Linux-libre 4.5-gnu

27 files changed, 713 insertions, 640 deletions

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 474691f8b..83cd7e68e 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,10 +14,10 @@ CFLAGS_REMOVE_return_address.o = -pg
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\
 			   sys.o stacktrace.o time.o traps.o io.o vdso.o	\
-			   hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o	\
+			   hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
-			   smp.o smp_spin_table.o topology.o
+			   smp.o smp_spin_table.o topology.o smccc-call.o
 
 extra-$(CONFIG_EFI)			:= efi-entry.o
 
@@ -41,6 +41,7 @@ arm64-obj-$(CONFIG_EFI)			+= efi.o efi-entry.stub.o
 arm64-obj-$(CONFIG_PCI)			+= pci.o
 arm64-obj-$(CONFIG_ARMV8_DEPRECATED)	+= armv8_deprecated.o
 arm64-obj-$(CONFIG_ACPI)		+= acpi.o
+arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 
 obj-y					+= $(arm64-obj-y) vdso/
 obj-m					+= $(arm64-obj-m)
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index ab9db0e98..d2ee1b21a 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -158,9 +158,3 @@ void apply_alternatives(void *start, size_t length)
 
 	__apply_alternatives(&region);
 }
-
-void free_alternatives_memory(void)
-{
-	free_reserved_area(__alt_instructions, __alt_instructions_end,
-			   0, "alternatives");
-}
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 3b6d8cc9d..678f30b05 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -26,6 +26,7 @@
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
+#include <linux/arm-smccc.h>
 
 #include <asm/checksum.h>
 
@@ -68,3 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit);
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
+
+	/* arm-smccc */
+EXPORT_SYMBOL(arm_smccc_smc);
+EXPORT_SYMBOL(arm_smccc_hvc);
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 937f5e58a..3e0120791 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -62,7 +62,7 @@ struct insn_emulation {
 };
 
 static LIST_HEAD(insn_emulation);
-static int nr_insn_emulated;
+static int nr_insn_emulated __initdata;
 static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
 
 static void register_emulation_hooks(struct insn_emulation_ops *ops)
@@ -173,7 +173,7 @@ static int update_insn_emulation_mode(struct insn_emulation *insn,
 	return ret;
 }
 
-static void register_insn_emulation(struct insn_emulation_ops *ops)
+static void __init register_insn_emulation(struct insn_emulation_ops *ops)
 {
 	unsigned long flags;
 	struct insn_emulation *insn;
@@ -237,7 +237,7 @@ static struct ctl_table ctl_abi[] = {
 	{ }
 };
 
