diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 20993615087acd16834672d7d12075b5c1d4441e..00c9aafa3a52aec8a8389eb73e1e65c863c2fa05 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -108,6 +108,16 @@
 	.endm
 #endif
 
+#if __LINUX_ARM_ARCH__ < 7
+	.macro	dsb, args
+	mcr	p15, 0, r0, c7, c10, 4
+	.endm
+
+	.macro	isb, args
+	mcr	p15, 0, r0, c7, c5, 4
+	.endm
+#endif
+
 	.macro asm_trace_hardirqs_off, save=1
 #if defined(CONFIG_TRACE_IRQFLAGS)
 	.if \save
diff --git a/arch/arm/include/asm/spectre.h b/arch/arm/include/asm/spectre.h
new file mode 100644
index 0000000000000000000000000000000000000000..85f9e538fb325730613f78419f52826a68b8d76c
--- /dev/null
+++ b/arch/arm/include/asm/spectre.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_SPECTRE_H
+#define __ASM_SPECTRE_H
+
+enum {
+	SPECTRE_UNAFFECTED,
+	SPECTRE_MITIGATED,
+	SPECTRE_VULNERABLE,
+};
+
+enum {
+	__SPECTRE_V2_METHOD_BPIALL,
+	__SPECTRE_V2_METHOD_ICIALLU,
+	__SPECTRE_V2_METHOD_SMC,
+	__SPECTRE_V2_METHOD_HVC,
+	__SPECTRE_V2_METHOD_LOOP8,
+};
+
+enum {
+	SPECTRE_V2_METHOD_BPIALL = BIT(__SPECTRE_V2_METHOD_BPIALL),
+	SPECTRE_V2_METHOD_ICIALLU = BIT(__SPECTRE_V2_METHOD_ICIALLU),
+	SPECTRE_V2_METHOD_SMC = BIT(__SPECTRE_V2_METHOD_SMC),
+	SPECTRE_V2_METHOD_HVC = BIT(__SPECTRE_V2_METHOD_HVC),
+	SPECTRE_V2_METHOD_LOOP8 = BIT(__SPECTRE_V2_METHOD_LOOP8),
+};
+
+#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES
+void spectre_v2_update_state(unsigned int state, unsigned int methods);
+#else
+static inline void spectre_v2_update_state(unsigned int state,
+					   unsigned int methods)
+{}
+#endif
+
+int spectre_bhb_update_vectors(unsigned int method);
+
+#endif
diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h
index be04f5b5056f76a01c5319ed4a054a321a311fb5..0b2b1c577eab84b79a31e1234135789d6d3a2b3c 100644
--- a/arch/arm/include/asm/vmlinux.lds.h
+++ b/arch/arm/include/asm/vmlinux.lds.h
@@ -26,6 +26,19 @@
 #define ARM_MMU_DISCARD(x)	x
 #endif
 
+/*
+ * ld.lld does not support NOCROSSREFS:
+ * https://github.com/ClangBuiltLinux/linux/issues/1609
+ */
+#ifdef CONFIG_LD_IS_LLD
+#define NOCROSSREFS
+#endif
+
+/* Set start/end symbol names to the LMA for the section */
+#define ARM_LMA(sym, section)						\
+	sym##_start = LOADADDR(section);				\
+	sym##_end = LOADADDR(section) + SIZEOF(section)
+
 #define PROC_INFO							\
 		. = ALIGN(4);						\
 		__proc_info_begin = .;					\
@@ -115,19 +128,31 @@
  * only thing that matters is their relative offsets
  */
 #define ARM_VECTORS							\
-	__vectors_start = .;						\
-	.vectors 0xffff0000 : AT(__vectors_start) {			\
-		*(.vectors)						\
+	__vectors_lma = .;						\
+	OVERLAY 0xffff0000 : NOCROSSREFS AT(__vectors_lma) {		\
+		.vectors {						\
+			*(.vectors)					\
+		}							\
+		.vectors.bhb.loop8 {					\
+			*(.vectors.bhb.loop8)				\
+		}							\
+		.vectors.bhb.bpiall {					\
+			*(.vectors.bhb.bpiall)				\
+		}							\
 	}								\
-	. = __vectors_start + SIZEOF(.vectors);				\
-	__vectors_end = .;						\
+	ARM_LMA(__vectors, .vectors);					\
+	ARM_LMA(__vectors_bhb_loop8, .vectors.bhb.loop8);		\
+	ARM_LMA(__vectors_bhb_bpiall, .vectors.bhb.bpiall);		\
+	. = __vectors_lma + SIZEOF(.vectors) +				\
+		SIZEOF(.vectors.bhb.loop8) +				\
+		SIZEOF(.vectors.bhb.bpiall);				\
 									\
-	__stubs_start = .;						\
-	.stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) {		\
+	__stubs_lma = .;						\
+	.stubs ADDR(.vectors) + 0x1000 : AT(__stubs_lma) {		\
 		*(.stubs)						\
 	}								\
-	. = __stubs_start + SIZEOF(.stubs);				\
-	__stubs_end = .;
+	ARM_LMA(__stubs, .stubs);					\
+	. = __stubs_lma + SIZEOF(.stubs);
 									\
 #define ARM_TCM								\
 	__itcm_start = ALIGN(4);					\
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index c38c8b019d24c6103a06ccaebd441929d3ac6c69..292378fbb89ec952d087b2a95dbe9b21929e60cc 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -110,4 +110,6 @@ endif
 
 obj-$(CONFIG_HAVE_ARM_SMCCC)	+= smccc-call.o
 
+obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += spectre.o
+
 extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index cd0a00032b22812031753a3aac8fc31cdded459f..e3eca3f8300e428345f2f63f28b528f7181eaeb0 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -1007,12 +1007,11 @@ __kuser_helper_end:
 	sub	lr, lr, #\correction
 	.endif
 
-	@
-	@ Save r0, lr_<exception> (parent PC) and spsr_<exception>
-	@ (parent CPSR)
-	@
+	@ Save r0, lr_<exception> (parent PC)
 	stmia	sp, {r0, lr}		@ save r0, lr
-	mrs	lr, spsr
+
+	@ Save spsr_<exception> (parent CPSR)
+2:	mrs	lr, spsr
 	str	lr, [sp, #8]		@ save spsr
 
 	@
@@ -1033,6 +1032,44 @@ __kuser_helper_end:
 	movs	pc, lr			@ branch to handler in SVC mode
 ENDPROC(.Lvector_\name)
 
