diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 600fc40b313f702a6ee69aec7062849f52d0f02d..e0dc240946aa89d9493aff5429f5d7da7ffc9923 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -737,6 +737,11 @@ static __always_inline bool system_supports_fa64(void)
 		cpus_have_const_cap(ARM64_SME_FA64);
 }
 
+static __always_inline bool system_supports_tpidr2(void)
+{
+	return system_supports_sme();
+}
+
 static __always_inline bool system_supports_cnp(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_CNP) &&
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ff37d2d618d0491a83349d7d2265b6c5ef817093..37cb6c10d67bec77efd78cd6298fae8219b8194c 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -166,7 +166,7 @@ struct thread_struct {
 #endif
 	KABI_USE(1, unsigned int vl[ARM64_VEC_MAX])
 	KABI_USE(2, unsigned int vl_onexec[ARM64_VEC_MAX])
-	KABI_RESERVE(3)
+	KABI_USE(3, u64 tpidr2_el0)
 	KABI_RESERVE(4)
 	KABI_RESERVE(5)
 	KABI_RESERVE(6)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 0d1eb210fd4df5966160eb4a80d863fe04db88a2..1956bcc5713f817021327e6e6deb2751cb9a8ebf 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1086,6 +1086,10 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 	/* Allow SME in kernel */
 	write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1);
 	isb();
+
+	/* Allow EL0 to access TPIDR2 */
+	write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1);
+	isb();
 }
 
 /*
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7317c79db9e8ba2f2302894a34ba4b25887474a9..76fd6b2f50922734f66d8982504198d8d0f6e88f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -320,6 +320,9 @@ void show_regs(struct pt_regs * regs)
 static void tls_thread_flush(void)
 {
 	write_sysreg(0, tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(0, SYS_TPIDR2_EL0);
+
 
 	if (is_a32_compat_task()) {
 		current->thread.uw.tp_value = 0;
@@ -414,6 +417,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		 * out-of-sync with the saved value.
 		 */
 		*task_user_tls(p) = read_sysreg(tpidr_el0);
+		if (system_supports_tpidr2())
+			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 
 		if (stack_start) {
 			if (is_a32_compat_thread(task_thread_info(p)))
@@ -424,10 +429,12 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 		/*
 		 * If a TLS pointer was passed to clone, use it for the new
-		 * thread.
+		 * thread.  We also reset TPIDR2 if it's in use.
 		 */
-		if (clone_flags & CLONE_SETTLS)
+		if (clone_flags & CLONE_SETTLS) {
 			p->thread.uw.tp_value = tls;
+			p->thread.tpidr2_el0 = 0;
+		}
 	} else {
 		/*
 		 * A kthread has no context to ERET to, so ensure any buggy
@@ -453,6 +460,8 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 void tls_preserve_current_state(void)
 {
 	*task_user_tls(current) = read_sysreg(tpidr_el0);
+	if (system_supports_tpidr2() && !is_compat_task())
+		current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
 }
 
 static void tls_thread_switch(struct task_struct *next)
@@ -465,6 +474,8 @@ static void tls_thread_switch(struct task_struct *next)
 		write_sysreg(0, tpidrro_el0);
 
 	write_sysreg(*task_user_tls(next), tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
 }
 
 /*