Merge branch 'for-next/spectre-bhb' into for-next/core

Merge in the latest Spectre mess to fix up conflicts with what was
already queued for 5.18 when the embargo finally lifted.

* for-next/spectre-bhb: (21 commits)
  arm64: Do not include __READ_ONCE() block in assembly files
  arm64: proton-pack: Include unprivileged eBPF status in Spectre v2 mitigation reporting
  arm64: Use the clearbhb instruction in mitigations
  KVM: arm64: Allow SMCCC_ARCH_WORKAROUND_3 to be discovered and migrated
  arm64: Mitigate spectre style branch history side channels
  arm64: proton-pack: Report Spectre-BHB vulnerabilities as part of Spectre-v2
  arm64: Add percpu vectors for EL1
  arm64: entry: Add macro for reading symbol addresses from the trampoline
  arm64: entry: Add vectors that have the bhb mitigation sequences
  arm64: entry: Add non-kpti __bp_harden_el1_vectors for mitigations
  arm64: entry: Allow the trampoline text to occupy multiple pages
  arm64: entry: Make the kpti trampoline's kpti sequence optional
  arm64: entry: Move trampoline macros out of ifdef'd section
  arm64: entry: Don't assume tramp_vectors is the start of the vectors
  arm64: entry: Allow tramp_alias to access symbols after the 4K boundary
  arm64: entry: Move the trampoline data page before the text page
  arm64: entry: Free up another register on kpti's tramp_exit path
  arm64: entry: Make the trampoline cleanup optional
  KVM: arm64: Allow indirect vectors to be used without SPECTRE_V3A
  arm64: spectre: Rename spectre_v4_patch_fw_mitigation_conduit
  ...

27 files changed, 827 insertions, 78 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1d1b5c0b157c..dbb6f66ac154 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1387,6 +1387,15 @@ config UNMAP_KERNEL_AT_EL0
 
 	  If unsure, say Y.
 
+config MITIGATE_SPECTRE_BRANCH_HISTORY
+	bool "Mitigate Spectre style attacks against branch history" if EXPERT
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  make use of branch history to influence future speculation.
+	  When taking an exception from user-space, a sequence of branches
+	  or a firmware call overwrites the branch history.
+
 config RODATA_FULL_DEFAULT_ENABLED
 	bool "Apply r/o permissions of VM areas also to their linear aliases"
 	default y
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 8df412178efb..8c5a61aeaf8e 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -109,6 +109,13 @@
 	.endm
 
 /*
+ * Clear Branch History instruction
+ */
+	.macro clearbhb
+	hint	#22
+	.endm
+
+/*
  * Speculation barrier
  */
 	.macro	sb
@@ -845,4 +852,50 @@ alternative_endif
 
 #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */
 
+	.macro __mitigate_spectre_bhb_loop      tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb  spectre_bhb_patch_loop_iter
+	mov	\tmp, #32		// Patched to correct the immediate
+alternative_cb_end
+.Lspectre_bhb_loop\@:
+	b	. + 4
+	subs	\tmp, \tmp, #1
+	b.ne	.Lspectre_bhb_loop\@
+	sb
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_loop	tmp
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb	spectre_bhb_patch_loop_mitigation_enable
+	b	.L_spectre_bhb_loop_done\@	// Patched to NOP
+alternative_cb_end
+	__mitigate_spectre_bhb_loop	\tmp
+.L_spectre_bhb_loop_done\@:
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	/* Save/restores x0-x3 to the stack */
+	.macro __mitigate_spectre_bhb_fw
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	stp	x0, x1, [sp, #-16]!
+	stp	x2, x3, [sp, #-16]!
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
+alternative_cb	smccc_patch_fw_mitigation_conduit
+	nop					// Patched to SMC/HVC #0
+alternative_cb_end
+	ldp	x2, x3, [sp], #16
+	ldp	x0, x1, [sp], #16
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
+
+	.macro mitigate_spectre_bhb_clear_insn
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+alternative_cb	spectre_bhb_patch_clearbhb
+	/* Patched to NOP when not supported */
+	clearbhb
+	isb
+alternative_cb_end
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	.endm
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 380238ae3321..c62e7e5e2f0c 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -640,6 +640,35 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
 }
 
+
+static inline bool supports_csv2p3(int scope)
+{
+	u64 pfr0;
+	u8 csv2_val;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
+	else
+		pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+	csv2_val = cpuid_feature_extract_unsigned_field(pfr0,
+							ID_AA64PFR0_CSV2_SHIFT);
+	return csv2_val == 3;
+}
+
+static inline bool supports_clearbhb(int scope)
+{
+	u64 isar2;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+	else
+		isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
+
+	return cpuid_feature_extract_unsigned_field(isar2,
+						    ID_AA64ISAR2_CLEARBHB_SHIFT);
+}
+
 const struct cpumask *system_32bit_el0_cpumask(void);
 DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 4596e7ca29a3..232b439cbaf3 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -73,10 +73,14 @@
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
 #define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 #define ARM_CPU_PART_CORTEX_A77		0xD0D
+#define ARM_CPU_PART_NEOVERSE_V1	0xD40
+#define ARM_CPU_PART_CORTEX_A78		0xD41
+#define ARM_CPU_PART_CORTEX_X1		0xD44
 #define ARM_CPU_PART_CORTEX_A510	0xD46
 #define ARM_CPU_PART_CORTEX_A710	0xD47
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
+#define ARM_CPU_PART_CORTEX_A78C	0xD4B
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -124,10 +128,14 @@
 #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_CORTEX_A77	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
+#define MIDR_NEOVERSE_V1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
+#define MIDR_CORTEX_A78	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_X1	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
 #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
 #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
+#define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
 #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/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 4335800201c9..daff882883f9 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -62,9 +62,11 @@ enum fixed_addresses {
 #endif /* CONFIG_ACPI_APEI_GHES */
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+	FIX_ENTRY_TRAMP_TEXT3,
+	FIX_ENTRY_TRAMP_TEXT2,
+	FIX_ENTRY_TRAMP_TEXT1,
 	FIX_ENTRY_TRAMP_DATA,
-	FIX_ENTRY_TRAMP_TEXT,
-#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT))
+#define TRAMP_VALIAS		(__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1))
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 	__end_of_permanent_fixed_addresses,
 
