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
  ...

Documentation/arm64/booting.txt

@@ -132,6 +132,10 @@ NOTE: versions prior to v4.6 cannot make use of memory below the
 physical offset of the Image so it is recommended that the Image be
 placed as close as possible to the start of system RAM.
 
+If an initrd/initramfs is passed to the kernel at boot, it must reside
+entirely within a 1 GB aligned physical memory window of up to 32 GB in
+size that fully covers the kernel Image as well.
+
 Any memory described to the kernel (even that below the start of the
 image) which is not marked as reserved from the kernel (e.g., with a
 memreserve region in the device tree) will be considered as available to

Documentation/devicetree/bindings/numa.txt

@@ -0,0 +1,275 @@
+==============================================================================
+NUMA binding description.
+==============================================================================
+
+==============================================================================
+1 - Introduction
+==============================================================================
+
+Systems employing a Non Uniform Memory Access (NUMA) architecture contain
+collections of hardware resources including processors, memory, and I/O buses,
+that comprise what is commonly known as a NUMA node.
+Processor accesses to memory within the local NUMA node is generally faster
+than processor accesses to memory outside of the local NUMA node.
+DT defines interfaces that allow the platform to convey NUMA node
+topology information to OS.
+
+==============================================================================
+2 - numa-node-id
+==============================================================================
+
+For the purpose of identification, each NUMA node is associated with a unique
+token known as a node id. For the purpose of this binding
+a node id is a 32-bit integer.
+
+A device node is associated with a NUMA node by the presence of a
+numa-node-id property which contains the node id of the device.
+
+Example:
+	/* numa node 0 */
+	numa-node-id = <0>;
+
+	/* numa node 1 */
+	numa-node-id = <1>;
+
+==============================================================================
+3 - distance-map
+==============================================================================
+
+The optional device tree node distance-map describes the relative
+distance (memory latency) between all numa nodes.
+
+- compatible : Should at least contain "numa-distance-map-v1".
+
+- distance-matrix
+  This property defines a matrix to describe the relative distances
+  between all numa nodes.
+  It is represented as a list of node pairs and their relative distance.
+
+  Note:
+	1. Each entry represents distance from first node to second node.
+	The distances are equal in either direction.
+	2. The distance from a node to self (local distance) is represented
+	with value 10 and all internode distance should be represented with
+	a value greater than 10.
+	3. distance-matrix should have entries in lexicographical ascending
+	order of nodes.
+	4. There must be only one device node distance-map which must
+	reside in the root node.
+	5. If the distance-map node is not present, a default
+	distance-matrix is used.
+
+Example:
+	4 nodes connected in mesh/ring topology as below,
+
+		0_______20______1
+		|               |
+		|               |
+		20             20
+		|               |
+		|               |
+		|_______________|
+		3       20      2
+
+	if relative distance for each hop is 20,
+	then internode distance would be,
+	      0 -> 1 = 20
+	      1 -> 2 = 20
+	      2 -> 3 = 20
+	      3 -> 0 = 20
+	      0 -> 2 = 40
+	      1 -> 3 = 40
+
+     and dt presentation for this distance matrix is,
+
+		distance-map {
+			 compatible = "numa-distance-map-v1";
+			 distance-matrix = <0 0  10>,
+					   <0 1  20>,
+					   <0 2  40>,
+					   <0 3  20>,
+					   <1 0  20>,
+					   <1 1  10>,
+					   <1 2  20>,
+					   <1 3  40>,
+					   <2 0  40>,
+					   <2 1  20>,
+					   <2 2  10>,
+					   <2 3  20>,
+					   <3 0  20>,
+					   <3 1  40>,
+					   <3 2  20>,
+					   <3 3  10>;
+		};
+
+==============================================================================
+4 - Example dts
+==============================================================================
+
+Dual socket system consists of 2 boards connected through ccn bus and
+each board having one socket/soc of 8 cpus, memory and pci bus.
+
+	memory@c00000 {
+		device_type = "memory";
+		reg = <0x0 0xc00000 0x0 0x80000000>;
+		/* node 0 */
+		numa-node-id = <0>;
+	};
+
+	memory@10000000000 {
+		device_type = "memory";
+		reg = <0x100 0x0 0x0 0x80000000>;
+		/* node 1 */
+		numa-node-id = <1>;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x0>;
+			enable-method = "psci";
+			/* node 0 */
+			numa-node-id = <0>;
+		};
+		cpu@1 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x1>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@2 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x2>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@3 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x3>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@4 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x4>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@5 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x5>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@6 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x6>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@7 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x7>;
+			enable-method = "psci";
+			numa-node-id = <0>;
+		};
+		cpu@8 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x8>;
+			enable-method = "psci";
+			/* node 1 */
+			numa-node-id = <1>;
+		};
+		cpu@9 {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0x9>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@a {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xa>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@b {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xb>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@c {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xc>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@d {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xd>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@e {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xe>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+		cpu@f {
+			device_type = "cpu";
+			compatible =  "arm,armv8";
+			reg = <0x0 0xf>;
+			enable-method = "psci";
+			numa-node-id = <1>;
+		};
+	};
+
+	pcie0: pcie0@848000000000 {
+		compatible = "arm,armv8";
+		device_type = "pci";
+		bus-range = <0 255>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0x8480 0x00000000 0 0x10000000>;  /* Configuration space */
+		ranges = <0x03000000 0x8010 0x00000000 0x8010 0x00000000 0x70 0x00000000>;
+		/* node 0 */
+		numa-node-id = <0>;
+        };
+
+	pcie1: pcie1@948000000000 {
+		compatible = "arm,armv8";
+		device_type = "pci";
+		bus-range = <0 255>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0x9480 0x00000000 0 0x10000000>;  /* Configuration space */
+		ranges = <0x03000000 0x9010 0x00000000 0x9010 0x00000000 0x70 0x00000000>;
+		/* node 1 */
+		numa-node-id = <1>;
+        };
+
+	distance-map {
+		compatible = "numa-distance-map-v1";
+		distance-matrix = <0 0 10>,
+				  <0 1 20>,
+				  <1 1 10>;
+	};

Documentation/kernel-parameters.txt

@@ -168,16 +168,18 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	acpi=		[HW,ACPI,X86,ARM64]
 			Advanced Configuration and Power Interface
-			Format: { force | off | strict | noirq | rsdt |
+			Format: { force | on | off | strict | noirq | rsdt |
 				  copy_dsdt }
 			force -- enable ACPI if default was off
+			on -- enable ACPI but allow fallback to DT [arm64]
 			off -- disable ACPI if default was on
 			noirq -- do not use ACPI for IRQ routing
 			strict -- Be less tolerant of platforms that are not
 				strictly ACPI specification compliant.
 			rsdt -- prefer RSDT over (default) XSDT
 			copy_dsdt -- copy DSDT to memory
-			For ARM64, ONLY "acpi=off" or "acpi=force" are available
+			For ARM64, ONLY "acpi=off", "acpi=on" or "acpi=force"
+			are available
 
 			See also Documentation/power/runtime_pm.txt, pci=noacpi
 

arch/arm/include/asm/kvm_host.h

@@ -265,6 +265,15 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
+static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+					phys_addr_t phys_idmap_start)
+{
+	/*
+	 * TODO
+	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
+	 */
+}
+
 static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 {
 	return 0;
@@ -277,7 +286,6 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 
-static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

arch/arm/include/asm/kvm_mmu.h

@@ -66,6 +66,7 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
+phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

arch/arm/kvm/arm.c

@@ -16,7 +16,6 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  */
 
-#include <linux/cpu.h>
 #include <linux/cpu_pm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -66,6 +65,8 @@ static DEFINE_SPINLOCK(kvm_vmid_lock);
 
 static bool vgic_present;
 
+static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
+
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
@@ -90,11 +91,6 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
 	return &kvm_arm_running_vcpu;
 }
 
-int kvm_arch_hardware_enable(void)
-{
-	return 0;
-}
-
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -1033,11 +1029,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }
 
-static void cpu_init_stage2(void *dummy)
-{
-	__cpu_init_stage2();
-}
-
 static void cpu_init_hyp_mode(void *dummy)
 {
 	phys_addr_t boot_pgd_ptr;
@@ -1065,43 +1056,87 @@ static void cpu_hyp_reinit(void)
 {
 	if (is_kernel_in_hyp_mode()) {
 		/*
-		 * cpu_init_stage2() is safe to call even if the PM
+		 * __cpu_init_stage2() is safe to call even if the PM
 		 * event was cancelled before the CPU was reset.
 		 */
-		cpu_init_stage2(NULL);
+		__cpu_init_stage2();
 	} else {
 		if (__hyp_get_vectors() == hyp_default_vectors)
 			cpu_init_hyp_mode(NULL);
 	}
 }
 
-static int hyp_init_cpu_notify(struct notifier_block *self,
-			       unsigned long action, void *cpu)
+static void cpu_hyp_reset(void)
+{
+	phys_addr_t boot_pgd_ptr;
+	phys_addr_t phys_idmap_start;
+
+	if (!is_kernel_in_hyp_mode()) {
+		boot_pgd_ptr = kvm_mmu_get_boot_httbr();
+		phys_idmap_start = kvm_get_idmap_start();
+
+		__cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);
+	}
+}
+
+static void _kvm_arch_hardware_enable(void *discard)
 {
-	switch (action) {
-	case CPU_STARTING:
-	case CPU_STARTING_FROZEN:
+	if (!__this_cpu_read(kvm_arm_hardware_enabled)) {
 		cpu_hyp_reinit();
+		__this_cpu_write(kvm_arm_hardware_enabled, 1);
 	}
+}
+
+int kvm_arch_hardware_enable(void)
+{
+	_kvm_arch_hardware_enable(NULL);
+	return 0;
+}
 
-	return NOTIFY_OK;
+static void _kvm_arch_hardware_disable(void *discard)
+{
+	if (__this_cpu_read(kvm_arm_hardware_enabled)) {
+		cpu_hyp_reset();
+		__this_cpu_write(kvm_arm_hardware_enabled, 0);
+	}
 }
 
-static struct notifier_block hyp_init_cpu_nb = {
-	.notifier_call = hyp_init_cpu_notify,
-};
+void kvm_arch_hardware_disable(void)
+{
+	_kvm_arch_hardware_disable(NULL);
+}
 
 #ifdef CONFIG_CPU_PM
 static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT) {
-		cpu_hyp_reinit();
+	/*
+	 * kvm_arm_hardware_enabled is left with its old value over
+	 * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should
+	 * re-enable hyp.
+	 */
+	switch (cmd) {
+	case CPU_PM_ENTER:
+		if (__this_cpu_read(kvm_arm_hardware_enabled))
+			/*
+			 * don't update kvm_arm_hardware_enabled here
+			 * so that the hardware will be re-enabled
+			 * when we resume. See below.
+			 */
+			cpu_hyp_reset();
+
+		return NOTIFY_OK;
+	case CPU_PM_EXIT:
+		if (__this_cpu_read(kvm_arm_hardware_enabled))
+			/* The hardware was enabled before suspend. */
+			cpu_hyp_reinit();
+
 		return NOTIFY_OK;
-	}
 
-	return NOTIFY_DONE;
+	default:
+		return NOTIFY_DONE;
+	}
 }
 
 static struct notifier_block hyp_init_cpu_pm_nb = {
@@ -1143,16 +1178,12 @@ static int init_common_resources(void)
 
 static int init_subsystems(void)
 {
-	int err;
+	int err = 0;
 
 	/*
-	 * Register CPU Hotplug notifier
+	 * Enable hardware so that subsystem initialisation can access EL2.
 	 */
-	err = register_cpu_notifier(&hyp_init_cpu_nb);
-	if (err) {
-		kvm_err("Cannot register KVM init CPU notifier (%d)\n", err);
-		return err;
-	}
+	on_each_cpu(_kvm_arch_hardware_enable, NULL, 1);
 
 	/*
 	 * Register CPU lower-power notifier
@@ -1170,9 +1201,10 @@ static int init_subsystems(void)
 	case -ENODEV:
 	case -ENXIO:
 		vgic_present = false;
+		err = 0;
 		break;
 	default:
-		return err;
+		goto out;
 	}
 
 	/*
@@ -1180,12 +1212,15 @@ static int init_subsystems(void)
 	 */
 	err = kvm_timer_hyp_init();
 	if (err)
-		return err;
+		goto out;
 
 	kvm_perf_init();
 	kvm_coproc_table_init();
 
-	return 0;
+out:
+	on_each_cpu(_kvm_arch_hardware_disable, NULL, 1);
+
+	return err;
 }
 
 static void teardown_hyp_mode(void)
@@ -1198,17 +1233,11 @@ static void teardown_hyp_mode(void)
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu)
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
-	unregister_cpu_notifier(&hyp_init_cpu_nb);
 	hyp_cpu_pm_exit();
 }
 
 static int init_vhe_mode(void)
 {
-	/*
-	 * Execute the init code on each CPU.
-	 */
-	on_each_cpu(cpu_init_stage2, NULL, 1);
-
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
 	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
@@ -1295,11 +1324,6 @@ static int init_hyp_mode(void)
 		}
 	}
 
-	/*
-	 * Execute the init code on each CPU.
-	 */
-	on_each_cpu(cpu_init_hyp_mode, NULL, 1);
-
 #ifndef CONFIG_HOTPLUG_CPU
 	free_boot_hyp_pgd();
 #endif

arch/arm/kvm/mmu.c

@@ -1666,6 +1666,11 @@ phys_addr_t kvm_get_idmap_vector(void)
 	return hyp_idmap_vector;
 }
 
+phys_addr_t kvm_get_idmap_start(void)
+{
+	return hyp_idmap_start;
+}
+
 int kvm_mmu_init(void)
 {
 	int err;

arch/arm64/Kconfig

@@ -11,6 +11,7 @@ config ARM64
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_NUMA_BALANCING
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select ARCH_WANT_FRAME_POINTERS
@@ -58,11 +59,14 @@ config ARM64
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+	select HAVE_ARM_SMCCC
 	select HAVE_BPF_JIT
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
+	select HAVE_CONTEXT_TRACKING
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
@@ -76,6 +80,7 @@ config ARM64
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP if NUMA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -89,15 +94,13 @@ config ARM64
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
+	select OF_NUMA if NUMA && OF
 	select OF_RESERVED_MEM
 	select PERF_USE_VMALLOC
 	select POWER_RESET
 	select POWER_SUPPLY
-	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
-	select HAVE_CONTEXT_TRACKING
-	select HAVE_ARM_SMCCC
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -546,10 +549,35 @@ config HOTPLUG_CPU
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
+# Common NUMA Features
+config NUMA
+	bool "Numa Memory Allocation and Scheduler Support"
+	depends on SMP
+	help
+	  Enable NUMA (Non Uniform Memory Access) support.
+
+	  The kernel will try to allocate memory used by a CPU on the
+	  local memory of the CPU and add some more
+	  NUMA awareness to the kernel.
+
+config NODES_SHIFT
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 10
+	default "2"
+	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
+
+config USE_PERCPU_NUMA_NODE_ID
+	def_bool y
+	depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	depends on !HIBERNATION
 	def_bool y
 
 config ARCH_HAS_HOLES_MEMORYMODEL
@@ -578,9 +606,6 @@ config SYS_SUPPORTS_HUGETLBFS
 config ARCH_WANT_HUGE_PMD_SHARE
 	def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
 
-config HAVE_ARCH_TRANSPARENT_HUGEPAGE
-	def_bool y
-
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
@@ -953,6 +978,14 @@ menu "Power management options"
 
 source "kernel/power/Kconfig"
 
+config ARCH_HIBERNATION_POSSIBLE
+	def_bool y
+	depends on CPU_PM
+
+config ARCH_HIBERNATION_HEADER
+	def_bool y
+	depends on HIBERNATION
+
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 

arch/arm64/Kconfig.debug

@@ -59,7 +59,7 @@ config DEBUG_RODATA
 	  If in doubt, say Y
 
 config DEBUG_ALIGN_RODATA
-	depends on DEBUG_RODATA && ARM64_4K_PAGES
+	depends on DEBUG_RODATA
 	bool "Align linker sections up to SECTION_SIZE"
 	help
 	  If this option is enabled, sections that may potentially be marked as

arch/arm64/include/asm/assembler.h

@@ -1,5 +1,5 @@
 /*
- * Based on arch/arm/include/asm/assembler.h
+ * Based on arch/arm/include/asm/assembler.h, arch/arm/mm/proc-macros.S
  *
  * Copyright (C) 1996-2000 Russell King
  * Copyright (C) 2012 ARM Ltd.
@@ -23,21 +23,12 @@
 #ifndef __ASM_ASSEMBLER_H
 #define __ASM_ASSEMBLER_H
 
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 
-/*
- * Stack pushing/popping (register pairs only). Equivalent to store decrement
- * before, load increment after.
- */
-	.macro	push, xreg1, xreg2
-	stp	\xreg1, \xreg2, [sp, #-16]!
-	.endm
-
-	.macro	pop, xreg1, xreg2
-	ldp	\xreg1, \xreg2, [sp], #16
-	.endm
-
 /*
  * Enable and disable interrupts.
  */
@@ -211,6 +202,102 @@ lr	.req	x30		// link register
 	add	\reg, \reg, \tmp
 	.endm
 
+/*
+ * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
+ */
+	.macro	vma_vm_mm, rd, rn
+	ldr	\rd, [\rn, #VMA_VM_MM]
+	.endm
+
+/*
+ * mmid - get context id from mm pointer (mm->context.id)
+ */
+	.macro	mmid, rd, rn
+	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+	.endm
+
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ */
+	.macro	dcache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrs	\tmp, ctr_el0			// read CTR
+	and	\tmp, \tmp, #0xf		// cache line size encoding
+	mov	\reg, #4			// bytes per word
+	lsl	\reg, \reg, \tmp		// actual cache line size
+	.endm
+
+/*
+ * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
+ */
+	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
+#ifndef CONFIG_ARM64_VA_BITS_48
+	ldr_l	\tmpreg, idmap_t0sz
+	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+#endif
+	.endm
+
+/*
+ * Macro to perform a data cache maintenance for the interval
+ * [kaddr, kaddr + size)
+ *
+ * 	op:		operation passed to dc instruction
+ * 	domain:		domain used in dsb instruciton
+ * 	kaddr:		starting virtual address of the region
+ * 	size:		size of the region
+ * 	Corrupts:	kaddr, size, tmp1, tmp2
+ */
+	.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
+	dcache_line_size \tmp1, \tmp2
+	add	\size, \kaddr, \size
+	sub	\tmp2, \tmp1, #1
+	bic	\kaddr, \kaddr, \tmp2
+9998:	dc	\op, \kaddr
+	add	\kaddr, \kaddr, \tmp1
+	cmp	\kaddr, \size
+	b.lo	9998b
+	dsb	\domain
+	.endm
+
+/*
+ * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
+ */
+	.macro	reset_pmuserenr_el0, tmpreg
+	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
+	sbfx	\tmpreg, \tmpreg, #8, #4
+	cmp	\tmpreg, #1			// Skip if no PMU present
+	b.lt	9000f
+	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
+9000:
+	.endm
+
+/*
+ * copy_page - copy src to dest using temp registers t1-t8
+ */
+	.macro copy_page dest:req src:req t1:req t2:req t3:req t4:req t5:req t6:req t7:req t8:req
+9998:	ldp	\t1, \t2, [\src]
+	ldp	\t3, \t4, [\src, #16]
+	ldp	\t5, \t6, [\src, #32]
+	ldp	\t7, \t8, [\src, #48]
+	add	\src, \src, #64
+	stnp	\t1, \t2, [\dest]
+	stnp	\t3, \t4, [\dest, #16]
+	stnp	\t5, \t6, [\dest, #32]
+	stnp	\t7, \t8, [\dest, #48]
+	add	\dest, \dest, #64
+	tst	\src, #(PAGE_SIZE - 1)
+	b.ne	9998b
+	.endm
+
 /*
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
@@ -233,4 +320,24 @@ lr	.req	x30		// link register
 	.long	\sym\()_hi32
 	.endm
 
