Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:

 - virt_to_page/page_address optimisations

 - support for NUMA systems described using device-tree

 - support for hibernate/suspend-to-disk

 - proper support for maxcpus= command line parameter

 - detection and graceful handling of AArch64-only CPUs

 - miscellaneous cleanups and non-critical fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
  arm64: do not enforce strict 16 byte alignment to stack pointer
  arm64: kernel: Fix incorrect brk randomization
  arm64: cpuinfo: Missing NULL terminator in compat_hwcap_str
  arm64: secondary_start_kernel: Remove unnecessary barrier
  arm64: Ensure pmd_present() returns false after pmd_mknotpresent()
  arm64: Replace hard-coded values in the pmd/pud_bad() macros
  arm64: Implement pmdp_set_access_flags() for hardware AF/DBM
  arm64: Fix typo in the pmdp_huge_get_and_clear() definition
  arm64: mm: remove unnecessary EXPORT_SYMBOL_GPL
  arm64: always use STRICT_MM_TYPECHECKS
  arm64: kvm: Fix kvm teardown for systems using the extended idmap
  arm64: kaslr: increase randomization granularity
  arm64: kconfig: drop CONFIG_RTC_LIB dependency
  arm64: make ARCH_SUPPORTS_DEBUG_PAGEALLOC depend on !HIBERNATION
  arm64: hibernate: Refuse to hibernate if the boot cpu is offline
  arm64: kernel: Add support for hibernate/suspend-to-disk
  PM / Hibernate: Call flush_icache_range() on pages restored in-place
  arm64: Add new asm macro copy_page
  arm64: Promote KERNEL_START/KERNEL_END definitions to a header file
  arm64: kernel: Include _AC definition in page.h
  ...

26 files changed, 1304 insertions, 560 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 3793003e16a2..2173149d8954 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -45,6 +45,7 @@ arm64-obj-$(CONFIG_ACPI)		+= acpi.o
 arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
+arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index d1ce8e2f98b9..3e4f1a45b125 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -42,6 +42,7 @@ int acpi_pci_disabled = 1;	/* skip ACPI PCI scan and IRQ initialization */
 EXPORT_SYMBOL(acpi_pci_disabled);
 
 static bool param_acpi_off __initdata;
+static bool param_acpi_on __initdata;
 static bool param_acpi_force __initdata;
 
 static int __init parse_acpi(char *arg)
@@ -52,6 +53,8 @@ static int __init parse_acpi(char *arg)
 	/* "acpi=off" disables both ACPI table parsing and interpreter */
 	if (strcmp(arg, "off") == 0)
 		param_acpi_off = true;
+	else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */
+		param_acpi_on = true;
 	else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */
 		param_acpi_force = true;
 	else
@@ -66,12 +69,24 @@ static int __init dt_scan_depth1_nodes(unsigned long node,
 				       void *data)
 {
 	/*
-	 * Return 1 as soon as we encounter a node at depth 1 that is
-	 * not the /chosen node.
+	 * Ignore anything not directly under the root node; we'll
+	 * catch its parent instead.
 	 */
-	if (depth == 1 && (strcmp(uname, "chosen") != 0))
-		return 1;
-	return 0;
+	if (depth != 1)
+		return 0;
+
+	if (strcmp(uname, "chosen") == 0)
+		return 0;
+
+	if (strcmp(uname, "hypervisor") == 0 &&
+	    of_flat_dt_is_compatible(node, "xen,xen"))
+		return 0;
+
+	/*
+	 * This node at depth 1 is neither a chosen node nor a xen node,
+	 * which we do not expect.
+	 */
+	return 1;
 }
 
 /*
@@ -184,11 +199,13 @@ void __init acpi_boot_table_init(void)
 	/*
 	 * Enable ACPI instead of device tree unless
 	 * - ACPI has been disabled explicitly (acpi=off), or
-	 * - the device tree is not empty (it has more than just a /chosen node)
-	 *   and ACPI has not been force enabled (acpi=force)
+	 * - the device tree is not empty (it has more than just a /chosen node,
+	 *   and a /hypervisor node when running on Xen)
+	 *   and ACPI has not been [force] enabled (acpi=on|force)
 	 */
 	if (param_acpi_off ||
-	    (!param_acpi_force && of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
+	    (!param_acpi_on && !param_acpi_force &&
+	     of_scan_flat_dt(dt_scan_depth1_nodes, NULL)))
 		return;
 
