Merge branches 'fixes' and 'ioremap' into for-linus

23 files changed, 646 insertions, 470 deletions

diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 8b839558838e..19de7537e7d3 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -36,12 +36,6 @@ EXPORT_SYMBOL(acpi_disabled);
 int acpi_pci_disabled = 1;	/* skip ACPI PCI scan and IRQ initialization */
 EXPORT_SYMBOL(acpi_pci_disabled);
 
-/* Processors with enabled flag and sane MPIDR */
-static int enabled_cpus;
-
-/* Boot CPU is valid or not in MADT */
-static bool bootcpu_valid  __initdata;
-
 static bool param_acpi_off __initdata;
 static bool param_acpi_force __initdata;
 
@@ -95,122 +89,15 @@ void __init __acpi_unmap_table(char *map, unsigned long size)
 	early_memunmap(map, size);
 }
 
-/**
- * acpi_map_gic_cpu_interface - generates a logical cpu number
- * and map to MPIDR represented by GICC structure
- */
-static void __init
-acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+bool __init acpi_psci_present(void)
 {
-	int i;
-	u64 mpidr = processor->arm_mpidr & MPIDR_HWID_BITMASK;
-	bool enabled = !!(processor->flags & ACPI_MADT_ENABLED);
-
-	if (mpidr == INVALID_HWID) {
-		pr_info("Skip MADT cpu entry with invalid MPIDR\n");
-		return;
-	}
-
-	total_cpus++;
-	if (!enabled)
-		return;
-
-	if (enabled_cpus >=  NR_CPUS) {
-		pr_warn("NR_CPUS limit of %d reached, Processor %d/0x%llx ignored.\n",
-			NR_CPUS, total_cpus, mpidr);
-		return;
-	}
-
-	/* Check if GICC structure of boot CPU is available in the MADT */
-	if (cpu_logical_map(0) == mpidr) {
-		if (bootcpu_valid) {
-			pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
-			       mpidr);
-			return;
-		}
-
-		bootcpu_valid = true;
-	}
-
-	/*
-	 * Duplicate MPIDRs are a recipe for disaster. Scan
-	 * all initialized entries and check for
-	 * duplicates. If any is found just ignore the CPU.
-	 */
-	for (i = 1; i < enabled_cpus; i++) {
-		if (cpu_logical_map(i) == mpidr) {
-			pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n",
-			       mpidr);
-			return;
-		}
-	}
-
-	if (!acpi_psci_present())
-		return;
-
-	cpu_ops[enabled_cpus] = cpu_get_ops("psci");
-	/* CPU 0 was already initialized */
-	if (enabled_cpus) {
-		if (!cpu_ops[enabled_cpus])
-			return;
-
-		if (cpu_ops[enabled_cpus]->cpu_init(NULL, enabled_cpus))
-			return;
-
-		/* map the logical cpu id to cpu MPIDR */
-		cpu_logical_map(enabled_cpus) = mpidr;
-	}
-
-	enabled_cpus++;
+	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT;
 }
 
-static int __init
-acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
-				const unsigned long end)
+/* Whether HVC must be used instead of SMC as the PSCI conduit */
+bool __init acpi_psci_use_hvc(void)
 {
-	struct acpi_madt_generic_interrupt *processor;
-
-	processor = (struct acpi_madt_generic_interrupt *)header;
-
-	if (BAD_MADT_ENTRY(processor, end))
-		return -EINVAL;
-
-	acpi_table_print_madt_entry(header);
-	acpi_map_gic_cpu_interface(processor);
-	return 0;
-}
-
-/* Parse GIC cpu interface entries in MADT for SMP init */
-void __init acpi_init_cpus(void)
-{
-	int count, i;
-
-	/*
-	 * do a partial walk of MADT to determine how many CPUs
-	 * we have including disabled CPUs, and get information
-	 * we need for SMP init
-	 */
-	count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
-			acpi_parse_gic_cpu_interface, 0);
-
-	if (!count) {
-		pr_err("No GIC CPU interface entries present\n");
-		return;
-	} else if (count < 0) {
-		pr_err("Error parsing GIC CPU interface entry\n");
-		return;
-	}
-
-	if (!bootcpu_valid) {
-		pr_err("MADT missing boot CPU MPIDR, not enabling secondaries\n");
-		return;
-	}
-
-	for (i = 0; i < enabled_cpus; i++)
-		set_cpu_possible(i, true);
-
-	/* Make boot-up look pretty */
-	pr_info("%d CPUs enabled, %d CPUs total\n", enabled_cpus, total_cpus);
+	return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC;
 }
 
 /*
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 28f8365edc4c..221b98312f0c 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -24,8 +24,13 @@
 #include <asm/cacheflush.h>
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 #include <linux/stop_machine.h>
 
+#define __ALT_PTR(a,f)		(u32 *)((void *)&(a)->f + (a)->f)
+#define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
+#define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
+
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 
 struct alt_region {
@@ -33,13 +38,63 @@ struct alt_region {
 	struct alt_instr *end;
 };
 
+/*
+ * Check if the target PC is within an alternative block.
+ */
+static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
+{
+	unsigned long replptr;
+
+	if (kernel_text_address(pc))
+		return 1;
+
+	replptr = (unsigned long)ALT_REPL_PTR(alt);
+	if (pc >= replptr && pc <= (replptr + alt->alt_len))
+		return 0;
+
+	/*
+	 * Branching into *another* alternate sequence is doomed, and
+	 * we're not even trying to fix it up.
+	 */
+	BUG();
+}
+
+static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
+{
+	u32 insn;
+
+	insn = le32_to_cpu(*altinsnptr);
+
+	if (aarch64_insn_is_branch_imm(insn)) {
+		s32 offset = aarch64_get_branch_offset(insn);
+		unsigned long target;
+
+		target = (unsigned long)altinsnptr + offset;
+
+		/*
+		 * If we're branching inside the alternate sequence,
+		 * do not rewrite the instruction, as it is already
+		 * correct. Otherwise, generate the new instruction.
+		 */
+		if (branch_insn_requires_update(alt, target)) {
+			offset = target - (unsigned long)insnptr;
+			insn = aarch64_set_branch_offset(insn, offset);
+		}
+	}
+
+	return insn;
+}
+
 static int __apply_alternatives(void *alt_region)
 {
 	struct alt_instr *alt;
 	struct alt_region *region = alt_region;
-	u8 *origptr, *replptr;
+	u32 *origptr, *replptr;
 
 	for (alt = region->begin; alt < region->end; alt++) {
+		u32 insn;
+		int i, nr_inst;
+
 		if (!cpus_have_cap(alt->cpufeature))
 			continue;
 
@@ -47,11 +102,17 @@ static int __apply_alternatives(void *alt_region)
 
 		pr_info_once("patching kernel code\n");
 