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 0b6b31307e68..1e5760d567ae 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_PSB  = 0x11 << 5,
 	AARCH64_INSN_HINT_TSB  = 0x12 << 5,
 	AARCH64_INSN_HINT_CSDB = 0x14 << 5,
+	AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5,
 
 	AARCH64_INSN_HINT_BTI   = 0x20 << 5,
 	AARCH64_INSN_HINT_BTIC  = 0x22 << 5,
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5bc01e62c08a..031e3a2537fc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -714,6 +714,11 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt)
 	ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr();
 }
 
+static inline bool kvm_system_needs_idmapped_vectors(void)
+{
+	return cpus_have_const_cap(ARM64_SPECTRE_V3A);
+}
+
 void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu);
 
 static inline void kvm_arch_hardware_unsetup(void) {}
diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h
index 1bce62fa908a..56f7b1d4d54b 100644
--- a/arch/arm64/include/asm/rwonce.h
+++ b/arch/arm64/include/asm/rwonce.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_RWONCE_H
 #define __ASM_RWONCE_H
 
-#ifdef CONFIG_LTO
+#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__)
 
 #include <linux/compiler_types.h>
 #include <asm/alternative-macros.h>
@@ -66,7 +66,7 @@
 })
 
 #endif	/* !BUILD_VDSO */
-#endif	/* CONFIG_LTO */
+#endif	/* CONFIG_LTO && !__ASSEMBLY__ */
 
 #include <asm-generic/rwonce.h>
 
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 152cb35bf9df..40971ac1303f 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];
 extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[];
 
+static inline size_t entry_tramp_text_size(void)
+{
+	return __entry_tramp_text_end - __entry_tramp_text_start;
+}
+
 #endif /* __ASM_SECTIONS_H */
diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h
index d476c06757c5..aa3d3607d5c8 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -94,5 +94,9 @@ void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
 
 enum mitigation_state arm64_get_meltdown_state(void);
 
+enum mitigation_state arm64_get_spectre_bhb_state(void);
+bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
+u8 spectre_bhb_loop_affected(int scope);
+void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 #endif	/* __ASSEMBLY__ */
 #endif	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 2023a0e6c6d6..c7ca3a105528 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -773,6 +773,7 @@
 #define ID_AA64ISAR1_GPI_IMP_DEF		0x1
 
 /* id_aa64isar2 */
+#define ID_AA64ISAR2_CLEARBHB_SHIFT	28
 #define ID_AA64ISAR2_APA3_SHIFT		12
 #define ID_AA64ISAR2_GPA3_SHIFT		8
 #define ID_AA64ISAR2_RPRES_SHIFT	4
@@ -916,6 +917,7 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ECBHB_SHIFT	60
 #define ID_AA64MMFR1_AFP_SHIFT		44
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
new file mode 100644
index 000000000000..f64613a96d53
--- /dev/null
+++ b/arch/arm64/include/asm/vectors.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2022 ARM Ltd.
+ */
+#ifndef __ASM_VECTORS_H
+#define __ASM_VECTORS_H
+
+#include <linux/bug.h>
+#include <linux/percpu.h>
+
+#include <asm/fixmap.h>
+
+extern char vectors[];
+extern char tramp_vectors[];
+extern char __bp_harden_el1_vectors[];
+
+/*
+ * Note: the order of this enum corresponds to two arrays in entry.S:
+ * tramp_vecs and __bp_harden_el1_vectors. By default the canonical
+ * 'full fat' vectors are used directly.
+ */
+enum arm64_bp_harden_el1_vectors {
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	/*
+	 * Perform the BHB loop mitigation, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_LOOP,
+
+	/*
+	 * Make the SMC call for firmware mitigation, before branching to the
+	 * canonical vectors.
+	 */
+	EL1_VECTOR_BHB_FW,
+
+	/*
+	 * Use the ClearBHB instruction, before branching to the canonical
+	 * vectors.
+	 */
+	EL1_VECTOR_BHB_CLEAR_INSN,
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+	/*
+	 * Remap the kernel before branching to the canonical vectors.
+	 */
+	EL1_VECTOR_KPTI,
+};
+
+#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+#define EL1_VECTOR_BHB_LOOP		-1
+#define EL1_VECTOR_BHB_FW		-1
+#define EL1_VECTOR_BHB_CLEAR_INSN	-1
+#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+
+/* The vectors to use on return from EL0. e.g. to remap the kernel */
+DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector);
+
+#ifndef CONFIG_UNMAP_KERNEL_AT_EL0
+#define TRAMP_VALIAS	0
+#endif
+
+static inline const char *
+arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot)
+{
+	if (arm64_kernel_unmapped_at_el0())
+		return (char *)TRAMP_VALIAS + SZ_2K * slot;
+
+	WARN_ON_ONCE(slot == EL1_VECTOR_KPTI);
+
+	return __bp_harden_el1_vectors + SZ_2K * slot;
+}
+
+#endif /* __ASM_VECTORS_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index b3edde68bc3e..323e251ed37b 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags {
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED	3
 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED     	(1U << 4)
 