 	/*
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 3ae6b310ac9b..f8e5d47f0880 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -22,6 +22,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/kvm_host.h>
+#include <linux/suspend.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
@@ -119,11 +120,14 @@ int main(void)
   DEFINE(CPU_CTX_SP,		offsetof(struct cpu_suspend_ctx, sp));
   DEFINE(MPIDR_HASH_MASK,	offsetof(struct mpidr_hash, mask));
   DEFINE(MPIDR_HASH_SHIFTS,	offsetof(struct mpidr_hash, shift_aff));
-  DEFINE(SLEEP_SAVE_SP_SZ,	sizeof(struct sleep_save_sp));
-  DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
-  DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
+  DEFINE(SLEEP_STACK_DATA_SYSTEM_REGS,	offsetof(struct sleep_stack_data, system_regs));
+  DEFINE(SLEEP_STACK_DATA_CALLEE_REGS,	offsetof(struct sleep_stack_data, callee_saved_regs));
 #endif
   DEFINE(ARM_SMCCC_RES_X0_OFFS,	offsetof(struct arm_smccc_res, a0));
   DEFINE(ARM_SMCCC_RES_X2_OFFS,	offsetof(struct arm_smccc_res, a2));
+  BLANK();
+  DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
+  DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
+  DEFINE(HIBERN_PBE_NEXT,	offsetof(struct pbe, next));
   return 0;
 }
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 06afd04e02c0..d42789499f17 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -22,14 +22,16 @@
 #include <asm/cpufeature.h>
 
 static bool __maybe_unused
-is_affected_midr_range(const struct arm64_cpu_capabilities *entry)
+is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
 {
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 	return MIDR_IS_CPU_MODEL_RANGE(read_cpuid_id(), entry->midr_model,
 				       entry->midr_range_min,
 				       entry->midr_range_max);
 }
 
 #define MIDR_RANGE(model, min, max) \
+	.def_scope = SCOPE_LOCAL_CPU, \
 	.matches = is_affected_midr_range, \
 	.midr_model = model, \
 	.midr_range_min = min, \
@@ -101,6 +103,26 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	}
 };
 
+/*
+ * The CPU Errata work arounds are detected and applied at boot time
+ * and the related information is freed soon after. If the new CPU requires
+ * an errata not detected at boot, fail this CPU.
+ */
+void verify_local_cpu_errata(void)
+{
+	const struct arm64_cpu_capabilities *caps = arm64_errata;
+
+	for (; caps->matches; caps++)
+		if (!cpus_have_cap(caps->capability) &&
+			caps->matches(caps, SCOPE_LOCAL_CPU)) {
+			pr_crit("CPU%d: Requires work around for %s, not detected"
+					" at boot time\n",
+				smp_processor_id(),
+				caps->desc ? : "an erratum");
+			cpu_die_early();
+		}
+}
+
 void check_local_cpu_errata(void)
 {
 	update_cpu_capabilities(arm64_errata, "enabling workaround for");
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 943f5140e0f3..811773d1c1d0 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -71,7 +71,8 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
 /* meta feature for alternatives */
 static bool __maybe_unused
-cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry);
+cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
+
 
 static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
@@ -130,7 +131,11 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 };
 
 static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_UAO_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_CNP_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -435,22 +440,26 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
-	init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
-	init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
-	init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
-	init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
-	init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
-	init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
-	init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
-	init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
-	init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
-	init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
-	init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
-	init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
-	init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
-	init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
-	init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
-	init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
+
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
+		init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0);
+		init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1);
+		init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2);
+		init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3);
+		init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4);
+		init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5);
+		init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0);
+		init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1);
+		init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2);
+		init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3);
+		init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0);
+		init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1);
+		init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0);
+		init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1);
+		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
+	}
+
 }
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
@@ -555,47 +564,51 @@ void update_cpu_features(int cpu,
 				      info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1);
 