-static void register_insn_emulation_sysctl(struct ctl_table *table)
+static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 {
 	unsigned long flags;
 	int i = 0;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 25de8b244..fffa4ac6c 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -28,6 +28,7 @@
 #include <asm/suspend.h>
 #include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 
 int main(void)
 {
@@ -108,49 +109,11 @@ int main(void)
   DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));
   DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_regs, regs));
   DEFINE(CPU_FP_REGS,		offsetof(struct kvm_regs, fp_regs));
-  DEFINE(CPU_SP_EL1,		offsetof(struct kvm_regs, sp_el1));
-  DEFINE(CPU_ELR_EL1,		offsetof(struct kvm_regs, elr_el1));
-  DEFINE(CPU_SPSR,		offsetof(struct kvm_regs, spsr));
-  DEFINE(CPU_SYSREGS,		offsetof(struct kvm_cpu_context, sys_regs));
+  DEFINE(VCPU_FPEXC32_EL2,	offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
   DEFINE(VCPU_ESR_EL2,		offsetof(struct kvm_vcpu, arch.fault.esr_el2));
   DEFINE(VCPU_FAR_EL2,		offsetof(struct kvm_vcpu, arch.fault.far_el2));
   DEFINE(VCPU_HPFAR_EL2,	offsetof(struct kvm_vcpu, arch.fault.hpfar_el2));
-  DEFINE(VCPU_DEBUG_FLAGS,	offsetof(struct kvm_vcpu, arch.debug_flags));
-  DEFINE(VCPU_DEBUG_PTR,	offsetof(struct kvm_vcpu, arch.debug_ptr));
-  DEFINE(DEBUG_BCR, 		offsetof(struct kvm_guest_debug_arch, dbg_bcr));
-  DEFINE(DEBUG_BVR, 		offsetof(struct kvm_guest_debug_arch, dbg_bvr));
-  DEFINE(DEBUG_WCR, 		offsetof(struct kvm_guest_debug_arch, dbg_wcr));
-  DEFINE(DEBUG_WVR, 		offsetof(struct kvm_guest_debug_arch, dbg_wvr));
-  DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
-  DEFINE(VCPU_MDCR_EL2,	offsetof(struct kvm_vcpu, arch.mdcr_el2));
-  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
   DEFINE(VCPU_HOST_CONTEXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(VCPU_HOST_DEBUG_STATE, offsetof(struct kvm_vcpu, arch.host_debug_state));
-  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
-  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
-  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
-  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
-  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
-  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
-  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
-  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
-  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
-  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
-  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
-  DEFINE(VGIC_V3_CPU_SRE,	offsetof(struct vgic_cpu, vgic_v3.vgic_sre));
-  DEFINE(VGIC_V3_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_hcr));
-  DEFINE(VGIC_V3_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr));
-  DEFINE(VGIC_V3_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_misr));
-  DEFINE(VGIC_V3_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v3.vgic_eisr));
-  DEFINE(VGIC_V3_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr));
-  DEFINE(VGIC_V3_CPU_AP0R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r));
-  DEFINE(VGIC_V3_CPU_AP1R,	offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r));
-  DEFINE(VGIC_V3_CPU_LR,	offsetof(struct vgic_cpu, vgic_v3.vgic_lr));
-  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
-  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
 #endif
 #ifdef CONFIG_CPU_PM
   DEFINE(CPU_SUSPEND_SZ,	sizeof(struct cpu_suspend_ctx));
@@ -161,5 +124,7 @@ int main(void)
   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));
 #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));
   return 0;
 }
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0669c6328..5c90aa490 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -684,7 +684,7 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = {
 	{},
 };
 
-static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
+static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
@@ -729,7 +729,7 @@ static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *
 	return rc;
 }
 
-static void setup_cpu_hwcaps(void)
+static void __init setup_cpu_hwcaps(void)
 {
 	int i;
 	const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps;
@@ -758,7 +758,8 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
  * Run through the enabled capabilities and enable() it on all active
  * CPUs
  */
-static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
+static void __init
+enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 {
 	int i;
 
@@ -897,7 +898,7 @@ static inline void set_sys_caps_initialised(void)
 
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-static void setup_feature_capabilities(void)
+static void __init setup_feature_capabilities(void)
 {
 	update_cpu_capabilities(arm64_features, "detected feature:");
 	enable_cpu_capabilities(arm64_features);
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 8aee3aeec..c536c9e30 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -226,11 +226,28 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 	return retval;
 }
 
+static void send_user_sigtrap(int si_code)
+{
+	struct pt_regs *regs = current_pt_regs();
+	siginfo_t info = {
+		.si_signo	= SIGTRAP,
+		.si_errno	= 0,
+		.si_code	= si_code,
+		.si_addr	= (void __user *)instruction_pointer(regs),
+	};
+
+	if (WARN_ON(!user_mode(regs)))
+		return;
+
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
+	force_sig_info(SIGTRAP, &info, current);
+}
+
 static int single_step_handler(unsigned long addr, unsigned int esr,
 			       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	/*
 	 * If we are stepping a pending breakpoint, call the hw_breakpoint
 	 * handler first.
@@ -239,11 +256,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		return 0;
 
 	if (user_mode(regs)) {
-		info.si_signo = SIGTRAP;
-		info.si_errno = 0;
-		info.si_code  = TRAP_HWBKPT;
-		info.si_addr  = (void __user *)instruction_pointer(regs);
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_HWBKPT);
 