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.subsection 1
+	.align 5
+vector_bhb_loop8_\name:
+	.if \correction
+	sub	lr, lr, #\correction
+	.endif
+
+	@ Save r0, lr_<exception> (parent PC)
+	stmia	sp, {r0, lr}
+
+	@ bhb workaround
+	mov	r0, #8
+3:	b	. + 4
+	subs	r0, r0, #1
+	bne	3b
+	dsb
+	isb
+	b	2b
+ENDPROC(vector_bhb_loop8_\name)
+
+vector_bhb_bpiall_\name:
+	.if \correction
+	sub	lr, lr, #\correction
+	.endif
+
+	@ Save r0, lr_<exception> (parent PC)
+	stmia	sp, {r0, lr}
+
+	@ bhb workaround
+	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	@ isb not needed due to "movs pc, lr" in the vector stub
+	@ which gives a "context synchronisation".
+	b	2b
+ENDPROC(vector_bhb_bpiall_\name)
+	.previous
+#endif
+
 	.align	2
 	@ handler addresses follow this label
 1:
@@ -1045,6 +1082,10 @@ ENDPROC(.Lvector_\name)
 #endif
 	@ This must be the first word
 	.word	vector_swi
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.word	vector_bhb_loop8_swi
+	.word	vector_bhb_bpiall_swi
+#endif
 
 .Lvector_rst:
  ARM(	swi	SYS_ERROR0	)
@@ -1159,8 +1200,10 @@ ENDPROC(.Lvector_\name)
  * FIQ "NMI" handler
  *-----------------------------------------------------------------------------
  * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86
- * systems.
+ * systems. This must be the last vector stub, so lets place it in its own
+ * subsection.
  */
+	.subsection 2
 	vector_stub	fiq, FIQ_MODE, 4
 
 	.long	__fiq_usr			@  0  (USR_26 / USR_32)
@@ -1191,6 +1234,30 @@ ENDPROC(.Lvector_\name)
 	W(b)	.Lvector_irq
 	W(b)	.Lvector_fiq
 
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.section .vectors.bhb.loop8, "ax", %progbits
+.L__vectors_bhb_loop8_start:
+	W(b)	.Lvector_rst
+	W(b)	vector_bhb_loop8_und
+	W(ldr)	pc, .L__vectors_bhb_loop8_start + 0x1004
+	W(b)	vector_bhb_loop8_pabt
+	W(b)	vector_bhb_loop8_dabt
+	W(b)	.Lvector_addrexcptn
+	W(b)	vector_bhb_loop8_irq
+	W(b)	vector_bhb_loop8_fiq
+
+	.section .vectors.bhb.bpiall, "ax", %progbits
+.L__vectors_bhb_bpiall_start:
+	W(b)	.Lvector_rst
+	W(b)	vector_bhb_bpiall_und
+	W(ldr)	pc, .L__vectors_bhb_bpiall_start + 0x1008
+	W(b)	vector_bhb_bpiall_pabt
+	W(b)	vector_bhb_bpiall_dabt
+	W(b)	.Lvector_addrexcptn
+	W(b)	vector_bhb_bpiall_irq
+	W(b)	vector_bhb_bpiall_fiq
+#endif
+
 	.data
 	.align	2
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index fee279e28a72e05bdb67ebc4e7a37a3b35ca3824..7a2e63dfb4d9a13b914568931f88e0f5c78f5654 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -165,6 +165,29 @@ ENDPROC(ret_from_fork)
  *-----------------------------------------------------------------------------
  */
 
+	.align	5
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+ENTRY(vector_bhb_loop8_swi)
+	sub	sp, sp, #PT_REGS_SIZE
+	stmia	sp, {r0 - r12}
+	mov	r8, #8
+1:	b	2f
+2:	subs	r8, r8, #1
+	bne	1b
+	dsb
+	isb
+	b	3f
+ENDPROC(vector_bhb_loop8_swi)
+
+	.align	5
+ENTRY(vector_bhb_bpiall_swi)
+	sub	sp, sp, #PT_REGS_SIZE
+	stmia	sp, {r0 - r12}
+	mcr	p15, 0, r8, c7, c5, 6	@ BPIALL
+	isb
+	b	3f
+ENDPROC(vector_bhb_bpiall_swi)
+#endif
 	.align	5
 ENTRY(vector_swi)
 #ifdef CONFIG_CPU_V7M
@@ -172,6 +195,7 @@ ENTRY(vector_swi)
 #else
 	sub	sp, sp, #PT_REGS_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
+3:
  ARM(	add	r8, sp, #S_PC		)
  ARM(	stmdb	r8, {sp, lr}^		)	@ Calling sp, lr
  THUMB(	mov	r8, sp			)
diff --git a/arch/arm/kernel/spectre.c b/arch/arm/kernel/spectre.c
new file mode 100644
index 0000000000000000000000000000000000000000..0dcefc36fb7a08af113ef923af1fe9c826da662d
--- /dev/null
+++ b/arch/arm/kernel/spectre.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/bpf.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+
+#include <asm/spectre.h>
+
+static bool _unprivileged_ebpf_enabled(void)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	return !sysctl_unprivileged_bpf_disabled;
+#else
+	return false;
+#endif
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+static unsigned int spectre_v2_state;
+static unsigned int spectre_v2_methods;
+
+void spectre_v2_update_state(unsigned int state, unsigned int method)
+{
+	if (state > spectre_v2_state)
+		spectre_v2_state = state;
+	spectre_v2_methods |= method;
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	const char *method;
+
+	if (spectre_v2_state == SPECTRE_UNAFFECTED)
+		return sprintf(buf, "%s\n", "Not affected");
+
+	if (spectre_v2_state != SPECTRE_MITIGATED)
+		return sprintf(buf, "%s\n", "Vulnerable");
+
+	if (_unprivileged_ebpf_enabled())
+		return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n");
+
+	switch (spectre_v2_methods) {
+	case SPECTRE_V2_METHOD_BPIALL:
+		method = "Branch predictor hardening";
+		break;
+
+	case SPECTRE_V2_METHOD_ICIALLU:
+		method = "I-cache invalidation";
+		break;
+
+	case SPECTRE_V2_METHOD_SMC:
+	case SPECTRE_V2_METHOD_HVC:
+		method = "Firmware call";
+		break;
+
+	case SPECTRE_V2_METHOD_LOOP8:
+		method = "History overwrite";
+		break;
+
+	default:
+		method = "Multiple mitigations";
+		break;
+	}
+
+	return sprintf(buf, "Mitigation: %s\n", method);
+}
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 17d5a785df28b10ee5714246d3ed342192c25e75..2d9e72ad1b0f923d8afafa49fd4e5cd5d1feadb6 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -30,6 +30,7 @@
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/exception.h>
+#include <asm/spectre.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
 #include <asm/ptrace.h>
@@ -806,10 +807,59 @@ static inline void __init kuser_init(void *vectors)
 }
 #endif
 