 	/*
-	 * If we have AArch32, we care about 32-bit features for compat. These
-	 * registers should be RES0 otherwise.
+	 * If we have AArch32, we care about 32-bit features for compat.
+	 * If the system doesn't support AArch32, don't update them.
 	 */
-	taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
+	if (id_aa64pfr0_32bit_el0(read_system_reg(SYS_ID_AA64PFR0_EL1)) &&
+		id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+
+		taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
 					info->reg_id_dfr0, boot->reg_id_dfr0);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu,
 					info->reg_id_isar0, boot->reg_id_isar0);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu,
 					info->reg_id_isar1, boot->reg_id_isar1);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu,
 					info->reg_id_isar2, boot->reg_id_isar2);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu,
 					info->reg_id_isar3, boot->reg_id_isar3);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu,
 					info->reg_id_isar4, boot->reg_id_isar4);
-	taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu,
 					info->reg_id_isar5, boot->reg_id_isar5);
 
-	/*
-	 * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
-	 * ACTLR formats could differ across CPUs and therefore would have to
-	 * be trapped for virtualization anyway.
-	 */
-	taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu,
+		/*
+		 * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and
+		 * ACTLR formats could differ across CPUs and therefore would have to
+		 * be trapped for virtualization anyway.
+		 */
+		taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu,
 					info->reg_id_mmfr0, boot->reg_id_mmfr0);
-	taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu,
 					info->reg_id_mmfr1, boot->reg_id_mmfr1);
-	taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu,
 					info->reg_id_mmfr2, boot->reg_id_mmfr2);
-	taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu,
 					info->reg_id_mmfr3, boot->reg_id_mmfr3);
-	taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu,
 					info->reg_id_pfr0, boot->reg_id_pfr0);
-	taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu,
 					info->reg_id_pfr1, boot->reg_id_pfr1);
-	taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu,
 					info->reg_mvfr0, boot->reg_mvfr0);
-	taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu,
 					info->reg_mvfr1, boot->reg_mvfr1);
-	taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu,
+		taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu,
 					info->reg_mvfr2, boot->reg_mvfr2);
+	}
 
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
@@ -614,6 +627,49 @@ u64 read_system_reg(u32 id)
 	return regp->sys_val;
 }
 