 		/*
 		 * ptrace will disable single step unless explicitly
@@ -307,17 +320,8 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 static int brk_handler(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	siginfo_t info;
-
 	if (user_mode(regs)) {
-		info = (siginfo_t) {
-			.si_signo = SIGTRAP,
-			.si_errno = 0,
-			.si_code  = TRAP_BRKPT,
-			.si_addr  = (void __user *)instruction_pointer(regs),
-		};
-
-		force_sig_info(SIGTRAP, &info, current);
+		send_user_sigtrap(TRAP_BRKPT);
 	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
 		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
@@ -328,7 +332,6 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 
 int aarch32_break_handler(struct pt_regs *regs)
 {
-	siginfo_t info;
 	u32 arm_instr;
 	u16 thumb_instr;
 	bool bp = false;
@@ -359,14 +362,7 @@ int aarch32_break_handler(struct pt_regs *regs)
 	if (!bp)
 		return -EFAULT;
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = pc,
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
+	send_user_sigtrap(TRAP_BRKPT);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 4eeb17198..b6abc852f 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -11,317 +11,34 @@
  *
  */
 
-#include <linux/atomic.h>
 #include <linux/dmi.h>
 #include <linux/efi.h>
-#include <linux/export.h>
-#include <linux/memblock.h>
-#include <linux/mm_types.h>
-#include <linux/bootmem.h>
-#include <linux/of.h>
-#include <linux/of_fdt.h>
-#include <linux/preempt.h>
-#include <linux/rbtree.h>
-#include <linux/rwsem.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
+#include <linux/init.h>
 
-#include <asm/cacheflush.h>
 #include <asm/efi.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/mmu.h>
-#include <asm/pgtable.h>
 
-struct efi_memory_map memmap;
-
-static u64 efi_system_table;
-
-static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss;
-
-static struct mm_struct efi_mm = {
-	.mm_rb			= RB_ROOT,
-	.pgd			= efi_pgd,
-	.mm_users		= ATOMIC_INIT(2),
-	.mm_count		= ATOMIC_INIT(1),
-	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
-	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
-	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
-};
-
-static int __init is_normal_ram(efi_memory_desc_t *md)
-{
-	if (md->attribute & EFI_MEMORY_WB)
-		return 1;
-	return 0;
-}
-
-/*
- * Translate a EFI virtual address into a physical address: this is necessary,
- * as some data members of the EFI system table are virtually remapped after
- * SetVirtualAddressMap() has been called.
- */
-static phys_addr_t efi_to_phys(unsigned long addr)
+int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
-	efi_memory_desc_t *md;
-
-	for_each_efi_memory_desc(&memmap, md) {
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
-			continue;
-		if (md->virt_addr == 0)
-			/* no virtual mapping has been installed by the stub */
-			break;
-		if (md->virt_addr <= addr &&
-		    (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT))
-			return md->phys_addr + addr - md->virt_addr;
-	}
-	return addr;
-}
-
-static int __init uefi_init(void)
-{
-	efi_char16_t *c16;
-	void *config_tables;
-	u64 table_size;
-	char vendor[100] = "unknown";
-	int i, retval;
-
-	efi.systab = early_memremap(efi_system_table,
-				    sizeof(efi_system_table_t));
-	if (efi.systab == NULL) {
-		pr_warn("Unable to map EFI system table.\n");
-		return -ENOMEM;
-	}
-
-	set_bit(EFI_BOOT, &efi.flags);
-	set_bit(EFI_64BIT, &efi.flags);
+	pteval_t prot_val;
 