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3	KVM_REG_ARM_FW_REG(3)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL		0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL		1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED	2
+
 /* SVE registers */
 #define KVM_REG_ARM64_SVE		(0x15 << KVM_REG_ARM_COPROC_SHIFT)
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6485d8e54cca..400a1c9cac90 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -517,6 +517,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.matches = has_spectre_v4,
 		.cpu_enable = spectre_v4_enable_mitigation,
 	},
+	{
+		.desc = "Spectre-BHB",
+		.capability = ARM64_SPECTRE_BHB,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = is_spectre_bhb_affected,
+		.cpu_enable = spectre_bhb_enable_mitigation,
+	},
 #ifdef CONFIG_ARM64_ERRATUM_1418040
 	{
 		.desc = "ARM erratum 1418040",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 32aa0eb3ed68..d72c4b4d389c 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -73,6 +73,8 @@
 #include <linux/mm.h>
 #include <linux/cpu.h>
 #include <linux/kasan.h>
+#include <linux/percpu.h>
+
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -85,6 +87,7 @@
 #include <asm/smp.h>
 #include <asm/sysreg.h>
 #include <asm/traps.h>
+#include <asm/vectors.h>
 #include <asm/virt.h>
 
 /* Kernel representation of AT_HWCAP and AT_HWCAP2 */
@@ -110,6 +113,8 @@ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 bool arm64_use_ng_mappings = false;
 EXPORT_SYMBOL(arm64_use_ng_mappings);
 
+DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors;
+
 /*
  * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs
  * support it?
@@ -226,6 +231,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_CLEARBHB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_APA3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
@@ -1599,6 +1605,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	int cpu = smp_processor_id();
 
+	if (__this_cpu_read(this_cpu_vector) == vectors) {
+		const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI);
+
+		__this_cpu_write(this_cpu_vector, v);
+	}
+
 	/*
 	 * We don't need to rewrite the page-tables if either we've done
 	 * it already or we have KASLR enabled and therefore have not
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a3ee79bcd5cb..ede028dee81b 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -37,18 +37,21 @@
 
 	.macro kernel_ventry, el:req, ht:req, regsize:req, label:req
 	.align 7
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+.Lventry_start\@:
 	.if	\el == 0
-alternative_if ARM64_UNMAP_KERNEL_AT_EL0
+	/*
+	 * This must be the first instruction of the EL0 vector entries. It is
+	 * skipped by the trampoline vectors, to trigger the cleanup.
+	 */
+	b	.Lskip_tramp_vectors_cleanup\@
 	.if	\regsize == 64
 	mrs	x30, tpidrro_el0
 	msr	tpidrro_el0, xzr
 	.else
 	mov	x30, xzr
 	.endif
-alternative_else_nop_endif
+.Lskip_tramp_vectors_cleanup\@:
 	.endif
-#endif
 
 	sub	sp, sp, #PT_REGS_SIZE
 #ifdef CONFIG_VMAP_STACK
@@ -95,11 +98,15 @@ alternative_else_nop_endif
 	mrs	x0, tpidrro_el0
 #endif
 	b	el\el\ht\()_\regsize\()_\label
+.org .Lventry_start\@ + 128	// Did we overflow the ventry slot?
 	.endm
 
-	.macro tramp_alias, dst, sym
+	.macro tramp_alias, dst, sym, tmp
 	mov_q	\dst, TRAMP_VALIAS
-	add	\dst, \dst, #(\sym - .entry.tramp.text)
+	adr_l	\tmp, \sym
+	add	\dst, \dst, \tmp
+	adr_l	\tmp, .entry.tramp.text
+	sub	\dst, \dst, \tmp
 	.endm
 
 	/*
@@ -116,7 +123,7 @@ alternative_cb_end
 	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
-alternative_cb	spectre_v4_patch_fw_mitigation_conduit
+alternative_cb	smccc_patch_fw_mitigation_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
 .L__asm_ssbd_skip\@:
@@ -410,21 +417,26 @@ alternative_else_nop_endif
 	ldp	x24, x25, [sp, #16 * 12]
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
-	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
-alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
+alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+	eret
+alternative_else_nop_endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	bne	4f
-	msr	far_el1, x30
-	tramp_alias	x30, tramp_exit_native
+	msr	far_el1, x29
+	tramp_alias	x30, tramp_exit_native, x29
 	br	x30
 4:
-	tramp_alias	x30, tramp_exit_compat
+	tramp_alias	x30, tramp_exit_compat, x29
 	br	x30
 #endif
 	.else
+	ldr	lr, [sp, #S_LR]
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
+
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
 
@@ -591,12 +603,6 @@ SYM_CODE_END(ret_to_user)
 
 	.popsection				// .entry.text
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-/*
- * Exception vectors trampoline.
- */
-	.pushsection ".entry.tramp.text", "ax"
-
 	// Move from tramp_pg_dir to swapper_pg_dir
 	.macro tramp_map_kernel, tmp
 	mrs	\tmp, ttbr1_el1
@@ -630,12 +636,47 @@ alternative_else_nop_endif
 	 */
 	.endm
 