+#ifndef CONFIG_CPU_V7M
+static void copy_from_lma(void *vma, void *lma_start, void *lma_end)
+{
+	memcpy(vma, lma_start, lma_end - lma_start);
+}
+
+static void flush_vectors(void *vma, size_t offset, size_t size)
+{
+	unsigned long start = (unsigned long)vma + offset;
+	unsigned long end = start + size;
+
+	flush_icache_range(start, end);
+}
+
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+int spectre_bhb_update_vectors(unsigned int method)
+{
+	extern char __vectors_bhb_bpiall_start[], __vectors_bhb_bpiall_end[];
+	extern char __vectors_bhb_loop8_start[], __vectors_bhb_loop8_end[];
+	void *vec_start, *vec_end;
+
+	if (system_state > SYSTEM_SCHEDULING) {
+		pr_err("CPU%u: Spectre BHB workaround too late - system vulnerable\n",
+		       smp_processor_id());
+		return SPECTRE_VULNERABLE;
+	}
+
+	switch (method) {
+	case SPECTRE_V2_METHOD_LOOP8:
+		vec_start = __vectors_bhb_loop8_start;
+		vec_end = __vectors_bhb_loop8_end;
+		break;
+
+	case SPECTRE_V2_METHOD_BPIALL:
+		vec_start = __vectors_bhb_bpiall_start;
+		vec_end = __vectors_bhb_bpiall_end;
+		break;
+
+	default:
+		pr_err("CPU%u: unknown Spectre BHB state %d\n",
+		       smp_processor_id(), method);
+		return SPECTRE_VULNERABLE;
+	}
+
+	copy_from_lma(vectors_page, vec_start, vec_end);
+	flush_vectors(vectors_page, 0, vec_end - vec_start);
+
+	return SPECTRE_MITIGATED;
+}
+#endif
+
 void __init early_trap_init(void *vectors_base)
 {
-#ifndef CONFIG_CPU_V7M
-	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	unsigned i;
@@ -830,17 +880,20 @@ void __init early_trap_init(void *vectors_base)
 	 * into the vector page, mapped at 0xffff0000, and ensure these
 	 * are visible to the instruction stream.
 	 */
-	memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start);
-	memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start);
+	copy_from_lma(vectors_base, __vectors_start, __vectors_end);
+	copy_from_lma(vectors_base + 0x1000, __stubs_start, __stubs_end);
 
 	kuser_init(vectors_base);
 
-	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
+	flush_vectors(vectors_base, 0, PAGE_SIZE * 2);
+}
 #else /* ifndef CONFIG_CPU_V7M */
+void __init early_trap_init(void *vectors_base)
+{
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated
 	 * memory area. The address is configurable and so a table in the kernel
 	 * image can be used.
 	 */
-#endif
 }
+#endif
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 02692fbe2db5c599cf5945c42fb217b712d0b212..8b6fc72f2c050fda0b9140c1a621571f706f1d35 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -833,6 +833,7 @@ config CPU_BPREDICT_DISABLE
 
 config CPU_SPECTRE
 	bool
+	select GENERIC_CPU_VULNERABILITIES
 
 config HARDEN_BRANCH_PREDICTOR
 	bool "Harden the branch predictor against aliasing attacks" if EXPERT
@@ -853,6 +854,16 @@ config HARDEN_BRANCH_PREDICTOR
 
 	   If unsure, say Y.
 
+config HARDEN_BRANCH_HISTORY
+	bool "Harden Spectre style attacks against branch history" if EXPERT
+	depends on CPU_SPECTRE
+	default y
+	help
+	  Speculation attacks against some high-performance processors can
+	  make use of branch history to influence future speculation. When
+	  taking an exception, a sequence of branches overwrites the branch
+	  history, or branch history is invalidated.
+
 config TLS_REG_EMUL
 	bool
 	select NEED_KUSER_HELPERS
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 114c05ab4dd919a26064eda1f395f1c8f4119ec1..06dbfb968182de7c585e41308da09eec15360600 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -6,8 +6,35 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/proc-fns.h>
+#include <asm/spectre.h>
 #include <asm/system_misc.h>
 
+#ifdef CONFIG_ARM_PSCI
+static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void)
+{
+	struct arm_smccc_res res;
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
+			     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
+
+	switch ((int)res.a0) {
+	case SMCCC_RET_SUCCESS:
+		return SPECTRE_MITIGATED;
+
+	case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED:
+		return SPECTRE_UNAFFECTED;
+
+	default:
+		return SPECTRE_VULNERABLE;
+	}
+}
+#else
+static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void)
+{
+	return SPECTRE_VULNERABLE;
+}
+#endif
+
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn);
 
@@ -36,13 +63,61 @@ static void __maybe_unused call_hvc_arch_workaround_1(void)
 	arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
 }
 
-static void cpu_v7_spectre_init(void)
+static unsigned int spectre_v2_install_workaround(unsigned int method)
 {
 	const char *spectre_v2_method = NULL;
 	int cpu = smp_processor_id();
 
 	if (per_cpu(harden_branch_predictor_fn, cpu))
-		return;
+		return SPECTRE_MITIGATED;
+
+	switch (method) {
+	case SPECTRE_V2_METHOD_BPIALL:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_bpiall;
+		spectre_v2_method = "BPIALL";
+		break;
+
+	case SPECTRE_V2_METHOD_ICIALLU:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			harden_branch_predictor_iciallu;
+		spectre_v2_method = "ICIALLU";
+		break;
+
+	case SPECTRE_V2_METHOD_HVC:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			call_hvc_arch_workaround_1;
+		cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
+		spectre_v2_method = "hypervisor";
+		break;
+
+	case SPECTRE_V2_METHOD_SMC:
+		per_cpu(harden_branch_predictor_fn, cpu) =
+			call_smc_arch_workaround_1;
+		cpu_do_switch_mm = cpu_v7_smc_switch_mm;
+		spectre_v2_method = "firmware";
+		break;
+	}
+
+	if (spectre_v2_method)
+		pr_info("CPU%u: Spectre v2: using %s workaround\n",
+			smp_processor_id(), spectre_v2_method);
+
+	return SPECTRE_MITIGATED;
+}
+#else
+static unsigned int spectre_v2_install_workaround(unsigned int method)
+{
+	pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n",
+		smp_processor_id());
+
+	return SPECTRE_VULNERABLE;
+}
+#endif
+
+static void cpu_v7_spectre_v2_init(void)
+{
+	unsigned int state, method = 0;
 