 	/*
-	 * Verify the EFI Table
+	 * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
+	 * executable, everything else can be mapped with the XN bits
+	 * set.
 	 */
-	if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) {
-		pr_err("System table signature incorrect\n");
-		retval = -EINVAL;
-		goto out;
-	}
-	if ((efi.systab->hdr.revision >> 16) < 2)
-		pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n",
-			efi.systab->hdr.revision >> 16,
-			efi.systab->hdr.revision & 0xffff);
-
-	/* Show what we know for posterity */
-	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor) * sizeof(efi_char16_t));
-	if (c16) {
-		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
-			vendor[i] = c16[i];
-		vendor[i] = '\0';
-		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
-	}
-
-	pr_info("EFI v%u.%.02u by %s\n",
-		efi.systab->hdr.revision >> 16,
-		efi.systab->hdr.revision & 0xffff, vendor);
-
-	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
-	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
-				       table_size);
-	if (config_tables == NULL) {
-		pr_warn("Unable to map EFI config table array.\n");
-		retval = -ENOMEM;
-		goto out;
-	}
-	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
-					 sizeof(efi_config_table_64_t), NULL);
-
-	early_memunmap(config_tables, table_size);
-out:
-	early_memunmap(efi.systab,  sizeof(efi_system_table_t));
-	return retval;
-}
-
-/*
- * Return true for RAM regions we want to permanently reserve.
- */
-static __init int is_reserve_region(efi_memory_desc_t *md)
-{
-	switch (md->type) {
-	case EFI_LOADER_CODE:
-	case EFI_LOADER_DATA:
-	case EFI_BOOT_SERVICES_CODE:
-	case EFI_BOOT_SERVICES_DATA:
-	case EFI_CONVENTIONAL_MEMORY:
-	case EFI_PERSISTENT_MEMORY:
-		return 0;
-	default:
-		break;
-	}
-	return is_normal_ram(md);
-}
-
-static __init void reserve_regions(void)
-{
-	efi_memory_desc_t *md;
-	u64 paddr, npages, size;
-
-	if (efi_enabled(EFI_DBG))
-		pr_info("Processing EFI memory map:\n");
-
-	for_each_efi_memory_desc(&memmap, md) {
-		paddr = md->phys_addr;
-		npages = md->num_pages;
-
-		if (efi_enabled(EFI_DBG)) {
-			char buf[64];
-
-			pr_info("  0x%012llx-0x%012llx %s",
-				paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1,
-				efi_md_typeattr_format(buf, sizeof(buf), md));
-		}
-
-		memrange_efi_to_native(&paddr, &npages);
-		size = npages << PAGE_SHIFT;
-
-		if (is_normal_ram(md))
-			early_init_dt_add_memory_arch(paddr, size);
-
-		if (is_reserve_region(md)) {
-			memblock_reserve(paddr, size);
-			if (efi_enabled(EFI_DBG))
-				pr_cont("*");
-		}
-
-		if (efi_enabled(EFI_DBG))
-			pr_cont("\n");
-	}
-
-	set_bit(EFI_MEMMAP, &efi.flags);
-}
-
-void __init efi_init(void)
-{
-	struct efi_fdt_params params;
-
-	/* Grab UEFI information placed in FDT by stub */
-	if (!efi_get_fdt_params(&params))
-		return;
-
-	efi_system_table = params.system_table;
-
-	memblock_reserve(params.mmap & PAGE_MASK,
-			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
-	memmap.phys_map = params.mmap;
-	memmap.map = early_memremap(params.mmap, params.mmap_size);
-	if (memmap.map == NULL) {
-		/*
-		* If we are booting via UEFI, the UEFI memory map is the only