-		origptr = (u8 *)&alt->orig_offset + alt->orig_offset;
-		replptr = (u8 *)&alt->alt_offset + alt->alt_offset;
-		memcpy(origptr, replptr, alt->alt_len);
+		origptr = ALT_ORIG_PTR(alt);
+		replptr = ALT_REPL_PTR(alt);
+		nr_inst = alt->alt_len / sizeof(insn);
+
+		for (i = 0; i < nr_inst; i++) {
+			insn = get_alt_insn(alt, origptr + i, replptr + i);
+			*(origptr + i) = cpu_to_le32(insn);
+		}
+
 		flush_icache_range((uintptr_t)origptr,
-				   (uintptr_t)(origptr + alt->alt_len));
+				   (uintptr_t)(origptr + nr_inst));
 	}
 
 	return 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index da675cc5dfae..c99701a34d7b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -127,7 +127,6 @@ int main(void)
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
   DEFINE(VGIC_SAVE_FN,		offsetof(struct vgic_sr_vectors, save_vgic));
   DEFINE(VGIC_RESTORE_FN,	offsetof(struct vgic_sr_vectors, restore_vgic));
-  DEFINE(VGIC_SR_VECTOR_SZ,	sizeof(struct vgic_sr_vectors));
   DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
   DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
   DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index fb8ff9ba467a..5ea337dd2f15 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -16,11 +16,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <asm/cpu_ops.h>
-#include <asm/smp_plat.h>
+#include <linux/acpi.h>
 #include <linux/errno.h>
 #include <linux/of.h>
 #include <linux/string.h>
+#include <asm/acpi.h>
+#include <asm/cpu_ops.h>
+#include <asm/smp_plat.h>
 
 extern const struct cpu_operations smp_spin_table_ops;
 extern const struct cpu_operations cpu_psci_ops;
@@ -35,7 +37,7 @@ static const struct cpu_operations *supported_cpu_ops[] __initconst = {
 	NULL,
 };
 
-const struct cpu_operations * __init cpu_get_ops(const char *name)
+static const struct cpu_operations * __init cpu_get_ops(const char *name)
 {
 	const struct cpu_operations **ops = supported_cpu_ops;
 
@@ -49,39 +51,53 @@ const struct cpu_operations * __init cpu_get_ops(const char *name)
 	return NULL;
 }
 
+static const char *__init cpu_read_enable_method(int cpu)
+{
+	const char *enable_method;
+
+	if (acpi_disabled) {
+		struct device_node *dn = of_get_cpu_node(cpu, NULL);
+
+		if (!dn) {
+			if (!cpu)
+				pr_err("Failed to find device node for boot cpu\n");
+			return NULL;
+		}
+
+		enable_method = of_get_property(dn, "enable-method", NULL);
+		if (!enable_method) {
+			/*
+			 * The boot CPU may not have an enable method (e.g.
+			 * when spin-table is used for secondaries).
+			 * Don't warn spuriously.
+			 */
+			if (cpu != 0)
+				pr_err("%s: missing enable-method property\n",
+					dn->full_name);
+		}
+	} else {
+		enable_method = acpi_get_enable_method(cpu);
+		if (!enable_method)
+			pr_err("Unsupported ACPI enable-method\n");
+	}
+
+	return enable_method;
+}
 /*
- * Read a cpu's enable method from the device tree and record it in cpu_ops.
+ * Read a cpu's enable method and record it in cpu_ops.
  */
-int __init cpu_read_ops(struct device_node *dn, int cpu)
+int __init cpu_read_ops(int cpu)
 {
-	const char *enable_method = of_get_property(dn, "enable-method", NULL);
-	if (!enable_method) {
-		/*
-		 * The boot CPU may not have an enable method (e.g. when
-		 * spin-table is used for secondaries). Don't warn spuriously.
-		 */
-		if (cpu != 0)
-			pr_err("%s: missing enable-method property\n",
-				dn->full_name);
-		return -ENOENT;
-	}
+	const char *enable_method = cpu_read_enable_method(cpu);
+
+	if (!enable_method)
+		return -ENODEV;
 
 	cpu_ops[cpu] = cpu_get_ops(enable_method);
 	if (!cpu_ops[cpu]) {
-		pr_warn("%s: unsupported enable-method property: %s\n",
-			dn->full_name, enable_method);
+		pr_warn("Unsupported enable-method: %s\n", enable_method);
 		return -EOPNOTSUPP;
 	}
 
 	return 0;
 }
-
-void __init cpu_read_bootcpu_ops(void)
-{
-	struct device_node *dn = of_get_cpu_node(0, NULL);
-	if (!dn) {
-		pr_err("Failed to find device node for boot cpu\n");
-		return;
-	}
-	cpu_read_ops(dn, 0);
-}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 3d9967e43d89..5ad86ceac010 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -22,7 +22,23 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
+static bool
+has_id_aa64pfr0_feature(const struct arm64_cpu_capabilities *entry)
+{
+	u64 val;
+
+	val = read_cpuid(id_aa64pfr0_el1);
+	return (val & entry->register_mask) == entry->register_value;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
+	{
+		.desc = "GIC system register CPU interface",
+		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
+		.matches = has_id_aa64pfr0_feature,
+		.register_mask = (0xf << 24),
+		.register_value = (1 << 24),
+	},
 	{},
 };
 
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index a78143a5c99f..7ce589ca54a4 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -18,15 +18,10 @@
 int arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
-	struct device_node *cpu_node = of_cpu_device_node_get(cpu);
-
-	if (!cpu_node)
-		return -ENODEV;
 
 	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
-		ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu);
+		ret = cpu_ops[cpu]->cpu_init_idle(cpu);
 
-	of_node_put(cpu_node);
 	return ret;
 }
 
@@ -37,7 +32,7 @@ int arm_cpuidle_init(unsigned int cpu)
  * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
  * operations back-end error code otherwise.
  */
-int cpu_suspend(unsigned long arg)
+int arm_cpuidle_suspend(int index)
 {
 	int cpu = smp_processor_id();
 
@@ -47,5 +42,5 @@ int cpu_suspend(unsigned long arg)
 	 */
 	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend)
 		return -EOPNOTSUPP;
-	return cpu_ops[cpu]->cpu_suspend(arg);
+	return cpu_ops[cpu]->cpu_suspend(index);
 }
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index ab21e0d58278..9d4aa18f2a82 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -158,6 +158,7 @@ static __init int is_reserve_region(efi_memory_desc_t *md)
 	case EFI_BOOT_SERVICES_CODE:
 	case EFI_BOOT_SERVICES_DATA:
 	case EFI_CONVENTIONAL_MEMORY:
+	case EFI_PERSISTENT_MEMORY:
 		return 0;
 	default:
 		break;
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 959fe8733560..a7691a378668 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -21,7 +21,7 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
@@ -124,21 +124,24 @@
 	msr	sp_el0, x23
 