+/*
+ * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated.
+ * Read the system register on the current CPU
+ */
+static u64 __raw_read_system_reg(u32 sys_id)
+{
+	switch (sys_id) {
+	case SYS_ID_PFR0_EL1:		return read_cpuid(ID_PFR0_EL1);
+	case SYS_ID_PFR1_EL1:		return read_cpuid(ID_PFR1_EL1);
+	case SYS_ID_DFR0_EL1:		return read_cpuid(ID_DFR0_EL1);
+	case SYS_ID_MMFR0_EL1:		return read_cpuid(ID_MMFR0_EL1);
+	case SYS_ID_MMFR1_EL1:		return read_cpuid(ID_MMFR1_EL1);
+	case SYS_ID_MMFR2_EL1:		return read_cpuid(ID_MMFR2_EL1);
+	case SYS_ID_MMFR3_EL1:		return read_cpuid(ID_MMFR3_EL1);
+	case SYS_ID_ISAR0_EL1:		return read_cpuid(ID_ISAR0_EL1);
+	case SYS_ID_ISAR1_EL1:		return read_cpuid(ID_ISAR1_EL1);
+	case SYS_ID_ISAR2_EL1:		return read_cpuid(ID_ISAR2_EL1);
+	case SYS_ID_ISAR3_EL1:		return read_cpuid(ID_ISAR3_EL1);
+	case SYS_ID_ISAR4_EL1:		return read_cpuid(ID_ISAR4_EL1);
+	case SYS_ID_ISAR5_EL1:		return read_cpuid(ID_ISAR4_EL1);
+	case SYS_MVFR0_EL1:		return read_cpuid(MVFR0_EL1);
+	case SYS_MVFR1_EL1:		return read_cpuid(MVFR1_EL1);
+	case SYS_MVFR2_EL1:		return read_cpuid(MVFR2_EL1);
+
+	case SYS_ID_AA64PFR0_EL1:	return read_cpuid(ID_AA64PFR0_EL1);
+	case SYS_ID_AA64PFR1_EL1:	return read_cpuid(ID_AA64PFR0_EL1);
+	case SYS_ID_AA64DFR0_EL1:	return read_cpuid(ID_AA64DFR0_EL1);
+	case SYS_ID_AA64DFR1_EL1:	return read_cpuid(ID_AA64DFR0_EL1);
+	case SYS_ID_AA64MMFR0_EL1:	return read_cpuid(ID_AA64MMFR0_EL1);
+	case SYS_ID_AA64MMFR1_EL1:	return read_cpuid(ID_AA64MMFR1_EL1);
+	case SYS_ID_AA64MMFR2_EL1:	return read_cpuid(ID_AA64MMFR2_EL1);
+	case SYS_ID_AA64ISAR0_EL1:	return read_cpuid(ID_AA64ISAR0_EL1);
+	case SYS_ID_AA64ISAR1_EL1:	return read_cpuid(ID_AA64ISAR1_EL1);
+
+	case SYS_CNTFRQ_EL0:		return read_cpuid(CNTFRQ_EL0);
+	case SYS_CTR_EL0:		return read_cpuid(CTR_EL0);
+	case SYS_DCZID_EL0:		return read_cpuid(DCZID_EL0);
+	default:
+		BUG();
+		return 0;
+	}
+}
+
 #include <linux/irqchip/arm-gic-v3.h>
 
 static bool
@@ -625,19 +681,24 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry)
 }
 
 static bool
-has_cpuid_feature(const struct arm64_cpu_capabilities *entry)
+has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
 {
 	u64 val;
 
-	val = read_system_reg(entry->sys_reg);
+	WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible());
+	if (scope == SCOPE_SYSTEM)
+		val = read_system_reg(entry->sys_reg);
+	else
+		val = __raw_read_system_reg(entry->sys_reg);
+
 	return feature_matches(val, entry);
 }
 
-static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
+static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, int scope)
 {
 	bool has_sre;
 
-	if (!has_cpuid_feature(entry))
+	if (!has_cpuid_feature(entry, scope))
 		return false;
 
 	has_sre = gic_enable_sre();
@@ -648,7 +709,7 @@ static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry)
 	return has_sre;
 }
 
-static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry)
+static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int __unused)
 {
 	u32 midr = read_cpuid_id();
 	u32 rv_min, rv_max;
@@ -660,7 +721,7 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry)
 	return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, rv_min, rv_max);
 }
 
-static bool runs_at_el2(const struct arm64_cpu_capabilities *entry)
+static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused)
 {
 	return is_kernel_in_hyp_mode();
 }
@@ -669,6 +730,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
 		.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = has_useable_gicv3_cpuif,
 		.sys_reg = SYS_ID_AA64PFR0_EL1,
 		.field_pos = ID_AA64PFR0_GIC_SHIFT,
@@ -679,6 +741,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "Privileged Access Never",
 		.capability = ARM64_HAS_PAN,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64MMFR1_EL1,
 		.field_pos = ID_AA64MMFR1_PAN_SHIFT,
@@ -691,6 +754,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "LSE atomic instructions",
 		.capability = ARM64_HAS_LSE_ATOMICS,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64ISAR0_EL1,
 		.field_pos = ID_AA64ISAR0_ATOMICS_SHIFT,
@@ -701,12 +765,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "Software prefetching using PRFM",
 		.capability = ARM64_HAS_NO_HW_PREFETCH,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = has_no_hw_prefetch,
 	},
 #ifdef CONFIG_ARM64_UAO
 	{
 		.desc = "User Access Override",
 		.capability = ARM64_HAS_UAO,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = has_cpuid_feature,
 		.sys_reg = SYS_ID_AA64MMFR2_EL1,
 		.field_pos = ID_AA64MMFR2_UAO_SHIFT,
@@ -717,20 +783,33 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 #ifdef CONFIG_ARM64_PAN
 	{
 		.capability = ARM64_ALT_PAN_NOT_UAO,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = cpufeature_pan_not_uao,
 	},
 #endif /* CONFIG_ARM64_PAN */
 	{
 		.desc = "Virtualization Host Extensions",
 		.capability = ARM64_HAS_VIRT_HOST_EXTN,
+		.def_scope = SCOPE_SYSTEM,
 		.matches = runs_at_el2,
 	},
+	{
+		.desc = "32-bit EL0 Support",
+		.capability = ARM64_HAS_32BIT_EL0,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64PFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64PFR0_EL0_SHIFT,
+		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
+	},
 	{},
 };
 