+	/*
+	 * mov_q - move an immediate constant into a 64-bit register using
+	 *         between 2 and 4 movz/movk instructions (depending on the
+	 *         magnitude and sign of the operand)
+	 */
+	.macro	mov_q, reg, val
+	.if (((\val) >> 31) == 0 || ((\val) >> 31) == 0x1ffffffff)
+	movz	\reg, :abs_g1_s:\val
+	.else
+	.if (((\val) >> 47) == 0 || ((\val) >> 47) == 0x1ffff)
+	movz	\reg, :abs_g2_s:\val
+	.else
+	movz	\reg, :abs_g3:\val
+	movk	\reg, :abs_g2_nc:\val
+	.endif
+	movk	\reg, :abs_g1_nc:\val
+	.endif
+	movk	\reg, :abs_g0_nc:\val
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */

arch/arm64/include/asm/cpufeature.h

@@ -35,8 +35,9 @@
 #define ARM64_ALT_PAN_NOT_UAO			10
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
+#define ARM64_HAS_32BIT_EL0			13
 
-#define ARM64_NCAPS				13
+#define ARM64_NCAPS				14
 
 #ifndef __ASSEMBLY__
 
@@ -77,10 +78,17 @@ struct arm64_ftr_reg {
 	struct arm64_ftr_bits	*ftr_bits;
 };
 
+/* scope of capability check */
+enum {
+	SCOPE_SYSTEM,
+	SCOPE_LOCAL_CPU,
+};
+
 struct arm64_cpu_capabilities {
 	const char *desc;
 	u16 capability;
-	bool (*matches)(const struct arm64_cpu_capabilities *);
+	int def_scope;			/* default scope */
+	bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope);
 	void (*enable)(void *);		/* Called on all active CPUs */
 	union {
 		struct {	/* To be used for erratum handling only */
@@ -101,6 +109,8 @@ struct arm64_cpu_capabilities {
 
 extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
+bool this_cpu_has_cap(unsigned int cap);
+
 static inline bool cpu_have_feature(unsigned int num)
 {
 	return elf_hwcap & (1UL << num);
@@ -170,12 +180,20 @@ static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
 		cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1;
 }
 
+static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
+{
+	u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL0_SHIFT);
+
+	return val == ID_AA64PFR0_EL0_32BIT_64BIT;
+}
+
 void __init setup_cpu_features(void);
 
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void check_local_cpu_errata(void);
 
+void verify_local_cpu_errata(void);
 void verify_local_cpu_capabilities(void);
 
 u64 read_system_reg(u32 id);
@@ -185,6 +203,11 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1));
 }
 
+static inline bool system_supports_32bit_el0(void)
+{
+	return cpus_have_cap(ARM64_HAS_32BIT_EL0);
+}
+
 static inline bool system_supports_mixed_endian_el0(void)
 {
 	return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));

arch/arm64/include/asm/elf.h

@@ -177,7 +177,8 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 
 /* AArch32 EABI. */
 #define EF_ARM_EABI_MASK		0xff000000
-#define compat_elf_check_arch(x)	(((x)->e_machine == EM_ARM) && \
+#define compat_elf_check_arch(x)	(system_supports_32bit_el0() && \
+					 ((x)->e_machine == EM_ARM) && \
 					 ((x)->e_flags & EF_ARM_EABI_MASK))
 
 #define compat_start_thread		compat_start_thread

arch/arm64/include/asm/kernel-pgtable.h

@@ -19,6 +19,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
+#include <asm/sparsemem.h>
 
 /*
  * The linear mapping and the start of memory are both 2M aligned (per
@@ -86,10 +87,24 @@
  * (64k granule), or a multiple that can be mapped using contiguous bits
  * in the page tables: 32 * PMD_SIZE (16k granule)
  */
-#ifdef CONFIG_ARM64_64K_PAGES
-#define ARM64_MEMSTART_ALIGN	SZ_512M
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ARM64_MEMSTART_SHIFT		PUD_SHIFT
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ARM64_MEMSTART_SHIFT		(PMD_SHIFT + 5)
 #else
-#define ARM64_MEMSTART_ALIGN	SZ_1G
+#define ARM64_MEMSTART_SHIFT		PMD_SHIFT
+#endif
+
+/*
+ * sparsemem vmemmap imposes an additional requirement on the alignment of
+ * memstart_addr, due to the fact that the base of the vmemmap region
+ * has a direct correspondence, and needs to appear sufficiently aligned
+ * in the virtual address space.
+ */
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS
+#define ARM64_MEMSTART_ALIGN	(1UL << SECTION_SIZE_BITS)
+#else
+#define ARM64_MEMSTART_ALIGN	(1UL << ARM64_MEMSTART_SHIFT)
 #endif
 
 #endif	/* __ASM_KERNEL_PGTABLE_H */

arch/arm64/include/asm/kvm_arm.h

@@ -84,17 +84,6 @@
 #define HCR_INT_OVERRIDE   (HCR_FMO | HCR_IMO)
 #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H)
 
-/* Hyp System Control Register (SCTLR_EL2) bits */
-#define SCTLR_EL2_EE	(1 << 25)
-#define SCTLR_EL2_WXN	(1 << 19)
-#define SCTLR_EL2_I	(1 << 12)
-#define SCTLR_EL2_SA	(1 << 3)
-#define SCTLR_EL2_C	(1 << 2)
-#define SCTLR_EL2_A	(1 << 1)
-#define SCTLR_EL2_M	1
-#define SCTLR_EL2_FLAGS	(SCTLR_EL2_M | SCTLR_EL2_A | SCTLR_EL2_C |	\
-			 SCTLR_EL2_SA | SCTLR_EL2_I)
-
 /* TCR_EL2 Registers bits */
 #define TCR_EL2_RES1	((1 << 31) | (1 << 23))
 #define TCR_EL2_TBI	(1 << 20)

arch/arm64/include/asm/kvm_asm.h

@@ -22,6 +22,8 @@
 
 #define ARM_EXCEPTION_IRQ	  0
 #define ARM_EXCEPTION_TRAP	  1
+/* The hyp-stub will return this for any kvm_call_hyp() call */
+#define ARM_EXCEPTION_HYP_GONE	  2
 
 #define KVM_ARM64_DEBUG_DIRTY_SHIFT	0
 #define KVM_ARM64_DEBUG_DIRTY		(1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
@@ -40,6 +42,7 @@ struct kvm_vcpu;
 
 extern char __kvm_hyp_init[];
 extern char __kvm_hyp_init_end[];
+extern char __kvm_hyp_reset[];
 
 extern char __kvm_hyp_vector[];
 

arch/arm64/include/asm/kvm_host.h

@@ -46,6 +46,8 @@
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
+unsigned long kvm_hyp_reset_entry(void);
+void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
 struct kvm_arch {
 	/* The VMID generation used for the virt. memory system */
@@ -352,7 +354,17 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 		       hyp_stack_ptr, vector_ptr);
 }
 
-static inline void kvm_arch_hardware_disable(void) {}
+static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+					phys_addr_t phys_idmap_start)
+{
+	/*
+	 * Call reset code, and switch back to stub hyp vectors.
+	 * Uses __kvm_call_hyp() to avoid kaslr's kvm_ksym_ref() translation.
+	 */
+	__kvm_call_hyp((void *)kvm_hyp_reset_entry(),
+		       boot_pgd_ptr, phys_idmap_start);
+}
+
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
 static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

arch/arm64/include/asm/kvm_mmu.h

@@ -109,6 +109,7 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
+phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

arch/arm64/include/asm/memory.h

@@ -39,6 +39,21 @@
  */
 #define PCI_IO_SIZE		SZ_16M
 
+/*
+ * Log2 of the upper bound of the size of a struct page. Used for sizing
+ * the vmemmap region only, does not affect actual memory footprint.
+ * We don't use sizeof(struct page) directly since taking its size here
+ * requires its definition to be available at this point in the inclusion
+ * chain, and it may not be a power of 2 in the first place.
+ */
+#define STRUCT_PAGE_MAX_SHIFT	6
+
+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ *                a struct page array
+ */
+#define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT))
+
 /*
  * PAGE_OFFSET - the virtual address of the start of the kernel image (top
  *		 (VA_BITS - 1))
@@ -54,7 +69,8 @@
 #define MODULES_END		(MODULES_VADDR + MODULES_VSIZE)
 #define MODULES_VADDR		(VA_START + KASAN_SHADOW_SIZE)
 #define MODULES_VSIZE		(SZ_128M)
-#define PCI_IO_END		(PAGE_OFFSET - SZ_2M)
+#define VMEMMAP_START		(PAGE_OFFSET - VMEMMAP_SIZE)
+#define PCI_IO_END		(VMEMMAP_START - SZ_2M)
 #define PCI_IO_START		(PCI_IO_END - PCI_IO_SIZE)
 #define FIXADDR_TOP		(PCI_IO_START - SZ_2M)
 #define TASK_SIZE_64		(UL(1) << VA_BITS)
@@ -71,6 +87,9 @@
 
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 4))
 
+#define KERNEL_START      _text
+#define KERNEL_END        _end
+
 /*
  * The size of the KASAN shadow region. This should be 1/8th of the
  * size of the entire kernel virtual address space.
@@ -192,9 +211,19 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define	virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#else
+#define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
+#define __page_to_voff(kaddr)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
 
+#define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
+#define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
+
+#define virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+					   + PHYS_OFFSET) >> PAGE_SHIFT)
+#endif
 #endif
 
 #include <asm-generic/memory_model.h>

arch/arm64/include/asm/mmu.h

@@ -29,6 +29,7 @@ typedef struct {
 #define ASID(mm)	((mm)->context.id.counter & 0xffff)
 
 extern void paging_init(void);
+extern void bootmem_init(void);
 extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,

arch/arm64/include/asm/mmzone.h

@@ -0,0 +1,12 @@
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */

arch/arm64/include/asm/numa.h

@@ -0,0 +1,45 @@
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+
+#ifdef CONFIG_NUMA
+
+/* currently, arm64 implements flat NUMA topology */
+#define parent_node(node)	(node)
+
+int __node_distance(int from, int to);
+#define node_distance(a, b) __node_distance(a, b)
+
+extern nodemask_t numa_nodes_parsed __initdata;
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+void numa_clear_node(unsigned int cpu);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+	return node_to_cpumask_map[node];
+}
+#endif
+
+void __init arm64_numa_init(void);
+int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+void __init numa_set_distance(int from, int to, int distance);
+void __init numa_free_distance(void);
+void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+void numa_store_cpu_info(unsigned int cpu);
+
+#else	/* CONFIG_NUMA */
+
+static inline void numa_store_cpu_info(unsigned int cpu) { }
+static inline void arm64_numa_init(void) { }
+static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+
+#endif	/* CONFIG_NUMA */
+
+#endif	/* __ASM_NUMA_H */

arch/arm64/include/asm/page.h

@@ -19,6 +19,8 @@
 #ifndef __ASM_PAGE_H
 #define __ASM_PAGE_H
 
+#include <linux/const.h>
+
 /* PAGE_SHIFT determines the page size */
 /* CONT_SHIFT determines the number of pages which can be tracked together  */
 #ifdef CONFIG_ARM64_64K_PAGES

arch/arm64/include/asm/pgtable-hwdef.h

@@ -133,7 +133,6 @@
  * Section
  */
 #define PMD_SECT_VALID		(_AT(pmdval_t, 1) << 0)
-#define PMD_SECT_PROT_NONE	(_AT(pmdval_t, 1) << 58)
 #define PMD_SECT_USER		(_AT(pmdval_t, 1) << 6)		/* AP[1] */
 #define PMD_SECT_RDONLY		(_AT(pmdval_t, 1) << 7)		/* AP[2] */
 #define PMD_SECT_S		(_AT(pmdval_t, 3) << 8)

arch/arm64/include/asm/pgtable-types.h

@@ -27,10 +27,6 @@ typedef u64 pmdval_t;
 typedef u64 pudval_t;
 typedef u64 pgdval_t;
 
-#undef STRICT_MM_TYPECHECKS
-
-#ifdef STRICT_MM_TYPECHECKS
-
 /*
  * These are used to make use of C type-checking..
  */
@@ -58,34 +54,6 @@ typedef struct { pteval_t pgprot; } pgprot_t;
 #define pgprot_val(x)	((x).pgprot)
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
-#else	/* !STRICT_MM_TYPECHECKS */
-
-typedef pteval_t pte_t;
-#define pte_val(x)	(x)
-#define __pte(x)	(x)
-
-#if CONFIG_PGTABLE_LEVELS > 2
-typedef pmdval_t pmd_t;
-#define pmd_val(x)	(x)
-#define __pmd(x)	(x)
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 3
-typedef pudval_t pud_t;
-#define pud_val(x)	(x)
-#define __pud(x)	(x)
-#endif
-
-typedef pgdval_t pgd_t;
-#define pgd_val(x)	(x)
-#define __pgd(x)	(x)
-
-typedef pteval_t pgprot_t;
-#define pgprot_val(x)	(x)
-#define __pgprot(x)	(x)
-
-#endif /* STRICT_MM_TYPECHECKS */
-
 #if CONFIG_PGTABLE_LEVELS == 2
 #include <asm-generic/pgtable-nopmd.h>
 #elif CONFIG_PGTABLE_LEVELS == 3

arch/arm64/include/asm/pgtable.h

@@ -24,22 +24,16 @@
 #include <asm/pgtable-prot.h>
 
 /*
- * VMALLOC and SPARSEMEM_VMEMMAP ranges.
+ * VMALLOC range.
  *
- * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array
- *	(rounded up to PUD_SIZE).
  * VMALLOC_START: beginning of the kernel vmalloc space
- * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
- *	fixed mappings and modules
+ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space
+ *	and fixed mappings
  */
-#define VMEMMAP_SIZE		ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
-
 #define VMALLOC_START		(MODULES_END)
 #define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
-#define VMEMMAP_START		(VMALLOC_END + SZ_64K)
-#define vmemmap			((struct page *)VMEMMAP_START - \
-				 SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT))
+#define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
 
 #define FIRST_USER_ADDRESS	0UL
 
@@ -58,7 +52,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  * for zero-mapped memory areas etc..
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr)	virt_to_page(empty_zero_page)
+#define ZERO_PAGE(vaddr)	pfn_to_page(PHYS_PFN(__pa(empty_zero_page)))
 
 #define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
 
@@ -272,6 +266,21 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot)
 	return __pgprot(pgprot_val(prot) & ~PTE_TABLE_BIT);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+/*
+ * See the comment in include/asm-generic/pgtable.h
+ */
+static inline int pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) == PTE_PROT_NONE;
+}
+
+static inline int pmd_protnone(pmd_t pmd)
+{
+	return pte_protnone(pmd_pte(pmd));
+}
+#endif
+
 /*
  * THP definitions.
  */
@@ -280,15 +289,16 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot)
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#define pmd_present(pmd)	pte_present(pmd_pte(pmd))
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
-#define pmd_mkclean(pmd)       pte_pmd(pte_mkclean(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
-#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
+#define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_SECT_VALID))
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
@@ -327,9 +337,8 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				     unsigned long size, pgprot_t vma_prot);
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
-#define pmd_present(pmd)	(pmd_val(pmd))
 
-#define pmd_bad(pmd)		(!(pmd_val(pmd) & 2))
+#define pmd_bad(pmd)		(!(pmd_val(pmd) & PMD_TABLE_BIT))
 
 #define pmd_table(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_TABLE)
@@ -394,7 +403,7 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
 
 #define pud_none(pud)		(!pud_val(pud))
-#define pud_bad(pud)		(!(pud_val(pud) & 2))
+#define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
 #define pud_present(pud)	(pud_val(pud))
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
@@ -526,6 +535,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 }
 
 #ifdef CONFIG_ARM64_HW_AFDBM
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp,
+					pmd_t entry, int dirty)
+{
+	return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty);
+}
+#endif
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -578,9 +602,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define __HAVE_ARCH_PMDP_GET_AND_CLEAR
-static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pmd_t *pmdp)
+#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
+static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+					    unsigned long address, pmd_t *pmdp)
 {
 	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
 }

arch/arm64/include/asm/smp.h

@@ -113,6 +113,17 @@ static inline void update_cpu_boot_status(int val)
 	dsb(ishst);
 }
 
+/*
+ * The calling secondary CPU has detected serious configuration mismatch,
+ * which calls for a kernel panic. Update the boot status and park the calling
+ * CPU.
+ */
+static inline void cpu_panic_kernel(void)
+{
+	update_cpu_boot_status(CPU_PANIC_KERNEL);
+	cpu_park_loop();
+}
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */

arch/arm64/include/asm/suspend.h

@@ -1,7 +1,8 @@
 #ifndef __ASM_SUSPEND_H
 #define __ASM_SUSPEND_H
 
-#define NR_CTX_REGS 11
+#define NR_CTX_REGS 10
+#define NR_CALLEE_SAVED_REGS 12
 
 /*
  * struct cpu_suspend_ctx must be 16-byte aligned since it is allocated on
@@ -16,11 +17,34 @@ struct cpu_suspend_ctx {
 	u64 sp;
 } __aligned(16);
 
-struct sleep_save_sp {
-	phys_addr_t *save_ptr_stash;
-	phys_addr_t save_ptr_stash_phys;
+/*
+ * Memory to save the cpu state is allocated on the stack by
+ * __cpu_suspend_enter()'s caller, and populated by __cpu_suspend_enter().
+ * This data must survive until cpu_resume() is called.
+ *
+ * This struct desribes the size and the layout of the saved cpu state.
+ * The layout of the callee_saved_regs is defined by the implementation
+ * of __cpu_suspend_enter(), and cpu_resume(). This struct must be passed
+ * in by the caller as __cpu_suspend_enter()'s stack-frame is gone once it
+ * returns, and the data would be subsequently corrupted by the call to the
+ * finisher.
+ */
+struct sleep_stack_data {
+	struct cpu_suspend_ctx	system_regs;
+	unsigned long		callee_saved_regs[NR_CALLEE_SAVED_REGS];
 };
 
+extern unsigned long *sleep_save_stash;
+
 extern int cpu_suspend(unsigned long arg, int (*fn)(unsigned long));
 extern void cpu_resume(void);
+int __cpu_suspend_enter(struct sleep_stack_data *state);
+void __cpu_suspend_exit(void);
+void _cpu_resume(void);
+
+int swsusp_arch_suspend(void);
+int swsusp_arch_resume(void);
+int arch_hibernation_header_save(void *addr, unsigned int max_size);
+int arch_hibernation_header_restore(void *addr);
+
 #endif

arch/arm64/include/asm/sysreg.h

@@ -86,10 +86,21 @@
 #define SET_PSTATE_UAO(x) __inst_arm(0xd5000000 | REG_PSTATE_UAO_IMM |\
 				     (!!x)<<8 | 0x1f)
 
-/* SCTLR_EL1 */
-#define SCTLR_EL1_CP15BEN	(0x1 << 5)
-#define SCTLR_EL1_SED		(0x1 << 8)
-#define SCTLR_EL1_SPAN		(0x1 << 23)
+/* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_EE    (1 << 25)
+#define SCTLR_ELx_I	(1 << 12)
+#define SCTLR_ELx_SA	(1 << 3)
+#define SCTLR_ELx_C	(1 << 2)
+#define SCTLR_ELx_A	(1 << 1)
+#define SCTLR_ELx_M	1
+
+#define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
+			 SCTLR_ELx_SA | SCTLR_ELx_I)
+
+/* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_SPAN		(1 << 23)
+#define SCTLR_EL1_SED		(1 << 8)
+#define SCTLR_EL1_CP15BEN	(1 << 5)
 
 
 /* id_aa64isar0 */
@@ -115,6 +126,7 @@
 #define ID_AA64PFR0_ASIMD_SUPPORTED	0x0
 #define ID_AA64PFR0_EL1_64BIT_ONLY	0x1
 #define ID_AA64PFR0_EL0_64BIT_ONLY	0x1
+#define ID_AA64PFR0_EL0_32BIT_64BIT	0x2
 
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
@@ -145,7 +157,11 @@
 #define ID_AA64MMFR1_VMIDBITS_16	2
 
 /* id_aa64mmfr2 */
+#define ID_AA64MMFR2_LVA_SHIFT		16
+#define ID_AA64MMFR2_IESB_SHIFT		12
+#define ID_AA64MMFR2_LSM_SHIFT		8
 #define ID_AA64MMFR2_UAO_SHIFT		4
+#define ID_AA64MMFR2_CNP_SHIFT		0
 