 #ifdef CONFIG_ARM64_ERRATUM_845719
-	alternative_insn						\
-	"nop",								\
-	"tbz x22, #4, 1f",						\
-	ARM64_WORKAROUND_845719
+
+#undef SEQUENCE_ORG
+#undef SEQUENCE_ALT
+
 #ifdef CONFIG_PID_IN_CONTEXTIDR
-	alternative_insn						\
-	"nop; nop",							\
-	"mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:",		\
-	ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG	"nop ; nop ; nop"
+#define SEQUENCE_ALT	"tbz x22, #4, 1f ; mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:"
+
 #else
-	alternative_insn						\
-	"nop",								\
-	"msr contextidr_el1, xzr; 1:",					\
-	ARM64_WORKAROUND_845719
+
+#define SEQUENCE_ORG	"nop ; nop"
+#define SEQUENCE_ALT	"tbz x22, #4, 1f ; msr contextidr_el1, xzr; 1:"
+
 #endif
+
+	alternative_insn SEQUENCE_ORG, SEQUENCE_ALT, ARM64_WORKAROUND_845719
+
 #endif
 	.endif
 	msr	elr_el1, x21			// set up the return data
@@ -517,6 +520,7 @@ el0_sp_pc:
 	mrs	x26, far_el1
 	// enable interrupts before calling the main handler
 	enable_dbg_and_irq
+	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -608,11 +612,16 @@ ENDPROC(cpu_switch_to)
  */
 ret_fast_syscall:
 	disable_irq				// disable interrupts
-	ldr	x1, [tsk, #TI_FLAGS]
+	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
+	and	x2, x1, #_TIF_SYSCALL_WORK
+	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, fast_work_pending
 	enable_step_tsk x1, x2
 	kernel_exit 0, ret = 1
+ret_fast_syscall_trace:
+	enable_irq				// enable interrupts
+	b	__sys_trace_return
 
 /*
  * Ok, we need to do extra processing, enter the slow path.
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 3dca15634e69..44d6f7545505 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -296,6 +297,35 @@ static void fpsimd_pm_init(void)
 static inline void fpsimd_pm_init(void) { }
 #endif /* CONFIG_CPU_PM */
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb,
+				       unsigned long action,
+				       void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		per_cpu(fpsimd_last_state, cpu) = NULL;
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block fpsimd_cpu_hotplug_notifier_block = {
+	.notifier_call = fpsimd_cpu_hotplug_notifier,
+};
+
+static inline void fpsimd_hotplug_init(void)
+{
+	register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block);
+}
+
+#else
+static inline void fpsimd_hotplug_init(void) { }
+#endif
+
 /*
  * FP/SIMD support code initialisation.
  */
@@ -315,6 +345,7 @@ static int __init fpsimd_init(void)
 		elf_hwcap |= HWCAP_ASIMD;
 
 	fpsimd_pm_init();
+	fpsimd_hotplug_init();
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 19f915e8f6e0..c0ff3ce4299e 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -237,8 +237,6 @@ ENTRY(stext)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
-
-	bl	__vet_fdt
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -270,24 +268,6 @@ preserve_boot_args:
 ENDPROC(preserve_boot_args)
 
 /*
- * Determine validity of the x21 FDT pointer.
- * The dtb must be 8-byte aligned and live in the first 512M of memory.
- */
-__vet_fdt:
-	tst	x21, #0x7
-	b.ne	1f
-	cmp	x21, x24
-	b.lt	1f
-	mov	x0, #(1 << 29)
-	add	x0, x0, x24
-	cmp	x21, x0
-	b.ge	1f
-	ret
-1:
-	mov	x21, #0
-	ret
-ENDPROC(__vet_fdt)
-/*
  * Macro to create a table entry to the next page.
  *
  *	tbl:	page table address
@@ -348,8 +328,7 @@ ENDPROC(__vet_fdt)
  * required to get the kernel running. The following sections are required:
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
- *     been enabled, including the FDT blob (TTBR1)
- *   - pgd entry for fixed mappings (TTBR1)
+ *     been enabled
  */
 __create_page_tables:
 	adrp	x25, idmap_pg_dir
@@ -382,7 +361,7 @@ __create_page_tables:
 	 * Create the identity mapping.
 	 */
 	mov	x0, x25				// idmap_pg_dir
-	adrp	x3, KERNEL_START		// __pa(KERNEL_START)
+	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
 #ifndef CONFIG_ARM64_VA_BITS_48
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
@@ -405,11 +384,11 @@ __create_page_tables:
 
 	/*
 	 * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
-	 * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used),
+	 * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
 	 * this number conveniently equals the number of leading zeroes in
-	 * the physical address of KERNEL_END.
+	 * the physical address of __idmap_text_end.
 	 */
-	adrp	x5, KERNEL_END
+	adrp	x5, __idmap_text_end
 	clz	x5, x5
 	cmp	x5, TCR_T0SZ(VA_BITS)	// default T0SZ small enough?
 	b.ge	1f			// .. then skip additional level
@@ -424,8 +403,8 @@ __create_page_tables:
 #endif
 
 	create_pgd_entry x0, x3, x5, x6
-	mov	x5, x3				// __pa(KERNEL_START)
-	adr_l	x6, KERNEL_END			// __pa(KERNEL_END)
+	mov	x5, x3				// __pa(__idmap_text_start)
+	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
@@ -439,22 +418,6 @@ __create_page_tables:
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
-	 * Map the FDT blob (maximum 2MB; must be within 512MB of
-	 * PHYS_OFFSET).
-	 */
-	mov	x3, x21				// FDT phys address
-	and	x3, x3, #~((1 << 21) - 1)	// 2MB aligned
-	mov	x6, #PAGE_OFFSET
-	sub	x5, x3, x24			// subtract PHYS_OFFSET
-	tst	x5, #~((1 << 29) - 1)		// within 512MB?
-	csel	x21, xzr, x21, ne		// zero the FDT pointer
-	b.ne	1f
-	add	x5, x5, x6			// __va(FDT blob)
-	add	x6, x5, #1 << 21		// 2MB for the FDT blob
-	sub	x6, x6, #1			// inclusive range
-	create_block_map x0, x7, x3, x5, x6
-1:
-	/*
 	 * Since the page tables have been populated with non-cacheable
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
@@ -669,6 +632,7 @@ ENDPROC(__secondary_switched)
  *
  * other registers depend on the function called upon completion
  */
+	.section	".idmap.text", "ax"
 __enable_mmu:
 	ldr	x5, =vectors
 	msr	vbar_el1, x5
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 924902083e47..dd9671cd0bb2 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -77,6 +77,14 @@ bool __kprobes aarch64_insn_is_nop(u32 insn)
 	}
 }
 
+bool aarch64_insn_is_branch_imm(u32 insn)
+{
+	return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) ||
+		aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) ||
+		aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+		aarch64_insn_is_bcond(insn));
+}
+
 static DEFINE_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap)
@@ -1057,6 +1065,58 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift);
 }
 
+/*
+ * Decode the imm field of a branch, and return the byte offset as a
+ * signed value (so it can be used when computing a new branch
+ * target).
+ */
+s32 aarch64_get_branch_offset(u32 insn)
+{
+	s32 imm;
+
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn);
+		return (imm << 6) >> 4;
+	}
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn);
+		return (imm << 13) >> 11;
+	}
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) {
+		imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn);
+		return (imm << 18) >> 16;
+	}
+
+	/* Unhandled instruction */
+	BUG();
+}
+
+/*
+ * Encode the displacement of a branch in the imm field and return the
+ * updated instruction.
+ */
+u32 aarch64_set_branch_offset(u32 insn, s32 offset)
+{
+	if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
+	    aarch64_insn_is_bcond(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
+						     offset >> 2);
+
+	if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn))
+		return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn,
+						     offset >> 2);
+
+	/* Unhandled instruction */
+	BUG();
+}
+
 bool aarch32_insn_is_wide(u32 insn)
 {
 	return insn >= 0xe800;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cce18c85d2e8..702591f6180a 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -488,7 +488,7 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 			}
 
 			err = request_irq(irq, armpmu->handle_irq,
-					IRQF_NOBALANCING,
+					IRQF_NOBALANCING | IRQF_NO_THREAD,
 					"arm-pmu", armpmu);
 			if (err) {
 				pr_err("unable to request IRQ%d for ARM PMU counters\n",
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c6b1f3b96f45..223b093c9440 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -58,14 +58,6 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-void soft_restart(unsigned long addr)
-{
-	setup_mm_for_reboot();
-	cpu_soft_restart(virt_to_phys(cpu_reset), addr);
-	/* Should never get here */
-	BUG();
-}
-
 /*
  * Function pointers to optional machine specific functions
  */
@@ -136,9 +128,7 @@ void machine_power_off(void)
 