 #define HWCAP_CAP(reg, field, s, min_value, type, cap)	\
 	{							\
 		.desc = #cap,					\
+		.def_scope = SCOPE_SYSTEM,			\
 		.matches = has_cpuid_feature,			\
 		.sys_reg = reg,					\
 		.field_pos = field,				\
@@ -740,7 +819,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.hwcap = cap,					\
 	}
 
-static const struct arm64_cpu_capabilities arm64_hwcaps[] = {
+static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
 	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
@@ -751,6 +830,10 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
 	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
+	{},
+};
+
+static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
 #ifdef CONFIG_COMPAT
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
 	HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
@@ -761,7 +844,7 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = {
 	{},
 };
 
-static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
+static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
@@ -782,7 +865,7 @@ static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
 }
 
 /* Check if we have a particular HWCAP enabled */
-static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *cap)
+static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	bool rc;
 
@@ -806,28 +889,23 @@ static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *
 	return rc;
 }
 
-static void __init setup_cpu_hwcaps(void)
+static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
-	int i;
-	const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps;
-
-	for (i = 0; hwcaps[i].matches; i++)
-		if (hwcaps[i].matches(&hwcaps[i]))
-			cap_set_hwcap(&hwcaps[i]);
+	for (; hwcaps->matches; hwcaps++)
+		if (hwcaps->matches(hwcaps, hwcaps->def_scope))
+			cap_set_elf_hwcap(hwcaps);
 }
 
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info)
 {
-	int i;
-
-	for (i = 0; caps[i].matches; i++) {
-		if (!caps[i].matches(&caps[i]))
+	for (; caps->matches; caps++) {
+		if (!caps->matches(caps, caps->def_scope))
 			continue;
 
-		if (!cpus_have_cap(caps[i].capability) && caps[i].desc)
-			pr_info("%s %s\n", info, caps[i].desc);
-		cpus_set_cap(caps[i].capability);
+		if (!cpus_have_cap(caps->capability) && caps->desc)
+			pr_info("%s %s\n", info, caps->desc);
+		cpus_set_cap(caps->capability);
 	}
 }
 
@@ -838,11 +916,9 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 static void __init
 enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
-	int i;
-
-	for (i = 0; caps[i].matches; i++)
-		if (caps[i].enable && cpus_have_cap(caps[i].capability))
-			on_each_cpu(caps[i].enable, NULL, true);
+	for (; caps->matches; caps++)
+		if (caps->enable && cpus_have_cap(caps->capability))
+			on_each_cpu(caps->enable, NULL, true);
 }
 