 /* id_aa64dfr0 */
 #define ID_AA64DFR0_CTX_CMPS_SHIFT	28

arch/arm64/include/asm/topology.h

@@ -22,6 +22,16 @@ void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
+#ifdef CONFIG_NUMA
+
+struct pci_bus;
+int pcibus_to_node(struct pci_bus *bus);
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+
+#endif /* CONFIG_NUMA */
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_ARM_TOPOLOGY_H */

arch/arm64/include/asm/virt.h

@@ -18,6 +18,22 @@
 #ifndef __ASM__VIRT_H
 #define __ASM__VIRT_H
 
+/*
+ * The arm64 hcall implementation uses x0 to specify the hcall type. A value
+ * less than 0xfff indicates a special hcall, such as get/set vector.
+ * Any other value is used as a pointer to the function to call.
+ */
+
+/* HVC_GET_VECTORS - Return the value of the vbar_el2 register. */
+#define HVC_GET_VECTORS 0
+
+/*
+ * HVC_SET_VECTORS - Set the value of the vbar_el2 register.
+ *
+ * @x1: Physical address of the new vector table.
+ */
+#define HVC_SET_VECTORS 1
+
 #define BOOT_CPU_MODE_EL1	(0xe11)
 #define BOOT_CPU_MODE_EL2	(0xe12)
 
@@ -60,6 +76,12 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return el == CurrentEL_EL2;
 }
 
+#ifdef CONFIG_ARM64_VHE
+extern void verify_cpu_run_el(void);
+#else
+static inline void verify_cpu_run_el(void) {}
+#endif
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];

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)

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;
 
 	/*

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;
 }

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");

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));
 }

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] || !cpu_ops[cpu]->cpu_suspend)
-		return -EOPNOTSUPP;
 	return cpu_ops[cpu]->cpu_suspend(index);
 }

arch/arm64/kernel/cpuinfo.c

@@ -87,7 +87,8 @@ static const char *const compat_hwcap_str[] = {
 	"idivt",
 	"vfpd32",
 	"lpae",
-	"evtstrm"
+	"evtstrm",
+	NULL
 };
 
 static const char *const compat_hwcap2_str[] = {
@@ -216,23 +217,26 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1);
 	info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1);
 
-	info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
-	info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
-	info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
-	info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
-	info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
-	info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
-	info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
-	info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
-	info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
-	info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
-	info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
-	info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
-	info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
-
-	info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
-	info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
-	info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+	/* Update the 32bit ID registers only if AArch32 is implemented */
+	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
+		info->reg_id_dfr0 = read_cpuid(ID_DFR0_EL1);
+		info->reg_id_isar0 = read_cpuid(ID_ISAR0_EL1);
+		info->reg_id_isar1 = read_cpuid(ID_ISAR1_EL1);
+		info->reg_id_isar2 = read_cpuid(ID_ISAR2_EL1);
+		info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1);
+		info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1);
+		info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1);
+		info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1);
+		info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1);
+		info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1);
+		info->reg_id_mmfr3 = read_cpuid(ID_MMFR3_EL1);
+		info->reg_id_pfr0 = read_cpuid(ID_PFR0_EL1);
+		info->reg_id_pfr1 = read_cpuid(ID_PFR1_EL1);
+
+		info->reg_mvfr0 = read_cpuid(MVFR0_EL1);
+		info->reg_mvfr1 = read_cpuid(MVFR1_EL1);
+		info->reg_mvfr2 = read_cpuid(MVFR2_EL1);
+	}
 
 	cpuinfo_detect_icache_policy(info);
 

arch/arm64/kernel/debug-monitors.c

@@ -135,9 +135,8 @@ static void clear_os_lock(void *unused)
 static int os_lock_notify(struct notifier_block *self,
 				    unsigned long action, void *data)
 {
-	int cpu = (unsigned long)data;
 	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
-		smp_call_function_single(cpu, clear_os_lock, NULL, 1);
+		clear_os_lock(NULL);
 	return NOTIFY_OK;
 }
 

arch/arm64/kernel/efi-entry.S

@@ -62,7 +62,7 @@ ENTRY(entry)
 	 */
 	mov	x20, x0		// DTB address
 	ldr	x0, [sp, #16]	// relocated _text address
-	movz	x21, #:abs_g0:stext_offset
+	ldr	w21, =stext_offset
 	add	x21, x0, x21
 
 	/*

arch/arm64/kernel/head.S

@@ -25,6 +25,7 @@
 #include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
+#include <asm/boot.h>
 #include <asm/ptrace.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
@@ -51,9 +52,6 @@
 #error TEXT_OFFSET must be less than 2MB
 #endif
 
-#define KERNEL_START	_text
-#define KERNEL_END	_end
-
 /*
  * Kernel startup entry point.
  * ---------------------------
@@ -102,8 +100,6 @@ _head:
 #endif
 
 #ifdef CONFIG_EFI
-	.globl	__efistub_stext_offset
-	.set	__efistub_stext_offset, stext - _head
 	.align 3
 pe_header:
 	.ascii	"PE"
@@ -123,11 +119,11 @@ optional_header:
 	.short	0x20b				// PE32+ format
 	.byte	0x02				// MajorLinkerVersion
 	.byte	0x14				// MinorLinkerVersion
-	.long	_end - stext			// SizeOfCode
+	.long	_end - efi_header_end		// SizeOfCode
 	.long	0				// SizeOfInitializedData
 	.long	0				// SizeOfUninitializedData
 	.long	__efistub_entry - _head		// AddressOfEntryPoint
-	.long	__efistub_stext_offset		// BaseOfCode
+	.long	efi_header_end - _head		// BaseOfCode
 
 extra_header_fields:
 	.quad	0				// ImageBase
@@ -144,7 +140,7 @@ extra_header_fields:
 	.long	_end - _head			// SizeOfImage
 
 	// Everything before the kernel image is considered part of the header
-	.long	__efistub_stext_offset		// SizeOfHeaders
+	.long	efi_header_end - _head		// SizeOfHeaders
 	.long	0				// CheckSum
 	.short	0xa				// Subsystem (EFI application)
 	.short	0				// DllCharacteristics
@@ -188,10 +184,10 @@ section_table:
 	.byte	0
 	.byte	0
 	.byte	0        		// end of 0 padding of section name
-	.long	_end - stext		// VirtualSize
-	.long	__efistub_stext_offset	// VirtualAddress
-	.long	_edata - stext		// SizeOfRawData
-	.long	__efistub_stext_offset	// PointerToRawData
+	.long	_end - efi_header_end	// VirtualSize
+	.long	efi_header_end - _head	// VirtualAddress
+	.long	_edata - efi_header_end	// SizeOfRawData
+	.long	efi_header_end - _head	// PointerToRawData
 
 	.long	0		// PointerToRelocations (0 for executables)
 	.long	0		// PointerToLineNumbers (0 for executables)
@@ -200,20 +196,23 @@ section_table:
 	.long	0xe0500020	// Characteristics (section flags)
 
 	/*
-	 * EFI will load stext onwards at the 4k section alignment
+	 * EFI will load .text onwards at the 4k section alignment
 	 * described in the PE/COFF header. To ensure that instruction
 	 * sequences using an adrp and a :lo12: immediate will function
-	 * correctly at this alignment, we must ensure that stext is
+	 * correctly at this alignment, we must ensure that .text is
 	 * placed at a 4k boundary in the Image to begin with.
 	 */
 	.align 12
+efi_header_end:
 #endif
 
+	__INIT
+
 ENTRY(stext)
 	bl	preserve_boot_args
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
-	mov	x23, xzr			// KASLR offset, defaults to 0
 	adrp	x24, __PHYS_OFFSET
+	and	x23, x24, MIN_KIMG_ALIGN - 1	// KASLR offset, defaults to 0
 	bl	set_cpu_boot_mode_flag
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
@@ -222,13 +221,11 @@ ENTRY(stext)
 	 * On return, the CPU will be ready for the MMU to be turned on and
 	 * the TCR will have been set.
 	 */
-	ldr	x27, 0f				// address to jump to after
+	bl	__cpu_setup			// initialise processor
+	adr_l	x27, __primary_switch		// address to jump to after
 						// MMU has been enabled
-	adr_l	lr, __enable_mmu		// return (PIC) address
-	b	__cpu_setup			// initialise processor
+	b	__enable_mmu
 ENDPROC(stext)
-	.align	3
-0:	.quad	__mmap_switched - (_head - TEXT_OFFSET) + KIMAGE_VADDR
 
 /*
  * Preserve the arguments passed by the bootloader in x0 .. x3
@@ -338,7 +335,7 @@ __create_page_tables:
 	cmp	x0, x6
 	b.lo	1b
 
-	ldr	x7, =SWAPPER_MM_MMUFLAGS
+	mov	x7, SWAPPER_MM_MMUFLAGS
 
 	/*
 	 * Create the identity mapping.
@@ -394,12 +391,13 @@ __create_page_tables:
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
 	mov	x0, x26				// swapper_pg_dir
-	ldr	x5, =KIMAGE_VADDR
+	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
 	create_pgd_entry x0, x5, x3, x6
-	ldr	w6, kernel_img_size
-	add	x6, x6, x5
-	mov	x3, x24				// phys offset
+	adrp	x6, _end			// runtime __pa(_end)
+	adrp	x3, _text			// runtime __pa(_text)
+	sub	x6, x6, x3			// _end - _text
+	add	x6, x6, x5			// runtime __va(_end)
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
@@ -414,16 +412,13 @@ __create_page_tables:
 
 	ret	x28
 ENDPROC(__create_page_tables)
-
-kernel_img_size:
-	.long	_end - (_head - TEXT_OFFSET)
 	.ltorg
 
 /*
  * The following fragment of code is executed with the MMU enabled.
  */
 	.set	initial_sp, init_thread_union + THREAD_START_SP
-__mmap_switched:
+__primary_switched:
 	mov	x28, lr				// preserve LR
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
@@ -437,44 +432,6 @@ __mmap_switched:
 	bl	__pi_memset
 	dsb	ishst				// Make zero page visible to PTW
 
-#ifdef CONFIG_RELOCATABLE
-
-	/*
-	 * Iterate over each entry in the relocation table, and apply the
-	 * relocations in place.
-	 */
-	adr_l	x8, __dynsym_start		// start of symbol table
-	adr_l	x9, __reloc_start		// start of reloc table
-	adr_l	x10, __reloc_end		// end of reloc table
-
-0:	cmp	x9, x10
-	b.hs	2f
-	ldp	x11, x12, [x9], #24
-	ldr	x13, [x9, #-8]
-	cmp	w12, #R_AARCH64_RELATIVE
-	b.ne	1f
-	add	x13, x13, x23			// relocate
-	str	x13, [x11, x23]
-	b	0b
-
-1:	cmp	w12, #R_AARCH64_ABS64
-	b.ne	0b
-	add	x12, x12, x12, lsl #1		// symtab offset: 24x top word
-	add	x12, x8, x12, lsr #(32 - 3)	// ... shifted into bottom word
-	ldrsh	w14, [x12, #6]			// Elf64_Sym::st_shndx
-	ldr	x15, [x12, #8]			// Elf64_Sym::st_value
-	cmp	w14, #-0xf			// SHN_ABS (0xfff1) ?
-	add	x14, x15, x23			// relocate
-	csel	x15, x14, x15, ne
-	add	x15, x13, x15
-	str	x15, [x11, x23]
-	b	0b
-
-2:	adr_l	x8, kimage_vaddr		// make relocated kimage_vaddr
-	dc	cvac, x8			// value visible to secondaries
-	dsb	sy				// with MMU off
-#endif
-
 	adr_l	sp, initial_sp, x4
 	mov	x4, sp
 	and	x4, x4, #~(THREAD_SIZE - 1)
@@ -490,17 +447,19 @@ __mmap_switched:
 	bl	kasan_early_init
 #endif
 #ifdef CONFIG_RANDOMIZE_BASE
-	cbnz	x23, 0f				// already running randomized?
+	tst	x23, ~(MIN_KIMG_ALIGN - 1)	// already running randomized?
+	b.ne	0f
 	mov	x0, x21				// pass FDT address in x0
+	mov	x1, x23				// pass modulo offset in x1
 	bl	kaslr_early_init		// parse FDT for KASLR options
 	cbz	x0, 0f				// KASLR disabled? just proceed
-	mov	x23, x0				// record KASLR offset
+	orr	x23, x23, x0			// record KASLR offset
 	ret	x28				// we must enable KASLR, return
 						// to __enable_mmu()
 0:
 #endif
 	b	start_kernel
-ENDPROC(__mmap_switched)
+ENDPROC(__primary_switched)
 
 /*
  * end early head section, begin head code that is also used for
@@ -650,7 +609,7 @@ ENDPROC(el2_setup)
  * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
  * in x20. See arch/arm64/include/asm/virt.h for more info.
  */
-ENTRY(set_cpu_boot_mode_flag)
+set_cpu_boot_mode_flag:
 	adr_l	x1, __boot_cpu_mode
 	cmp	w20, #BOOT_CPU_MODE_EL2
 	b.ne	1f
@@ -683,7 +642,7 @@ ENTRY(secondary_holding_pen)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	bl	set_cpu_boot_mode_flag
 	mrs	x0, mpidr_el1
-	ldr     x1, =MPIDR_HWID_BITMASK
+	mov_q	x1, MPIDR_HWID_BITMASK
 	and	x0, x0, x1
 	adr_l	x3, secondary_holding_pen_release
 pen:	ldr	x4, [x3]
@@ -703,7 +662,7 @@ ENTRY(secondary_entry)
 	b	secondary_startup
 ENDPROC(secondary_entry)
 
-ENTRY(secondary_startup)
+secondary_startup:
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
@@ -711,14 +670,11 @@ ENTRY(secondary_startup)
 	adrp	x26, swapper_pg_dir
 	bl	__cpu_setup			// initialise processor
 
-	ldr	x8, kimage_vaddr
-	ldr	w9, 0f
-	sub	x27, x8, w9, sxtw		// address to jump to after enabling the MMU
+	adr_l	x27, __secondary_switch		// address to jump to after enabling the MMU
 	b	__enable_mmu
 ENDPROC(secondary_startup)
-0:	.long	(_text - TEXT_OFFSET) - __secondary_switched
 
-ENTRY(__secondary_switched)
+__secondary_switched:
 	adr_l	x5, vectors
 	msr	vbar_el1, x5
 	isb
@@ -768,7 +724,7 @@ ENTRY(__early_cpu_boot_status)
  * If it isn't, park the CPU
  */
 	.section	".idmap.text", "ax"
-__enable_mmu:
+ENTRY(__enable_mmu)
 	mrs	x22, sctlr_el1			// preserve old SCTLR_EL1 value
 	mrs	x1, ID_AA64MMFR0_EL1
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
@@ -806,7 +762,6 @@ __enable_mmu:
 	ic	iallu				// flush instructions fetched
 	dsb	nsh				// via old mapping
 	isb
-	add	x27, x27, x23			// relocated __mmap_switched
 #endif
 	br	x27
 ENDPROC(__enable_mmu)
@@ -819,3 +774,53 @@ __no_granule_support:
 	wfi
 	b 1b
 ENDPROC(__no_granule_support)
+
+__primary_switch:
+#ifdef CONFIG_RELOCATABLE
+	/*
+	 * Iterate over each entry in the relocation table, and apply the
+	 * relocations in place.
+	 */
+	ldr	w8, =__dynsym_offset		// offset to symbol table
+	ldr	w9, =__rela_offset		// offset to reloc table
+	ldr	w10, =__rela_size		// size of reloc table
+
+	mov_q	x11, KIMAGE_VADDR		// default virtual offset
+	add	x11, x11, x23			// actual virtual offset
+	add	x8, x8, x11			// __va(.dynsym)
+	add	x9, x9, x11			// __va(.rela)
+	add	x10, x9, x10			// __va(.rela) + sizeof(.rela)
+
+0:	cmp	x9, x10
+	b.hs	2f
+	ldp	x11, x12, [x9], #24
+	ldr	x13, [x9, #-8]
+	cmp	w12, #R_AARCH64_RELATIVE
+	b.ne	1f
+	add	x13, x13, x23			// relocate
+	str	x13, [x11, x23]
+	b	0b
+
+1:	cmp	w12, #R_AARCH64_ABS64
+	b.ne	0b
+	add	x12, x12, x12, lsl #1		// symtab offset: 24x top word
+	add	x12, x8, x12, lsr #(32 - 3)	// ... shifted into bottom word
+	ldrsh	w14, [x12, #6]			// Elf64_Sym::st_shndx
+	ldr	x15, [x12, #8]			// Elf64_Sym::st_value
+	cmp	w14, #-0xf			// SHN_ABS (0xfff1) ?
+	add	x14, x15, x23			// relocate
+	csel	x15, x14, x15, ne
+	add	x15, x13, x15
+	str	x15, [x11, x23]
+	b	0b
+
+2:
+#endif
+	ldr	x8, =__primary_switched
+	br	x8
+ENDPROC(__primary_switch)
+
+__secondary_switch:
+	ldr	x8, =__secondary_switched
+	br	x8
+ENDPROC(__secondary_switch)

arch/arm64/kernel/hibernate-asm.S

@@ -0,0 +1,176 @@
+/*
+ * Hibernate low-level support
+ *
+ * Copyright (C) 2016 ARM Ltd.
+ * Author:	James Morse <james.morse@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/linkage.h>
+#include <linux/errno.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/assembler.h>
+#include <asm/cputype.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+#include <asm/virt.h>
+
+/*
+ * To prevent the possibility of old and new partial table walks being visible
+ * in the tlb, switch the ttbr to a zero page when we invalidate the old
+ * records. D4.7.1 'General TLB maintenance requirements' in ARM DDI 0487A.i
+ * Even switching to our copied tables will cause a changed output address at
+ * each stage of the walk.
+ */
+.macro break_before_make_ttbr_switch zero_page, page_table
+	msr	ttbr1_el1, \zero_page
+	isb
+	tlbi	vmalle1is
+	dsb	ish
+	msr	ttbr1_el1, \page_table
+	isb
+.endm
+
+
+/*
+ * Resume from hibernate
+ *
+ * Loads temporary page tables then restores the memory image.
+ * Finally branches to cpu_resume() to restore the state saved by
+ * swsusp_arch_suspend().
+ *
+ * Because this code has to be copied to a 'safe' page, it can't call out to
+ * other functions by PC-relative address. Also remember that it may be
+ * mid-way through over-writing other functions. For this reason it contains
+ * code from flush_icache_range() and uses the copy_page() macro.
+ *
+ * This 'safe' page is mapped via ttbr0, and executed from there. This function
+ * switches to a copy of the linear map in ttbr1, performs the restore, then
+ * switches ttbr1 to the original kernel's swapper_pg_dir.
+ *
+ * All of memory gets written to, including code. We need to clean the kernel
+ * text to the Point of Coherence (PoC) before secondary cores can be booted.
+ * Because the kernel modules and executable pages mapped to user space are
+ * also written as data, we clean all pages we touch to the Point of
+ * Unification (PoU).
+ *
+ * x0: physical address of temporary page tables
+ * x1: physical address of swapper page tables
+ * x2: address of cpu_resume
+ * x3: linear map address of restore_pblist in the current kernel
+ * x4: physical address of __hyp_stub_vectors, or 0
+ * x5: physical address of a  zero page that remains zero after resume
+ */
+.pushsection    ".hibernate_exit.text", "ax"
+ENTRY(swsusp_arch_suspend_exit)
+	/*
+	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
+	 * with a break-before-make via the zero page
+	 */
+	break_before_make_ttbr_switch	x5, x0
+
+	mov	x21, x1
+	mov	x30, x2
+	mov	x24, x4
+	mov	x25, x5
+
+	/* walk the restore_pblist and use copy_page() to over-write memory */
+	mov	x19, x3
+
+1:	ldr	x10, [x19, #HIBERN_PBE_ORIG]
+	mov	x0, x10
+	ldr	x1, [x19, #HIBERN_PBE_ADDR]
+
+	copy_page	x0, x1, x2, x3, x4, x5, x6, x7, x8, x9
+
+	add	x1, x10, #PAGE_SIZE
+	/* Clean the copied page to PoU - based on flush_icache_range() */
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x4, x10, x3
+2:	dc	cvau, x4	/* clean D line / unified line */
+	add	x4, x4, x2
+	cmp	x4, x1
+	b.lo	2b
+
+	ldr	x19, [x19, #HIBERN_PBE_NEXT]
+	cbnz	x19, 1b
+	dsb	ish		/* wait for PoU cleaning to finish */
+
+	/* switch to the restored kernels page tables */
+	break_before_make_ttbr_switch	x25, x21
+
+	ic	ialluis
+	dsb	ish
+	isb
+
+	cbz	x24, 3f		/* Do we need to re-initialise EL2? */
+	hvc	#0
+3:	ret
+
+	.ltorg
+ENDPROC(swsusp_arch_suspend_exit)
+
+/*
+ * Restore the hyp stub.
+ * This must be done before the hibernate page is unmapped by _cpu_resume(),
+ * but happens before any of the hyp-stub's code is cleaned to PoC.
+ *
+ * x24: The physical address of __hyp_stub_vectors
+ */
+el1_sync:
+	msr	vbar_el2, x24
+	eret
+ENDPROC(el1_sync)
+
+.macro invalid_vector	label
+\label:
+	b \label
+ENDPROC(\label)
+.endm
+
+	invalid_vector	el2_sync_invalid
+	invalid_vector	el2_irq_invalid
+	invalid_vector	el2_fiq_invalid
+	invalid_vector	el2_error_invalid
+	invalid_vector	el1_sync_invalid
+	invalid_vector	el1_irq_invalid
+	invalid_vector	el1_fiq_invalid
+	invalid_vector	el1_error_invalid
+
+/* el2 vectors - switch el2 here while we restore the memory image. */
+	.align 11
+ENTRY(hibernate_el2_vectors)
+	ventry	el2_sync_invalid		// Synchronous EL2t
+	ventry	el2_irq_invalid			// IRQ EL2t
+	ventry	el2_fiq_invalid			// FIQ EL2t
+	ventry	el2_error_invalid		// Error EL2t
+
+	ventry	el2_sync_invalid		// Synchronous EL2h
+	ventry	el2_irq_invalid			// IRQ EL2h
+	ventry	el2_fiq_invalid			// FIQ EL2h
+	ventry	el2_error_invalid		// Error EL2h
+
+	ventry	el1_sync			// Synchronous 64-bit EL1
+	ventry	el1_irq_invalid			// IRQ 64-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 64-bit EL1
+	ventry	el1_error_invalid		// Error 64-bit EL1
+
+	ventry	el1_sync_invalid		// Synchronous 32-bit EL1
+	ventry	el1_irq_invalid			// IRQ 32-bit EL1
+	ventry	el1_fiq_invalid			// FIQ 32-bit EL1
+	ventry	el1_error_invalid		// Error 32-bit EL1
+END(hibernate_el2_vectors)
+
+.popsection