 /*
  * Restart requires that the secondary CPUs stop performing any activity
- * while the primary CPU resets the system. Systems with a single CPU can
- * use soft_restart() as their machine descriptor's .restart hook, since that
- * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * while the primary CPU resets the system. Systems with multiple CPUs must
  * provide a HW restart implementation, to ensure that all CPUs reset at once.
  * This is required so that any code running after reset on the primary CPU
  * doesn't have to co-ordinate with other CPUs to ensure they aren't still
@@ -243,7 +233,8 @@ void release_thread(struct task_struct *dead_task)
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	fpsimd_preserve_current_state();
+	if (current->mm)
+		fpsimd_preserve_current_state();
 	*dst = *src;
 	return 0;
 }
@@ -254,35 +245,35 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		unsigned long stk_sz, struct task_struct *p)
 {
 	struct pt_regs *childregs = task_pt_regs(p);
-	unsigned long tls = p->thread.tp_value;
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->regs[0] = 0;
-		if (is_compat_thread(task_thread_info(p))) {
-			if (stack_start)
+
+		/*
+		 * Read the current TLS pointer from tpidr_el0 as it may be
+		 * out-of-sync with the saved value.
+		 */
+		asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+
+		if (stack_start) {
+			if (is_compat_thread(task_thread_info(p)))
 				childregs->compat_sp = stack_start;
-		} else {
-			/*
-			 * Read the current TLS pointer from tpidr_el0 as it may be
-			 * out-of-sync with the saved value.
-			 */
-			asm("mrs %0, tpidr_el0" : "=r" (tls));
-			if (stack_start) {
-				/* 16-byte aligned stack mandatory on AArch64 */
-				if (stack_start & 15)
-					return -EINVAL;
+			/* 16-byte aligned stack mandatory on AArch64 */
+			else if (stack_start & 15)
+				return -EINVAL;
+			else
 				childregs->sp = stack_start;
-			}
 		}
+
 		/*
 		 * If a TLS pointer was passed to clone (4th argument), use it
 		 * for the new thread.
 		 */
 		if (clone_flags & CLONE_SETTLS)
-			tls = childregs->regs[3];
+			p->thread.tp_value = childregs->regs[3];
 	} else {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h;
@@ -291,7 +282,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	}
 	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
 	p->thread.cpu_context.sp = (unsigned long)childregs;
-	p->thread.tp_value = tls;
 
 	ptrace_hw_copy_thread(p);
 
@@ -302,18 +292,12 @@ static void tls_thread_switch(struct task_struct *next)
 {
 	unsigned long tpidr, tpidrro;
 
-	if (!is_compat_task()) {
-		asm("mrs %0, tpidr_el0" : "=r" (tpidr));
-		current->thread.tp_value = tpidr;
-	}
+	asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+	*task_user_tls(current) = tpidr;
 
-	if (is_compat_thread(task_thread_info(next))) {
-		tpidr = 0;
-		tpidrro = next->thread.tp_value;
-	} else {
-		tpidr = next->thread.tp_value;
-		tpidrro = 0;
-	}
+	tpidr = *task_user_tls(next);
+	tpidrro = is_compat_thread(task_thread_info(next)) ?
+		  next->thread.tp_value : 0;
 
 	asm(
 	"	msr	tpidr_el0, %0\n"
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index ea18cb53921e..869f202748e8 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -15,7 +15,6 @@
 
 #define pr_fmt(fmt) "psci: " fmt
 
-#include <linux/acpi.h>
 #include <linux/init.h>
 #include <linux/of.h>
 #include <linux/smp.h>
@@ -25,8 +24,8 @@
 #include <linux/slab.h>
 #include <uapi/linux/psci.h>
 
-#include <asm/acpi.h>
 #include <asm/compiler.h>
+#include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/errno.h>
 #include <asm/psci.h>
@@ -37,16 +36,31 @@
 #define PSCI_POWER_STATE_TYPE_STANDBY		0
 #define PSCI_POWER_STATE_TYPE_POWER_DOWN	1
 
-struct psci_power_state {
-	u16	id;
-	u8	type;
-	u8	affinity_level;
-};
+static bool psci_power_state_loses_context(u32 state)
+{
+	return state & PSCI_0_2_POWER_STATE_TYPE_MASK;
+}
+
+static bool psci_power_state_is_valid(u32 state)
+{
+	const u32 valid_mask = PSCI_0_2_POWER_STATE_ID_MASK |
+			       PSCI_0_2_POWER_STATE_TYPE_MASK |
+			       PSCI_0_2_POWER_STATE_AFFL_MASK;
+
+	return !(state & ~valid_mask);
+}
+
+/*
+ * The CPU any Trusted OS is resident on. The trusted OS may reject CPU_OFF
+ * calls to its resident CPU, so we must avoid issuing those. We never migrate
+ * a Trusted OS even if it claims to be capable of migration -- doing so will
+ * require cooperation with a Trusted OS driver.
+ */
+static int resident_cpu = -1;
 
 struct psci_operations {
-	int (*cpu_suspend)(struct psci_power_state state,
-			   unsigned long entry_point);
-	int (*cpu_off)(struct psci_power_state state);
+	int (*cpu_suspend)(u32 state, unsigned long entry_point);
+	int (*cpu_off)(u32 state);
 	int (*cpu_on)(unsigned long cpuid, unsigned long entry_point);
 	int (*migrate)(unsigned long cpuid);
 	int (*affinity_info)(unsigned long target_affinity,
@@ -56,23 +70,21 @@ struct psci_operations {
 
 static struct psci_operations psci_ops;
 
-static int (*invoke_psci_fn)(u64, u64, u64, u64);
-typedef int (*psci_initcall_t)(const struct device_node *);
-
-asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64);
-asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64);
+typedef unsigned long (psci_fn)(unsigned long, unsigned long,
+				unsigned long, unsigned long);
+asmlinkage psci_fn __invoke_psci_fn_hvc;
+asmlinkage psci_fn __invoke_psci_fn_smc;
+static psci_fn *invoke_psci_fn;
 
 enum psci_function {
 	PSCI_FN_CPU_SUSPEND,
 	PSCI_FN_CPU_ON,
 	PSCI_FN_CPU_OFF,
 	PSCI_FN_MIGRATE,
-	PSCI_FN_AFFINITY_INFO,
-	PSCI_FN_MIGRATE_INFO_TYPE,
 	PSCI_FN_MAX,
 };
 