-	.macro tramp_ventry, regsize = 64
+	.macro tramp_data_page	dst
+	adr_l	\dst, .entry.tramp.text
+	sub	\dst, \dst, PAGE_SIZE
+	.endm
+
+	.macro tramp_data_read_var	dst, var
+#ifdef CONFIG_RANDOMIZE_BASE
+	tramp_data_page		\dst
+	add	\dst, \dst, #:lo12:__entry_tramp_data_\var
+	ldr	\dst, [\dst]
+#else
+	ldr	\dst, =\var
+#endif
+	.endm
+
+#define BHB_MITIGATION_NONE	0
+#define BHB_MITIGATION_LOOP	1
+#define BHB_MITIGATION_FW	2
+#define BHB_MITIGATION_INSN	3
+
+	.macro tramp_ventry, vector_start, regsize, kpti, bhb
 	.align	7
 1:
 	.if	\regsize == 64
 	msr	tpidrro_el0, x30	// Restored in kernel_ventry
 	.endif
+
+	.if	\bhb == BHB_MITIGATION_LOOP
+	/*
+	 * This sequence must appear before the first indirect branch. i.e. the
+	 * ret out of tramp_ventry. It appears here because x30 is free.
+	 */
+	__mitigate_spectre_bhb_loop	x30
+	.endif // \bhb == BHB_MITIGATION_LOOP
+
+	.if	\bhb == BHB_MITIGATION_INSN
+	clearbhb
+	isb
+	.endif // \bhb == BHB_MITIGATION_INSN
+
+	.if	\kpti == 1
 	/*
 	 * Defend against branch aliasing attacks by pushing a dummy
 	 * entry onto the return stack and using a RET instruction to
@@ -645,46 +686,75 @@ alternative_else_nop_endif
 	b	.
 2:
 	tramp_map_kernel	x30
-#ifdef CONFIG_RANDOMIZE_BASE
-	adr	x30, tramp_vectors + PAGE_SIZE
 alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
-	ldr	x30, [x30]
-#else
-	ldr	x30, =vectors
-#endif
+	tramp_data_read_var	x30, vectors
 alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
-	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+	prfm	plil1strm, [x30, #(1b - \vector_start)]
 alternative_else_nop_endif
+
 	msr	vbar_el1, x30
-	add	x30, x30, #(1b - tramp_vectors)
 	isb
+	.else
+	ldr	x30, =vectors
+	.endif // \kpti == 1
+
+	.if	\bhb == BHB_MITIGATION_FW
+	/*
+	 * The firmware sequence must appear before the first indirect branch.
+	 * i.e. the ret out of tramp_ventry. But it also needs the stack to be
+	 * mapped to save/restore the registers the SMC clobbers.
+	 */
+	__mitigate_spectre_bhb_fw
+	.endif // \bhb == BHB_MITIGATION_FW
+
+	add	x30, x30, #(1b - \vector_start + 4)
 	ret
+.org 1b + 128	// Did we overflow the ventry slot?
 	.endm
 
 	.macro tramp_exit, regsize = 64
-	adr	x30, tramp_vectors
+	tramp_data_read_var	x30, this_cpu_vector
+	get_this_cpu_offset x29
+	ldr	x30, [x30, x29]
+
 	msr	vbar_el1, x30
-	tramp_unmap_kernel	x30
+	ldr	lr, [sp, #S_LR]
+	tramp_unmap_kernel	x29
 	.if	\regsize == 64
-	mrs	x30, far_el1
+	mrs	x29, far_el1
 	.endif
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 	eret
 	sb
 	.endm
 
-	.align	11
-SYM_CODE_START_NOALIGN(tramp_vectors)
+	.macro	generate_tramp_vector,	kpti, bhb
+.Lvector_start\@:
 	.space	0x400
 
-	tramp_ventry
-	tramp_ventry
-	tramp_ventry
-	tramp_ventry
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 64, \kpti, \bhb
+	.endr
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 32, \kpti, \bhb
+	.endr
+	.endm
 
-	tramp_ventry	32
-	tramp_ventry	32
-	tramp_ventry	32
-	tramp_ventry	32
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+/*
+ * Exception vectors trampoline.
+ * The order must match __bp_harden_el1_vectors and the
+ * arm64_bp_harden_el1_vectors enum.
+ */
+	.pushsection ".entry.tramp.text", "ax"
+	.align	11
+SYM_CODE_START_NOALIGN(tramp_vectors)
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_LOOP
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_FW
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_INSN
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+	generate_tramp_vector	kpti=1, bhb=BHB_MITIGATION_NONE
 SYM_CODE_END(tramp_vectors)
 
