ARM64_WORKAROUND_843419) &&
+	return cpus_have_final_cap(ARM64_WORKAROUND_843419) &&
 	       ((u64)place & 0xfff) >= 0xff8;
 }
 
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 4cedbaa16..91fbd5c8a 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -90,7 +90,7 @@ static inline bool try_page_mte_tagging(struct page *page)
 }
 
 void mte_zero_clear_page_tags(void *addr);
-void mte_sync_tags(pte_t pte);
+void mte_sync_tags(pte_t pte, unsigned int nr_pages);
 void mte_copy_page_tags(void *kto, const void *kfrom);
 void mte_thread_init_user(void);
 void mte_thread_switch(struct task_struct *next);
@@ -122,7 +122,7 @@ static inline bool try_page_mte_tagging(struct page *page)
 static inline void mte_zero_clear_page_tags(void *addr)
 {
 }
-static inline void mte_sync_tags(pte_t pte)
+static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages)
 {
 }
 static inline void mte_copy_page_tags(void *kto, const void *kfrom)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index eed814b00..e9624f632 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -75,11 +75,7 @@ extern bool arm64_use_ng_mappings;
  * If we have userspace only BTI we don't want to mark kernel pages
  * guarded even if the system does support BTI.
  */
-#ifdef CONFIG_ARM64_BTI_KERNEL
-#define PTE_MAYBE_GP		(system_supports_bti() ? PTE_GP : 0)
-#else
-#define PTE_MAYBE_GP		0
-#endif
+#define PTE_MAYBE_GP		(system_supports_bti_kernel() ? PTE_GP : 0)
 
 #define PAGE_KERNEL		__pgprot(_PAGE_KERNEL)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_KERNEL_RO)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 07bdf5dd8..79ce70fbb 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -325,8 +325,7 @@ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep,
 		     __func__, pte_val(old_pte), pte_val(pte));
 }
 
-static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, pte_t pte)
+static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
 {
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
@@ -339,24 +338,22 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (system_supports_mte() && pte_access_permitted(pte, false) &&
 	    !pte_special(pte) && pte_tagged(pte))
-		mte_sync_tags(pte);
-
-	__check_safe_pte_update(mm, ptep, pte);
-
-	set_pte(ptep, pte);
+		mte_sync_tags(pte, nr_pages);
 }
 
-static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void set_ptes(struct mm_struct *mm,
+			    unsigned long __always_unused addr,
+			    pte_t *ptep, pte_t pte, unsigned int nr)
 {
 	page_table_check_ptes_set(mm, ptep, pte, nr);
+	__sync_cache_and_tags(pte, nr);
 
 	for (;;) {
-		__set_pte_at(mm, addr, ptep, pte);
+		__check_safe_pte_update(mm, ptep, pte);
+		set_pte(ptep, pte);
 		if (--nr == 0)
 			break;
 		ptep++;
-		addr += PAGE_SIZE;
 		pte_val(pte) += PAGE_SIZE;
 	}
 }
@@ -531,18 +528,29 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
+static inline void __set_pte_at(struct mm_struct *mm,
+				unsigned long __always_unused addr,
+				pte_t *ptep, pte_t pte, unsigned int nr)
+{
+	__sync_cache_and_tags(pte, nr);
+	__check_safe_pte_update(mm, ptep, pte);
+	set_pte(ptep, pte);
+}
+
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
 {
 	page_table_check_pmd_set(mm, pmdp, pmd);
-	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
+						PMD_SIZE >> PAGE_SHIFT);
 }
 
 static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
 			      pud_t *pudp, pud_t pud)
 {
 	page_table_check_pud_set(mm, pudp, pud);
-	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
+						PUD_SIZE >> PAGE_SHIFT);
 }
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 9b31e6d0d..efb13112b 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -89,9 +89,9 @@ extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 #ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
+extern void arch_send_wakeup_ipi(unsigned int cpu);
 #else
-static inline void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
+static inline void arch_send_wakeup_ipi(unsigned int cpu)
 {
 	BUILD_BUG();
 }
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index 9cc501450..06c357d83 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -73,7 +73,7 @@ static __always_inline void arm64_apply_bp_hardening(void)
 {
 	struct bp_hardening_data *d;
 