arch/arm64/kernel/hibernate.c

@@ -0,0 +1,487 @@
+/*:
+ * Hibernate support specific for ARM64
+ *
+ * Derived from work on ARM hibernation support by:
+ *
+ * Ubuntu project, hibernation support for mach-dove
+ * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu)
+ * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.)
+ *  https://lkml.org/lkml/2010/6/18/4
+ *  https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html
+ *  https://patchwork.kernel.org/patch/96442/
+ *
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+#define pr_fmt(x) "hibernate: " x
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <linux/notifier.h>
+#include <linux/pm.h>
+#include <linux/sched.h>
+#include <linux/suspend.h>
+#include <linux/utsname.h>
+#include <linux/version.h>
+
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+#include <asm/irqflags.h>
+#include <asm/memory.h>
+#include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/sections.h>
+#include <asm/suspend.h>
+#include <asm/virt.h>
+
+/*
+ * Hibernate core relies on this value being 0 on resume, and marks it
+ * __nosavedata assuming it will keep the resume kernel's '0' value. This
+ * doesn't happen with either KASLR.
+ *
+ * defined as "__visible int in_suspend __nosavedata" in
+ * kernel/power/hibernate.c
+ */
+extern int in_suspend;
+
+/* Find a symbols alias in the linear map */
+#define LMADDR(x)	phys_to_virt(virt_to_phys(x))
+
+/* Do we need to reset el2? */
+#define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode())
+
+/*
+ * Start/end of the hibernate exit code, this must be copied to a 'safe'
+ * location in memory, and executed from there.
+ */
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+
+/* temporary el2 vectors in the __hibernate_exit_text section. */
+extern char hibernate_el2_vectors[];
+
+/* hyp-stub vectors, used to restore el2 during resume from hibernate. */
+extern char __hyp_stub_vectors[];
+
+/*
+ * Values that may not change over hibernate/resume. We put the build number
+ * and date in here so that we guarantee not to resume with a different
+ * kernel.
+ */
+struct arch_hibernate_hdr_invariants {
+	char		uts_version[__NEW_UTS_LEN + 1];
+};
+
+/* These values need to be know across a hibernate/restore. */
+static struct arch_hibernate_hdr {
+	struct arch_hibernate_hdr_invariants invariants;
+
+	/* These are needed to find the relocated kernel if built with kaslr */
+	phys_addr_t	ttbr1_el1;
+	void		(*reenter_kernel)(void);
+
+	/*
+	 * We need to know where the __hyp_stub_vectors are after restore to
+	 * re-configure el2.
+	 */
+	phys_addr_t	__hyp_stub_vectors;
+} resume_hdr;
+
+static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
+{
+	memset(i, 0, sizeof(*i));
+	memcpy(i->uts_version, init_utsname()->version, sizeof(i->uts_version));
+}
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
+	unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);
+
+	return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+}
+
+void notrace save_processor_state(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+}
+
+void notrace restore_processor_state(void)
+{
+}
+
+int arch_hibernation_header_save(void *addr, unsigned int max_size)
+{
+	struct arch_hibernate_hdr *hdr = addr;
+
+	if (max_size < sizeof(*hdr))
+		return -EOVERFLOW;
+
+	arch_hdr_invariants(&hdr->invariants);
+	hdr->ttbr1_el1		= virt_to_phys(swapper_pg_dir);
+	hdr->reenter_kernel	= _cpu_resume;
+
+	/* We can't use __hyp_get_vectors() because kvm may still be loaded */
+	if (el2_reset_needed())
+		hdr->__hyp_stub_vectors = virt_to_phys(__hyp_stub_vectors);
+	else
+		hdr->__hyp_stub_vectors = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL(arch_hibernation_header_save);
+
+int arch_hibernation_header_restore(void *addr)
+{
+	struct arch_hibernate_hdr_invariants invariants;
+	struct arch_hibernate_hdr *hdr = addr;
+
+	arch_hdr_invariants(&invariants);
+	if (memcmp(&hdr->invariants, &invariants, sizeof(invariants))) {
+		pr_crit("Hibernate image not generated by this kernel!\n");
+		return -EINVAL;
+	}
+
+	resume_hdr = *hdr;
+
+	return 0;
+}
+EXPORT_SYMBOL(arch_hibernation_header_restore);
+
+/*
+ * Copies length bytes, starting at src_start into an new page,
+ * perform cache maintentance, then maps it at the specified address low
+ * address as executable.
+ *
+ * This is used by hibernate to copy the code it needs to execute when
+ * overwriting the kernel text. This function generates a new set of page
+ * tables, which it loads into ttbr0.
+ *
+ * Length is provided as we probably only want 4K of data, even on a 64K
+ * page system.
+ */
+static int create_safe_exec_page(void *src_start, size_t length,
+				 unsigned long dst_addr,
+				 phys_addr_t *phys_dst_addr,
+				 void *(*allocator)(gfp_t mask),
+				 gfp_t mask)
+{
+	int rc = 0;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long dst = (unsigned long)allocator(mask);
+
+	if (!dst) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	memcpy((void *)dst, src_start, length);
+	flush_icache_range(dst, dst + length);
+
+	pgd = pgd_offset_raw(allocator(mask), dst_addr);
+	if (pgd_none(*pgd)) {
+		pud = allocator(mask);
+		if (!pud) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		pgd_populate(&init_mm, pgd, pud);
+	}
+
+	pud = pud_offset(pgd, dst_addr);
+	if (pud_none(*pud)) {
+		pmd = allocator(mask);
+		if (!pmd) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		pud_populate(&init_mm, pud, pmd);
+	}
+
+	pmd = pmd_offset(pud, dst_addr);
+	if (pmd_none(*pmd)) {
+		pte = allocator(mask);
+		if (!pte) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		pmd_populate_kernel(&init_mm, pmd, pte);
+	}
+
+	pte = pte_offset_kernel(pmd, dst_addr);
+	set_pte(pte, __pte(virt_to_phys((void *)dst) |
+			 pgprot_val(PAGE_KERNEL_EXEC)));
+
+	/* Load our new page tables */
+	asm volatile("msr	ttbr0_el1, %0;"
+		     "isb;"
+		     "tlbi	vmalle1is;"
+		     "dsb	ish;"
+		     "isb" : : "r"(virt_to_phys(pgd)));
+
+	*phys_dst_addr = virt_to_phys((void *)dst);
+
+out:
+	return rc;
+}
+
+
+int swsusp_arch_suspend(void)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct sleep_stack_data state;
+
+	local_dbg_save(flags);
+
+	if (__cpu_suspend_enter(&state)) {
+		ret = swsusp_save();
+	} else {
+		/* Clean kernel to PoC for secondary core startup */
+		__flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START);
+
+		/*
+		 * Tell the hibernation core that we've just restored
+		 * the memory
+		 */
+		in_suspend = 0;
+
+		__cpu_suspend_exit();
+	}
+
+	local_dbg_restore(flags);
+
+	return ret;
+}
+
+static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
+		    unsigned long end)
+{
+	pte_t *src_pte;
+	pte_t *dst_pte;
+	unsigned long addr = start;
+
+	dst_pte = (pte_t *)get_safe_page(GFP_ATOMIC);
+	if (!dst_pte)
+		return -ENOMEM;
+	pmd_populate_kernel(&init_mm, dst_pmd, dst_pte);
+	dst_pte = pte_offset_kernel(dst_pmd, start);
+
+	src_pte = pte_offset_kernel(src_pmd, start);
+	do {
+		if (!pte_none(*src_pte))
+			/*
+			 * Resume will overwrite areas that may be marked
+			 * read only (code, rodata). Clear the RDONLY bit from
+			 * the temporary mappings we use during restore.
+			 */
+			set_pte(dst_pte, __pte(pte_val(*src_pte) & ~PTE_RDONLY));
+	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+
+	return 0;
+}
+
+static int copy_pmd(pud_t *dst_pud, pud_t *src_pud, unsigned long start,
+		    unsigned long end)
+{
+	pmd_t *src_pmd;
+	pmd_t *dst_pmd;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (pud_none(*dst_pud)) {
+		dst_pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pmd)
+			return -ENOMEM;
+		pud_populate(&init_mm, dst_pud, dst_pmd);
+	}
+	dst_pmd = pmd_offset(dst_pud, start);
+
+	src_pmd = pmd_offset(src_pud, start);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*src_pmd))
+			continue;
+		if (pmd_table(*src_pmd)) {
+			if (copy_pte(dst_pmd, src_pmd, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pmd(dst_pmd,
+				__pmd(pmd_val(*src_pmd) & ~PMD_SECT_RDONLY));
+		}
+	} while (dst_pmd++, src_pmd++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_pud(pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long start,
+		    unsigned long end)
+{
+	pud_t *dst_pud;
+	pud_t *src_pud;
+	unsigned long next;
+	unsigned long addr = start;
+
+	if (pgd_none(*dst_pgd)) {
+		dst_pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+		if (!dst_pud)
+			return -ENOMEM;
+		pgd_populate(&init_mm, dst_pgd, dst_pud);
+	}
+	dst_pud = pud_offset(dst_pgd, start);
+
+	src_pud = pud_offset(src_pgd, start);
+	do {
+		next = pud_addr_end(addr, end);
+		if (pud_none(*src_pud))
+			continue;
+		if (pud_table(*(src_pud))) {
+			if (copy_pmd(dst_pud, src_pud, addr, next))
+				return -ENOMEM;
+		} else {
+			set_pud(dst_pud,
+				__pud(pud_val(*src_pud) & ~PMD_SECT_RDONLY));
+		}
+	} while (dst_pud++, src_pud++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int copy_page_tables(pgd_t *dst_pgd, unsigned long start,
+			    unsigned long end)
+{
+	unsigned long next;
+	unsigned long addr = start;
+	pgd_t *src_pgd = pgd_offset_k(start);
+
+	dst_pgd = pgd_offset_raw(dst_pgd, start);
+	do {
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(*src_pgd))
+			continue;
+		if (copy_pud(dst_pgd, src_pgd, addr, next))
+			return -ENOMEM;
+	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
+
+	return 0;
+}
+
+/*
+ * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit().
+ *
+ * Memory allocated by get_safe_page() will be dealt with by the hibernate code,
+ * we don't need to free it here.
+ */
+int swsusp_arch_resume(void)
+{
+	int rc = 0;
+	void *zero_page;
+	size_t exit_size;
+	pgd_t *tmp_pg_dir;
+	void *lm_restore_pblist;
+	phys_addr_t phys_hibernate_exit;
+	void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
+					  void *, phys_addr_t, phys_addr_t);
+
+	/*
+	 * Locate the exit code in the bottom-but-one page, so that *NULL
+	 * still has disastrous affects.
+	 */
+	hibernate_exit = (void *)PAGE_SIZE;
+	exit_size = __hibernate_exit_text_end - __hibernate_exit_text_start;
+	/*
+	 * Copy swsusp_arch_suspend_exit() to a safe page. This will generate
+	 * a new set of ttbr0 page tables and load them.
+	 */
+	rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size,
+				   (unsigned long)hibernate_exit,
+				   &phys_hibernate_exit,
+				   (void *)get_safe_page, GFP_ATOMIC);
+	if (rc) {
+		pr_err("Failed to create safe executable page for hibernate_exit code.");
+		goto out;
+	}
+
+	/*
+	 * The hibernate exit text contains a set of el2 vectors, that will
+	 * be executed at el2 with the mmu off in order to reload hyp-stub.
+	 */
+	__flush_dcache_area(hibernate_exit, exit_size);
+
+	/*
+	 * Restoring the memory image will overwrite the ttbr1 page tables.
+	 * Create a second copy of just the linear map, and use this when
+	 * restoring.
+	 */
+	tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+	if (!tmp_pg_dir) {
+		pr_err("Failed to allocate memory for temporary page tables.");
+		rc = -ENOMEM;
+		goto out;
+	}
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	if (rc)
+		goto out;
+
+	/*
+	 * Since we only copied the linear map, we need to find restore_pblist's
+	 * linear map address.
+	 */
+	lm_restore_pblist = LMADDR(restore_pblist);
+
+	/*
+	 * KASLR will cause the el2 vectors to be in a different location in
+	 * the resumed kernel. Load hibernate's temporary copy into el2.
+	 *
+	 * We can skip this step if we booted at EL1, or are running with VHE.
+	 */
+	if (el2_reset_needed()) {
+		phys_addr_t el2_vectors = phys_hibernate_exit;  /* base */
+		el2_vectors += hibernate_el2_vectors -
+			       __hibernate_exit_text_start;     /* offset */
+
+		__hyp_set_vectors(el2_vectors);
+	}
+
+	/*
+	 * We need a zero page that is zero before & after resume in order to
+	 * to break before make on the ttbr1 page tables.
+	 */
+	zero_page = (void *)get_safe_page(GFP_ATOMIC);
+
+	hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
+		       resume_hdr.reenter_kernel, lm_restore_pblist,
+		       resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
+
+out:
+	return rc;
+}
+
+static int check_boot_cpu_online_pm_callback(struct notifier_block *nb,
+					     unsigned long action, void *ptr)
+{
+	if (action == PM_HIBERNATION_PREPARE &&
+	     cpumask_first(cpu_online_mask) != 0) {
+		pr_warn("CPU0 is offline.\n");
+		return notifier_from_errno(-ENODEV);
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init check_boot_cpu_online_init(void)
+{
+	/*
+	 * Set this pm_notifier callback with a lower priority than
+	 * cpu_hotplug_pm_callback, so that cpu_hotplug_pm_callback will be
+	 * called earlier to disable cpu hotplug before the cpu online check.
+	 */
+	pm_notifier(check_boot_cpu_online_pm_callback, -INT_MAX);
+
+	return 0;
+}
+core_initcall(check_boot_cpu_online_init);

arch/arm64/kernel/hw_breakpoint.c

@@ -886,9 +886,11 @@ static int hw_breakpoint_reset_notify(struct notifier_block *self,
 						unsigned long action,
 						void *hcpu)
 {
-	int cpu = (long)hcpu;
-	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
-		smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1);
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) {
+		local_irq_disable();
+		hw_breakpoint_reset(NULL);
+		local_irq_enable();
+	}
 	return NOTIFY_OK;
 }
 

arch/arm64/kernel/hyp-stub.S

@@ -22,6 +22,8 @@
 #include <linux/irqchip/arm-gic-v3.h>
 
 #include <asm/assembler.h>
+#include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
@@ -53,15 +55,26 @@ ENDPROC(__hyp_stub_vectors)
 	.align 11
 
 el1_sync:
-	mrs	x1, esr_el2
-	lsr	x1, x1, #26
-	cmp	x1, #0x16
-	b.ne	2f				// Not an HVC trap
-	cbz	x0, 1f
-	msr	vbar_el2, x0			// Set vbar_el2
-	b	2f
-1:	mrs	x0, vbar_el2			// Return vbar_el2
-2:	eret
+	mrs	x30, esr_el2
+	lsr	x30, x30, #ESR_ELx_EC_SHIFT
+
+	cmp	x30, #ESR_ELx_EC_HVC64
+	b.ne	9f				// Not an HVC trap
+
+	cmp	x0, #HVC_GET_VECTORS
+	b.ne	1f
+	mrs	x0, vbar_el2
+	b	9f
+
+1:	cmp	x0, #HVC_SET_VECTORS
+	b.ne	2f
+	msr	vbar_el2, x1
+	b	9f
+
+	/* Someone called kvm_call_hyp() against the hyp-stub... */
+2:	mov     x0, #ARM_EXCEPTION_HYP_GONE
+
+9:	eret
 ENDPROC(el1_sync)
 
 .macro invalid_vector	label
@@ -101,10 +114,18 @@ ENDPROC(\label)
  */
 
 ENTRY(__hyp_get_vectors)
-	mov	x0, xzr
-	// fall through
-ENTRY(__hyp_set_vectors)
+	str	lr, [sp, #-16]!
+	mov	x0, #HVC_GET_VECTORS
 	hvc	#0
+	ldr	lr, [sp], #16
 	ret
 ENDPROC(__hyp_get_vectors)
+
+ENTRY(__hyp_set_vectors)
+	str	lr, [sp, #-16]!
+	mov	x1, x0
+	mov	x0, #HVC_SET_VECTORS
+	hvc	#0
+	ldr	lr, [sp], #16
+	ret
 ENDPROC(__hyp_set_vectors)

arch/arm64/kernel/image.h

@@ -73,6 +73,8 @@
 
 #ifdef CONFIG_EFI
 
+__efistub_stext_offset = stext - _text;
+
 /*
  * Prevent the symbol aliases below from being emitted into the kallsyms
  * table, by forcing them to be absolute symbols (which are conveniently

arch/arm64/kernel/insn.c

@@ -96,7 +96,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 	if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
 		page = vmalloc_to_page(addr);
 	else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA))
-		page = virt_to_page(addr);
+		page = pfn_to_page(PHYS_PFN(__pa(addr)));
 	else
 		return addr;
 

arch/arm64/kernel/kaslr.c

@@ -74,7 +74,7 @@ extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
  * containing function pointers) to be reinitialized, and zero-initialized
  * .bss variables will be reset to 0.
  */
-u64 __init kaslr_early_init(u64 dt_phys)
+u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
 {
 	void *fdt;
 	u64 seed, offset, mask, module_range;
@@ -132,8 +132,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * boundary (for 4KB/16KB/64KB granule kernels, respectively). If this
 	 * happens, increase the KASLR offset by the size of the kernel image.
 	 */
-	if ((((u64)_text + offset) >> SWAPPER_TABLE_SHIFT) !=
-	    (((u64)_end + offset) >> SWAPPER_TABLE_SHIFT))
+	if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
+	    (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT))
 		offset = (offset + (u64)(_end - _text)) & mask;
 
 	if (IS_ENABLED(CONFIG_KASAN))

arch/arm64/kernel/pci.c

@@ -74,6 +74,16 @@ int raw_pci_write(unsigned int domain, unsigned int bus,
 	return -ENXIO;
 }
 