-		* description of memory we have, so there is little point in
-		* proceeding if we cannot access it.
-		*/
-		panic("Unable to map EFI memory map.\n");
-	}
-	memmap.map_end = memmap.map + params.mmap_size;
-	memmap.desc_size = params.desc_size;
-	memmap.desc_version = params.desc_ver;
-
-	if (uefi_init() < 0)
-		return;
-
-	reserve_regions();
-	early_memunmap(memmap.map, params.mmap_size);
-}
-
-static bool __init efi_virtmap_init(void)
-{
-	efi_memory_desc_t *md;
-
-	init_new_context(NULL, &efi_mm);
-
-	for_each_efi_memory_desc(&memmap, md) {
-		pgprot_t prot;
-
-		if (!(md->attribute & EFI_MEMORY_RUNTIME))
-			continue;
-		if (md->virt_addr == 0)
-			return false;
-
-		pr_info("  EFI remap 0x%016llx => %p\n",
-			md->phys_addr, (void *)md->virt_addr);
-
-		/*
-		 * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be
-		 * executable, everything else can be mapped with the XN bits
-		 * set.
-		 */
-		if (!is_normal_ram(md))
-			prot = __pgprot(PROT_DEVICE_nGnRE);
-		else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
-			 !PAGE_ALIGNED(md->phys_addr))
-			prot = PAGE_KERNEL_EXEC;
-		else
-			prot = PAGE_KERNEL;
-
-		create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
-				   md->num_pages << EFI_PAGE_SHIFT, 
-				   __pgprot(pgprot_val(prot) | PTE_NG));
-	}
-	return true;
-}
-
-/*
- * Enable the UEFI Runtime Services if all prerequisites are in place, i.e.,
- * non-early mapping of the UEFI system table and virtual mappings for all
- * EFI_MEMORY_RUNTIME regions.
- */
-static int __init arm64_enable_runtime_services(void)
-{
-	u64 mapsize;
-
-	if (!efi_enabled(EFI_BOOT)) {
-		pr_info("EFI services will not be available.\n");
-		return 0;
-	}
-
-	if (efi_runtime_disabled()) {
-		pr_info("EFI runtime services will be disabled.\n");
-		return 0;
-	}
-
-	pr_info("Remapping and enabling EFI services.\n");
-
-	mapsize = memmap.map_end - memmap.map;
-	memmap.map = (__force void *)ioremap_cache(memmap.phys_map,
-						   mapsize);
-	if (!memmap.map) {
-		pr_err("Failed to remap EFI memory map\n");
-		return -ENOMEM;
-	}
-	memmap.map_end = memmap.map + mapsize;
-	efi.memmap = &memmap;
-
-	efi.systab = (__force void *)ioremap_cache(efi_system_table,
-						   sizeof(efi_system_table_t));
-	if (!efi.systab) {
-		pr_err("Failed to remap EFI System Table\n");
-		return -ENOMEM;
-	}
-	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
-
-	if (!efi_virtmap_init()) {
-		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-		return -ENOMEM;
-	}
-
-	/* Set up runtime services function pointers */
-	efi_native_runtime_setup();
-	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
-
-	efi.runtime_version = efi.systab->hdr.revision;
-
+	if ((md->attribute & EFI_MEMORY_WB) == 0)
+		prot_val = PROT_DEVICE_nGnRE;
+	else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+		 !PAGE_ALIGNED(md->phys_addr))
+		prot_val = pgprot_val(PAGE_KERNEL_EXEC);
+	else
+		prot_val = pgprot_val(PAGE_KERNEL);
+
+	create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
+			   md->num_pages << EFI_PAGE_SHIFT,
+			   __pgprot(prot_val | PTE_NG));
 	return 0;
 }
-early_initcall(arm64_enable_runtime_services);
 