 	switch (read_cpuid_part()) {
 	case ARM_CPU_PART_CORTEX_A8:
@@ -51,69 +126,133 @@ static void cpu_v7_spectre_init(void)
 	case ARM_CPU_PART_CORTEX_A17:
 	case ARM_CPU_PART_CORTEX_A73:
 	case ARM_CPU_PART_CORTEX_A75:
-		per_cpu(harden_branch_predictor_fn, cpu) =
-			harden_branch_predictor_bpiall;
-		spectre_v2_method = "BPIALL";
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_BPIALL;
 		break;
 
 	case ARM_CPU_PART_CORTEX_A15:
 	case ARM_CPU_PART_BRAHMA_B15:
-		per_cpu(harden_branch_predictor_fn, cpu) =
-			harden_branch_predictor_iciallu;
-		spectre_v2_method = "ICIALLU";
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_ICIALLU;
 		break;
 
-#ifdef CONFIG_ARM_PSCI
 	case ARM_CPU_PART_BRAHMA_B53:
 		/* Requires no workaround */
+		state = SPECTRE_UNAFFECTED;
 		break;
+
 	default:
 		/* Other ARM CPUs require no workaround */
-		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM)
+		if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) {
+			state = SPECTRE_UNAFFECTED;
 			break;
+		}
+
 		fallthrough;
-		/* Cortex A57/A72 require firmware workaround */
-	case ARM_CPU_PART_CORTEX_A57:
-	case ARM_CPU_PART_CORTEX_A72: {
-		struct arm_smccc_res res;
 
-		arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
-				     ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 != 0)
-			return;
+	/* Cortex A57/A72 require firmware workaround */
+	case ARM_CPU_PART_CORTEX_A57:
+	case ARM_CPU_PART_CORTEX_A72:
+		state = spectre_v2_get_cpu_fw_mitigation_state();
+		if (state != SPECTRE_MITIGATED)
+			break;
 
 		switch (arm_smccc_1_1_get_conduit()) {
 		case SMCCC_CONDUIT_HVC:
-			per_cpu(harden_branch_predictor_fn, cpu) =
-				call_hvc_arch_workaround_1;
-			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
-			spectre_v2_method = "hypervisor";
+			method = SPECTRE_V2_METHOD_HVC;
 			break;
 
 		case SMCCC_CONDUIT_SMC:
-			per_cpu(harden_branch_predictor_fn, cpu) =
-				call_smc_arch_workaround_1;
-			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
-			spectre_v2_method = "firmware";
+			method = SPECTRE_V2_METHOD_SMC;
 			break;
 
 		default:
+			state = SPECTRE_VULNERABLE;
 			break;
 		}
 	}
-#endif
+
+	if (state == SPECTRE_MITIGATED)
+		state = spectre_v2_install_workaround(method);
+
+	spectre_v2_update_state(state, method);
+}
+
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+static int spectre_bhb_method;
+
+static const char *spectre_bhb_method_name(int method)
+{
+	switch (method) {
+	case SPECTRE_V2_METHOD_LOOP8:
+		return "loop";
+
+	case SPECTRE_V2_METHOD_BPIALL:
+		return "BPIALL";
+
+	default:
+		return "unknown";
 	}
+}
 
-	if (spectre_v2_method)
-		pr_info("CPU%u: Spectre v2: using %s workaround\n",
-			smp_processor_id(), spectre_v2_method);
+static int spectre_bhb_install_workaround(int method)
+{
+	if (spectre_bhb_method != method) {
+		if (spectre_bhb_method) {
+			pr_err("CPU%u: Spectre BHB: method disagreement, system vulnerable\n",
+			       smp_processor_id());
+
+			return SPECTRE_VULNERABLE;
+		}
+
+		if (spectre_bhb_update_vectors(method) == SPECTRE_VULNERABLE)
+			return SPECTRE_VULNERABLE;
+
+		spectre_bhb_method = method;
+	}
+
+	pr_info("CPU%u: Spectre BHB: using %s workaround\n",
+		smp_processor_id(), spectre_bhb_method_name(method));
+
+	return SPECTRE_MITIGATED;
 }
 #else
-static void cpu_v7_spectre_init(void)
+static int spectre_bhb_install_workaround(int method)
 {
+	return SPECTRE_VULNERABLE;
 }
 #endif
 
+static void cpu_v7_spectre_bhb_init(void)
+{
+	unsigned int state, method = 0;
+
+	switch (read_cpuid_part()) {
+	case ARM_CPU_PART_CORTEX_A15:
+	case ARM_CPU_PART_BRAHMA_B15:
+	case ARM_CPU_PART_CORTEX_A57:
+	case ARM_CPU_PART_CORTEX_A72:
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_LOOP8;
+		break;
+
+	case ARM_CPU_PART_CORTEX_A73:
+	case ARM_CPU_PART_CORTEX_A75:
+		state = SPECTRE_MITIGATED;
+		method = SPECTRE_V2_METHOD_BPIALL;
+		break;
+
+	default:
+		state = SPECTRE_UNAFFECTED;
+		break;
+	}
+
+	if (state == SPECTRE_MITIGATED)
+		state = spectre_bhb_install_workaround(method);
+
+	spectre_v2_update_state(state, method);
+}
+
 static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned,
 						  u32 mask, const char *msg)
 {
@@ -142,16 +281,17 @@ static bool check_spectre_auxcr(bool *warned, u32 bit)
 void cpu_v7_ca8_ibe(void)
 {
 	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6)))
-		cpu_v7_spectre_init();
+		cpu_v7_spectre_v2_init();
 }
 
 void cpu_v7_ca15_ibe(void)
 {
 	if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0)))
-		cpu_v7_spectre_init();
+		cpu_v7_spectre_v2_init();
 }
 
 void cpu_v7_bugs_init(void)
 {
-	cpu_v7_spectre_init();
+	cpu_v7_spectre_v2_init();
+	cpu_v7_spectre_bhb_init();
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c505c3b5c97e1271d11067e1cf6a38f658c42cb4..09c41d56fe78dbf209a2717b485cb7ec8edc8d56 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1182,6 +1182,15 @@ 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 c7b9b859a8607908574b0bf6fbfed441d7999359..ef5e60d6d57709e7be6b1208efdfe700ae180670 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -106,6 +106,13 @@
 	hint	#20
 	.endm
 