-static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state);
+static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
 
 static u32 psci_function_id[PSCI_FN_MAX];
 
@@ -92,56 +104,28 @@ static int psci_to_linux_errno(int errno)
 	return -EINVAL;
 }
 
-static u32 psci_power_state_pack(struct psci_power_state state)
-{
-	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
-			& PSCI_0_2_POWER_STATE_ID_MASK) |
-		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
-		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
-		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
-		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
-}
-
-static void psci_power_state_unpack(u32 power_state,
-				    struct psci_power_state *state)
-{
-	state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >>
-			PSCI_0_2_POWER_STATE_ID_SHIFT;
-	state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >>
-			PSCI_0_2_POWER_STATE_TYPE_SHIFT;
-	state->affinity_level =
-			(power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >>
-			PSCI_0_2_POWER_STATE_AFFL_SHIFT;
-}
-
-static int psci_get_version(void)
+static u32 psci_get_version(void)
 {
-	int err;
-
-	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
-	return err;
+	return invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
 }
 
-static int psci_cpu_suspend(struct psci_power_state state,
-			    unsigned long entry_point)
+static int psci_cpu_suspend(u32 state, unsigned long entry_point)
 {
 	int err;
-	u32 fn, power_state;
+	u32 fn;
 
 	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, entry_point, 0);
+	err = invoke_psci_fn(fn, state, entry_point, 0);
 	return psci_to_linux_errno(err);
 }
 
-static int psci_cpu_off(struct psci_power_state state)
+static int psci_cpu_off(u32 state)
 {
 	int err;
-	u32 fn, power_state;
+	u32 fn;
 
 	fn = psci_function_id[PSCI_FN_CPU_OFF];
-	power_state = psci_power_state_pack(state);
-	err = invoke_psci_fn(fn, power_state, 0, 0);
+	err = invoke_psci_fn(fn, state, 0, 0);
 	return psci_to_linux_errno(err);
 }
 
@@ -168,30 +152,29 @@ static int psci_migrate(unsigned long cpuid)
 static int psci_affinity_info(unsigned long target_affinity,
 		unsigned long lowest_affinity_level)
 {
-	int err;
-	u32 fn;
-
-	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
-	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
-	return err;
+	return invoke_psci_fn(PSCI_0_2_FN64_AFFINITY_INFO, target_affinity,
+			      lowest_affinity_level, 0);
 }
 
 static int psci_migrate_info_type(void)
 {
-	int err;
-	u32 fn;
+	return invoke_psci_fn(PSCI_0_2_FN_MIGRATE_INFO_TYPE, 0, 0, 0);
+}
 
-	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
-	err = invoke_psci_fn(fn, 0, 0, 0);
-	return err;
+static unsigned long psci_migrate_info_up_cpu(void)
+{
+	return invoke_psci_fn(PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU, 0, 0, 0);
 }
 
-static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
-						 unsigned int cpu)
+static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu)
 {
 	int i, ret, count = 0;
-	struct psci_power_state *psci_states;
-	struct device_node *state_node;
+	u32 *psci_states;
+	struct device_node *state_node, *cpu_node;
+
+	cpu_node = of_get_cpu_node(cpu, NULL);
+	if (!cpu_node)
+		return -ENODEV;
 
 	/*
 	 * If the PSCI cpu_suspend function hook has not been initialized
@@ -215,13 +198,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
 		return -ENOMEM;
 
 	for (i = 0; i < count; i++) {
-		u32 psci_power_state;
+		u32 state;
 
 		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
 
 		ret = of_property_read_u32(state_node,
 					   "arm,psci-suspend-param",
-					   &psci_power_state);
+					   &state);
 		if (ret) {
 			pr_warn(" * %s missing arm,psci-suspend-param property\n",
 				state_node->full_name);
@@ -230,9 +213,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node,
 		}
 
 		of_node_put(state_node);
-		pr_debug("psci-power-state %#x index %d\n", psci_power_state,
-							    i);
-		psci_power_state_unpack(psci_power_state, &psci_states[i]);
+		pr_debug("psci-power-state %#x index %d\n", state, i);
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			ret = -EINVAL;
+			goto free_mem;
+		}
+		psci_states[i] = state;
 	}
 	/* Idle states parsed correctly, initialize per-cpu pointer */
 	per_cpu(psci_power_state, cpu) = psci_states;
@@ -275,6 +262,46 @@ static void psci_sys_poweroff(void)
 	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
 }
 
+/*
+ * Detect the presence of a resident Trusted OS which may cause CPU_OFF to
+ * return DENIED (which would be fatal).
+ */
+static void __init psci_init_migrate(void)
+{
+	unsigned long cpuid;
+	int type, cpu;
+
+	type = psci_ops.migrate_info_type();
+
+	if (type == PSCI_0_2_TOS_MP) {
+		pr_info("Trusted OS migration not required\n");
+		return;
+	}
+
+	if (type == PSCI_RET_NOT_SUPPORTED) {
+		pr_info("MIGRATE_INFO_TYPE not supported.\n");
+		return;
+	}
+
+	if (type != PSCI_0_2_TOS_UP_MIGRATE &&
+	    type != PSCI_0_2_TOS_UP_NO_MIGRATE) {
+		pr_err("MIGRATE_INFO_TYPE returned unknown type (%d)\n", type);
+		return;
+	}
+
+	cpuid = psci_migrate_info_up_cpu();
+	if (cpuid & ~MPIDR_HWID_BITMASK) {
+		pr_warn("MIGRATE_INFO_UP_CPU reported invalid physical ID (0x%lx)\n",
+			cpuid);
+		return;
+	}
+
+	cpu = get_logical_index(cpuid);
+	resident_cpu = cpu >= 0 ? cpu : -1;
+
+	pr_info("Trusted OS resident on physical CPU 0x%lx\n", cpuid);
+}
+
 static void __init psci_0_2_set_functions(void)
 {
 	pr_info("Using standard PSCI v0.2 function IDs\n");
@@ -290,11 +317,8 @@ static void __init psci_0_2_set_functions(void)
 	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE;
 	psci_ops.migrate = psci_migrate;
 
-	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO;
 	psci_ops.affinity_info = psci_affinity_info;
 
-	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
-		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
 	psci_ops.migrate_info_type = psci_migrate_info_type;
 
 	arm_pm_restart = psci_sys_reset;
@@ -307,32 +331,26 @@ static void __init psci_0_2_set_functions(void)
  */
 static int __init psci_probe(void)
 {
-	int ver = psci_get_version();
-
-	if (ver == PSCI_RET_NOT_SUPPORTED) {
-		/*
-		 * PSCI versions >=0.2 mandates implementation of
-		 * PSCI_VERSION.
-		 */
-		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
-		return -EOPNOTSUPP;
-	} else {
-		pr_info("PSCIv%d.%d detected in firmware.\n",
-				PSCI_VERSION_MAJOR(ver),
-				PSCI_VERSION_MINOR(ver));
-
-		if (PSCI_VERSION_MAJOR(ver) == 0 &&
-				PSCI_VERSION_MINOR(ver) < 2) {
-			pr_err("Conflicting PSCI version detected.\n");
-			return -EINVAL;
-		}
+	u32 ver = psci_get_version();
+
+	pr_info("PSCIv%d.%d detected in firmware.\n",
+			PSCI_VERSION_MAJOR(ver),
+			PSCI_VERSION_MINOR(ver));
+
+	if (PSCI_VERSION_MAJOR(ver) == 0 && PSCI_VERSION_MINOR(ver) < 2) {
+		pr_err("Conflicting PSCI version detected.\n");
+		return -EINVAL;
 	}
 
 	psci_0_2_set_functions();
 