-	if (!cpus_have_const_cap(ARM64_SPECTRE_V2))
+	if (!alternative_has_cap_unlikely(ARM64_SPECTRE_V2))
 		return;
 
 	d = this_cpu_ptr(&bp_hardening_data);
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index c8dca8ae3..23d27623e 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -21,13 +21,13 @@
  * (IPA_SHIFT - 4).
  */
 #define stage2_pgtable_levels(ipa)	ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
-#define kvm_stage2_levels(kvm)		VTCR_EL2_LVLS(kvm->arch.vtcr)
+#define kvm_stage2_levels(mmu)		VTCR_EL2_LVLS((mmu)->vtcr)
 
 /*
  * kvm_mmmu_cache_min_pages() is the number of pages required to install
  * a stage-2 translation. We pre-allocate the entry level page table at
  * the VM creation.
  */
-#define kvm_mmu_cache_min_pages(kvm)	(kvm_stage2_levels(kvm) - 1)
+#define kvm_mmu_cache_min_pages(mmu)	(kvm_stage2_levels(mmu) - 1)
 
 #endif	/* __ARM64_S2_PGTABLE_H_ */
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
index 7a0e7b59b..abb57bc54 100644
--- a/arch/arm64/include/asm/syscall_wrapper.h
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -51,7 +51,6 @@
 	ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO);			\
 	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
-	asmlinkage long __arm64_sys##name(const struct pt_regs *regs);		\
 	asmlinkage long __arm64_sys##name(const struct pt_regs *regs)		\
 	{									\
 		return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 38296579a..5e65f51c1 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -270,6 +270,8 @@
 /* ETM */
 #define SYS_TRCOSLAR			sys_reg(2, 1, 1, 0, 4)
 
+#define SYS_BRBCR_EL2			sys_reg(2, 4, 9, 0, 0)
+
 #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)
@@ -484,6 +486,7 @@
 
 #define SYS_SCTLR_EL2			sys_reg(3, 4, 1, 0, 0)
 #define SYS_ACTLR_EL2			sys_reg(3, 4, 1, 0, 1)
+#define SYS_SCTLR2_EL2			sys_reg(3, 4, 1, 0, 3)
 #define SYS_HCR_EL2			sys_reg(3, 4, 1, 1, 0)
 #define SYS_MDCR_EL2			sys_reg(3, 4, 1, 1, 1)
 #define SYS_CPTR_EL2			sys_reg(3, 4, 1, 1, 2)
@@ -497,10 +500,15 @@
 #define SYS_VTCR_EL2			sys_reg(3, 4, 2, 1, 2)
 
 #define SYS_TRFCR_EL2			sys_reg(3, 4, 1, 2, 1)
+#define SYS_VNCR_EL2			sys_reg(3, 4, 2, 2, 0)
 #define SYS_HAFGRTR_EL2			sys_reg(3, 4, 3, 1, 6)
 #define SYS_SPSR_EL2			sys_reg(3, 4, 4, 0, 0)
 #define SYS_ELR_EL2			sys_reg(3, 4, 4, 0, 1)
 #define SYS_SP_EL1			sys_reg(3, 4, 4, 1, 0)
+#define SYS_SPSR_irq			sys_reg(3, 4, 4, 3, 0)
+#define SYS_SPSR_abt			sys_reg(3, 4, 4, 3, 1)
+#define SYS_SPSR_und			sys_reg(3, 4, 4, 3, 2)
+#define SYS_SPSR_fiq			sys_reg(3, 4, 4, 3, 3)
 #define SYS_IFSR32_EL2			sys_reg(3, 4, 5, 0, 1)
 #define SYS_AFSR0_EL2			sys_reg(3, 4, 5, 1, 0)
 #define SYS_AFSR1_EL2			sys_reg(3, 4, 5, 1, 1)
@@ -514,6 +522,18 @@
 
 #define SYS_MAIR_EL2			sys_reg(3, 4, 10, 2, 0)
 #define SYS_AMAIR_EL2			sys_reg(3, 4, 10, 3, 0)
+#define SYS_MPAMHCR_EL2			sys_reg(3, 4, 10, 4, 0)
+#define SYS_MPAMVPMV_EL2		sys_reg(3, 4, 10, 4, 1)
+#define SYS_MPAM2_EL2			sys_reg(3, 4, 10, 5, 0)
+#define __SYS__MPAMVPMx_EL2(x)		sys_reg(3, 4, 10, 6, x)
+#define SYS_MPAMVPM0_EL2		__SYS__MPAMVPMx_EL2(0)
+#define SYS_MPAMVPM1_EL2		__SYS__MPAMVPMx_EL2(1)
+#define SYS_MPAMVPM2_EL2		__SYS__MPAMVPMx_EL2(2)
+#define SYS_MPAMVPM3_EL2		__SYS__MPAMVPMx_EL2(3)
+#define SYS_MPAMVPM4_EL2		__SYS__MPAMVPMx_EL2(4)
+#define SYS_MPAMVPM5_EL2		__SYS__MPAMVPMx_EL2(5)
+#define SYS_MPAMVPM6_EL2		__SYS__MPAMVPMx_EL2(6)
+#define SYS_MPAMVPM7_EL2		__SYS__MPAMVPMx_EL2(7)
 