 SYM_CODE_START(tramp_exit_native)
@@ -701,13 +771,57 @@ SYM_CODE_END(tramp_exit_compat)
 	.pushsection ".rodata", "a"
 	.align PAGE_SHIFT
 SYM_DATA_START(__entry_tramp_data_start)
+__entry_tramp_data_vectors:
 	.quad	vectors
+#ifdef CONFIG_ARM_SDE_INTERFACE
+__entry_tramp_data___sdei_asm_handler:
+	.quad	__sdei_asm_handler
+#endif /* CONFIG_ARM_SDE_INTERFACE */
+__entry_tramp_data_this_cpu_vector:
+	.quad	this_cpu_vector
 SYM_DATA_END(__entry_tramp_data_start)
 	.popsection				// .rodata
 #endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 /*
+ * Exception vectors for spectre mitigations on entry from EL1 when
+ * kpti is not in use.
+ */
+	.macro generate_el1_vector, bhb
+.Lvector_start\@:
+	kernel_ventry	1, t, 64, sync		// Synchronous EL1t
+	kernel_ventry	1, t, 64, irq		// IRQ EL1t
+	kernel_ventry	1, t, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, t, 64, error		// Error EL1t
+
+	kernel_ventry	1, h, 64, sync		// Synchronous EL1h
+	kernel_ventry	1, h, 64, irq		// IRQ EL1h
+	kernel_ventry	1, h, 64, fiq		// FIQ EL1h
+	kernel_ventry	1, h, 64, error		// Error EL1h
+
+	.rept	4
+	tramp_ventry	.Lvector_start\@, 64, 0, \bhb
+	.endr
+	.rept 4
+	tramp_ventry	.Lvector_start\@, 32, 0, \bhb
+	.endr
+	.endm
+
+/* The order must match tramp_vecs and the arm64_bp_harden_el1_vectors enum. */
+	.pushsection ".entry.text", "ax"
+	.align	11
+SYM_CODE_START(__bp_harden_el1_vectors)
+#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY
+	generate_el1_vector	bhb=BHB_MITIGATION_LOOP
+	generate_el1_vector	bhb=BHB_MITIGATION_FW
+	generate_el1_vector	bhb=BHB_MITIGATION_INSN
+#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */
+SYM_CODE_END(__bp_harden_el1_vectors)
+	.popsection
+
+
+/*
  * Register switch for AArch64. The callee-saved registers need to be saved
  * and restored. On entry:
  *   x0 = previous task_struct (must be preserved across the switch)
@@ -832,14 +946,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline)
 	 * Remember whether to unmap the kernel on exit.
 	 */
 1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)]
-
-#ifdef CONFIG_RANDOMIZE_BASE
-	adr	x4, tramp_vectors + PAGE_SIZE
-	add	x4, x4, #:lo12:__sdei_asm_trampoline_next_handler
-	ldr	x4, [x4]
-#else
-	ldr	x4, =__sdei_asm_handler
-#endif
+	tramp_data_read_var     x4, __sdei_asm_handler
 	br	x4
 SYM_CODE_END(__sdei_asm_entry_trampoline)
 NOKPROBE(__sdei_asm_entry_trampoline)
@@ -862,13 +969,6 @@ SYM_CODE_END(__sdei_asm_exit_trampoline)
 NOKPROBE(__sdei_asm_exit_trampoline)
 	.ltorg
 .popsection		// .entry.tramp.text
-#ifdef CONFIG_RANDOMIZE_BASE
-.pushsection ".rodata", "a"
-SYM_DATA_START(__sdei_asm_trampoline_next_handler)
-	.quad	__sdei_asm_handler
-SYM_DATA_END(__sdei_asm_trampoline_next_handler)
-.popsection		// .rodata
-#endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 /*
@@ -978,7 +1078,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
 alternative_else_nop_endif
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline
+	tramp_alias	dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3
 	br	x5
 #endif
 SYM_CODE_END(__sdei_asm_handler)
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 7eaf1f7c4168..55a1ced8eb77 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -66,6 +66,10 @@ KVM_NVHE_ALIAS(kvm_patch_vector_branch);
 KVM_NVHE_ALIAS(kvm_update_va_mask);
 KVM_NVHE_ALIAS(kvm_get_kimage_voffset);
 KVM_NVHE_ALIAS(kvm_compute_final_ctr_el0);
+KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter);
+KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable);
+KVM_NVHE_ALIAS(spectre_bhb_patch_wa3);
+KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb);
 
 /* Global kernel state accessed by nVHE hyp code. */
 KVM_NVHE_ALIAS(kvm_vgic_global_state);
diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index ea78f0b3d847..5777929d35bf 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -18,15 +18,18 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/bpf.h>
 #include <linux/cpu.h>
 #include <linux/device.h>
 #include <linux/nospec.h>
 #include <linux/prctl.h>
 #include <linux/sched/task_stack.h>
 
+#include <asm/debug-monitors.h>
 #include <asm/insn.h>
 #include <asm/spectre.h>
 #include <asm/traps.h>
+#include <asm/vectors.h>
 #include <asm/virt.h>
 
 /*
@@ -96,14 +99,51 @@ static bool spectre_v2_mitigations_off(void)
 	return ret;
 }
 
+static const char *get_bhb_affected_string(enum mitigation_state bhb_state)
+{
+	switch (bhb_state) {
+	case SPECTRE_UNAFFECTED:
+		return "";
+	default:
+	case SPECTRE_VULNERABLE:
+		return ", but not BHB";
+	case SPECTRE_MITIGATED:
+		return ", BHB";
+	}
+}
+
+static bool _unprivileged_ebpf_enabled(void)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	return !sysctl_unprivileged_bpf_disabled;
+#else
+	return false;
+#endif
+}
+
 ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
+	enum mitigation_state bhb_state = arm64_get_spectre_bhb_state();
+	const char *bhb_str = get_bhb_affected_string(bhb_state);
+	const char *v2_str = "Branch predictor hardening";
+
 	switch (spectre_v2_state) {
 	case SPECTRE_UNAFFECTED:
-		return sprintf(buf, "Not affected\n");
+		if (bhb_state == SPECTRE_UNAFFECTED)
+			return sprintf(buf, "Not affected\n");
+
+		/*
+		 * Platforms affected by Spectre-BHB can't report
+		 * "Not affected" for Spectre-v2.
+		 */
+		v2_str = "CSV2";
+		fallthrough;
 	case SPECTRE_MITIGATED:
-		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+		if (bhb_state == SPECTRE_MITIGATED && _unprivileged_ebpf_enabled())
+			return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n");
+
+		return sprintf(buf, "Mitigation: %s%s\n", v2_str, bhb_str);
 	case SPECTRE_VULNERABLE:
 		fallthrough;
 	default:
@@ -557,9 +597,9 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt,
  * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction
  * to call into firmware to adjust the mitigation state.
  */
-void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt,
-						   __le32 *origptr,
-						   __le32 *updptr, int nr_inst)
+void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt,
+					       __le32 *origptr,
+					       __le32 *updptr, int nr_inst)
 {
 	u32 insn;
 