+	psci_init_migrate();
+
 	return 0;
 }
 
+typedef int (*psci_initcall_t)(const struct device_node *);
+
 /*
  * PSCI init function for PSCI versions >=0.2
  *
@@ -421,6 +439,7 @@ int __init psci_dt_init(void)
 	return init_fn(np);
 }
 
+#ifdef CONFIG_ACPI
 /*
  * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's
  * explicitly clarified in SBBR
@@ -441,10 +460,11 @@ int __init psci_acpi_init(void)
 
 	return psci_probe();
 }
+#endif
 
 #ifdef CONFIG_SMP
 
-static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu)
+static int __init cpu_psci_cpu_init(unsigned int cpu)
 {
 	return 0;
 }
@@ -469,11 +489,21 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static bool psci_tos_resident_on(int cpu)
+{
+	return cpu == resident_cpu;
+}
+
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
 	if (!psci_ops.cpu_off)
 		return -EOPNOTSUPP;
+
+	/* Trusted OS will deny CPU_OFF */
+	if (psci_tos_resident_on(cpu))
+		return -EPERM;
+
 	return 0;
 }
 
@@ -484,9 +514,8 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 	 * There are no known implementations of PSCI actually using the
 	 * power state field, pass a sensible default for now.
 	 */
-	struct psci_power_state state = {
-		.type = PSCI_POWER_STATE_TYPE_POWER_DOWN,
-	};
+	u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
+		    PSCI_0_2_POWER_STATE_TYPE_SHIFT;
 
 	ret = psci_ops.cpu_off(state);
 
@@ -498,7 +527,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 	int err, i;
 
 	if (!psci_ops.affinity_info)
-		return 1;
+		return 0;
 	/*
 	 * cpu_kill could race with cpu_die and we can
 	 * potentially end up declaring this cpu undead
@@ -509,7 +538,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 		err = psci_ops.affinity_info(cpu_logical_map(cpu), 0);
 		if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) {
 			pr_info("CPU%d killed.\n", cpu);
-			return 1;
+			return 0;
 		}
 
 		msleep(10);
@@ -518,15 +547,14 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 
 	pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n",
 			cpu, err);
-	/* Make op_cpu_kill() fail. */
-	return 0;
+	return -ETIMEDOUT;
 }
 #endif
 #endif
 
 static int psci_suspend_finisher(unsigned long index)
 {
-	struct psci_power_state *state = __this_cpu_read(psci_power_state);
+	u32 *state = __this_cpu_read(psci_power_state);
 
 	return psci_ops.cpu_suspend(state[index - 1],
 				    virt_to_phys(cpu_resume));
@@ -535,7 +563,7 @@ static int psci_suspend_finisher(unsigned long index)
 static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
 {
 	int ret;
-	struct psci_power_state *state = __this_cpu_read(psci_power_state);
+	u32 *state = __this_cpu_read(psci_power_state);
 	/*
 	 * idle state index 0 corresponds to wfi, should never be called
 	 * from the cpu_suspend operations
@@ -543,10 +571,10 @@ static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index)
 	if (WARN_ON_ONCE(!index))
 		return -EINVAL;
 
-	if (state[index - 1].type == PSCI_POWER_STATE_TYPE_STANDBY)
+	if (!psci_power_state_loses_context(state[index - 1]))
 		ret = psci_ops.cpu_suspend(state[index - 1], 0);
 	else
-		ret = __cpu_suspend(index, psci_suspend_finisher);
+		ret = cpu_suspend(index, psci_suspend_finisher);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 74753132c3ac..ffd3970721bf 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -105,18 +105,6 @@ static struct resource mem_res[] = {
 #define kernel_code mem_res[0]
 #define kernel_data mem_res[1]
 
-void __init early_print(const char *str, ...)
-{
-	char buf[256];
-	va_list ap;
-
-	va_start(ap, str);
-	vsnprintf(buf, sizeof(buf), str, ap);
-	va_end(ap);
-
-	printk("%s", buf);
-}
-
 /*
  * The recorded values of x0 .. x3 upon kernel entry.
  */
@@ -326,12 +314,14 @@ static void __init setup_processor(void)
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) {
-		early_print("\n"
-			"Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n"
-			"The dtb must be 8-byte aligned and passed in the first 512MB of memory\n"
-			"\nPlease check your bootloader.\n",
-			dt_phys, phys_to_virt(dt_phys));
+	void *dt_virt = fixmap_remap_fdt(dt_phys);
+
+	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
+		pr_crit("\n"
+			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
+			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
+			"\nPlease check your bootloader.",
+			&dt_phys, dt_virt);
 
 		while (true)
 			cpu_relax();
@@ -374,8 +364,6 @@ void __init setup_arch(char **cmdline_p)
 {
 	setup_processor();
 
-	setup_machine_fdt(__fdt_pointer);
-
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -386,6 +374,8 @@ void __init setup_arch(char **cmdline_p)
 	early_fixmap_init();
 	early_ioremap_init();
 
+	setup_machine_fdt(__fdt_pointer);
+
 	parse_early_param();
 
 	/*
@@ -408,16 +398,13 @@ void __init setup_arch(char **cmdline_p)
 	if (acpi_disabled) {
 		unflatten_device_tree();
 		psci_dt_init();
-		cpu_read_bootcpu_ops();
-#ifdef CONFIG_SMP
-		of_smp_init_cpus();
-#endif
 	} else {
 		psci_acpi_init();
-		acpi_init_cpus();
 	}
 
+	cpu_read_bootcpu_ops();
 #ifdef CONFIG_SMP
+	smp_init_cpus();
 	smp_build_mpidr_hash();
 #endif
 
