diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 314fa5bc2655..f28853f80089 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -171,6 +171,7 @@ infrastructure:
 
 
   3) ID_AA64PFR1_EL1 - Processor Feature Register 1
+
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
@@ -181,6 +182,7 @@ infrastructure:
 
 
   4) MIDR_EL1 - Main ID Register
+
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 7ae54d7d333a..9f0ec21d6327 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -58,6 +58,7 @@ struct arch_timer_erratum_workaround {
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
 	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
+	bool disable_compat_vdso;
 };
 
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2e7e0f452301..4d867c6446c4 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -67,7 +67,7 @@ extern bool arm64_use_ng_mappings;
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h
index df6ea65c1dec..b054d9febfb5 100644
--- a/arch/arm64/include/asm/vdso/clocksource.h
+++ b/arch/arm64/include/asm/vdso/clocksource.h
@@ -2,7 +2,10 @@
 #ifndef __ASM_VDSOCLOCKSOURCE_H
 #define __ASM_VDSOCLOCKSOURCE_H
 
-#define VDSO_ARCH_CLOCKMODES	\
-	VDSO_CLOCKMODE_ARCHTIMER
+#define VDSO_ARCH_CLOCKMODES					\
+	/* vdso clocksource for both 32 and 64bit tasks */	\
+	VDSO_CLOCKMODE_ARCHTIMER,				\
+	/* vdso clocksource for 64bit tasks only */		\
+	VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT
 
 #endif
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index b6907ae78e53..9a625e8947ff 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -111,7 +111,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
 	 * update. Return something. Core will do another round and then
 	 * see the mode change and fallback to the syscall.
 	 */
-	if (clock_mode == VDSO_CLOCKMODE_NONE)
+	if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
 		return 0;
 
 	/*
@@ -152,6 +152,12 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
 	return ret;
 }
 
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+}
+#define vdso_clocksource_ok	vdso_clocksource_ok
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef1b1e7..73039949b5ce 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature)
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 8e302dc093d0..79728bfb5351 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -782,6 +782,7 @@ static const struct midr_range erratum_1463225[] = {
 	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
 	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
 	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
+	{},
 };
 #endif
 
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3dbdf9752b11..d3be9dbf5490 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -57,7 +57,7 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
 	/*
 	 * The CPU masked interrupts, and we are leaving them masked during
 	 * do_debug_exception(). Update PMR as if we had called
-	 * local_mask_daif().
+	 * local_daif_mask().
 	 */
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5304d193c79d..35de8ba60e3d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -126,8 +126,10 @@ alternative_else_nop_endif
 	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
-	// This macro corrupts x0-x3. It is the caller's duty
-	// to save/restore them if required.
+	/*
+	 * This macro corrupts x0-x3. It is the caller's duty  to save/restore
+	 * them if required.
+	 */
 	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
@@ -167,13 +169,28 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	.if	\regsize == 32
+	/*
+	 * If we're returning from a 32-bit task on a system affected by
+	 * 1418040 then re-enable userspace access to the virtual counter.
+	 */
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
 	msr	sp_el0, tsk
 
-	// Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
-	// when scheduling.
+	/*
+	 * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
+	 * when scheduling.
+	 */
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
@@ -320,6 +337,14 @@ alternative_else_nop_endif
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
@@ -331,21 +356,6 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if_not ARM64_WORKAROUND_1418040
-	b	4f
-alternative_else_nop_endif
-	/*
-	 * if (x22.mode32 == cntkctl_el1.el0vcten)
-	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
-	 */
-	mrs	x1, cntkctl_el1
-	eon	x0, x1, x22, lsr #3
-	tbz	x0, #1, 4f
-	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x1
-4:
-#endif
 	scs_save tsk, x0
 
 	/* No kernel C function calls after this as user keys are set. */
@@ -377,11 +387,11 @@ alternative_else_nop_endif
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	5f
+	bne	4f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-5:
+4:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 43119922341f..1a157ca33262 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ecf7b7db2d05..6c3e84180146 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -480,6 +480,14 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.set_next_event_virt = erratum_set_next_event_tval_virt,
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+	{
+		.match_type = ate_match_local_cap_id,
+		.id = (void *)ARM64_WORKAROUND_1418040,
+		.desc = "ARM erratum 1418040",
+		.disable_compat_vdso = true,
+	},
+#endif
 };
 
 typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *,
@@ -566,6 +574,9 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 	if (wa->read_cntvct_el0) {
 		clocksource_counter.vdso_clock_mode = VDSO_CLOCKMODE_NONE;
 		vdso_default = VDSO_CLOCKMODE_NONE;
+	} else if (wa->disable_compat_vdso && vdso_default != VDSO_CLOCKMODE_NONE) {
+		vdso_default = VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT;
+		clocksource_counter.vdso_clock_mode = vdso_default;
 	}
 }
 
diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c
index 873841af8d57..3d6ba425dbb9 100644
--- a/drivers/firmware/psci/psci_checker.c
+++ b/drivers/firmware/psci/psci_checker.c
@@ -157,8 +157,10 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups)
 
 	cpu_groups = kcalloc(nb_available_cpus, sizeof(cpu_groups),
 			     GFP_KERNEL);
-	if (!cpu_groups)
+	if (!cpu_groups) {
+		free_cpumask_var(tmp);
 		return -ENOMEM;
+	}
 
 	cpumask_copy(tmp, cpu_online_mask);
 
@@ -167,6 +169,7 @@ static int alloc_init_cpu_groups(cpumask_var_t **pcpu_groups)
 			topology_core_cpumask(cpumask_any(tmp));
 
 		if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) {
+			free_cpumask_var(tmp);
 			free_cpu_groups(num_groups, &cpu_groups);
 			return -ENOMEM;
 		}
@@ -196,13 +199,12 @@ static int hotplug_tests(void)
 	if (!page_buf)
 		goto out_free_cpu_groups;
 
-	err = 0;
 	/*
 	 * Of course the last CPU cannot be powered down and cpu_down() should
 	 * refuse doing that.
 	 */
 	pr_info("Trying to turn off and on again all CPUs\n");
-	err += down_and_up_cpus(cpu_online_mask, offlined_cpus);
+	err = down_and_up_cpus(cpu_online_mask, offlined_cpus);
 
 	/*
 	 * Take down CPUs by cpu group this time. When the last CPU is turned