@@ -773,3 +813,344 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 		return -ENODEV;
 	}
 }
+
+/*
+ * Spectre BHB.
+ *
+ * A CPU is either:
+ * - Mitigated by a branchy loop a CPU specific number of times, and listed
+ *   in our "loop mitigated list".
+ * - Mitigated in software by the firmware Spectre v2 call.
+ * - Has the ClearBHB instruction to perform the mitigation.
+ * - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no
+ *   software mitigation in the vectors is needed.
+ * - Has CSV2.3, so is unaffected.
+ */
+static enum mitigation_state spectre_bhb_state;
+
+enum mitigation_state arm64_get_spectre_bhb_state(void)
+{
+	return spectre_bhb_state;
+}
+
+enum bhb_mitigation_bits {
+	BHB_LOOP,
+	BHB_FW,
+	BHB_HW,
+	BHB_INSN,
+};
+static unsigned long system_bhb_mitigations;
+
+/*
+ * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any
+ * SCOPE_SYSTEM call will give the right answer.
+ */
+u8 spectre_bhb_loop_affected(int scope)
+{
+	u8 k = 0;
+	static u8 max_bhb_k;
+
+	if (scope == SCOPE_LOCAL_CPU) {
+		static const struct midr_range spectre_bhb_k32_list[] = {
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
+			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
+			{},
+		};
+		static const struct midr_range spectre_bhb_k24_list[] = {
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
+			MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
+			{},
+		};
+		static const struct midr_range spectre_bhb_k8_list[] = {
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
+			MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
+			{},
+		};
+
+		if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list))
+			k = 32;
+		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list))
+			k = 24;
+		else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list))
+			k =  8;
+
+		max_bhb_k = max(max_bhb_k, k);
+	} else {
+		k = max_bhb_k;
+	}
+
+	return k;
+}
+
+static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void)
+{
+	int ret;
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_3, &res);
+
+	ret = res.a0;
+	switch (ret) {
+	case SMCCC_RET_SUCCESS:
+		return SPECTRE_MITIGATED;
+	case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
+		return SPECTRE_UNAFFECTED;
+	default:
+		fallthrough;
+	case SMCCC_RET_NOT_SUPPORTED:
+		return SPECTRE_VULNERABLE;
+	}
+}
+
+static bool is_spectre_bhb_fw_affected(int scope)
+{
+	static bool system_affected;
+	enum mitigation_state fw_state;
+	bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE;
+	static const struct midr_range spectre_bhb_firmware_mitigated_list[] = {
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+		MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
+		{},
+	};
+	bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(),
+					 spectre_bhb_firmware_mitigated_list);
+
+	if (scope != SCOPE_LOCAL_CPU)
+		return system_affected;
+
+	fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
+	if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) {
+		system_affected = true;
+		return true;
+	}
+
+	return false;
+}
+
+static bool supports_ecbhb(int scope)
+{
+	u64 mmfr1;
+
+	if (scope == SCOPE_LOCAL_CPU)
+		mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1);
+	else
+		mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+
+	return cpuid_feature_extract_unsigned_field(mmfr1,
+						    ID_AA64MMFR1_ECBHB_SHIFT);
+}
+
+bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry,
+			     int scope)
+{
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	if (supports_csv2p3(scope))
+		return false;
+
+	if (supports_clearbhb(scope))
+		return true;
+
+	if (spectre_bhb_loop_affected(scope))
+		return true;
+
+	if (is_spectre_bhb_fw_affected(scope))
+		return true;
+
+	return false;
+}
+
+static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot)
+{
+	const char *v = arm64_get_bp_hardening_vector(slot);
+
+	if (slot < 0)
+		return;
+
+	__this_cpu_write(this_cpu_vector, v);
+
+	/*
+	 * When KPTI is in use, the vectors are switched when exiting to
+	 * user-space.
+	 */
+	if (arm64_kernel_unmapped_at_el0())
+		return;
+
+	write_sysreg(v, vbar_el1);
+	isb();
+}
+
+void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
+{
+	bp_hardening_cb_t cpu_cb;
+	enum mitigation_state fw_state, state = SPECTRE_VULNERABLE;
+	struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data);
+
+	if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU))
+		return;
+
+	if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) {
+		/* No point mitigating Spectre-BHB alone. */
+	} else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) {
+		pr_info_once("spectre-bhb mitigation disabled by compile time option\n");
+	} else if (cpu_mitigations_off()) {
+		pr_info_once("spectre-bhb mitigation disabled by command line option\n");
+	} else if (supports_ecbhb(SCOPE_LOCAL_CPU)) {
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_HW, &system_bhb_mitigations);
+	} else if (supports_clearbhb(SCOPE_LOCAL_CPU)) {
+		/*
+		 * Ensure KVM uses the indirect vector which will have ClearBHB