+#ifdef CONFIG_NUMA
+
+int pcibus_to_node(struct pci_bus *bus)
+{
+	return dev_to_node(&bus->dev);
+}
+EXPORT_SYMBOL(pcibus_to_node);
+
+#endif
+
 #ifdef CONFIG_ACPI
 /* Root bridge scanning */
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)

arch/arm64/kernel/process.c

@@ -265,9 +265,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		if (stack_start) {
 			if (is_compat_thread(task_thread_info(p)))
 				childregs->compat_sp = stack_start;
-			/* 16-byte aligned stack mandatory on AArch64 */
-			else if (stack_start & 15)
-				return -EINVAL;
 			else
 				childregs->sp = stack_start;
 		}
@@ -382,13 +379,14 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ~0xf;
 }
 
-static unsigned long randomize_base(unsigned long base)
-{
-	unsigned long range_end = base + (STACK_RND_MASK << PAGE_SHIFT) + 1;
-	return randomize_range(base, range_end, 0) ? : base;
-}
-
 unsigned long arch_randomize_brk(struct mm_struct *mm)
 {
-	return randomize_base(mm->brk);
+	unsigned long range_end = mm->brk;
+
+	if (is_compat_task())
+		range_end += 0x02000000;
+	else
+		range_end += 0x40000000;
+
+	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
 }

arch/arm64/kernel/setup.c

@@ -53,6 +53,7 @@
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
 #include <asm/kasan.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp_plat.h>
@@ -175,7 +176,6 @@ static void __init smp_build_mpidr_hash(void)
 	 */
 	if (mpidr_hash_size() > 4 * num_possible_cpus())
 		pr_warn("Large number of MPIDR hash buckets detected\n");
-	__flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash));
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
@@ -224,69 +224,6 @@ static void __init request_standard_resources(void)
 	}
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-/*
- * Relocate initrd if it is not completely within the linear mapping.
- * This would be the case if mem= cuts out all or part of it.
- */
-static void __init relocate_initrd(void)
-{
-	phys_addr_t orig_start = __virt_to_phys(initrd_start);
-	phys_addr_t orig_end = __virt_to_phys(initrd_end);
-	phys_addr_t ram_end = memblock_end_of_DRAM();
-	phys_addr_t new_start;
-	unsigned long size, to_free = 0;
-	void *dest;
-
-	if (orig_end <= ram_end)
-		return;
-
-	/*
-	 * Any of the original initrd which overlaps the linear map should
-	 * be freed after relocating.
-	 */
-	if (orig_start < ram_end)
-		to_free = ram_end - orig_start;
-
-	size = orig_end - orig_start;
-	if (!size)
-		return;
-
-	/* initrd needs to be relocated completely inside linear mapping */
-	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
-					   size, PAGE_SIZE);
-	if (!new_start)
-		panic("Cannot relocate initrd of size %ld\n", size);
-	memblock_reserve(new_start, size);
-
-	initrd_start = __phys_to_virt(new_start);
-	initrd_end   = initrd_start + size;
-
-	pr_info("Moving initrd from [%llx-%llx] to [%llx-%llx]\n",
-		orig_start, orig_start + size - 1,
-		new_start, new_start + size - 1);
-
-	dest = (void *)initrd_start;
-
-	if (to_free) {
-		memcpy(dest, (void *)__phys_to_virt(orig_start), to_free);
-		dest += to_free;
-	}
-
-	copy_from_early_mem(dest, orig_start + to_free, size - to_free);
-
-	if (to_free) {
-		pr_info("Freeing original RAMDISK from [%llx-%llx]\n",
-			orig_start, orig_start + to_free - 1);
-		memblock_free(orig_start, to_free);
-	}
-}
-#else
-static inline void __init relocate_initrd(void)
-{
-}
-#endif
-
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
@@ -327,7 +264,11 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_table_init();
 
 	paging_init();
-	relocate_initrd();
+
+	if (acpi_disabled)
+		unflatten_device_tree();
+
+	bootmem_init();
 
 	kasan_init();
 
@@ -335,12 +276,11 @@ void __init setup_arch(char **cmdline_p)
 
 	early_ioremap_reset();
 
-	if (acpi_disabled) {
-		unflatten_device_tree();
+	if (acpi_disabled)
 		psci_dt_init();
-	} else {
+	else
 		psci_acpi_init();
-	}
+
 	xen_early_init();
 
 	cpu_read_bootcpu_ops();
@@ -379,6 +319,9 @@ static int __init topology_init(void)
 {
 	int i;
 
+	for_each_online_node(i)
+		register_one_node(i);
+
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
 		cpu->hotpluggable = 1;

arch/arm64/kernel/sleep.S

@@ -49,39 +49,32 @@
 	orr	\dst, \dst, \mask		// dst|=(aff3>>rs3)
 	.endm
 /*
- * Save CPU state for a suspend and execute the suspend finisher.
- * On success it will return 0 through cpu_resume - ie through a CPU
- * soft/hard reboot from the reset vector.
- * On failure it returns the suspend finisher return value or force
- * -EOPNOTSUPP if the finisher erroneously returns 0 (the suspend finisher
- * is not allowed to return, if it does this must be considered failure).
- * It saves callee registers, and allocates space on the kernel stack
- * to save the CPU specific registers + some other data for resume.
+ * Save CPU state in the provided sleep_stack_data area, and publish its
+ * location for cpu_resume()'s use in sleep_save_stash.
  *
- *  x0 = suspend finisher argument
- *  x1 = suspend finisher function pointer
+ * cpu_resume() will restore this saved state, and return. Because the
+ * link-register is saved and restored, it will appear to return from this
+ * function. So that the caller can tell the suspend/resume paths apart,
+ * __cpu_suspend_enter() will always return a non-zero value, whereas the
+ * path through cpu_resume() will return 0.
+ *
+ *  x0 = struct sleep_stack_data area
  */
 ENTRY(__cpu_suspend_enter)
-	stp	x29, lr, [sp, #-96]!
-	stp	x19, x20, [sp,#16]
-	stp	x21, x22, [sp,#32]
-	stp	x23, x24, [sp,#48]
-	stp	x25, x26, [sp,#64]
-	stp	x27, x28, [sp,#80]
-	/*
-	 * Stash suspend finisher and its argument in x20 and x19
-	 */
-	mov	x19, x0
-	mov	x20, x1
+	stp	x29, lr, [x0, #SLEEP_STACK_DATA_CALLEE_REGS]
+	stp	x19, x20, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+16]
+	stp	x21, x22, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+32]
+	stp	x23, x24, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+48]
+	stp	x25, x26, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+64]
+	stp	x27, x28, [x0,#SLEEP_STACK_DATA_CALLEE_REGS+80]
+
+	/* save the sp in cpu_suspend_ctx */
 	mov	x2, sp
-	sub	sp, sp, #CPU_SUSPEND_SZ	// allocate cpu_suspend_ctx
-	mov	x0, sp
-	/*
-	 * x0 now points to struct cpu_suspend_ctx allocated on the stack
-	 */
-	str	x2, [x0, #CPU_CTX_SP]
-	ldr	x1, =sleep_save_sp
-	ldr	x1, [x1, #SLEEP_SAVE_SP_VIRT]
+	str	x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
+
+	/* find the mpidr_hash */
+	ldr	x1, =sleep_save_stash
+	ldr	x1, [x1]
 	mrs	x7, mpidr_el1
 	ldr	x9, =mpidr_hash
 	ldr	x10, [x9, #MPIDR_HASH_MASK]
@@ -93,74 +86,28 @@ ENTRY(__cpu_suspend_enter)
 	ldp	w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10
 	add	x1, x1, x8, lsl #3
-	bl	__cpu_suspend_save
-	/*
-	 * Grab suspend finisher in x20 and its argument in x19
-	 */
-	mov	x0, x19
-	mov	x1, x20
-	/*
-	 * We are ready for power down, fire off the suspend finisher
-	 * in x1, with argument in x0
-	 */
-	blr	x1
-        /*
-	 * Never gets here, unless suspend finisher fails.
-	 * Successful cpu_suspend should return from cpu_resume, returning
-	 * through this code path is considered an error
-	 * If the return value is set to 0 force x0 = -EOPNOTSUPP
-	 * to make sure a proper error condition is propagated
-	 */
-	cmp	x0, #0
-	mov	x3, #-EOPNOTSUPP
-	csel	x0, x3, x0, eq
-	add	sp, sp, #CPU_SUSPEND_SZ	// rewind stack pointer
-	ldp	x19, x20, [sp, #16]
-	ldp	x21, x22, [sp, #32]
-	ldp	x23, x24, [sp, #48]
-	ldp	x25, x26, [sp, #64]
-	ldp	x27, x28, [sp, #80]
-	ldp	x29, lr, [sp], #96
+
+	str	x0, [x1]
+	add	x0, x0, #SLEEP_STACK_DATA_SYSTEM_REGS
+	stp	x29, lr, [sp, #-16]!
+	bl	cpu_do_suspend
+	ldp	x29, lr, [sp], #16
+	mov	x0, #1
 	ret
 ENDPROC(__cpu_suspend_enter)
 	.ltorg
 
-/*
- * 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
-	/*
-	 * Invalidate the local I-cache so that any instructions fetched
-	 * speculatively from the PoC are discarded, since they may have
-	 * been dynamically patched at the PoU.
-	 */
-	ic	iallu
-	dsb	nsh
-	isb
-	br	x3			// global jump to virtual address
-ENDPROC(cpu_resume_mmu)
-	.popsection
-cpu_resume_after_mmu:
-#ifdef CONFIG_KASAN
-	mov	x0, sp
-	bl	kasan_unpoison_remaining_stack
-#endif
-	mov	x0, #0			// return zero on success
-	ldp	x19, x20, [sp, #16]
-	ldp	x21, x22, [sp, #32]
-	ldp	x23, x24, [sp, #48]
-	ldp	x25, x26, [sp, #64]
-	ldp	x27, x28, [sp, #80]
-	ldp	x29, lr, [sp], #96
-	ret
-ENDPROC(cpu_resume_after_mmu)
-
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
+	/* enable the MMU early - so we can access sleep_save_stash by va */
+	adr_l	lr, __enable_mmu	/* __cpu_setup will return here */
+	ldr	x27, =_cpu_resume	/* __enable_mmu will branch here */
+	adrp	x25, idmap_pg_dir
+	adrp	x26, swapper_pg_dir
+	b	__cpu_setup
+ENDPROC(cpu_resume)
+
+ENTRY(_cpu_resume)
 	mrs	x1, mpidr_el1
 	adrp	x8, mpidr_hash
 	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
@@ -170,20 +117,32 @@ ENTRY(cpu_resume)
 	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
         /* x7 contains hash index, let's use it to grab context pointer */
-	ldr_l	x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS
+	ldr_l	x0, sleep_save_stash
 	ldr	x0, [x0, x7, lsl #3]
+	add	x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS
+	add	x0, x0, #SLEEP_STACK_DATA_SYSTEM_REGS
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
-	/* load physical address of identity map page table in x1 */
-	adrp	x1, idmap_pg_dir
 	mov	sp, x2
 	/* save thread_info */
 	and	x2, x2, #~(THREAD_SIZE - 1)
 	msr	sp_el0, x2
 	/*
-	 * cpu_do_resume expects x0 to contain context physical address
-	 * pointer and x1 to contain physical address of 1:1 page tables
+	 * cpu_do_resume expects x0 to contain context address pointer
 	 */
-	bl	cpu_do_resume		// PC relative jump, MMU off
-	b	cpu_resume_mmu		// Resume MMU, never returns
-ENDPROC(cpu_resume)
+	bl	cpu_do_resume
+
+#ifdef CONFIG_KASAN
+	mov	x0, sp
+	bl	kasan_unpoison_remaining_stack
+#endif
+
+	ldp	x19, x20, [x29, #16]
+	ldp	x21, x22, [x29, #32]
+	ldp	x23, x24, [x29, #48]
+	ldp	x25, x26, [x29, #64]
+	ldp	x27, x28, [x29, #80]
+	ldp	x29, lr, [x29]
+	mov	x0, #0
+	ret
+ENDPROC(_cpu_resume)

arch/arm64/kernel/smp.c

@@ -45,6 +45,7 @@
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/mmu_context.h>
+#include <asm/numa.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
@@ -75,6 +76,43 @@ enum ipi_msg_type {
 	IPI_WAKEUP
 };
 
+#ifdef CONFIG_ARM64_VHE
+
+/* Whether the boot CPU is running in HYP mode or not*/
+static bool boot_cpu_hyp_mode;
+
+static inline void save_boot_cpu_run_el(void)
+{
+	boot_cpu_hyp_mode = is_kernel_in_hyp_mode();
+}
+
+static inline bool is_boot_cpu_in_hyp_mode(void)
+{
+	return boot_cpu_hyp_mode;
+}
+
+/*
+ * Verify that a secondary CPU is running the kernel at the same
+ * EL as that of the boot CPU.
+ */
+void verify_cpu_run_el(void)
+{
+	bool in_el2 = is_kernel_in_hyp_mode();
+	bool boot_cpu_el2 = is_boot_cpu_in_hyp_mode();
+
+	if (in_el2 ^ boot_cpu_el2) {
+		pr_crit("CPU%d: mismatched Exception Level(EL%d) with boot CPU(EL%d)\n",
+					smp_processor_id(),
+					in_el2 ? 2 : 1,
+					boot_cpu_el2 ? 2 : 1);
+		cpu_panic_kernel();
+	}
+}
+
+#else
+static inline void save_boot_cpu_run_el(void) {}
+#endif
+
 #ifdef CONFIG_HOTPLUG_CPU
 static int op_cpu_kill(unsigned int cpu);
 #else
@@ -166,6 +204,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 static void smp_store_cpu_info(unsigned int cpuid)
 {
 	store_cpu_topology(cpuid);
+	numa_store_cpu_info(cpuid);
 }
 
 /*
@@ -225,8 +264,6 @@ asmlinkage void secondary_start_kernel(void)
 	pr_info("CPU%u: Booted secondary processor [%08x]\n",
 					 cpu, read_cpuid_id());
 	update_cpu_boot_status(CPU_BOOT_SUCCESS);
-	/* Make sure the status update is visible before we complete */
-	smp_wmb();
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
@@ -401,6 +438,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 void __init smp_prepare_boot_cpu(void)
 {
 	cpuinfo_store_boot_cpu();
+	save_boot_cpu_run_el();
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 }
 
@@ -595,6 +633,8 @@ static void __init of_parse_and_init_cpus(void)
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
 		cpu_logical_map(cpu_count) = hwid;
+
+		early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
 next:
 		cpu_count++;
 	}
@@ -647,33 +687,18 @@ void __init smp_init_cpus(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int err;
-	unsigned int cpu, ncores = num_possible_cpus();
+	unsigned int cpu;
 
 	init_cpu_topology();
 
 	smp_store_cpu_info(smp_processor_id());
 
-	/*
-	 * are we trying to boot more cores than exist?
-	 */
-	if (max_cpus > ncores)
-		max_cpus = ncores;
-
-	/* Don't bother if we're effectively UP */
-	if (max_cpus <= 1)
-		return;
-
 	/*
 	 * Initialise the present map (which describes the set of CPUs
 	 * actually populated at the present time) and release the
 	 * secondaries from the bootloader.
-	 *
-	 * Make sure we online at most (max_cpus - 1) additional CPUs.
 	 */
-	max_cpus--;
 	for_each_possible_cpu(cpu) {
-		if (max_cpus == 0)
-			break;
 
 		if (cpu == smp_processor_id())
 			continue;
@@ -686,7 +711,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 			continue;
 
 		set_cpu_present(cpu, true);
-		max_cpus--;
 	}
 }
 
@@ -763,21 +787,11 @@ void arch_irq_work_raise(void)
 }
 #endif
 
-static DEFINE_RAW_SPINLOCK(stop_lock);
-
 /*
  * ipi_cpu_stop - handle IPI from smp_send_stop()
  */
 static void ipi_cpu_stop(unsigned int cpu)
 {
-	if (system_state == SYSTEM_BOOTING ||
-	    system_state == SYSTEM_RUNNING) {
-		raw_spin_lock(&stop_lock);
-		pr_crit("CPU%u: stopping\n", cpu);
-		dump_stack();
-		raw_spin_unlock(&stop_lock);
-	}
-
 	set_cpu_online(cpu, false);
 
 	local_irq_disable();
@@ -872,6 +886,9 @@ void smp_send_stop(void)
 		cpumask_copy(&mask, cpu_online_mask);
 		cpumask_clear_cpu(smp_processor_id(), &mask);
 
+		if (system_state == SYSTEM_BOOTING ||
+		    system_state == SYSTEM_RUNNING)
+			pr_crit("SMP: stopping secondary CPUs\n");
 		smp_cross_call(&mask, IPI_CPU_STOP);
 	}
 
@@ -881,7 +898,8 @@ void smp_send_stop(void)
 		udelay(1);
 
 	if (num_online_cpus() > 1)
-		pr_warning("SMP: failed to stop secondary CPUs\n");
+		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(cpu_online_mask));
 }
 
 /*

arch/arm64/kernel/suspend.c

@@ -10,30 +10,11 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend_enter(unsigned long arg, int (*fn)(unsigned long));
 /*
- * This is called by __cpu_suspend_enter() to save the state, and do whatever
- * flushing is required to ensure that when the CPU goes to sleep we have
- * the necessary data available when the caches are not searched.
- *
- * ptr: CPU context virtual address
- * save_ptr: address of the location where the context physical address
- *           must be saved
+ * This is allocated by cpu_suspend_init(), and used to store a pointer to
+ * the 'struct sleep_stack_data' the contains a particular CPUs state.
  */
-void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr,
-				phys_addr_t *save_ptr)
-{
-	*save_ptr = virt_to_phys(ptr);
-
-	cpu_do_suspend(ptr);
-	/*
-	 * Only flush the context that must be retrieved with the MMU
-	 * off. VA primitives ensure the flush is applied to all
-	 * cache levels so context is pushed to DRAM.
-	 */
-	__flush_dcache_area(ptr, sizeof(*ptr));
-	__flush_dcache_area(save_ptr, sizeof(*save_ptr));
-}
+unsigned long *sleep_save_stash;
 
 /*
  * This hook is provided so that cpu_suspend code can restore HW
@@ -51,6 +32,30 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 	hw_breakpoint_restore = hw_bp_restore;
 }
 
+void notrace __cpu_suspend_exit(void)
+{
+	/*
+	 * We are resuming from reset with the idmap active in TTBR0_EL1.
+	 * We must uninstall the idmap and restore the expected MMU
+	 * state before we can possibly return to userspace.
+	 */
+	cpu_uninstall_idmap();
+
+	/*
+	 * Restore per-cpu offset before any kernel
+	 * subsystem relying on it has a chance to run.
+	 */
+	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+
+	/*
+	 * Restore HW breakpoint registers to sane values
+	 * before debug exceptions are possibly reenabled
+	 * through local_dbg_restore.
+	 */
+	if (hw_breakpoint_restore)
+		hw_breakpoint_restore(NULL);
+}
+
 /*
  * cpu_suspend
  *
@@ -60,8 +65,9 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
  */
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
-	int ret;
+	int ret = 0;
 	unsigned long flags;
+	struct sleep_stack_data state;
 
 	/*
 	 * From this point debug exceptions are disabled to prevent
@@ -77,34 +83,21 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 */
 	pause_graph_tracing();
 
-	/*
-	 * mm context saved on the stack, it will be restored when
-	 * the cpu comes out of reset through the identity mapped
-	 * page tables, so that the thread address space is properly
-	 * set-up on function return.
-	 */
-	ret = __cpu_suspend_enter(arg, fn);
-	if (ret == 0) {
-		/*
-		 * We are resuming from reset with the idmap active in TTBR0_EL1.
-		 * We must uninstall the idmap and restore the expected MMU
-		 * state before we can possibly return to userspace.
-		 */
-		cpu_uninstall_idmap();
+	if (__cpu_suspend_enter(&state)) {
+		/* Call the suspend finisher */
+		ret = fn(arg);
 