 /*
@@ -861,54 +937,45 @@ static inline void set_sys_caps_initialised(void)
 }
 
 /*
- * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated.
+ * Check for CPU features that are used in early boot
+ * based on the Boot CPU value.
  */
-static u64 __raw_read_system_reg(u32 sys_id)
+static void check_early_cpu_features(void)
 {
-	switch (sys_id) {
-	case SYS_ID_PFR0_EL1:		return read_cpuid(ID_PFR0_EL1);
-	case SYS_ID_PFR1_EL1:		return read_cpuid(ID_PFR1_EL1);
-	case SYS_ID_DFR0_EL1:		return read_cpuid(ID_DFR0_EL1);
-	case SYS_ID_MMFR0_EL1:		return read_cpuid(ID_MMFR0_EL1);
-	case SYS_ID_MMFR1_EL1:		return read_cpuid(ID_MMFR1_EL1);
-	case SYS_ID_MMFR2_EL1:		return read_cpuid(ID_MMFR2_EL1);
-	case SYS_ID_MMFR3_EL1:		return read_cpuid(ID_MMFR3_EL1);
-	case SYS_ID_ISAR0_EL1:		return read_cpuid(ID_ISAR0_EL1);
-	case SYS_ID_ISAR1_EL1:		return read_cpuid(ID_ISAR1_EL1);
-	case SYS_ID_ISAR2_EL1:		return read_cpuid(ID_ISAR2_EL1);
-	case SYS_ID_ISAR3_EL1:		return read_cpuid(ID_ISAR3_EL1);
-	case SYS_ID_ISAR4_EL1:		return read_cpuid(ID_ISAR4_EL1);
-	case SYS_ID_ISAR5_EL1:		return read_cpuid(ID_ISAR4_EL1);
-	case SYS_MVFR0_EL1:		return read_cpuid(MVFR0_EL1);
-	case SYS_MVFR1_EL1:		return read_cpuid(MVFR1_EL1);
-	case SYS_MVFR2_EL1:		return read_cpuid(MVFR2_EL1);
+	verify_cpu_run_el();
+	verify_cpu_asid_bits();
+}
 
-	case SYS_ID_AA64PFR0_EL1:	return read_cpuid(ID_AA64PFR0_EL1);
-	case SYS_ID_AA64PFR1_EL1:	return read_cpuid(ID_AA64PFR0_EL1);
-	case SYS_ID_AA64DFR0_EL1:	return read_cpuid(ID_AA64DFR0_EL1);
-	case SYS_ID_AA64DFR1_EL1:	return read_cpuid(ID_AA64DFR0_EL1);
-	case SYS_ID_AA64MMFR0_EL1:	return read_cpuid(ID_AA64MMFR0_EL1);
-	case SYS_ID_AA64MMFR1_EL1:	return read_cpuid(ID_AA64MMFR1_EL1);
-	case SYS_ID_AA64MMFR2_EL1:	return read_cpuid(ID_AA64MMFR2_EL1);
-	case SYS_ID_AA64ISAR0_EL1:	return read_cpuid(ID_AA64ISAR0_EL1);
-	case SYS_ID_AA64ISAR1_EL1:	return read_cpuid(ID_AA64ISAR1_EL1);
+static void
+verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps)
+{
 
-	case SYS_CNTFRQ_EL0:		return read_cpuid(CNTFRQ_EL0);
-	case SYS_CTR_EL0:		return read_cpuid(CTR_EL0);
-	case SYS_DCZID_EL0:		return read_cpuid(DCZID_EL0);
-	default:
-		BUG();
-		return 0;
-	}
+	for (; caps->matches; caps++)
+		if (cpus_have_elf_hwcap(caps) && !caps->matches(caps, SCOPE_LOCAL_CPU)) {
+			pr_crit("CPU%d: missing HWCAP: %s\n",
+					smp_processor_id(), caps->desc);
+			cpu_die_early();
+		}
 }
 
-/*
- * Check for CPU features that are used in early boot
- * based on the Boot CPU value.
- */
-static void check_early_cpu_features(void)
+static void
+verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 {
-	verify_cpu_asid_bits();
+	for (; caps->matches; caps++) {
+		if (!cpus_have_cap(caps->capability))
+			continue;
+		/*
+		 * If the new CPU misses an advertised feature, we cannot proceed
+		 * further, park the cpu.
+		 */
+		if (!caps->matches(caps, SCOPE_LOCAL_CPU)) {
+			pr_crit("CPU%d: missing feature: %s\n",
+					smp_processor_id(), caps->desc);
+			cpu_die_early();
+		}
+		if (caps->enable)
+			caps->enable(NULL);
+	}
 }
 