+/*
+ * Clear Branch History instruction
+ */
+	.macro clearbhb
+	hint	#22
+	.endm
+
 /*
  * Speculation barrier
  */
@@ -763,4 +770,30 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 
 #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
+
+	/* 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
 #endif	/* __ASM_ASSEMBLER_H */
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 7faae6ff3ab4d5c27896305d609494cdb13d54e6..24ed6643da2660d7f2ae0381e7690942680771d4 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -25,6 +25,7 @@ struct cpuinfo_arm64 {
 	u64		reg_id_aa64dfr1;
 	u64		reg_id_aa64isar0;
 	u64		reg_id_aa64isar1;
+	u64		reg_id_aa64isar2;
 	u64		reg_id_aa64mmfr0;
 	u64		reg_id_aa64mmfr1;
 	u64		reg_id_aa64mmfr2;
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index e7d98997c09c3058dd0656af26528ebd220cd2bc..f42fd0a2e81c8ca260e278a3a7b74ccff605757c 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -66,7 +66,8 @@
 #define ARM64_HAS_TLB_RANGE			56
 #define ARM64_MTE				57
 #define ARM64_WORKAROUND_1508412		58
+#define ARM64_SPECTRE_BHB			59
 
-#define ARM64_NCAPS				59
+#define ARM64_NCAPS				60
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index da250e4741bd7ecd8a189d10dab5f18678d5040a..423f9b40e4d951a8403263cf2b7d4d9a40452487 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -606,6 +606,34 @@ 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);
+}
+
 static inline bool system_supports_32bit_el0(void)
 {
 	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index ef5b040dee44dff5bd9fd0011e56fa792833f4d9..7a58d54eec0fcd887770da8598e671f6a29f923b 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -72,6 +72,10 @@
 #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_A78C	0xD4B
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -109,6 +113,10 @@
 #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_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 4335800201c97ad1d22bc61ec2a3b12f498f2377..daff882883f92c956775b3a8cf15f560f2de2d56 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 4b39293d0f72dddb809c734aace5df8f80fdc669..d45b42295254d9ab4ad7da44e0070fb8732420cc 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_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 044bb9e2cd74f72347743f04e8d91b486b401dfb..ada24a20a5671db51522e6fcdbdd9e7c3b3edf59 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -35,6 +35,9 @@
 #define KVM_VECTOR_PREAMBLE	(2 * AARCH64_INSN_SIZE)
 
 #define __SMCCC_WORKAROUND_1_SMC_SZ 36
+#define __SMCCC_WORKAROUND_3_SMC_SZ 36
+#define __SPECTRE_BHB_LOOP_SZ       44
+#define __SPECTRE_BHB_CLEARBHB_SZ   12
 
 #define KVM_HOST_SMCCC_ID(id)						\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -199,6 +202,11 @@ extern void __vgic_v3_init_lrs(void);
 extern u32 __kvm_get_mdcr_el2(void);
 
 extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
+extern char __smccc_workaround_3_smc[__SMCCC_WORKAROUND_3_SMC_SZ];
+extern char __spectre_bhb_loop_k8[__SPECTRE_BHB_LOOP_SZ];
+extern char __spectre_bhb_loop_k24[__SPECTRE_BHB_LOOP_SZ];
+extern char __spectre_bhb_loop_k32[__SPECTRE_BHB_LOOP_SZ];
+extern char __spectre_bhb_clearbhb[__SPECTRE_BHB_LOOP_SZ];
 
 /*
  * Obtain the PC-relative address of a kernel symbol
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 331394306ccee34633d178dbec9c1800612ac910..47dafd6ab3a30abd5aef575a34950abca498295f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -237,7 +237,8 @@ static inline void *kvm_get_hyp_vector(void)
 	void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector));
 	int slot = -1;
 
-	if (cpus_have_const_cap(ARM64_SPECTRE_V2) && data->fn) {
+	if ((cpus_have_const_cap(ARM64_SPECTRE_V2) ||
+	     cpus_have_const_cap(ARM64_SPECTRE_BHB)) && data->template_start) {
 		vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
 		slot = data->hyp_vectors_slot;
 	}
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index c7315862e2435945e4ed71949b1c7ec4379fae00..bc151b7dc042cfd2f78c5d52d0de956df3844d5d 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -67,6 +67,12 @@ typedef void (*bp_hardening_cb_t)(void);
 struct bp_hardening_data {
 	int			hyp_vectors_slot;
 	bp_hardening_cb_t	fn;
+
+	/*
+	 * template_start is only used by the BHB mitigation to identify the
+	 * hyp_vectors_slot sequence.
+	 */
+	const char *template_start;
 };
 
 DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 3994169985efc62b2c84556934d31bd5c8c1cadd..6a45c26da46e351c690c64e2dfb9b76cab2a7505 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -19,4 +19,9 @@ extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_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 fcdfbce302bdfb9fec12cef198139b4814e9642d..4b3a5f050f71f946f8a8143733b99b1ee2ef75db 100644
--- a/arch/arm64/include/asm/spectre.h
+++ b/arch/arm64/include/asm/spectre.h
@@ -29,4 +29,8 @@ bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope);
 void spectre_v4_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
 void spectre_v4_enable_task_mitigation(struct task_struct *tsk);
 
+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	/* __ASM_SPECTRE_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 801861d054268a6aeefdda02c204ab2e5f37fec6..ecae3523d8634d466f0ccae1457e0931aabdcd79 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -175,6 +175,7 @@
 
 #define SYS_ID_AA64ISAR0_EL1		sys_reg(3, 0, 0, 6, 0)
 #define SYS_ID_AA64ISAR1_EL1		sys_reg(3, 0, 0, 6, 1)
+#define SYS_ID_AA64ISAR2_EL1		sys_reg(3, 0, 0, 6, 2)
 
 #define SYS_ID_AA64MMFR0_EL1		sys_reg(3, 0, 0, 7, 0)
 #define SYS_ID_AA64MMFR1_EL1		sys_reg(3, 0, 0, 7, 1)
@@ -687,6 +688,21 @@
 #define ID_AA64ISAR1_GPI_NI			0x0
 #define ID_AA64ISAR1_GPI_IMP_DEF		0x1
 