 		/*
-		 * Restore per-cpu offset before any kernel
-		 * subsystem relying on it has a chance to run.
+		 * Never gets here, unless the suspend finisher fails.
+		 * Successful cpu_suspend() should return from cpu_resume(),
+		 * returning through this code path is considered an error
+		 * If the return value is set to 0 force ret = -EOPNOTSUPP
+		 * to make sure a proper error condition is propagated
 		 */
-		set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-
-		/*
-		 * Restore HW breakpoint registers to sane values
-		 * before debug exceptions are possibly reenabled
-		 * through local_dbg_restore.
-		 */
-		if (hw_breakpoint_restore)
-			hw_breakpoint_restore(NULL);
+		if (!ret)
+			ret = -EOPNOTSUPP;
+	} else {
+		__cpu_suspend_exit();
 	}
 
 	unpause_graph_tracing();
@@ -119,22 +112,15 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	return ret;
 }
 
-struct sleep_save_sp sleep_save_sp;
-
 static int __init cpu_suspend_init(void)
 {
-	void *ctx_ptr;
-
 	/* ctx_ptr is an array of physical addresses */
-	ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(phys_addr_t), GFP_KERNEL);
+	sleep_save_stash = kcalloc(mpidr_hash_size(), sizeof(*sleep_save_stash),
+				   GFP_KERNEL);
 
-	if (WARN_ON(!ctx_ptr))
+	if (WARN_ON(!sleep_save_stash))
 		return -ENOMEM;
 
-	sleep_save_sp.save_ptr_stash = ctx_ptr;
-	sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr);
-	__flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp));
-
 	return 0;
 }
 early_initcall(cpu_suspend_init);

arch/arm64/kernel/sys.c

@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
+#include <asm/cpufeature.h>
 
 asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 			 unsigned long prot, unsigned long flags,
@@ -36,11 +37,20 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 	return sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
 }
 
+SYSCALL_DEFINE1(arm64_personality, unsigned int, personality)
+{
+	if (personality(personality) == PER_LINUX32 &&
+		!system_supports_32bit_el0())
+		return -EINVAL;
+	return sys_personality(personality);
+}
+
 /*
  * Wrappers to pass the pt_regs argument.
  */
 asmlinkage long sys_rt_sigreturn_wrapper(void);
 #define sys_rt_sigreturn	sys_rt_sigreturn_wrapper
+#define sys_personality		sys_arm64_personality
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	[nr] = sym,

arch/arm64/kernel/vdso.c

@@ -131,11 +131,11 @@ static int __init vdso_init(void)
 		return -ENOMEM;
 
 	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = virt_to_page(vdso_data);
+	vdso_pagelist[0] = pfn_to_page(PHYS_PFN(__pa(vdso_data)));
 
 	/* Grab the vDSO code pages. */
 	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i + 1] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+		vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i);
 
 	/* Populate the special mapping structures */
 	vdso_spec[0] = (struct vm_special_mapping) {

arch/arm64/kernel/vmlinux.lds.S

@@ -46,6 +46,16 @@ jiffies = jiffies_64;
 	*(.idmap.text)					\
 	VMLINUX_SYMBOL(__idmap_text_end) = .;
 
+#ifdef CONFIG_HIBERNATION
+#define HIBERNATE_TEXT					\
+	. = ALIGN(SZ_4K);				\
+	VMLINUX_SYMBOL(__hibernate_exit_text_start) = .;\
+	*(.hibernate_exit.text)				\
+	VMLINUX_SYMBOL(__hibernate_exit_text_end) = .;
+#else
+#define HIBERNATE_TEXT
+#endif
+
 /*
  * 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
@@ -63,14 +73,19 @@ PECOFF_FILE_ALIGNMENT = 0x200;
 #endif
 
 #if defined(CONFIG_DEBUG_ALIGN_RODATA)
-#define ALIGN_DEBUG_RO			. = ALIGN(1<<SECTION_SHIFT);
-#define ALIGN_DEBUG_RO_MIN(min)		ALIGN_DEBUG_RO
-#elif defined(CONFIG_DEBUG_RODATA)
-#define ALIGN_DEBUG_RO			. = ALIGN(1<<PAGE_SHIFT);
-#define ALIGN_DEBUG_RO_MIN(min)		ALIGN_DEBUG_RO
+/*
+ *  4 KB granule:   1 level 2 entry
+ * 16 KB granule: 128 level 3 entries, with contiguous bit
+ * 64 KB granule:  32 level 3 entries, with contiguous bit
+ */
+#define SEGMENT_ALIGN			SZ_2M
 #else
-#define ALIGN_DEBUG_RO
-#define ALIGN_DEBUG_RO_MIN(min)		. = ALIGN(min);
+/*
+ *  4 KB granule:  16 level 3 entries, with contiguous bit
+ * 16 KB granule:   4 level 3 entries, without contiguous bit
+ * 64 KB granule:   1 level 3 entry
+ */
+#define SEGMENT_ALIGN			SZ_64K
 #endif
 
 SECTIONS
@@ -96,7 +111,6 @@ SECTIONS
 		_text = .;
 		HEAD_TEXT
 	}
-	ALIGN_DEBUG_RO_MIN(PAGE_SIZE)
 	.text : {			/* Real text segment		*/
 		_stext = .;		/* Text and read-only data	*/
 			__exception_text_start = .;
@@ -109,18 +123,19 @@ SECTIONS
 			LOCK_TEXT
 			HYPERVISOR_TEXT
 			IDMAP_TEXT
+			HIBERNATE_TEXT
 			*(.fixup)
 			*(.gnu.warning)
 		. = ALIGN(16);
 		*(.got)			/* Global offset table		*/
 	}
 
-	ALIGN_DEBUG_RO_MIN(PAGE_SIZE)
+	. = ALIGN(SEGMENT_ALIGN);
 	RO_DATA(PAGE_SIZE)		/* everything from this point to */
 	EXCEPTION_TABLE(8)		/* _etext will be marked RO NX   */
 	NOTES
 
-	ALIGN_DEBUG_RO_MIN(PAGE_SIZE)
+	. = ALIGN(SEGMENT_ALIGN);
 	_etext = .;			/* End of text and rodata section */
 	__init_begin = .;
 
@@ -154,12 +169,9 @@ SECTIONS
 		*(.altinstr_replacement)
 	}
 	.rela : ALIGN(8) {
-		__reloc_start = .;
 		*(.rela .rela*)
-		__reloc_end = .;
 	}
 	.dynsym : ALIGN(8) {
-		__dynsym_start = .;
 		*(.dynsym)
 	}
 	.dynstr : {
@@ -169,7 +181,11 @@ SECTIONS
 		*(.hash)
 	}
 
-	. = ALIGN(PAGE_SIZE);
+	__rela_offset	= ADDR(.rela) - KIMAGE_VADDR;
+	__rela_size	= SIZEOF(.rela);
+	__dynsym_offset	= ADDR(.dynsym) - KIMAGE_VADDR;
+
+	. = ALIGN(SEGMENT_ALIGN);
 	__init_end = .;
 
 	_data = .;
@@ -201,6 +217,10 @@ 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")
+#ifdef CONFIG_HIBERNATION
+ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1))
+	<= SZ_4K, "Hibernate exit text too big or misaligned")
+#endif
 
 /*
  * If padding is applied before .head.text, virt<->phys conversions will fail.

arch/arm64/kvm/handle_exit.c

@@ -186,6 +186,13 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		exit_handler = kvm_get_exit_handler(vcpu);
 
 		return exit_handler(vcpu, run);
+	case ARM_EXCEPTION_HYP_GONE:
+		/*
+		 * EL2 has been reset to the hyp-stub. This happens when a guest
+		 * is pre-empted by kvm_reboot()'s shutdown call.
+		 */
+		run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+		return 0;
 	default:
 		kvm_pr_unimpl("Unsupported exception type: %d",
 			      exception_index);

arch/arm64/kvm/hyp-init.S

@@ -21,6 +21,7 @@
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
 #include <asm/pgtable-hwdef.h>
+#include <asm/sysreg.h>
 
 	.text
 	.pushsection	.hyp.idmap.text, "ax"
@@ -103,8 +104,8 @@ __do_hyp_init:
 	dsb	sy
 
 	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_EL2_FLAGS
+	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
+	ldr	x5, =SCTLR_ELx_FLAGS
 	orr	x4, x4, x5
 	msr	sctlr_el2, x4
 	isb
@@ -138,6 +139,49 @@ merged:
 	eret
 ENDPROC(__kvm_hyp_init)
 
+	/*
+	 * Reset kvm back to the hyp stub. This is the trampoline dance in
+	 * reverse. If kvm used an extended idmap, __extended_idmap_trampoline
+	 * calls this code directly in the idmap. In this case switching to the
+	 * boot tables is a no-op.
+	 *
+	 * x0: HYP boot pgd
+	 * x1: HYP phys_idmap_start
+	 */
+ENTRY(__kvm_hyp_reset)
+	/* We're in trampoline code in VA, switch back to boot page tables */
+	msr	ttbr0_el2, x0
+	isb
+
+	/* Ensure the PA branch doesn't find a stale tlb entry or stale code. */
+	ic	iallu
+	tlbi	alle2
+	dsb	sy
+	isb
+
+	/* Branch into PA space */
+	adr	x0, 1f
+	bfi	x1, x0, #0, #PAGE_SHIFT
+	br	x1
+
+	/* We're now in idmap, disable MMU */
+1:	mrs	x0, sctlr_el2
+	ldr	x1, =SCTLR_ELx_FLAGS
+	bic	x0, x0, x1		// Clear SCTL_M and etc
+	msr	sctlr_el2, x0
+	isb
+
+	/* Invalidate the old TLBs */
+	tlbi	alle2
+	dsb	sy
+
+	/* Install stub vectors */
+	adr_l	x0, __hyp_stub_vectors
+	msr	vbar_el2, x0
+
+	eret
+ENDPROC(__kvm_hyp_reset)
+
 	.ltorg
 
 	.popsection

arch/arm64/kvm/hyp.S

@@ -35,16 +35,21 @@
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in x0.
  *
- * A function pointer with a value of 0 has a special meaning, and is
- * used to implement __hyp_get_vectors in the same way as in
+ * A function pointer with a value less than 0xfff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
  * arch/arm64/kernel/hyp_stub.S.
+ * HVC behaves as a 'bl' call and will clobber lr.
  */
 ENTRY(__kvm_call_hyp)
-alternative_if_not ARM64_HAS_VIRT_HOST_EXTN	
+alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
+	str     lr, [sp, #-16]!
 	hvc	#0
+	ldr     lr, [sp], #16
 	ret
 alternative_else
 	b	__vhe_hyp_call
 	nop
+	nop
+	nop
 alternative_endif
 ENDPROC(__kvm_call_hyp)

arch/arm64/kvm/hyp/entry.S

@@ -164,3 +164,22 @@ alternative_endif
 
 	eret
 ENDPROC(__fpsimd_guest_restore)
+
+/*
+ * When using the extended idmap, we don't have a trampoline page we can use
+ * while we switch pages tables during __kvm_hyp_reset. Accessing the idmap
+ * directly would be ideal, but if we're using the extended idmap then the
+ * idmap is located above HYP_PAGE_OFFSET, and the address will be masked by
+ * kvm_call_hyp using kern_hyp_va.
+ *
+ * x0: HYP boot pgd
+ * x1: HYP phys_idmap_start
+ */
+ENTRY(__extended_idmap_trampoline)
+	mov	x4, x1
+	adr_l	x3, __kvm_hyp_reset
+
+	/* insert __kvm_hyp_reset()s offset into phys_idmap_start */
+	bfi	x4, x3, #0, #PAGE_SHIFT
+	br	x4
+ENDPROC(__extended_idmap_trampoline)

arch/arm64/kvm/hyp/hyp-entry.S

@@ -42,19 +42,17 @@
 	 * Shuffle the parameters before calling the function
 	 * pointed to in x0. Assumes parameters in x[1,2,3].
 	 */
-	sub	sp, sp, #16
-	str	lr, [sp]
 	mov	lr, x0
 	mov	x0, x1
 	mov	x1, x2
 	mov	x2, x3
 	blr	lr
-	ldr	lr, [sp]
-	add	sp, sp, #16
 .endm
 
 ENTRY(__vhe_hyp_call)
+	str	lr, [sp, #-16]!
 	do_el2_call
+	ldr	lr, [sp], #16
 	/*
 	 * We used to rely on having an exception return to get
 	 * an implicit isb. In the E2H case, we don't have it anymore.
@@ -84,8 +82,8 @@ alternative_endif
 	/* Here, we're pretty sure the host called HVC. */
 	restore_x0_to_x3
 
-	/* Check for __hyp_get_vectors */
-	cbnz	x0, 1f
+	cmp	x0, #HVC_GET_VECTORS
+	b.ne	1f
 	mrs	x0, vbar_el2
 	b	2f
 

arch/arm64/kvm/reset.c

@@ -29,7 +29,9 @@
 #include <asm/cputype.h>
 #include <asm/ptrace.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_asm.h>
 #include <asm/kvm_coproc.h>
+#include <asm/kvm_mmu.h>
 
 /*
  * ARMv8 Reset Values
@@ -130,3 +132,31 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	/* Reset timer */
 	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
 }
+
+extern char __hyp_idmap_text_start[];
+
+unsigned long kvm_hyp_reset_entry(void)
+{
+	if (!__kvm_cpu_uses_extended_idmap()) {
+		unsigned long offset;
+
+		/*
+		 * Find the address of __kvm_hyp_reset() in the trampoline page.
+		 * This is present in the running page tables, and the boot page
+		 * tables, so we call the code here to start the trampoline
+		 * dance in reverse.
+		 */
+		offset = (unsigned long)__kvm_hyp_reset
+			 - ((unsigned long)__hyp_idmap_text_start & PAGE_MASK);
+
+		return TRAMPOLINE_VA + offset;
+	} else {
+		/*
+		 * KVM is running with merged page tables, which don't have the
+		 * trampoline page mapped. We know the idmap is still mapped,
+		 * but can't be called into directly. Use
+		 * __extended_idmap_trampoline to do the call.
+		 */
+		return (unsigned long)kvm_ksym_ref(__extended_idmap_trampoline);
+	}
+}

arch/arm64/mm/Makefile

@@ -4,6 +4,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+obj-$(CONFIG_NUMA)		+= numa.o
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o
 KASAN_SANITIZE_kasan_init.o	:= n

arch/arm64/mm/cache.S

@@ -24,8 +24,6 @@
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
 
-#include "proc-macros.S"
-
 /*
  *	flush_icache_range(start,end)
  *

arch/arm64/mm/context.c

@@ -75,8 +75,7 @@ void verify_cpu_asid_bits(void)
 		 */
 		pr_crit("CPU%d: smaller ASID size(%u) than boot CPU (%u)\n",
 				smp_processor_id(), asid, asid_bits);
-		update_cpu_boot_status(CPU_PANIC_KERNEL);
-		cpu_park_loop();
+		cpu_panic_kernel();
 	}
 }
 

arch/arm64/mm/dma-mapping.c

@@ -804,57 +804,24 @@ struct iommu_dma_notifier_data {
 static LIST_HEAD(iommu_dma_masters);
 static DEFINE_MUTEX(iommu_dma_notifier_lock);
 
-/*
- * Temporarily "borrow" a domain feature flag to to tell if we had to resort
- * to creating our own domain here, in case we need to clean it up again.
- */
-#define __IOMMU_DOMAIN_FAKE_DEFAULT		(1U << 31)
-
 static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
 			   u64 dma_base, u64 size)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
 	/*
-	 * Best case: The device is either part of a group which was
-	 * already attached to a domain in a previous call, or it's
-	 * been put in a default DMA domain by the IOMMU core.
+	 * If the IOMMU driver has the DMA domain support that we require,
+	 * then the IOMMU core will have already configured a group for this
+	 * device, and allocated the default domain for that group.
 	 */
-	if (!domain) {
-		/*
-		 * Urgh. The IOMMU core isn't going to do default domains
-		 * for non-PCI devices anyway, until it has some means of
-		 * abstracting the entirely implementation-specific
-		 * sideband data/SoC topology/unicorn dust that may or
-		 * may not differentiate upstream masters.
-		 * So until then, HORRIBLE HACKS!
-		 */
-		domain = ops->domain_alloc(IOMMU_DOMAIN_DMA);
-		if (!domain)
-			goto out_no_domain;
-
-		domain->ops = ops;
-		domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_FAKE_DEFAULT;
-
-		if (iommu_attach_device(domain, dev))
-			goto out_put_domain;
+	if (!domain || iommu_dma_init_domain(domain, dma_base, size)) {
+		pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+			dev_name(dev));
+		return false;
 	}
 
-	if (iommu_dma_init_domain(domain, dma_base, size))
-		goto out_detach;
-
 	dev->archdata.dma_ops = &iommu_dma_ops;
 	return true;
-
-out_detach:
-	iommu_detach_device(domain, dev);
-out_put_domain:
-	if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
-		iommu_domain_free(domain);
-out_no_domain:
-	pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-		dev_name(dev));
-	return false;
 }
 
 static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
@@ -933,6 +900,10 @@ static int __init __iommu_dma_init(void)
 		ret = register_iommu_dma_ops_notifier(&platform_bus_type);
 	if (!ret)
 		ret = register_iommu_dma_ops_notifier(&amba_bustype);
+#ifdef CONFIG_PCI
+	if (!ret)
+		ret = register_iommu_dma_ops_notifier(&pci_bus_type);
+#endif
 
 	/* handle devices queued before this arch_initcall */
 	if (!ret)
@@ -967,11 +938,8 @@ void arch_teardown_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
-	if (domain) {
+	if (WARN_ON(domain))
 		iommu_detach_device(domain, dev);
-		if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT)
-			iommu_domain_free(domain);
-	}
 
 	dev->archdata.dma_ops = NULL;
 }

arch/arm64/mm/dump.c

@@ -23,6 +23,7 @@
 #include <linux/seq_file.h>
 
 #include <asm/fixmap.h>
+#include <asm/kasan.h>
 #include <asm/memory.h>
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
@@ -32,37 +33,25 @@ struct addr_marker {
 	const char *name;
 };
 
-enum address_markers_idx {
-	MODULES_START_NR = 0,
-	MODULES_END_NR,
-	VMALLOC_START_NR,
-	VMALLOC_END_NR,
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	VMEMMAP_START_NR,
-	VMEMMAP_END_NR,
+static const struct addr_marker address_markers[] = {
+#ifdef CONFIG_KASAN
+	{ KASAN_SHADOW_START,		"Kasan shadow start" },
+	{ KASAN_SHADOW_END,		"Kasan shadow end" },
 #endif
-	FIXADDR_START_NR,
-	FIXADDR_END_NR,
-	PCI_START_NR,
-	PCI_END_NR,
-	KERNEL_SPACE_NR,
-};
-
-static struct addr_marker address_markers[] = {
-	{ MODULES_VADDR,	"Modules start" },
-	{ MODULES_END,		"Modules end" },
-	{ VMALLOC_START,	"vmalloc() Area" },
-	{ VMALLOC_END,		"vmalloc() End" },
+	{ MODULES_VADDR,		"Modules start" },
+	{ MODULES_END,			"Modules end" },
+	{ VMALLOC_START,		"vmalloc() Area" },
+	{ VMALLOC_END,			"vmalloc() End" },
+	{ FIXADDR_START,		"Fixmap start" },
+	{ FIXADDR_TOP,			"Fixmap end" },
+	{ PCI_IO_START,			"PCI I/O start" },
+	{ PCI_IO_END,			"PCI I/O end" },
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-	{ 0,			"vmemmap start" },
-	{ 0,			"vmemmap end" },
+	{ VMEMMAP_START,		"vmemmap start" },
+	{ VMEMMAP_START + VMEMMAP_SIZE,	"vmemmap end" },
 #endif
-	{ FIXADDR_START,	"Fixmap start" },
-	{ FIXADDR_TOP,		"Fixmap end" },
-	{ PCI_IO_START,		"PCI I/O start" },
-	{ PCI_IO_END,		"PCI I/O end" },
-	{ PAGE_OFFSET,		"Linear Mapping" },
-	{ -1,			NULL },
+	{ PAGE_OFFSET,			"Linear Mapping" },
+	{ -1,				NULL },
 };
 