 #define SYS_VBAR_EL2			sys_reg(3, 4, 12, 0, 0)
 #define SYS_RVBAR_EL2			sys_reg(3, 4, 12, 0, 1)
@@ -562,24 +582,49 @@
 
 #define SYS_CONTEXTIDR_EL2		sys_reg(3, 4, 13, 0, 1)
 #define SYS_TPIDR_EL2			sys_reg(3, 4, 13, 0, 2)
+#define SYS_SCXTNUM_EL2			sys_reg(3, 4, 13, 0, 7)
+
+#define __AMEV_op2(m)			(m & 0x7)
+#define __AMEV_CRm(n, m)		(n | ((m & 0x8) >> 3))
+#define __SYS__AMEVCNTVOFF0n_EL2(m)	sys_reg(3, 4, 13, __AMEV_CRm(0x8, m), __AMEV_op2(m))
+#define SYS_AMEVCNTVOFF0n_EL2(m)	__SYS__AMEVCNTVOFF0n_EL2(m)
+#define __SYS__AMEVCNTVOFF1n_EL2(m)	sys_reg(3, 4, 13, __AMEV_CRm(0xA, m), __AMEV_op2(m))
+#define SYS_AMEVCNTVOFF1n_EL2(m)	__SYS__AMEVCNTVOFF1n_EL2(m)
 
 #define SYS_CNTVOFF_EL2			sys_reg(3, 4, 14, 0, 3)
 #define SYS_CNTHCTL_EL2			sys_reg(3, 4, 14, 1, 0)
+#define SYS_CNTHP_TVAL_EL2		sys_reg(3, 4, 14, 2, 0)
+#define SYS_CNTHP_CTL_EL2		sys_reg(3, 4, 14, 2, 1)
+#define SYS_CNTHP_CVAL_EL2		sys_reg(3, 4, 14, 2, 2)
+#define SYS_CNTHV_TVAL_EL2		sys_reg(3, 4, 14, 3, 0)
+#define SYS_CNTHV_CTL_EL2		sys_reg(3, 4, 14, 3, 1)
+#define SYS_CNTHV_CVAL_EL2		sys_reg(3, 4, 14, 3, 2)
 
 /* VHE encodings for architectural EL0/1 system registers */
+#define SYS_BRBCR_EL12			sys_reg(2, 5, 9, 0, 0)
 #define SYS_SCTLR_EL12			sys_reg(3, 5, 1, 0, 0)
+#define SYS_CPACR_EL12			sys_reg(3, 5, 1, 0, 2)
+#define SYS_SCTLR2_EL12			sys_reg(3, 5, 1, 0, 3)
+#define SYS_ZCR_EL12			sys_reg(3, 5, 1, 2, 0)
+#define SYS_TRFCR_EL12			sys_reg(3, 5, 1, 2, 1)
+#define SYS_SMCR_EL12			sys_reg(3, 5, 1, 2, 6)
 #define SYS_TTBR0_EL12			sys_reg(3, 5, 2, 0, 0)
 #define SYS_TTBR1_EL12			sys_reg(3, 5, 2, 0, 1)
 #define SYS_TCR_EL12			sys_reg(3, 5, 2, 0, 2)
+#define SYS_TCR2_EL12			sys_reg(3, 5, 2, 0, 3)
 #define SYS_SPSR_EL12			sys_reg(3, 5, 4, 0, 0)
 #define SYS_ELR_EL12			sys_reg(3, 5, 4, 0, 1)
 #define SYS_AFSR0_EL12			sys_reg(3, 5, 5, 1, 0)
 #define SYS_AFSR1_EL12			sys_reg(3, 5, 5, 1, 1)
 #define SYS_ESR_EL12			sys_reg(3, 5, 5, 2, 0)
 #define SYS_TFSR_EL12			sys_reg(3, 5, 5, 6, 0)
+#define SYS_FAR_EL12			sys_reg(3, 5, 6, 0, 0)
+#define SYS_PMSCR_EL12			sys_reg(3, 5, 9, 9, 0)
 #define SYS_MAIR_EL12			sys_reg(3, 5, 10, 2, 0)
 #define SYS_AMAIR_EL12			sys_reg(3, 5, 10, 3, 0)
 #define SYS_VBAR_EL12			sys_reg(3, 5, 12, 0, 0)
+#define SYS_CONTEXTIDR_EL12		sys_reg(3, 5, 13, 0, 1)
+#define SYS_SCXTNUM_EL12		sys_reg(3, 5, 13, 0, 7)
 #define SYS_CNTKCTL_EL12		sys_reg(3, 5, 14, 1, 0)
 #define SYS_CNTP_TVAL_EL02		sys_reg(3, 5, 14, 2, 0)
 #define SYS_CNTP_CTL_EL02		sys_reg(3, 5, 14, 2, 1)
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 2c29239d0..846c56368 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -96,7 +96,10 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 				  unsigned long addr)
 {
-	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pudp));
+	struct ptdesc *ptdesc = virt_to_ptdesc(pudp);
+
+	pagetable_pud_dtor(ptdesc);
+	tlb_remove_ptdesc(tlb, ptdesc);
 }
 #endif
 