+/* id_aa64isar2 */
+#define ID_AA64ISAR2_CLEARBHB_SHIFT	28
+#define ID_AA64ISAR2_RPRES_SHIFT	4
+#define ID_AA64ISAR2_WFXT_SHIFT		0
+
+#define ID_AA64ISAR2_RPRES_8BIT		0x0
+#define ID_AA64ISAR2_RPRES_12BIT	0x1
+/*
+ * Value 0x1 has been removed from the architecture, and is
+ * reserved, but has not yet been removed from the ARM ARM
+ * as of ARM DDI 0487G.b.
+ */
+#define ID_AA64ISAR2_WFXT_NI		0x0
+#define ID_AA64ISAR2_WFXT_SUPPORTED	0x2
+
 /* id_aa64pfr0 */
 #define ID_AA64PFR0_CSV3_SHIFT		60
 #define ID_AA64PFR0_CSV2_SHIFT		56
@@ -786,6 +802,7 @@
 #endif
 
 /* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ECBHB_SHIFT	60
 #define ID_AA64MMFR1_ETS_SHIFT		36
 #define ID_AA64MMFR1_TWED_SHIFT		32
 #define ID_AA64MMFR1_XNX_SHIFT		28
diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h
new file mode 100644
index 0000000000000000000000000000000000000000..bc9a2145f4194e5d8bff099f36a9c1e9a568df91
--- /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	0ul
+#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 1c17c3a24411d6b0dfd33424d1b493d4750d0221..531ff62e82e959636b32e3d51da1e4d6cfd2c275 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -273,6 +273,11 @@ struct kvm_vcpu_events {
 #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 cafaf0da05b7c74c5a406c5d0e07a789732cdafa..533559c7d2b31bb3cb6db6af22c00d0dbf4d0225 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -473,6 +473,13 @@ 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 5001c43ea6c33a0b0efb624f3cf137623626b56b..ec8ed4fc3281fd9de0d924c3e7834cb12ab12d4a 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -65,11 +65,13 @@
 #include <linux/bsearch.h>
 #include <linux/cpumask.h>
 #include <linux/crash_dump.h>
+#include <linux/percpu.h>
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/cpu.h>
+
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -79,6 +81,7 @@
 #include <asm/processor.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 */
@@ -104,6 +107,8 @@ 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;
+
 /*
  * Flag to indicate if we have computed the system wide
  * capabilities based on the boot time active CPUs. This
@@ -205,6 +210,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 	ARM64_FTR_END,
 };
 
+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_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
@@ -596,6 +606,7 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 0, CRm = 6 */
 	ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
 	ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1),
+	ARM64_FTR_REG(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2),
 
 	/* Op1 = 0, CRn = 0, CRm = 7 */
 	ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0),
@@ -830,6 +841,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64DFR1_EL1, info->reg_id_aa64dfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0);
 	init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1);
+	init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1);
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
@@ -1058,6 +1070,8 @@ void update_cpu_features(int cpu,
 				      info->reg_id_aa64isar0, boot->reg_id_aa64isar0);
 	taint |= check_update_ftr_reg(SYS_ID_AA64ISAR1_EL1, cpu,
 				      info->reg_id_aa64isar1, boot->reg_id_aa64isar1);
+	taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu,
+				      info->reg_id_aa64isar2, boot->reg_id_aa64isar2);
 
 	/*
 	 * Differing PARange support is fine as long as all peripherals and
@@ -1157,6 +1171,7 @@ static u64 __read_sysreg_by_encoding(u32 sys_id)
 	read_sysreg_case(SYS_ID_AA64MMFR2_EL1);
 	read_sysreg_case(SYS_ID_AA64ISAR0_EL1);
 	read_sysreg_case(SYS_ID_AA64ISAR1_EL1);
+	read_sysreg_case(SYS_ID_AA64ISAR2_EL1);
 
 	read_sysreg_case(SYS_CNTFRQ_EL0);
 	read_sysreg_case(SYS_CTR_EL0);
@@ -1402,6 +1417,12 @@ 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/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 77605aec25fec843e6169c639b7f3b16392947d8..61204ba07799efea645c96e3a6fed4573517ff78 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -364,6 +364,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1);
 	info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1);
 	info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1);
+	info->reg_id_aa64isar2 = read_cpuid(ID_AA64ISAR2_EL1);
 	info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 	info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1);
 	info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index fe83d6d67ec3dc72ae9e3a3d07d4eb8e5149b7c7..d5bc1dbdd2fda84cd1e6e9508c07be5b41fae793 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -62,18 +62,21 @@
 
 	.macro kernel_ventry, el, label, regsize = 64
 	.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, #S_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
@@ -120,11 +123,15 @@ alternative_else_nop_endif
 	mrs	x0, tpidrro_el0
 #endif
 	b	el\()\el\()_\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
 
 	/*
@@ -141,7 +148,7 @@ 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\@:
@@ -351,21 +358,26 @@ 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, #S_FRAME_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, #S_FRAME_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, #S_FRAME_SIZE		// restore sp
+
 	/* Ensure any device/NC reads complete */
 	alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412
 
@@ -764,12 +776,6 @@ 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
@@ -803,12 +809,47 @@ 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
@@ -818,46 +859,75 @@ 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
+	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, #S_FRAME_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)
@@ -874,12 +944,56 @@ 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, sync_invalid			// Synchronous EL1t
+	kernel_ventry	1, irq_invalid			// IRQ EL1t
+	kernel_ventry	1, fiq_invalid			// FIQ EL1t
+	kernel_ventry	1, error_invalid		// Error EL1t
+
+	kernel_ventry	1, sync				// Synchronous EL1h
+	kernel_ventry	1, irq				// IRQ EL1h
+	kernel_ventry	1, fiq_invalid			// FIQ EL1h
+	kernel_ventry	1, 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:
@@ -969,13 +1083,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline)
 	 */
 1:	str	x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
 
-#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)
@@ -998,13 +1106,6 @@ 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 */
 
 /*
@@ -1112,7 +1213,7 @@ 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/proton-pack.c b/arch/arm64/kernel/proton-pack.c
index f6e4e3737405dea81ba0f21faa90050b1750e71a..5d5f2fa19c93e802c365856f2c4b0a0a60e3ecff 100644
--- a/arch/arm64/kernel/proton-pack.c
+++ b/arch/arm64/kernel/proton-pack.c
@@ -18,14 +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/insn.h>
 #include <asm/spectre.h>
 #include <asm/traps.h>
+#include <asm/vectors.h>
+#include <asm/virt.h>
 