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d26fcd4cd6e6..1670f15ef69e 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -370,7 +370,7 @@ badframe:
 	if (show_unhandled_signals)
 		pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
 				    current->comm, task_pid_nr(current), __func__,
-				    regs->pc, regs->sp);
+				    regs->pc, regs->compat_sp);
 	force_sig(SIGSEGV, current);
 	return 0;
 }
@@ -407,7 +407,7 @@ badframe:
 	if (show_unhandled_signals)
 		pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n",
 				    current->comm, task_pid_nr(current), __func__,
-				    regs->pc, regs->sp);
+				    regs->pc, regs->compat_sp);
 	force_sig(SIGSEGV, current);
 	return 0;
 }
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index ede186cdd452..803cfea41962 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -130,12 +130,14 @@ ENDPROC(__cpu_suspend_enter)
 /*
  * x0 must contain the sctlr value retrieved from restored context
  */
+	.pushsection	".idmap.text", "ax"
 ENTRY(cpu_resume_mmu)
 	ldr	x3, =cpu_resume_after_mmu
 	msr	sctlr_el1, x0		// restore sctlr_el1
 	isb
 	br	x3			// global jump to virtual address
 ENDPROC(cpu_resume_mmu)
+	.popsection
 cpu_resume_after_mmu:
 	mov	x0, #0			// return zero on success
 	ldp	x19, x20, [sp, #16]
@@ -162,15 +164,12 @@ ENTRY(cpu_resume)
 #else
 	mov	x7, xzr
 #endif
-	adrp	x0, sleep_save_sp
-	add	x0, x0, #:lo12:sleep_save_sp
-	ldr	x0, [x0, #SLEEP_SAVE_SP_PHYS]
+	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
 	ldr	x0, [x0, x7, lsl #3]
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	adrp	x1, sleep_idmap_phys
 	/* load physical address of identity map page table in x1 */
-	ldr	x1, [x1, #:lo12:sleep_idmap_phys]
+	adrp	x1, idmap_pg_dir
 	mov	sp, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context physical address
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2cb008177252..4b2121bd7f9c 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
@@ -248,20 +249,20 @@ static int op_cpu_kill(unsigned int cpu)
 	 * time and hope that it's dead, so let's skip the wait and just hope.
 	 */
 	if (!cpu_ops[cpu]->cpu_kill)
-		return 1;
+		return 0;
 
 	return cpu_ops[cpu]->cpu_kill(cpu);
 }
 
-static DECLARE_COMPLETION(cpu_died);
-
 /*
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
 void __cpu_die(unsigned int cpu)
 {
-	if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) {
+	int err;
+
+	if (!cpu_wait_death(cpu, 5)) {
 		pr_crit("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
@@ -273,8 +274,10 @@ void __cpu_die(unsigned int cpu)
 	 * verify that it has really left the kernel before we consider
 	 * clobbering anything it might still be using.
 	 */
-	if (!op_cpu_kill(cpu))
-		pr_warn("CPU%d may not have shut down cleanly\n", cpu);
+	err = op_cpu_kill(cpu);
+	if (err)
+		pr_warn("CPU%d may not have shut down cleanly: %d\n",
+			cpu, err);
 }
 
 /*
@@ -294,7 +297,7 @@ void cpu_die(void)
 	local_irq_disable();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	complete(&cpu_died);
+	(void)cpu_report_death();
 
 	/*
 	 * Actually shutdown the CPU. This must never fail. The specific hotplug
@@ -318,57 +321,158 @@ void __init smp_prepare_boot_cpu(void)
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 }
 
+static u64 __init of_get_cpu_mpidr(struct device_node *dn)
+{
+	const __be32 *cell;
+	u64 hwid;
+
+	/*
+	 * A cpu node with missing "reg" property is
+	 * considered invalid to build a cpu_logical_map
+	 * entry.
+	 */
+	cell = of_get_property(dn, "reg", NULL);
+	if (!cell) {
+		pr_err("%s: missing reg property\n", dn->full_name);
+		return INVALID_HWID;
+	}
+
+	hwid = of_read_number(cell, of_n_addr_cells(dn));
+	/*
+	 * Non affinity bits must be set to 0 in the DT
+	 */
+	if (hwid & ~MPIDR_HWID_BITMASK) {
+		pr_err("%s: invalid reg property\n", dn->full_name);
+		return INVALID_HWID;
+	}
+	return hwid;
+}
+
+/*
+ * Duplicate MPIDRs are a recipe for disaster. Scan all initialized
+ * entries and check for duplicates. If any is found just ignore the
+ * cpu. cpu_logical_map was initialized to INVALID_HWID to avoid
+ * matching valid MPIDR values.
+ */
+static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
+{
+	unsigned int i;
+
+	for (i = 1; (i < cpu) && (i < NR_CPUS); i++)
+		if (cpu_logical_map(i) == hwid)
+			return true;
+	return false;
+}
+
+/*
+ * Initialize cpu operations for a logical cpu and
+ * set it in the possible mask on success
+ */
+static int __init smp_cpu_setup(int cpu)
+{
+	if (cpu_read_ops(cpu))
+		return -ENODEV;
+
+	if (cpu_ops[cpu]->cpu_init(cpu))
+		return -ENODEV;
+
+	set_cpu_possible(cpu, true);
+
+	return 0;
+}
+
+static bool bootcpu_valid __initdata;
+static unsigned int cpu_count = 1;
+
+#ifdef CONFIG_ACPI
+/*
+ * acpi_map_gic_cpu_interface - parse processor MADT entry
+ *
+ * Carry out sanity checks on MADT processor entry and initialize
+ * cpu_logical_map on success
+ */
+static void __init
+acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+{
+	u64 hwid = processor->arm_mpidr;
+
+	if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) {
+		pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid);
+		return;
+	}
+
+	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+		pr_err("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
+		return;
+	}
+
+	if (is_mpidr_duplicate(cpu_count, hwid)) {
+		pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid);
+		return;
+	}
+
+	/* Check if GICC structure of boot CPU is available in the MADT */
+	if (cpu_logical_map(0) == hwid) {
+		if (bootcpu_valid) {
+			pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n",
+			       hwid);
+			return;
+		}
+		bootcpu_valid = true;
+		return;
+	}
+
+	if (cpu_count >= NR_CPUS)
+		return;
+
+	/* map the logical cpu id to cpu MPIDR */
+	cpu_logical_map(cpu_count) = hwid;
+
+	cpu_count++;
+}
+
+static int __init
+acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
+			     const unsigned long end)
+{
+	struct acpi_madt_generic_interrupt *processor;
+
+	processor = (struct acpi_madt_generic_interrupt *)header;
+	if (BAD_MADT_ENTRY(processor, end))
+		return -EINVAL;
+
+	acpi_table_print_madt_entry(header);
+
+	acpi_map_gic_cpu_interface(processor);
+
+	return 0;
+}
+#else
+#define acpi_table_parse_madt(...)	do { } while (0)
+#endif
+
 /*
  * Enumerate the possible CPU set from the device tree and build the
  * cpu logical map array containing MPIDR values related to logical
  * cpus. Assumes that cpu_logical_map(0) has already been initialized.
  */
-void __init of_smp_init_cpus(void)
+void __init of_parse_and_init_cpus(void)
 {
 	struct device_node *dn = NULL;
-	unsigned int i, cpu = 1;
-	bool bootcpu_valid = false;
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
-		const u32 *cell;
-		u64 hwid;
+		u64 hwid = of_get_cpu_mpidr(dn);
 
-		/*
-		 * A cpu node with missing "reg" property is
-		 * considered invalid to build a cpu_logical_map
-		 * entry.
-		 */
-		cell = of_get_property(dn, "reg", NULL);
-		if (!cell) {
-			pr_err("%s: missing reg property\n", dn->full_name);
+		if (hwid == INVALID_HWID)
 			goto next;
-		}
-		hwid = of_read_number(cell, of_n_addr_cells(dn));
 
-		/*
-		 * Non affinity bits must be set to 0 in the DT
-		 */
-		if (hwid & ~MPIDR_HWID_BITMASK) {
-			pr_err("%s: invalid reg property\n", dn->full_name);
+		if (is_mpidr_duplicate(cpu_count, hwid)) {
+			pr_err("%s: duplicate cpu reg properties in the DT\n",
+				dn->full_name);
 			goto next;
 		}
 