+		 * added.
+		 */
+		if (!data->slot)
+			data->slot = HYP_VECTOR_INDIRECT;
+
+		this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_INSN, &system_bhb_mitigations);
+	} else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) {
+		/*
+		 * Ensure KVM uses the indirect vector which will have the
+		 * branchy-loop added. A57/A72-r0 will already have selected
+		 * the spectre-indirect vector, which is sufficient for BHB
+		 * too.
+		 */
+		if (!data->slot)
+			data->slot = HYP_VECTOR_INDIRECT;
+
+		this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
+		state = SPECTRE_MITIGATED;
+		set_bit(BHB_LOOP, &system_bhb_mitigations);
+	} else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) {
+		fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
+		if (fw_state == SPECTRE_MITIGATED) {
+			/*
+			 * Ensure KVM uses one of the spectre bp_hardening
+			 * vectors. The indirect vector doesn't include the EL3
+			 * call, so needs upgrading to
+			 * HYP_VECTOR_SPECTRE_INDIRECT.
+			 */
+			if (!data->slot || data->slot == HYP_VECTOR_INDIRECT)
+				data->slot += 1;
+
+			this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
+
+			/*
+			 * The WA3 call in the vectors supersedes the WA1 call
+			 * made during context-switch. Uninstall any firmware
+			 * bp_hardening callback.
+			 */
+			cpu_cb = spectre_v2_get_sw_mitigation_cb();
+			if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb)
+				__this_cpu_write(bp_hardening_data.fn, NULL);
+
+			state = SPECTRE_MITIGATED;
+			set_bit(BHB_FW, &system_bhb_mitigations);
+		}
+	}
+
+	update_mitigation_state(&spectre_bhb_state, state);
+}
+
+/* Patched to NOP when enabled */
+void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt,
+						     __le32 *origptr,
+						      __le32 *updptr, int nr_inst)
+{
+	BUG_ON(nr_inst != 1);
+
+	if (test_bit(BHB_LOOP, &system_bhb_mitigations))
+		*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
+}
+
+/* Patched to NOP when enabled */
+void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt,
+						   __le32 *origptr,
+						   __le32 *updptr, int nr_inst)
+{
+	BUG_ON(nr_inst != 1);
+
+	if (test_bit(BHB_FW, &system_bhb_mitigations))
+		*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
+}
+
+/* Patched to correct the immediate */
+void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt,
+				   __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	u8 rd;
+	u32 insn;
+	u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM);
+
+	BUG_ON(nr_inst != 1); /* MOV -> MOV */
+
+	if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY))
+		return;
+
+	insn = le32_to_cpu(*origptr);
+	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
+	insn = aarch64_insn_gen_movewide(rd, loop_count, 0,
+					 AARCH64_INSN_VARIANT_64BIT,
+					 AARCH64_INSN_MOVEWIDE_ZERO);
+	*updptr++ = cpu_to_le32(insn);
+}
+
+/* Patched to mov WA3 when supported */
+void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt,
+				   __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	u8 rd;
+	u32 insn;
+
+	BUG_ON(nr_inst != 1); /* MOV -> MOV */
+
+	if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) ||
+	    !test_bit(BHB_FW, &system_bhb_mitigations))
+		return;
+
+	insn = le32_to_cpu(*origptr);
+	rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn);
+
+	insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_ORR,
+						  AARCH64_INSN_VARIANT_32BIT,
+						  AARCH64_INSN_REG_ZR, rd,
+						  ARM_SMCCC_ARCH_WORKAROUND_3);
+	if (WARN_ON_ONCE(insn == AARCH64_BREAK_FAULT))
+		return;
+
+	*updptr++ = cpu_to_le32(insn);
+}
+
+/* Patched to NOP when not supported */
+void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt,
+				   __le32 *origptr, __le32 *updptr, int nr_inst)
+{
+	BUG_ON(nr_inst != 2);
+
+	if (test_bit(BHB_INSN, &system_bhb_mitigations))
+		return;
+
+	*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
+	*updptr++ = cpu_to_le32(aarch64_insn_gen_nop());
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+#define EBPF_WARN "Unprivileged eBPF is enabled, data leaks possible via Spectre v2 BHB attacks!\n"
+void unpriv_ebpf_notify(int new_state)
+{
+	if (spectre_v2_state == SPECTRE_VULNERABLE ||
+	    spectre_bhb_state != SPECTRE_MITIGATED)
+		return;
+
+	if (!new_state)
+		pr_err("WARNING: %s", EBPF_WARN);
+}
+#endif
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 50bab186c49b..edaf0faf766f 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -341,7 +341,7 @@ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
 	<= SZ_4K, "Hibernate exit text too big or misaligned")
 #endif
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE,
+ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE,
 	"Entry trampoline text too big")
 #endif
 #ifdef CONFIG_KVM
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f3bfc0ddeb0b..946e401ef6b0 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1491,10 +1491,7 @@ static int kvm_init_vector_slots(void)
 	base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 	kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT);
 