 /*
@@ -921,8 +988,6 @@ static void check_early_cpu_features(void)
  */
 void verify_local_cpu_capabilities(void)
 {
-	int i;
-	const struct arm64_cpu_capabilities *caps;
 
 	check_early_cpu_features();
 
@@ -933,32 +998,11 @@ void verify_local_cpu_capabilities(void)
 	if (!sys_caps_initialised)
 		return;
 
-	caps = arm64_features;
-	for (i = 0; caps[i].matches; i++) {
-		if (!cpus_have_cap(caps[i].capability) || !caps[i].sys_reg)
-			continue;
-		/*
-		 * If the new CPU misses an advertised feature, we cannot proceed
-		 * further, park the cpu.
-		 */
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
-			pr_crit("CPU%d: missing feature: %s\n",
-					smp_processor_id(), caps[i].desc);
-			cpu_die_early();
-		}
-		if (caps[i].enable)
-			caps[i].enable(NULL);
-	}
-
-	for (i = 0, caps = arm64_hwcaps; caps[i].matches; i++) {
-		if (!cpus_have_hwcap(&caps[i]))
-			continue;
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
-			pr_crit("CPU%d: missing HWCAP: %s\n",
-					smp_processor_id(), caps[i].desc);
-			cpu_die_early();
-		}
-	}
+	verify_local_cpu_errata();
+	verify_local_cpu_features(arm64_features);
+	verify_local_elf_hwcaps(arm64_elf_hwcaps);
+	if (system_supports_32bit_el0())
+		verify_local_elf_hwcaps(compat_elf_hwcaps);
 }
 
 static void __init setup_feature_capabilities(void)
@@ -967,6 +1011,24 @@ static void __init setup_feature_capabilities(void)
 	enable_cpu_capabilities(arm64_features);
 }
 
+/*
+ * Check if the current CPU has a given feature capability.
+ * Should be called from non-preemptible context.
+ */
+bool this_cpu_has_cap(unsigned int cap)
+{
+	const struct arm64_cpu_capabilities *caps;
+
+	if (WARN_ON(preemptible()))
+		return false;
+
+	for (caps = arm64_features; caps->desc; caps++)
+		if (caps->capability == cap && caps->matches)
+			return caps->matches(caps, SCOPE_LOCAL_CPU);
+
+	return false;
+}
+
 void __init setup_cpu_features(void)
 {
 	u32 cwg;
@@ -974,7 +1036,10 @@ void __init setup_cpu_features(void)
 
 	/* Set the CPU feature capabilies */
 	setup_feature_capabilities();
-	setup_cpu_hwcaps();
+	setup_elf_hwcaps(arm64_elf_hwcaps);
+
+	if (system_supports_32bit_el0())
+		setup_elf_hwcaps(compat_elf_hwcaps);
 
 	/* Advertise that we have computed the system capabilities */
 	set_sys_caps_initialised();
@@ -993,7 +1058,7 @@ void __init setup_cpu_features(void)
 }
 
 static bool __maybe_unused
-cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry)
+cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
 {
 	return (cpus_have_cap(ARM64_HAS_PAN) && !cpus_have_cap(ARM64_HAS_UAO));
 }
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 9047cab68fd3..e11857fce05f 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -19,7 +19,8 @@ int __init arm_cpuidle_init(unsigned int cpu)
 {
 	int ret = -EOPNOTSUPP;
 
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle)
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_suspend &&
+			cpu_ops[cpu]->cpu_init_idle)
 		ret = cpu_ops[cpu]->cpu_init_idle(cpu);
 
 	return ret;
@@ -36,11 +37,5 @@ int arm_cpuidle_suspend(int index)
 {
 	int cpu = smp_processor_id();
 
-	/*
-	 * If cpu_ops have not been registered or suspend
-	 * has not been initialized, cpu_suspend call fails early.
-	 */
-	if (!cpu_ops[cpu] |