 		/*
-		 * Duplicate MPIDRs are a recipe for disaster. Scan
-		 * all initialized entries and check for
-		 * duplicates. If any is found just ignore the cpu.
-		 * cpu_logical_map was initialized to INVALID_HWID to
-		 * avoid matching valid MPIDR values.
-		 */
-		for (i = 1; (i < cpu) && (i < NR_CPUS); i++) {
-			if (cpu_logical_map(i) == hwid) {
-				pr_err("%s: duplicate cpu reg properties in the DT\n",
-					dn->full_name);
-				goto next;
-			}
-		}
-
-		/*
 		 * The numbering scheme requires that the boot CPU
 		 * must be assigned logical id 0. Record it so that
 		 * the logical map built from DT is validated and can
@@ -392,38 +496,58 @@ void __init of_smp_init_cpus(void)
 			continue;
 		}
 
-		if (cpu >= NR_CPUS)
-			goto next;
-
-		if (cpu_read_ops(dn, cpu) != 0)
-			goto next;
-
-		if (cpu_ops[cpu]->cpu_init(dn, cpu))
+		if (cpu_count >= NR_CPUS)
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
-		cpu_logical_map(cpu) = hwid;
+		cpu_logical_map(cpu_count) = hwid;
 next:
-		cpu++;
+		cpu_count++;
 	}
+}
+
+/*
+ * Enumerate the possible CPU set from the device tree or ACPI and build the
+ * cpu logical map array containing MPIDR values related to logical
+ * cpus. Assumes that cpu_logical_map(0) has already been initialized.
+ */
+void __init smp_init_cpus(void)
+{
+	int i;
 
-	/* sanity check */
-	if (cpu > NR_CPUS)
-		pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n",
-			   cpu, NR_CPUS);
+	if (acpi_disabled)
+		of_parse_and_init_cpus();
+	else
+		/*
+		 * do a walk of MADT to determine how many CPUs
+		 * we have including disabled CPUs, and get information
+		 * we need for SMP init
+		 */
+		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+				      acpi_parse_gic_cpu_interface, 0);
+
+	if (cpu_count > NR_CPUS)
+		pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
+			cpu_count, NR_CPUS);
 
 	if (!bootcpu_valid) {
-		pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n");
+		pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
 		return;
 	}
 
 	/*
-	 * All the cpus that made it to the cpu_logical_map have been
-	 * validated so set them as possible cpus.
+	 * We need to set the cpu_logical_map entries before enabling
+	 * the cpus so that cpu processor description entries (DT cpu nodes
+	 * and ACPI MADT entries) can be retrieved by matching the cpu hwid
+	 * with entries in cpu_logical_map while initializing the cpus.
+	 * If the cpu set-up fails, invalidate the cpu_logical_map entry.
 	 */
-	for (i = 0; i < NR_CPUS; i++)
-		if (cpu_logical_map(i) != INVALID_HWID)
-			set_cpu_possible(i, true);
+	for (i = 1; i < NR_CPUS; i++) {
+		if (cpu_logical_map(i) != INVALID_HWID) {
+			if (smp_cpu_setup(i))
+				cpu_logical_map(i) = INVALID_HWID;
+		}
+	}
 }
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 14944e5b28da..aef3605a8c47 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -49,8 +49,14 @@ static void write_pen_release(u64 val)
 }
 
 
-static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu)
+static int smp_spin_table_cpu_init(unsigned int cpu)
 {
+	struct device_node *dn;
+
+	dn = of_get_cpu_node(cpu, NULL);
+	if (!dn)
+		return -ENODEV;
+
 	/*
 	 * Determine the address from which the CPU is polling.
 	 */
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index d7daf45ae7a2..8297d502217e 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -51,13 +51,13 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 }
 
 /*
- * __cpu_suspend
+ * cpu_suspend
  *
  * arg: argument to pass to the finisher function
  * fn: finisher function pointer
  *
  */
-int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
+int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	struct mm_struct *mm = current->active_mm;
 	int ret;
@@ -82,7 +82,7 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 		 * We are resuming from reset with TTBR0_EL1 set to the
 		 * idmap to enable the MMU; restore the active_mm mappings in
 		 * TTBR0_EL1 unless the active_mm == &init_mm, in which case
-		 * the thread entered __cpu_suspend with TTBR0_EL1 set to
+		 * the thread entered cpu_suspend with TTBR0_EL1 set to
 		 * reserved TTBR0 page tables and should be restored as such.
 		 */
 		if (mm == &init_mm)
@@ -118,7 +118,6 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 }
 
 struct sleep_save_sp sleep_save_sp;
-phys_addr_t sleep_idmap_phys;
 
 static int __init cpu_suspend_init(void)
 {
@@ -132,9 +131,7 @@ static int __init cpu_suspend_init(void)
 
 	sleep_save_sp.save_ptr_stash = ctx_ptr;
 	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
-	sleep_idmap_phys = virt_to_phys(idmap_pg_dir);
 	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
-	__flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys));
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 1ef2940df13c..a12251c074a8 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -335,8 +335,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (call_undef_hook(regs) == 0)
 		return;
 
-	if (show_unhandled_signals && unhandled_signal(current, SIGILL) &&
-	    printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited() && unhandled_signal(current, SIGILL)) {
 		pr_info("%s[%d]: undefined instruction: pc=%p\n",
 			current->comm, task_pid_nr(current), pc);
 		dump_instr(KERN_INFO, regs);
@@ -363,7 +362,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 	}
 #endif
 
-	if (show_unhandled_signals && printk_ratelimit()) {
+	if (show_unhandled_signals_ratelimited()) {
 		pr_info("%s[%d]: syscall %d\n", current->comm,
 			task_pid_nr(current), (int)regs->syscallno);
 		dump_instr("", regs);
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index ff3bddea482d..f6fe17d88da5 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -15,6 +15,10 @@ ccflags-y := -shared -fno-common -fno-builtin
 ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
 		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 
+# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
+# down to collect2, resulting in silent corruption of the vDSO image.
+ccflags-y += -Wl,-shared
+
 obj-y += vdso.o
 extra-y += vdso.lds vdso-offsets.h
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index a2c29865c3fe..98073332e2d0 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -38,6 +38,12 @@ jiffies = jiffies_64;
 	*(.hyp.text)					\
 	VMLINUX_SYMBOL(__hyp_text_end) = .;
 
+#define IDMAP_TEXT					\
+	. = ALIGN(SZ_4K);				\
+	VMLINUX_SYMBOL(__idmap_text_start) = .;		\
+	*(.idmap.text)					\
+	VMLINUX_SYMBOL(__idmap_text_end) = .;
+
 /*
  * The size of the PE/COFF section that covers the kernel image, which
  * runs from stext to _edata, must be a round multiple of the PE/COFF
@@ -95,6 +101,7 @@ SECTIONS
 			SCHED_TEXT
 			LOCK_TEXT
 			HYPERVISOR_TEXT
+			IDMAP_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
@@ -167,11 +174,13 @@ SECTIONS
 }
 
 /*
- * The HYP init code can't be more than a page long,
+ * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.
  */
 ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
 	"HYP init code too big or misaligned")
+ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K,
+	"ID map text too big or misaligned")
 
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.