 /*
@@ -347,13 +336,6 @@ static int ptdump_init(void)
 			for (j = 0; j < pg_level[i].num; j++)
 				pg_level[i].mask |= pg_level[i].bits[j].mask;
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	address_markers[VMEMMAP_START_NR].start_address =
-				(unsigned long)virt_to_page(PAGE_OFFSET);
-	address_markers[VMEMMAP_END_NR].start_address =
-				(unsigned long)virt_to_page(high_memory);
-#endif
-
 	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
 				 &ptdump_fops);
 	return pe ? 0 : -ENOMEM;

arch/arm64/mm/fault.c

@@ -81,6 +81,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 	printk("\n");
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/*
+ * This function sets the access flags (dirty, accessed), as well as write
+ * permission, and only to a more permissive setting.
+ *
+ * It needs to cope with hardware update of the accessed/dirty state by other
+ * agents in the system and can safely skip the __sync_icache_dcache() call as,
+ * like set_pte_at(), the PTE is never changed from no-exec to exec here.
+ *
+ * Returns whether or not the PTE actually changed.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	pteval_t old_pteval;
+	unsigned int tmp;
+
+	if (pte_same(*ptep, entry))
+		return 0;
+
+	/* only preserve the access flags and write permission */
+	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
+
+	/*
+	 * PTE_RDONLY is cleared by default in the asm below, so set it in
+	 * back if necessary (read-only or clean PTE).
+	 */
+	if (!pte_write(entry) || !dirty)
+		pte_val(entry) |= PTE_RDONLY;
+
+	/*
+	 * Setting the flags must be done atomically to avoid racing with the
+	 * hardware update of the access/dirty state.
+	 */
+	asm volatile("//	ptep_set_access_flags\n"
+	"	prfm	pstl1strm, %2\n"
+	"1:	ldxr	%0, %2\n"
+	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	orr	%0, %0, %4		// set flags\n"
+	"	stxr	%w1, %0, %2\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
+	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+
+	flush_tlb_fix_spurious_fault(vma, address);
+	return 1;
+}
+#endif
+
 /*
  * The kernel tried to access some page that wasn't present.
  */
@@ -212,10 +262,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	tsk = current;
 	mm  = tsk->mm;
 
-	/* Enable interrupts if they were enabled in the parent context. */
-	if (interrupts_enabled(regs))
-		local_irq_enable();
-
 	/*
 	 * If we're in an interrupt or have no user context, we must not take
 	 * the fault.
@@ -555,20 +601,33 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 {
 	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
 	struct siginfo info;
+	int rv;
 
-	if (!inf->fn(addr, esr, regs))
-		return 1;
+	/*
+	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
+	 * already disabled to preserve the last enabled/disabled addresses.
+	 */
+	if (interrupts_enabled(regs))
+		trace_hardirqs_off();
 
-	pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
-		 inf->name, esr, addr);
+	if (!inf->fn(addr, esr, regs)) {
+		rv = 1;
+	} else {
+		pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
+			 inf->name, esr, addr);
+
+		info.si_signo = inf->sig;
+		info.si_errno = 0;
+		info.si_code  = inf->code;
+		info.si_addr  = (void __user *)addr;
+		arm64_notify_die("", regs, &info, 0);
+		rv = 0;
+	}
 
-	info.si_signo = inf->sig;
-	info.si_errno = 0;
-	info.si_code  = inf->code;
-	info.si_addr  = (void __user *)addr;
-	arm64_notify_die("", regs, &info, 0);
+	if (interrupts_enabled(regs))
+		trace_hardirqs_on();
 
-	return 0;
+	return rv;
 }
 
 #ifdef CONFIG_ARM64_PAN

arch/arm64/mm/init.c

@@ -40,6 +40,7 @@
 #include <asm/kasan.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
+#include <asm/numa.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -86,6 +87,21 @@ static phys_addr_t __init max_zone_dma_phys(void)
 	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
 }
 
+#ifdef CONFIG_NUMA
+
+static void __init zone_sizes_init(unsigned long min, unsigned long max)
+{
+	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
+
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		max_zone_pfns[ZONE_DMA] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_NORMAL] = max;
+
+	free_area_init_nodes(max_zone_pfns);
+}
+
+#else
+
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
@@ -126,6 +142,8 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	free_area_init_node(0, zone_size, min, zhole_size);
 }
 
+#endif /* CONFIG_NUMA */
+
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
@@ -142,10 +160,15 @@ static void __init arm64_memory_present(void)
 static void __init arm64_memory_present(void)
 {
 	struct memblock_region *reg;
+	int nid = 0;
 
-	for_each_memblock(memory, reg)
-		memory_present(0, memblock_region_memory_base_pfn(reg),
-			       memblock_region_memory_end_pfn(reg));
+	for_each_memblock(memory, reg) {
+#ifdef CONFIG_NUMA
+		nid = reg->nid;
+#endif
+		memory_present(nid, memblock_region_memory_base_pfn(reg),
+				memblock_region_memory_end_pfn(reg));
+	}
 }
 #endif
 
@@ -190,8 +213,12 @@ void __init arm64_memblock_init(void)
 	 */
 	memblock_remove(max_t(u64, memstart_addr + linear_region_size, __pa(_end)),
 			ULLONG_MAX);
-	if (memblock_end_of_DRAM() > linear_region_size)
-		memblock_remove(0, memblock_end_of_DRAM() - linear_region_size);
+	if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
+		/* ensure that memstart_addr remains sufficiently aligned */
+		memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
+					 ARM64_MEMSTART_ALIGN);
+		memblock_remove(0, memstart_addr);
+	}
 
 	/*
 	 * Apply the memory limit if it was set. Since the kernel may be loaded
@@ -203,6 +230,35 @@ void __init arm64_memblock_init(void)
 		memblock_add(__pa(_text), (u64)(_end - _text));
 	}
 
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) {
+		/*
+		 * Add back the memory we just removed if it results in the
+		 * initrd to become inaccessible via the linear mapping.
+		 * Otherwise, this is a no-op
+		 */
+		u64 base = initrd_start & PAGE_MASK;
+		u64 size = PAGE_ALIGN(initrd_end) - base;
+
+		/*
+		 * We can only add back the initrd memory if we don't end up
+		 * with more memory than we can address via the linear mapping.
+		 * It is up to the bootloader to position the kernel and the
+		 * initrd reasonably close to each other (i.e., within 32 GB of
+		 * each other) so that all granule/#levels combinations can
+		 * always access both.
+		 */
+		if (WARN(base < memblock_start_of_DRAM() ||
+			 base + size > memblock_start_of_DRAM() +
+				       linear_region_size,
+			"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
+			initrd_start = 0;
+		} else {
+			memblock_remove(base, size); /* clear MEMBLOCK_ flags */
+			memblock_add(base, size);
+			memblock_reserve(base, size);
+		}
+	}
+
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
 		u64 range = linear_region_size -
@@ -245,7 +301,6 @@ void __init arm64_memblock_init(void)
 	dma_contiguous_reserve(arm64_dma_phys_limit);
 
 	memblock_allow_resize();
-	memblock_dump_all();
 }
 
 void __init bootmem_init(void)
@@ -257,6 +312,9 @@ void __init bootmem_init(void)
 
 	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
 
+	max_pfn = max_low_pfn = max;
+
+	arm64_numa_init();
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
 	 * done after the fixed reservations.
@@ -267,7 +325,7 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;
-	max_pfn = max_low_pfn = max;
+	memblock_dump_all();
 }
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
@@ -371,26 +429,27 @@ void __init mem_init(void)
 		MLM(MODULES_VADDR, MODULES_END));
 	pr_cont("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(VMALLOC_START, VMALLOC_END));
-	pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n"
-		"    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n"
-		"      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n"
-		"      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(_text, __start_rodata),
-		MLK_ROUNDUP(__start_rodata, _etext),
-		MLK_ROUNDUP(__init_begin, __init_end),
+	pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		MLK_ROUNDUP(_text, __start_rodata));
+	pr_cont("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		MLK_ROUNDUP(__start_rodata, _etext));
+	pr_cont("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		MLK_ROUNDUP(__init_begin, __init_end));
+	pr_cont("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(_sdata, _edata));
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-	pr_cont("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n"
-		"              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
-		MLG(VMEMMAP_START,
-		    VMEMMAP_START + VMEMMAP_SIZE),
-		MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
-		    (unsigned long)virt_to_page(high_memory)));
-#endif
+	pr_cont("       .bss : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		MLK_ROUNDUP(__bss_start, __bss_stop));
 	pr_cont("    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n",
 		MLK(FIXADDR_START, FIXADDR_TOP));
 	pr_cont("    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(PCI_IO_START, PCI_IO_END));
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	pr_cont("    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n",
+		MLG(VMEMMAP_START, VMEMMAP_START + VMEMMAP_SIZE));
+	pr_cont("              0x%16lx - 0x%16lx   (%6ld MB actual)\n",
+		MLM((unsigned long)phys_to_page(memblock_start_of_DRAM()),
+		    (unsigned long)virt_to_page(high_memory)));
+#endif
 	pr_cont("    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n",
 		MLM(__phys_to_virt(memblock_start_of_DRAM()),
 		    (unsigned long)high_memory));
@@ -407,6 +466,12 @@ void __init mem_init(void)
 	BUILD_BUG_ON(TASK_SIZE_32			> TASK_SIZE_64);
 #endif
 
+	/*
+	 * Make sure we chose the upper bound of sizeof(struct page)
+	 * correctly.
+	 */
+	BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+
 	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
 		extern int sysctl_overcommit_memory;
 		/*
@@ -419,7 +484,8 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	free_initmem_default(0);
+	free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
+			   0, "unused kernel");
 	fixup_init();
 }
 

arch/arm64/mm/mm.h

@@ -1,3 +1,2 @@
-extern void __init bootmem_init(void);
 
 void fixup_init(void);

arch/arm64/mm/mmap.c

@@ -95,8 +95,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
-EXPORT_SYMBOL_GPL(arch_pick_mmap_layout);
-
 
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go

arch/arm64/mm/mmu.c

@@ -385,7 +385,7 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 
 static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
 {
-	unsigned long kernel_start = __pa(_stext);
+	unsigned long kernel_start = __pa(_text);
 	unsigned long kernel_end = __pa(_etext);
 
 	/*
@@ -417,7 +417,7 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end
 				     early_pgtable_alloc);
 
 	/*
-	 * Map the linear alias of the [_stext, _etext) interval as
+	 * Map the linear alias of the [_text, _etext) interval as
 	 * read-only/non-executable. This makes the contents of the
 	 * region accessible to subsystems such as hibernate, but
 	 * protects it from inadvertent modification or execution.
@@ -449,8 +449,8 @@ void mark_rodata_ro(void)
 {
 	unsigned long section_size;
 
-	section_size = (unsigned long)__start_rodata - (unsigned long)_stext;
-	create_mapping_late(__pa(_stext), (unsigned long)_stext,
+	section_size = (unsigned long)__start_rodata - (unsigned long)_text;
+	create_mapping_late(__pa(_text), (unsigned long)_text,
 			    section_size, PAGE_KERNEL_ROX);
 	/*
 	 * mark .rodata as read only. Use _etext rather than __end_rodata to
@@ -471,8 +471,8 @@ void fixup_init(void)
 	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
-static void __init map_kernel_chunk(pgd_t *pgd, void *va_start, void *va_end,
-				    pgprot_t prot, struct vm_struct *vma)
+static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
+				      pgprot_t prot, struct vm_struct *vma)
 {
 	phys_addr_t pa_start = __pa(va_start);
 	unsigned long size = va_end - va_start;
@@ -499,11 +499,11 @@ static void __init map_kernel(pgd_t *pgd)
 {
 	static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data;
 
-	map_kernel_chunk(pgd, _stext, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text);
-	map_kernel_chunk(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata);
-	map_kernel_chunk(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC,
-			 &vmlinux_init);
-	map_kernel_chunk(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
+	map_kernel_segment(pgd, _text, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text);
+	map_kernel_segment(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata);
+	map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC,
+			   &vmlinux_init);
+	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
 
 	if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
 		/*
@@ -564,8 +564,6 @@ void __init paging_init(void)
 	 */
 	memblock_free(__pa(swapper_pg_dir) + PAGE_SIZE,
 		      SWAPPER_DIR_SIZE - PAGE_SIZE);
-
-	bootmem_init();
 }
 
 /*

arch/arm64/mm/numa.c

@@ -0,0 +1,396 @@
+/*
+ * NUMA support, based on the x86 implementation.
+ *
+ * Copyright (C) 2015 Cavium Inc.
+ * Author: Ganapatrao Kulkarni <gkulkarni@cavium.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/bootmem.h>
+#include <linux/memblock.h>
+#include <linux/module.h>
+#include <linux/of.h>
+
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
+nodemask_t numa_nodes_parsed __initdata;
+static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
+
+static int numa_distance_cnt;
+static u8 *numa_distance;
+static int numa_off;
+
+static __init int numa_parse_early_param(char *opt)
+{
+	if (!opt)
+		return -EINVAL;
+	if (!strncmp(opt, "off", 3)) {
+		pr_info("%s\n", "NUMA turned off");
+		numa_off = 1;
+	}
+	return 0;
+}
+early_param("numa", numa_parse_early_param);
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	if (WARN_ON(node >= nr_node_ids))
+		return cpu_none_mask;
+
+	if (WARN_ON(node_to_cpumask_map[node] == NULL))
+		return cpu_online_mask;
+
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+#endif
+
+static void map_cpu_to_node(unsigned int cpu, int nid)
+{
+	set_cpu_numa_node(cpu, nid);
+	if (nid >= 0)
+		cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+	int nid = cpu_to_node(cpu);
+
+	if (nid >= 0)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+	set_cpu_numa_node(cpu, NUMA_NO_NODE);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+static void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int cpu;
+	int node;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES)
+		setup_nr_node_ids();
+
+	/* allocate and clear the mapping */
+	for (node = 0; node < nr_node_ids; node++) {
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+		cpumask_clear(node_to_cpumask_map[node]);
+	}
+
+	for_each_possible_cpu(cpu)
+		set_cpu_numa_node(cpu, NUMA_NO_NODE);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+/*
+ *  Set the cpu to node and mem mapping
+ */
+void numa_store_cpu_info(unsigned int cpu)
+{
+	map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+}
+
+void __init early_map_cpu_to_node(unsigned int cpu, int nid)
+{
+	/* fallback to node 0 */
+	if (nid < 0 || nid >= MAX_NUMNODES)
+		nid = 0;
+
+	cpu_to_node_map[cpu] = nid;
+}
+
+/**
+ * numa_add_memblk - Set node id to memblk
+ * @nid: NUMA node ID of the new memblk
+ * @start: Start address of the new memblk
+ * @size:  Size of the new memblk
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int __init numa_add_memblk(int nid, u64 start, u64 size)
+{
+	int ret;
+
+	ret = memblock_set_node(start, size, &memblock.memory, nid);
+	if (ret < 0) {
+		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+			start, (start + size - 1), nid);
+		return ret;
+	}
+
+	node_set(nid, numa_nodes_parsed);
+	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+			start, (start + size - 1), nid);
+	return ret;
+}
+
+/**
+ * Initialize NODE_DATA for a node on the local memory
+ */
+static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+{
+	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);
+	u64 nd_pa;
+	void *nd;
+	int tnid;
+
+	pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+			nid, start_pfn << PAGE_SHIFT,
+			(end_pfn << PAGE_SHIFT) - 1);
+
+	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
+	nd = __va(nd_pa);
+
+	/* report and initialize */
+	pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+		nd_pa, nd_pa + nd_size - 1);
+	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
+	if (tnid != nid)
+		pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+
+	node_data[nid] = nd;
+	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+	NODE_DATA(nid)->node_id = nid;
+	NODE_DATA(nid)->node_start_pfn = start_pfn;
+	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
+}
+
+/**
+ * numa_free_distance
+ *
+ * The current table is freed.
+ */
+void __init numa_free_distance(void)
+{
+	size_t size;
+
+	if (!numa_distance)
+		return;
+
+	size = numa_distance_cnt * numa_distance_cnt *
+		sizeof(numa_distance[0]);
+
+	memblock_free(__pa(numa_distance), size);
+	numa_distance_cnt = 0;
+	numa_distance = NULL;
+}
+
+/**
+ *
+ * Create a new NUMA distance table.
+ *
+ */
+static int __init numa_alloc_distance(void)
+{
+	size_t size;
+	u64 phys;
+	int i, j;
+
+	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
+	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+				      size, PAGE_SIZE);
+	if (WARN_ON(!phys))
+		return -ENOMEM;
+
+	memblock_reserve(phys, size);
+
+	numa_distance = __va(phys);
+	numa_distance_cnt = nr_node_ids;
+
+	/* fill with the default distances */
+	for (i = 0; i < numa_distance_cnt; i++)
+		for (j = 0; j < numa_distance_cnt; j++)
+			numa_distance[i * numa_distance_cnt + j] = i == j ?
+				LOCAL_DISTANCE : REMOTE_DISTANCE;
+
+	pr_debug("NUMA: Initialized distance table, cnt=%d\n",
+			numa_distance_cnt);
+
+	return 0;
+}
+
+/**
+ * numa_set_distance - Set inter node NUMA distance from node to node.
+ * @from: the 'from' node to set distance
+ * @to: the 'to'  node to set distance
+ * @distance: NUMA distance
+ *
+ * Set the distance from node @from to @to to @distance.
+ * If distance table doesn't exist, a warning is printed.
+ *
+ * If @from or @to is higher than the highest known node or lower than zero
+ * or @distance doesn't make sense, the call is ignored.
+ *
+ */
+void __init numa_set_distance(int from, int to, int distance)
+{
+	if (!numa_distance) {
+		pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+		return;
+	}
+
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+			from < 0 || to < 0) {
+		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+			    from, to, distance);
+		return;
+	}
+
+	if ((u8)distance != distance ||
+	    (from == to && distance != LOCAL_DISTANCE)) {
+		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+			     from, to, distance);
+		return;
+	}
+
+	numa_distance[from * numa_distance_cnt + to] = distance;
+}
+
+/**
+ * Return NUMA distance @from to @to
+ */
+int __node_distance(int from, int to)
+{
+	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
+		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
+	return numa_distance[from * numa_distance_cnt + to];
+}
+EXPORT_SYMBOL(__node_distance);
+
+static int __init numa_register_nodes(void)
+{
+	int nid;
+	struct memblock_region *mblk;
+
+	/* Check that valid nid is set to memblks */
+	for_each_memblock(memory, mblk)
+		if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
+			pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+				mblk->nid, mblk->base,
+				mblk->base + mblk->size - 1);
+			return -EINVAL;
+		}
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, numa_nodes_parsed) {
+		unsigned long start_pfn, end_pfn;
+
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+		setup_node_data(nid, start_pfn, end_pfn);
+		node_set_online(nid);
+	}
+
+	/* Setup online nodes to actual nodes*/
+	node_possible_map = numa_nodes_parsed;
+
+	return 0;
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+	int ret;
+
+	nodes_clear(numa_nodes_parsed);
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	numa_free_distance();
+
+	ret = numa_alloc_distance();
+	if (ret < 0)
+		return ret;
+
+	ret = init_func();
+	if (ret < 0)
+		return ret;
+
+	if (nodes_empty(numa_nodes_parsed))
+		return -EINVAL;
+
+	ret = numa_register_nodes();
+	if (ret < 0)
+		return ret;
+
+	setup_node_to_cpumask_map();
+
+	/* init boot processor */
+	cpu_to_node_map[0] = 0;
+	map_cpu_to_node(0, 0);
+
+	return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node (node 0) and add memory blocks that cover all
+ * allowed memory. It is unlikely that this function fails.
+ */
+static int __init dummy_numa_init(void)
+{
+	int ret;
+	struct memblock_region *mblk;
+
+	pr_info("%s\n", "No NUMA configuration found");
+	pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
+	       0LLU, PFN_PHYS(max_pfn) - 1);
+
+	for_each_memblock(memory, mblk) {
+		ret = numa_add_memblk(0, mblk->base, mblk->size);
+		if (!ret)
+			continue;
+
+		pr_err("NUMA init failed\n");
+		return ret;
+	}
+
+	numa_off = 1;
+	return 0;
+}
+
+/**
+ * arm64_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encomapssing whole memory.
+ */
+void __init arm64_numa_init(void)
+{
+	if (!numa_off) {
+		if (!numa_init(of_numa_init))
+			return;
+	}
+
+	numa_init(dummy_numa_init);
+}

arch/arm64/mm/proc-macros.S

@@ -1,98 +0,0 @@
-/*
- * Based on arch/arm/mm/proc-macros.S
- *
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-
-/*
- * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
- */
-	.macro	vma_vm_mm, rd, rn
-	ldr	\rd, [\rn, #VMA_VM_MM]
-	.endm
-
-/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
-	.macro	mmid, rd, rn
-	ldr	\rd, [\rn, #MM_CONTEXT_ID]
-	.endm
-
-/*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
- */
-	.macro	dcache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
-
-/*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
- */
-	.macro	icache_line_size, reg, tmp
-	mrs	\tmp, ctr_el0			// read CTR
-	and	\tmp, \tmp, #0xf		// cache line size encoding
-	mov	\reg, #4			// bytes per word
-	lsl	\reg, \reg, \tmp		// actual cache line size
-	.endm
-
-/*
- * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
- */
-	.macro	tcr_set_idmap_t0sz, valreg, tmpreg
-#ifndef CONFIG_ARM64_VA_BITS_48
-	ldr_l	\tmpreg, idmap_t0sz
-	bfi	\valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
-#endif
-	.endm
-
-/*
- * Macro to perform a data cache maintenance for the interval
- * [kaddr, kaddr + size)
- *
- * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
- * 	kaddr:		starting virtual address of the region
- * 	size:		size of the region
- * 	Corrupts: 	kaddr, size, tmp1, tmp2
- */
-	.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
-	dcache_line_size \tmp1, \tmp2
-	add	\size, \kaddr, \size
-	sub	\tmp2, \tmp1, #1
-	bic	\kaddr, \kaddr, \tmp2
-9998:	dc	\op, \kaddr
-	add	\kaddr, \kaddr, \tmp1
-	cmp	\kaddr, \size
-	b.lo	9998b
-	dsb	\domain
-	.endm
-
-/*
- * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
- */
-	.macro	reset_pmuserenr_el0, tmpreg
-	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	\tmpreg, \tmpreg, #8, #4
-	cmp	\tmpreg, #1			// Skip if no PMU present
-	b.lt	9000f
-	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
-9000:
-	.endm

arch/arm64/mm/proc.S

@@ -23,13 +23,11 @@
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/hwcap.h>
-#include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
 