-	if (!cpus_have_const_cap(ARM64_SPECTRE_V3A))
-		return 0;
-
-	if (!has_vhe()) {
+	if (kvm_system_needs_idmapped_vectors() && !has_vhe()) {
 		err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs),
 					       __BP_HARDEN_HYP_VECS_SZ, &base);
 		if (err)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index b6b6801d96d5..7839d075729b 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -62,6 +62,10 @@ el1_sync:				// Guest trapped into EL2
 	/* ARM_SMCCC_ARCH_WORKAROUND_2 handling */
 	eor	w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \
 			  ARM_SMCCC_ARCH_WORKAROUND_2)
+	cbz	w1, wa_epilogue
+
+	eor	w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_2 ^ \
+			  ARM_SMCCC_ARCH_WORKAROUND_3)
 	cbnz	w1, el1_trap
 
 wa_epilogue:
@@ -192,7 +196,10 @@ SYM_CODE_END(__kvm_hyp_vector)
 	sub	sp, sp, #(8 * 4)
 	stp	x2, x3, [sp, #(8 * 0)]
 	stp	x0, x1, [sp, #(8 * 2)]
+	alternative_cb spectre_bhb_patch_wa3
+	/* Patched to mov WA3 when supported */
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_1
+	alternative_cb_end
 	smc	#0
 	ldp	x2, x3, [sp, #(8 * 0)]
 	add	sp, sp, #(8 * 2)
@@ -205,6 +212,8 @@ SYM_CODE_END(__kvm_hyp_vector)
 	spectrev2_smccc_wa1_smc
 	.else
 	stp	x0, x1, [sp, #-16]!
+	mitigate_spectre_bhb_loop	x0
+	mitigate_spectre_bhb_clear_insn
 	.endif
 	.if \indirect != 0
 	alternative_cb  kvm_patch_vector_branch
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index 526a7d6fa86f..cdbe8e246418 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -148,8 +148,10 @@ int hyp_map_vectors(void)
 	phys_addr_t phys;
 	void *bp_base;
 
-	if (!cpus_have_const_cap(ARM64_SPECTRE_V3A))
+	if (!kvm_system_needs_idmapped_vectors()) {
+		__hyp_bp_vect_base = __bp_harden_hyp_vecs;
 		return 0;
+	}
 
 	phys = __hyp_pa(__bp_harden_hyp_vecs);
 	bp_base = (void *)__pkvm_create_private_mapping(phys,
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 619353b06e38..262dfe03134d 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -10,6 +10,7 @@
 #include <linux/kvm_host.h>
 #include <linux/types.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
 #include <uapi/linux/psci.h>
 
 #include <kvm/arm_psci.h>
@@ -24,6 +25,8 @@
 #include <asm/fpsimd.h>
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
+#include <asm/thread_info.h>
+#include <asm/vectors.h>
 
 /* VHE specific context */
 DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
@@ -67,7 +70,7 @@ NOKPROBE_SYMBOL(__activate_traps);
 
 static void __deactivate_traps(struct kvm_vcpu *vcpu)
 {
-	extern char vectors[];	/* kernel exception vectors */
+	const char *host_vectors = vectors;
 
 	___deactivate_traps(vcpu);
 
@@ -81,7 +84,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
-	write_sysreg(vectors, vbar_el1);
+
+	if (!arm64_kernel_unmapped_at_el0())
+		host_vectors = __this_cpu_read(this_cpu_vector);
+	write_sysreg(host_vectors, vbar_el1);
 }
 NOKPROBE_SYMBOL(__deactivate_traps);
 
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 30da78f72b3b..202b8c455724 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -107,6 +107,18 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 				break;
 			}
 			break;
+		case ARM_SMCCC_ARCH_WORKAROUND_3:
+			switch (arm64_get_spectre_bhb_state()) {
+			case SPECTRE_VULNERABLE:
+				break;
+			case SPECTRE_MITIGATED:
+				val[0] = SMCCC_RET_SUCCESS;
+				break;
+			case SPECTRE_UNAFFECTED:
+				val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
+				break;
+			}
+			break;
 		case ARM_SMCCC_HV_PV_TIME_FEATURES:
 			val[0] = SMCCC_RET_SUCCESS;
 			break;
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index 3eae32876897..14b9726041ff 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -406,7 +406,7 @@ int kvm_psci_call(struct kvm_vcpu *vcpu)
 
 int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu)
 {
-	return 3;		/* PSCI version and two workaround registers */
+	return 4;		/* PSCI version and three workaround registers */
 }
 
 int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
@@ -420,6 +420,9 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++))
 		return -EFAULT;
 
+	if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++))
+		return -EFAULT;
+
 	return 0;
 }
 
@@ -459,6 +462,17 @@ static int get_kernel_wa_level(u64 regid)
 		case SPECTRE_VULNERABLE:
 			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
 		}
+		break;
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
+		switch (arm64_get_spectre_bhb_state()) {
+		case SPECTRE_VULNERABLE:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
+		case SPECTRE_MITIGATED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL;
+		case SPECTRE_UNAFFECTED:
+			return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED;
+		}
+		return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL;
 	}
 
 	return -EINVAL;
@@ -475,6 +489,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		break;
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
 		val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
 		break;
 	default:
@@ -520,6 +535,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+	case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
 		if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
 			return -EINVAL;
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 298f3834b6b5..0b7d25887ec3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -645,6 +645,8 @@ early_param("rodata", parse_rodata);
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __init map_entry_trampoline(void)
 {
+	int i;
+
 	pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
 	phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start);
 
@@ -653,11 +655,15 @@ static int __init map_entry_trampoline(void)
 
 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
-	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
-			     prot, __pgd_pgtable_alloc, 0);
+	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS,
+			     entry_tramp_text_size(), prot,
+			     __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS);
 
 	/* Map both the text and data into the kernel page table */
-	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
+	for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++)
+		__set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i,
+			     pa_start + i * PAGE_SIZE, prot);
+
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern char __entry_tramp_data_start[];
 
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 162bc2443217..3ed418f70e3b 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -46,6 +46,7 @@ MTE_ASYMM
 SPECTRE_V2
 SPECTRE_V3A
 SPECTRE_V4
+SPECTRE_BHB
 SSBS
 SVE
 UNMAP_KERNEL_AT_EL0