 /*
  * We try to ensure that the mitigation state can never change as the result of
@@ -94,14 +98,51 @@ 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:
@@ -195,9 +236,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
+static DEFINE_RAW_SPINLOCK(bp_lock);
 static void install_bp_hardening_cb(bp_hardening_cb_t fn)
 {
-	static DEFINE_RAW_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
 	const char *hyp_vecs_start = __smccc_workaround_1_smc;
 	const char *hyp_vecs_end = __smccc_workaround_1_smc +
@@ -228,6 +269,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn)
 
 	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
 	__this_cpu_write(bp_hardening_data.fn, fn);
+	__this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start);
 	raw_spin_unlock(&bp_lock);
 }
 #else
@@ -571,9 +613,9 @@ 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;
 
@@ -787,3 +829,305 @@ 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;
+}
+
+/*
+ * 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_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();
+}
+
+#ifdef CONFIG_KVM
+static int kvm_bhb_get_vecs_size(const char *start)
+{
+	if (start == __smccc_workaround_3_smc)
+		return __SMCCC_WORKAROUND_3_SMC_SZ;
+	else if (start == __spectre_bhb_loop_k8 ||
+		 start == __spectre_bhb_loop_k24 ||
+		 start == __spectre_bhb_loop_k32)
+		return __SPECTRE_BHB_LOOP_SZ;
+	else if (start == __spectre_bhb_clearbhb)
+		return __SPECTRE_BHB_CLEARBHB_SZ;
+
+	return 0;
+}
+
+static void kvm_setup_bhb_slot(const char *hyp_vecs_start)
+{
+	int cpu, slot = -1, size;
+	const char *hyp_vecs_end;
+
+	if (!IS_ENABLED(CONFIG_KVM) || !is_hyp_mode_available())
+		return;
+
+	size = kvm_bhb_get_vecs_size(hyp_vecs_start);
+	if (WARN_ON_ONCE(!hyp_vecs_start || !size))
+		return;
+	hyp_vecs_end = hyp_vecs_start + size;
+
+	raw_spin_lock(&bp_lock);
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(bp_hardening_data.template_start, cpu) == hyp_vecs_start) {
+			slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu);
+			break;
+		}
+	}
+
+	if (slot == -1) {
+		slot = atomic_inc_return(&arm64_el2_vector_last_slot);
+		BUG_ON(slot >= BP_HARDEN_EL2_SLOTS);
+		__copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end);
+	}
+
+	__this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot);
+	__this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start);
+	raw_spin_unlock(&bp_lock);
+}
+#else
+#define __smccc_workaround_3_smc NULL
+#define __spectre_bhb_loop_k8 NULL
+#define __spectre_bhb_loop_k24 NULL
+#define __spectre_bhb_loop_k32 NULL
+#define __spectre_bhb_clearbhb NULL
+
+static void kvm_setup_bhb_slot(const char *hyp_vecs_start) { }
+#endif /* CONFIG_KVM */
+
+void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
+{
+	enum mitigation_state fw_state, state = SPECTRE_VULNERABLE;
+
+	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;
+	} else if (supports_clearbhb(SCOPE_LOCAL_CPU)) {
+		kvm_setup_bhb_slot(__spectre_bhb_clearbhb);
+		this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN);
+
+		state = SPECTRE_MITIGATED;
+	} else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) {
+		switch (spectre_bhb_loop_affected(SCOPE_SYSTEM)) {
+		case 8:
+			kvm_setup_bhb_slot(__spectre_bhb_loop_k8);
+			break;
+		case 24:
+			kvm_setup_bhb_slot(__spectre_bhb_loop_k24);
+			break;
+		case 32:
+			kvm_setup_bhb_slot(__spectre_bhb_loop_k32);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+		}
+		this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP);
+
+		state = SPECTRE_MITIGATED;
+	} else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) {
+		fw_state = spectre_bhb_get_cpu_fw_mitigation_state();
+		if (fw_state == SPECTRE_MITIGATED) {
+			kvm_setup_bhb_slot(__smccc_workaround_3_smc);
+			this_cpu_set_vectors(EL1_VECTOR_BHB_FW);
+
+			state = SPECTRE_MITIGATED;
+		}
+	}
+
+	update_mitigation_state(&spectre_bhb_state, state);
+}
+
+/* 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);
+}
+
+#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 30c102978942748b995d51729ca3a4e0b82dddba..71f4b5f24d15fafecae3f7f039b8677b3a37df33 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -299,7 +299,7 @@ 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
 /*
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 5bc978be804340a43d1835ab12058e4f15ca2ec5..4d63fcd7574b2c4a69ef81dd2a8c5be74e6cfcbe 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1337,7 +1337,8 @@ static int kvm_map_vectors(void)
 	 * !SV2 +  HEL2 -> allocate one vector slot and use exec mapping
 	 *  SV2 +  HEL2 -> use hardened vectors and use exec mapping
 	 */
-	if (cpus_have_const_cap(ARM64_SPECTRE_V2)) {
+	if (cpus_have_const_cap(ARM64_SPECTRE_V2) ||
+	    cpus_have_const_cap(ARM64_SPECTRE_BHB)) {
 		__kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
 		__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
 	}
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 0a5b36eb54b3e9e2fb17becf14644b29b6903e1c..99204c41f12016166b1a9bc115c4aa1f3864cd60 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -61,6 +61,10 @@ 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:
diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S
index b0441dbdf68bd012f84d9c4f25eac4824dddb417..533b0aa73256a07e92628014c3f723fe2730a541 100644
--- a/arch/arm64/kvm/hyp/smccc_wa.S
+++ b/arch/arm64/kvm/hyp/smccc_wa.S
@@ -30,3 +30,78 @@ SYM_DATA_START(__smccc_workaround_1_smc)
 1:	.org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
 	.org 1b
 SYM_DATA_END(__smccc_workaround_1_smc)
+
+	.global		__smccc_workaround_3_smc
+SYM_DATA_START(__smccc_workaround_3_smc)
+	esb
+	sub	sp, sp, #(8 * 4)
+	stp	x2, x3, [sp, #(8 * 0)]
+	stp	x0, x1, [sp, #(8 * 2)]
+	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_3
+	smc	#0
+	ldp	x2, x3, [sp, #(8 * 0)]
+	ldp	x0, x1, [sp, #(8 * 2)]
+	add	sp, sp, #(8 * 4)
+1:	.org __smccc_workaround_3_smc + __SMCCC_WORKAROUND_3_SMC_SZ
+	.org 1b
+SYM_DATA_END(__smccc_workaround_3_smc)
+
+	.global	__spectre_bhb_loop_k8
+SYM_DATA_START(__spectre_bhb_loop_k8)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov	x0, #8
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+1:	.org __spectre_bhb_loop_k8 + __SPECTRE_BHB_LOOP_SZ
+	.org 1b
+SYM_DATA_END(__spectre_bhb_loop_k8)
+
+	.global	__spectre_bhb_loop_k24
+SYM_DATA_START(__spectre_bhb_loop_k24)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov	x0, #24
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+1:	.org __spectre_bhb_loop_k24 + __SPECTRE_BHB_LOOP_SZ
+	.org 1b
+SYM_DATA_END(__spectre_bhb_loop_k24)
+
+	.global	__spectre_bhb_loop_k32
+SYM_DATA_START(__spectre_bhb_loop_k32)
+	esb
+	sub	sp, sp, #(8 * 2)
+	stp	x0, x1, [sp, #(8 * 0)]
+	mov	x0, #32
+2:	b	. + 4
+	subs	x0, x0, #1
+	b.ne	2b
+	dsb	nsh
+	isb
+	ldp	x0, x1, [sp, #(8 * 0)]
+	add	sp, sp, #(8 * 2)
+1:	.org __spectre_bhb_loop_k32 + __SPECTRE_BHB_LOOP_SZ
+	.org 1b
+SYM_DATA_END(__spectre_bhb_loop_k32)
+
+	.global	__spectre_bhb_clearbhb
+SYM_DATA_START(__spectre_bhb_clearbhb)
+	esb
+	clearbhb
+	isb
+1:	.org __spectre_bhb_clearbhb + __SPECTRE_BHB_CLEARBHB_SZ
+	.org 1b
+SYM_DATA_END(__spectre_bhb_clearbhb)
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 62546e20b25115ecac7a3c00f932cf8e8a60ad17..532e687f693660aa77cfc7b0d27aad3e26c0e244 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>
@@ -25,6 +26,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/processor.h>
 #include <asm/thread_info.h>
+#include <asm/vectors.h>
 