-#include "proc-macros.S"
-
 #ifdef CONFIG_ARM64_64K_PAGES
 #define TCR_TG_FLAGS	TCR_TG0_64K | TCR_TG1_64K
 #elif defined(CONFIG_ARM64_16K_PAGES)
@@ -66,62 +64,50 @@ ENTRY(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
-	mrs	x5, mair_el1
-	mrs	x6, cpacr_el1
-	mrs	x7, ttbr1_el1
-	mrs	x8, tcr_el1
-	mrs	x9, vbar_el1
-	mrs	x10, mdscr_el1
-	mrs	x11, oslsr_el1
-	mrs	x12, sctlr_el1
+	mrs	x5, cpacr_el1
+	mrs	x6, tcr_el1
+	mrs	x7, vbar_el1
+	mrs	x8, mdscr_el1
+	mrs	x9, oslsr_el1
+	mrs	x10, sctlr_el1
 	stp	x2, x3, [x0]
-	stp	x4, x5, [x0, #16]
-	stp	x6, x7, [x0, #32]
-	stp	x8, x9, [x0, #48]
-	stp	x10, x11, [x0, #64]
-	str	x12, [x0, #80]
+	stp	x4, xzr, [x0, #16]
+	stp	x5, x6, [x0, #32]
+	stp	x7, x8, [x0, #48]
+	stp	x9, x10, [x0, #64]
 	ret
 ENDPROC(cpu_do_suspend)
 
 /**
  * cpu_do_resume - restore CPU register context
  *
- * x0: Physical address of context pointer
- * x1: ttbr0_el1 to be restored
- *
- * Returns:
- *	sctlr_el1 value in x0
+ * x0: Address of context pointer
  */
 ENTRY(cpu_do_resume)
-	/*
-	 * Invalidate local tlb entries before turning on MMU
-	 */
-	tlbi	vmalle1
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
-	ldp	x6, x7, [x0, #32]
-	ldp	x8, x9, [x0, #48]
-	ldp	x10, x11, [x0, #64]
-	ldr	x12, [x0, #80]
+	ldp	x6, x8, [x0, #32]
+	ldp	x9, x10, [x0, #48]
+	ldp	x11, x12, [x0, #64]
 	msr	tpidr_el0, x2
 	msr	tpidrro_el0, x3
 	msr	contextidr_el1, x4
-	msr	mair_el1, x5
 	msr	cpacr_el1, x6
-	msr	ttbr0_el1, x1
-	msr	ttbr1_el1, x7
-	tcr_set_idmap_t0sz x8, x7
+
+	/* Don't change t0sz here, mask those bits when restoring */
+	mrs	x5, tcr_el1
+	bfi	x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
 	msr	mdscr_el1, x10
+	msr	sctlr_el1, x12
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
-	mov	x0, x12
-	dsb	nsh		// Make sure local tlb invalidation completed
 	isb
 	ret
 ENDPROC(cpu_do_resume)

arch/nios2/include/asm/io.h

@@ -50,7 +50,6 @@ static inline void iounmap(void __iomem *addr)
 
 /* Pages to physical address... */
 #define page_to_phys(page)	virt_to_phys(page_to_virt(page))
-#define page_to_bus(page)	page_to_virt(page)
 
 /* Macros used for converting between virtual and physical mappings. */
 #define phys_to_virt(vaddr)	\

arch/nios2/include/asm/page.h

@@ -84,7 +84,7 @@ extern struct page *mem_map;
 	((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET))
 
 #define page_to_virt(page)	\
-	((((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET)
+	((void *)(((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET)
 
 # define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 # define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET &&	\

arch/nios2/include/asm/pgtable.h

@@ -209,7 +209,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
-	unsigned long paddr = page_to_virt(pte_page(pteval));
+	unsigned long paddr = (unsigned long)page_to_virt(pte_page(pteval));
 
 	flush_dcache_range(paddr, paddr + PAGE_SIZE);
 	set_pte(ptep, pteval);

arch/openrisc/include/asm/page.h

@@ -81,8 +81,6 @@ typedef struct page *pgtable_t;
 
 #define virt_to_page(addr) \
 	(mem_map + (((unsigned long)(addr)-PAGE_OFFSET) >> PAGE_SHIFT))
-#define page_to_virt(page) \
-	((((page) - mem_map) << PAGE_SHIFT) + PAGE_OFFSET)
 
 #define page_to_phys(page)      ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
 

drivers/firmware/efi/arm-init.c

@@ -178,6 +178,14 @@ static __init void reserve_regions(void)
 	if (efi_enabled(EFI_DBG))
 		pr_info("Processing EFI memory map:\n");
 
+	/*
+	 * Discard memblocks discovered so far: if there are any at this
+	 * point, they originate from memory nodes in the DT, and UEFI
+	 * uses its own memory map instead.
+	 */
+	memblock_dump_all();
+	memblock_remove(0, (phys_addr_t)ULLONG_MAX);
+
 	for_each_efi_memory_desc(md) {
 		paddr = md->phys_addr;
 		npages = md->num_pages;

drivers/firmware/efi/libstub/arm64-stub.c

@@ -80,16 +80,25 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table_arg,
 	kernel_memsize = kernel_size + (_end - _edata);
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
+		/*
+		 * If CONFIG_DEBUG_ALIGN_RODATA is not set, produce a
+		 * displacement in the interval [0, MIN_KIMG_ALIGN) that
+		 * is a multiple of the minimal segment alignment (SZ_64K)
+		 */
+		u32 mask = (MIN_KIMG_ALIGN - 1) & ~(SZ_64K - 1);
+		u32 offset = !IS_ENABLED(CONFIG_DEBUG_ALIGN_RODATA) ?
+			     (phys_seed >> 32) & mask : TEXT_OFFSET;
+
 		/*
 		 * If KASLR is enabled, and we have some randomness available,
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
-		*reserve_size = kernel_memsize + TEXT_OFFSET;
+		*reserve_size = kernel_memsize + offset;
 		status = efi_random_alloc(sys_table_arg, *reserve_size,
 					  MIN_KIMG_ALIGN, reserve_addr,
-					  phys_seed);
+					  (u32)phys_seed);
 
-		*image_addr = *reserve_addr + TEXT_OFFSET;
+		*image_addr = *reserve_addr + offset;
 	} else {
 		/*
 		 * Else, try a straight allocation at the preferred offset.

drivers/firmware/efi/libstub/fdt.c

@@ -24,7 +24,7 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 			unsigned long map_size, unsigned long desc_size,
 			u32 desc_ver)
 {
-	int node, prev, num_rsv;
+	int node, num_rsv;
 	int status;
 	u32 fdt_val32;
 	u64 fdt_val64;
@@ -53,28 +53,6 @@ efi_status_t update_fdt(efi_system_table_t *sys_table, void *orig_fdt,
 	if (status != 0)
 		goto fdt_set_fail;
 
-	/*
-	 * Delete any memory nodes present. We must delete nodes which
-	 * early_init_dt_scan_memory may try to use.
-	 */
-	prev = 0;
-	for (;;) {
-		const char *type;
-		int len;
-
-		node = fdt_next_node(fdt, prev, NULL);
-		if (node < 0)
-			break;
-
-		type = fdt_getprop(fdt, node, "device_type", &len);
-		if (type && strncmp(type, "memory", len) == 0) {
-			fdt_del_node(fdt, node);
-			continue;
-		}
-
-		prev = node;
-	}
-
 	/*
 	 * Delete all memory reserve map entries. When booting via UEFI,
 	 * kernel will use the UEFI memory map to find reserved regions.

drivers/irqchip/irq-gic.c

@@ -55,7 +55,7 @@
 
 static void gic_check_cpu_features(void)
 {
-	WARN_TAINT_ONCE(cpus_have_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
+	WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_SYSREG_GIC_CPUIF),
 			TAINT_CPU_OUT_OF_SPEC,
 			"GICv3 system registers enabled, broken firmware!\n");
 }
@@ -490,6 +490,7 @@ static void gic_cpu_init(struct gic_chip_data *gic)
 		 * Get what the GIC says our CPU mask is.
 		 */
 		BUG_ON(cpu >= NR_GIC_CPU_IF);
+		gic_check_cpu_features();
 		cpu_mask = gic_get_cpumask(gic);
 		gic_cpu_map[cpu] = cpu_mask;
 
@@ -1021,8 +1022,6 @@ static void __init __gic_init_bases(unsigned int gic_nr, int irq_start,
 
 	BUG_ON(gic_nr >= CONFIG_ARM_GIC_MAX_NR);
 
-	gic_check_cpu_features();
-
 	gic = &gic_data[gic_nr];
 
 	/* Initialize irq_chip */

drivers/of/Kconfig

@@ -112,4 +112,7 @@ config OF_OVERLAY
 	  While this option is selected automatically when needed, you can
 	  enable it manually to improve device tree unit test coverage.
 
+config OF_NUMA
+	bool
+
 endif # OF

drivers/of/Makefile

@@ -14,5 +14,6 @@ obj-$(CONFIG_OF_MTD)	+= of_mtd.o
 obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
 obj-$(CONFIG_OF_RESOLVE)  += resolver.o
 obj-$(CONFIG_OF_OVERLAY) += overlay.o
+obj-$(CONFIG_OF_NUMA) += of_numa.o
 
 obj-$(CONFIG_OF_UNITTEST) += unittest-data/

drivers/of/of_numa.c

@@ -0,0 +1,211 @@
+/*
+ * OF NUMA Parsing support.
+ *
+ * Copyright (C) 2015 - 2016 Cavium Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/nodemask.h>
+
+#include <asm/numa.h>
+
+/* define default numa node to 0 */
+#define DEFAULT_NODE 0
+
+/*
+ * Even though we connect cpus to numa domains later in SMP
+ * init, we need to know the node ids now for all cpus.
+*/
+static void __init of_numa_parse_cpu_nodes(void)
+{
+	u32 nid;
+	int r;
+	struct device_node *cpus;
+	struct device_node *np = NULL;
+
+	cpus = of_find_node_by_path("/cpus");
+	if (!cpus)
+		return;
+
+	for_each_child_of_node(cpus, np) {
+		/* Skip things that are not CPUs */
+		if (of_node_cmp(np->type, "cpu") != 0)
+			continue;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		if (r)
+			continue;
+
+		pr_debug("NUMA: CPU on %u\n", nid);
+		if (nid >= MAX_NUMNODES)
+			pr_warn("NUMA: Node id %u exceeds maximum value\n",
+				nid);
+		else
+			node_set(nid, numa_nodes_parsed);
+	}
+}
+
+static int __init of_numa_parse_memory_nodes(void)
+{
+	struct device_node *np = NULL;
+	struct resource rsrc;
+	u32 nid;
+	int r = 0;
+
+	for (;;) {
+		np = of_find_node_by_type(np, "memory");
+		if (!np)
+			break;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		if (r == -EINVAL)
+			/*
+			 * property doesn't exist if -EINVAL, continue
+			 * looking for more memory nodes with
+			 * "numa-node-id" property
+			 */
+			continue;
+		else if (r)
+			/* some other error */
+			break;
+
+		r = of_address_to_resource(np, 0, &rsrc);
+		if (r) {
+			pr_err("NUMA: bad reg property in memory node\n");
+			break;
+		}
+
+		pr_debug("NUMA:  base = %llx len = %llx, node = %u\n",
+			 rsrc.start, rsrc.end - rsrc.start + 1, nid);
+
+		r = numa_add_memblk(nid, rsrc.start,
+				    rsrc.end - rsrc.start + 1);
+		if (r)
+			break;
+	}
+	of_node_put(np);
+
+	return r;
+}
+
+static int __init of_numa_parse_distance_map_v1(struct device_node *map)
+{
+	const __be32 *matrix;
+	int entry_count;
+	int i;
+
+	pr_info("NUMA: parsing numa-distance-map-v1\n");
+
+	matrix = of_get_property(map, "distance-matrix", NULL);
+	if (!matrix) {
+		pr_err("NUMA: No distance-matrix property in distance-map\n");
+		return -EINVAL;
+	}
+
+	entry_count = of_property_count_u32_elems(map, "distance-matrix");
+	if (entry_count <= 0) {
+		pr_err("NUMA: Invalid distance-matrix\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i + 2 < entry_count; i += 3) {
+		u32 nodea, nodeb, distance;
+
+		nodea = of_read_number(matrix, 1);
+		matrix++;
+		nodeb = of_read_number(matrix, 1);
+		matrix++;
+		distance = of_read_number(matrix, 1);
+		matrix++;
+
+		numa_set_distance(nodea, nodeb, distance);
+		pr_debug("NUMA:  distance[node%d -> node%d] = %d\n",
+			 nodea, nodeb, distance);
+
+		/* Set default distance of node B->A same as A->B */
+		if (nodeb > nodea)
+			numa_set_distance(nodeb, nodea, distance);
+	}
+
+	return 0;
+}
+
+static int __init of_numa_parse_distance_map(void)
+{
+	int ret = 0;
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL,
+				     "numa-distance-map-v1");
+	if (np)
+		ret = of_numa_parse_distance_map_v1(np);
+
+	of_node_put(np);
+	return ret;
+}
+
+int of_node_to_nid(struct device_node *device)
+{
+	struct device_node *np;
+	u32 nid;
+	int r = -ENODATA;
+
+	np = of_node_get(device);
+
+	while (np) {
+		struct device_node *parent;
+
+		r = of_property_read_u32(np, "numa-node-id", &nid);
+		/*
+		 * -EINVAL indicates the property was not found, and
+		 *  we walk up the tree trying to find a parent with a
+		 *  "numa-node-id".  Any other type of error indicates
+		 *  a bad device tree and we give up.
+		 */
+		if (r != -EINVAL)
+			break;
+
+		parent = of_get_parent(np);
+		of_node_put(np);
+		np = parent;
+	}
+	if (np && r)
+		pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+			np->name);
+	of_node_put(np);
+
+	if (!r) {
+		if (nid >= MAX_NUMNODES)
+			pr_warn("NUMA: Node id %u exceeds maximum value\n",
+				nid);
+		else
+			return nid;
+	}
+
+	return NUMA_NO_NODE;
+}
+EXPORT_SYMBOL(of_node_to_nid);
+
+int __init of_numa_init(void)
+{
+	int r;
+
+	of_numa_parse_cpu_nodes();
+	r = of_numa_parse_memory_nodes();
+	if (r)
+		return r;
+	return of_numa_parse_distance_map();
+}

include/linux/mm.h

@@ -72,6 +72,10 @@ extern int mmap_rnd_compat_bits __read_mostly;
 #define __pa_symbol(x)  __pa(RELOC_HIDE((unsigned long)(x), 0))
 #endif
 
+#ifndef page_to_virt
+#define page_to_virt(x)	__va(PFN_PHYS(page_to_pfn(x)))
+#endif
+
 /*
  * To prevent common memory management code establishing
  * a zero page mapping on a read fault.
@@ -957,7 +961,7 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
 
 static __always_inline void *lowmem_page_address(const struct page *page)
 {
-	return __va(PFN_PHYS(page_to_pfn(page)));
+	return page_to_virt(page);
 }
 
 #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)

include/linux/of.h

@@ -685,6 +685,15 @@ static inline int of_node_to_nid(struct device_node *device)
 }
 #endif
 
+#ifdef CONFIG_OF_NUMA
+extern int of_numa_init(void);
+#else
+static inline int of_numa_init(void)
+{
+	return -ENOSYS;
+}
+#endif
+
 static inline struct device_node *of_find_matching_node(
 	struct device_node *from,
 	const struct of_device_id *matches)

kernel/power/swap.c

@@ -36,6 +36,14 @@
 
 #define HIBERNATE_SIG	"S1SUSPEND"
 
+/*
+ * When reading an {un,}compressed image, we may restore pages in place,
+ * in which case some architectures need these pages cleaning before they
+ * can be executed. We don't know which pages these may be, so clean the lot.
+ */
+static bool clean_pages_on_read;
+static bool clean_pages_on_decompress;
+
 /*
  *	The swap map is a data structure used for keeping track of each page
  *	written to a swap partition.  It consists of many swap_map_page
@@ -241,6 +249,9 @@ static void hib_end_io(struct bio *bio)
 
 	if (bio_data_dir(bio) == WRITE)
 		put_page(page);
+	else if (clean_pages_on_read)
+		flush_icache_range((unsigned long)page_address(page),
+				   (unsigned long)page_address(page) + PAGE_SIZE);
 
 	if (bio->bi_error && !hb->error)
 		hb->error = bio->bi_error;
@@ -1049,6 +1060,7 @@ static int load_image(struct swap_map_handle *handle,
 
 	hib_init_batch(&hb);
 
+	clean_pages_on_read = true;
 	printk(KERN_INFO "PM: Loading image data pages (%u pages)...\n",
 		nr_to_read);
 	m = nr_to_read / 10;
@@ -1124,6 +1136,10 @@ static int lzo_decompress_threadfn(void *data)
 		d->unc_len = LZO_UNC_SIZE;
 		d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len,
 		                               d->unc, &d->unc_len);
+		if (clean_pages_on_decompress)
+			flush_icache_range((unsigned long)d->unc,
+					   (unsigned long)d->unc + d->unc_len);
+
 		atomic_set(&d->stop, 1);
 		wake_up(&d->done);
 	}
@@ -1189,6 +1205,8 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	}
 	memset(crc, 0, offsetof(struct crc_data, go));
 
+	clean_pages_on_decompress = true;
+
 	/*
 	 * Start the decompression threads.
 	 */