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b149cf9f9..bb2c2833a 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -105,7 +105,7 @@ static inline unsigned long get_trans_granule(void)
 #define __tlbi_level(op, addr, level) do {				\
 	u64 arg = addr;							\
 									\
-	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
+	if (alternative_has_cap_unlikely(ARM64_HAS_ARMv8_4_TTL) &&	\
 	    level) {							\
 		u64 ttl = level & 3;					\
 		ttl |= get_trans_granule() << 2;			\
@@ -284,16 +284,15 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
 {
-#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
 	/*
 	 * TLB flush deferral is not required on systems which are affected by
 	 * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
 	 * will have two consecutive TLBI instructions with a dsb(ish) in between
 	 * defeating the purpose (i.e save overall 'dsb ish' cost).
 	 */
-	if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI)))
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
 		return false;
-#endif
+
 	return true;
 }
 
@@ -333,7 +332,7 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
  * This is meant to avoid soft lock-ups on large TLB flushing ranges and not
  * necessarily a performance improvement.
  */
-#define MAX_TLBI_OPS	PTRS_PER_PTE
+#define MAX_DVM_OPS	PTRS_PER_PTE
 
 /*
  * __flush_tlb_range_op - Perform TLBI operation upon a range
@@ -413,12 +412,12 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 
 	/*
 	 * When not uses TLB range ops, we can handle up to
-	 * (MAX_TLBI_OPS - 1) pages;
+	 * (MAX_DVM_OPS - 1) pages;
 	 * When uses TLB range ops, we can handle up to
 	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
 	 */
 	if ((!system_supports_tlb_range() &&
-	     (end - start) >= (MAX_TLBI_OPS * stride)) ||
+	     (end - start) >= (MAX_DVM_OPS * stride)) ||
 	    pages >= MAX_TLBI_RANGE_PAGES) {
 		flush_tlb_mm(vma->vm_mm);
 		return;
@@ -451,7 +450,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 {
 	unsigned long addr;
 
-	if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) {
+	if ((end - start) > (MAX_DVM_OPS * PAGE_SIZE)) {
 		flush_tlb_all();
 		return;
 	}
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index d66dfb3a7..eefe766d6 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -9,10 +9,9 @@
 
 #include <linux/list.h>
 #include <asm/esr.h>
+#include <asm/ptrace.h>
 #include <asm/sections.h>
 
-struct pt_regs;
-
 #ifdef CONFIG_ARMV8_DEPRECATED
 bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn);
 #else
@@ -101,4 +100,55 @@ static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr)
 
 bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr);
 void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr);
+
+static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned long esr)
+{
+	bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION;
+	bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A;
+	int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr);
+	int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr);
+	int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr);
+	unsigned long dst, src, size;
+
+	dst = regs->regs[dstreg];
+	src = regs->regs[srcreg];
+	size = regs->regs[sizereg];
+
+	/*
+	 * Put the registers back in the original format suitable for a
+	 * prologue instruction, using the generic return routine from the
+	 * Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH.
+	 */
+	if (esr & ESR_ELx_MOPS_ISS_MEM_INST) {
+		/* SET* instruction */
+		if (option_a ^ wrong_option) {
+			/* Format is from Option A; forward set */
+			regs->regs[dstreg] = dst + size;
+			regs->regs[sizereg] = -size;
+		}
+	} else {
+		/* CPY* instruction */
+		if (!(option_a ^ wrong_option)) {
+			/* Format is from Option B */
+			if (regs->pstate & PSR_N_BIT) {
+				/* Backward copy */
+				regs->regs[dstreg] = dst - size;
+				regs->regs[srcreg] = src - size;
+			}
+		} else {
+			/* Format is from Option A */
+			if (size & BIT(63)) {
+				/* Forward copy */
+				regs->regs[dstreg] = dst + size;
+				regs->regs[srcreg] = src + size;
+				regs->regs[sizereg] = -size;
+			}
+		}
+	}
+
+	if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE)
+		regs->pc -= 8;
+	else
+		regs->pc -= 4;
+}
 #endif
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index bd77253b6..531effca5 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		453
+#define __NR_compat_syscalls		457
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 78b68311e..9f7c1bf99 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -508,8 +508,8 @@ __SYSCALL(__NR_io_submit, compat_sys_io_submit)
 __SYSCALL(__NR_io_cancel, sys_io_cancel)
 #define __NR_exit_group 248
 __SYSCALL(__NR_exit_group, sys_exit_group)
-#define __NR_lookup_dcookie 249
-__SYSCALL(__NR_lookup_dcookie, compat_sys_lookup_dcookie)
+			/* 249 was lookup_dcookie */
+__SYSCALL(249, sys_ni_syscall)
 #define __NR_epoll_create 250
 __SYSCALL(__NR_epoll_create, sys_epoll_create)
 #define __NR_epoll_ctl 251
@@ -911,6 +911,14 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 __SYSCALL(__NR_cachestat, sys_cachestat)
 #define __NR_fchmodat2 452
 __SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_map_shadow_stack 453
+__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
index bc9a2145f..b815d8f2c 100644
--- a/arch/arm64/include/asm/vectors.h
+++ b/arch/arm64/include/asm/vectors.h
@@ -62,7 +62,7 @@ DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
 static inline const char *
 arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
 {
-	if (arm64_kernel_unmapped_at_el0())
+	if (cpus_have_cap(ARM64_UNMAP_KERNEL_AT_EL0))
 		return (char *)(TRAMP_VALIAS + SZ_2K * slot);
 
 	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 53026f45a..5023599fa 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -104,5 +104,8 @@
 #define HWCAP2_SME_F16F16	(1UL << 42)
 #define HWCAP2_MOPS		(1UL << 43)
 #define HWCAP2_HBC		(1UL << 44)
+#define HWCAP2_SVE_B16B16	(1UL << 45)
+#define HWCAP2_LRCPC3		(1UL << 46)
+#define HWCAP2_LSE128		(1UL << 47)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index f7ddd73a8..89d2fc872 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -505,6 +505,38 @@ struct kvm_smccc_filter {
 #define KVM_HYPERCALL_EXIT_SMC		(1U << 0)
 #define KVM_HYPERCALL_EXIT_16BIT	(1U << 1)
 
+/*
+ * Get feature ID registers userspace writable mask.
+ *
+ * From DDI0487J.a, D19.2.66 ("ID_AA64MMFR2_EL1, AArch64 Memory Model
+ * Feature Register 2"):
+ *
+ * "The Feature ID space is defined as the System register space in
+ * AArch64 with op0==3, op1=={0, 1, 3}, CRn==0, CRm=={0-7},
+ * op2=={0-7}."
+ *
+ * This covers all currently known R/O registers that indicate
+ * anything useful feature wise, including the ID registers.
+ *
+ * If we ever need to introduce a new range, it will be described as
+ * such in the range field.
+ */
+#define KVM_ARM_FEATURE_ID_RANGE_IDX(op0, op1, crn, crm, op2)		\
+	({								\
+		__u64 __op1 = (op1) & 3;				\
+		__op1 -= (__op1 == 3);					\
+		(__op1 << 6 | ((crm) & 7) << 3 | (op2));		\
+	})
+
+#define KVM_ARM_FEATURE_ID_RANGE	0
+#define KVM_ARM_FEATURE_ID_RANGE_SIZE	(3 * 8 * 8)
+
+struct reg_mask_range {
+	__u64 addr;		/* Pointer to mask array */
+	__u32 range;		/* Requested range */
+	__u32 reserved[13];
+};
+
 #endif
 
 #endif /* __ARM_KVM_H__ */
-- 
cgit v1.2.3