 const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n";
 
@@ -70,7 +72,7 @@ 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);
 
@@ -84,7 +86,10 @@ 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 25ea4ecb6449fb3c6475af75723092a815d1059d..bc111a1aff0324946820df88d7ac8a08d8554d30 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -58,6 +58,18 @@ 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 = SMCCC_RET_SUCCESS;
+				break;
+			case SPECTRE_UNAFFECTED:
+				val = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED;
+				break;
+			}
+			break;
 		case ARM_SMCCC_HV_PV_TIME_FEATURES:
 			val = SMCCC_RET_SUCCESS;
 			break;
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index db4056ecccfda9319233e7be71c27d8d9db16c84..20ba5136ac3ddab57ff5858a2825efa41925de54 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -397,7 +397,7 @@ 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)
@@ -411,6 +411,9 @@ 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;
 }
 
@@ -450,6 +453,17 @@ 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;
@@ -466,6 +480,7 @@ 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:
@@ -511,6 +526,7 @@ 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/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 568f11e23830c353944568186b47009801994a41..835fa036b2d541f91bdacd22ee9093d8e7a01b98 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1517,7 +1517,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	/* CRm=6 */
 	ID_SANITISED(ID_AA64ISAR0_EL1),
 	ID_SANITISED(ID_AA64ISAR1_EL1),
-	ID_UNALLOCATED(6,2),
+	ID_SANITISED(ID_AA64ISAR2_EL1),
 	ID_UNALLOCATED(6,3),
 	ID_UNALLOCATED(6,4),
 	ID_UNALLOCATED(6,5),
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 58dc93e566179ede33c58f41dc37b2a7d0faac96..104408d4c82af16efa47ffc41c19b2f821fcde97 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -592,6 +592,8 @@ 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);
 
@@ -600,11 +602,15 @@ 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/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c
index 529be35ac1782a62e9f18b71905fa597ea52a222..54d228acc0f5d9bac7b617cb2c36376abe1a0a42 100644
--- a/drivers/nfc/nfcmrvl/main.c
+++ b/drivers/nfc/nfcmrvl/main.c
@@ -194,6 +194,7 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv)
 {
 	struct nci_dev *ndev = priv->ndev;
 
+	nci_unregister_device(ndev);
 	if (priv->ndev->nfc_dev->fw_download_in_progress)
 		nfcmrvl_fw_dnld_abort(priv);
 
@@ -202,7 +203,6 @@ void nfcmrvl_nci_unregister_dev(struct nfcmrvl_private *priv)
 	if (gpio_is_valid(priv->config.reset_n_io))
 		gpio_free(priv->config.reset_n_io);
 
-	nci_unregister_device(ndev);
 	nci_free_device(ndev);
 	kfree(priv);
 }
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index f860645f6512833c602aea5f277e896a0cf9a442..ff38737475ecb85e294c0fea6b19c34bf7adee7d 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -87,6 +87,11 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x7fff)
 
+#define ARM_SMCCC_ARCH_WORKAROUND_3					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_32,				\
+			   0, 0x3fff)
+
 #define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED	1
 
 /* Paravirtualised time calls (defined by ARM DEN0057A) */
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 269ee89d2c2bed67fe1c7f7de7c1265b931daa92..4100aec3017d14174b0227266fdc76266bbfbff1 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev)
 {
 	ax25_dev *ax25_dev;
 	ax25_cb *s;
+	struct sock *sk;
 
 	if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL)
 		return;
@@ -85,11 +86,22 @@ static void ax25_kill_by_device(struct net_device *dev)
 again:
 	ax25_for_each(s, &ax25_list) {
 		if (s->ax25_dev == ax25_dev) {
-			s->ax25_dev = NULL;
+			sk = s->sk;
+			if (!sk) {
+				spin_unlock_bh(&ax25_list_lock);
+				s->ax25_dev = NULL;
+				ax25_disconnect(s, ENETUNREACH);
+				spin_lock_bh(&ax25_list_lock);
+				goto again;
+			}
+			sock_hold(sk);
 			spin_unlock_bh(&ax25_list_lock);
+			lock_sock(sk);
+			s->ax25_dev = NULL;
 			ax25_disconnect(s, ENETUNREACH);
+			release_sock(sk);
 			spin_lock_bh(&ax25_list_lock);
-
+			sock_put(sk);
 			/* The entry could have been deleted from the
 			 * list meanwhile and thus the next pointer is
 			 * no longer valid.  Play it safe and restart