 static int __init arm64_dmi_init(void)
 {
@@ -337,23 +54,6 @@ static int __init arm64_dmi_init(void)
 }
 core_initcall(arm64_dmi_init);
 
-static void efi_set_pgd(struct mm_struct *mm)
-{
-	switch_mm(NULL, mm, NULL);
-}
-
-void efi_virtmap_load(void)
-{
-	preempt_disable();
-	efi_set_pgd(&efi_mm);
-}
-
-void efi_virtmap_unload(void)
-{
-	efi_set_pgd(current->active_mm);
-	preempt_enable();
-}
-
 /*
  * UpdateCapsule() depends on the system being shutdown via
  * ResetSystem().
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7ed3d75f6..1f7f5a2b6 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -27,6 +27,7 @@
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
+#include <asm/irq.h>
 #include <asm/thread_info.h>
 #include <asm/unistd.h>
 
@@ -88,9 +89,12 @@
 
 	.if	\el == 0
 	mrs	x21, sp_el0
-	get_thread_info tsk			// Ensure MDSCR_EL1.SS is clear,
+	mov	tsk, sp
+	and	tsk, tsk, #~(THREAD_SIZE - 1)	// Ensure MDSCR_EL1.SS is clear,
 	ldr	x19, [tsk, #TI_FLAGS]		// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
+
+	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	.endif
@@ -108,6 +112,13 @@
 	.endif
 
 	/*
+	 * Set sp_el0 to current thread_info.
+	 */
+	.if	\el == 0
+	msr	sp_el0, tsk
+	.endif
+
+	/*
 	 * Registers that may be useful after this macro is invoked:
 	 *
 	 * x21 - aborted SP
@@ -164,8 +175,44 @@ alternative_endif
 	.endm
 
 	.macro	get_thread_info, rd
-	mov	\rd, sp
-	and	\rd, \rd, #~(THREAD_SIZE - 1)	// top of stack
+	mrs	\rd, sp_el0
+	.endm
+
+	.macro	irq_stack_entry
+	mov	x19, sp			// preserve the original sp
+
+	/*
+	 * Compare sp with the current thread_info, if the top
+	 * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and
+	 * should switch to the irq stack.
+	 */
+	and	x25, x19, #~(THREAD_SIZE - 1)
+	cmp	x25, tsk
+	b.ne	9998f
+
+	this_cpu_ptr irq_stack, x25, x26
+	mov	x26, #IRQ_STACK_START_SP
+	add	x26, x25, x26
+
+	/* switch to the irq stack */
+	mov	sp, x26
+
+	/*
+	 * Add a dummy stack frame, this non-standard format is fixed up
+	 * by unwind_frame()
+	 */
+	stp     x29, x19, [sp, #-16]!
+	mov	x29, sp
+
+9998:
+	.endm
+
+	/*
+	 * x19 should be preserved between irq_stack_entry and
+	 * irq_stack_exit.
+	 */
+	.macro	irq_stack_exit
+	mov	sp, x19
 	.endm
 
 /*
@@ -183,10 +230,11 @@ tsk	.req	x28		// current thread_info
  * Interrupt handling.
  */
 	.macro	irq_handler
-	adrp	x1, handle_arch_irq
-	ldr	x1, [x1, #:lo12:handle_arch_irq]
+	ldr_l	x1, handle_arch_irq
 	mov	x0, sp
+	irq_stack_entry
 	blr	x1
+	irq_stack_exit
 	.endm
 
 	.text
@@ -358,10 +406,10 @@ el1_irq:
 	bl	trace_hardirqs_off
 #endif
 
+	get_thread_info tsk
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
-	get_thread_info tsk
 	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
 	cbnz	w24, 1f				// preempt count != 0
 	ldr	x0, [tsk, #TI_FLAGS]		// get flags
@@ -599,6 +647,8 @@ ENTRY(cpu_switch_to)
 	ldp	x29, x9, [x8], #16
 	ldr	lr, [x8]
 	mov	sp, x9
+	and	x9, x9, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x9
 	ret
 ENDPROC(cpu_switch_to)
 
@@ -626,14 +676,14 @@ ret_fast_syscall_trace:
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
-	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
-	tst	x2, #PSR_MODE_MASK		// user mode regs?
-	b.ne	no_work_pending			// returning to kernel
 	enable_irq				// enable interrupts for do_notify_resume()
 	bl	do_notify_resume
 	b	ret_to_user
 work_resched:
+#ifdef CONFIG_TRACE_IRQFLAGS
+	bl	trace_hardirqs_off		// the IRQs are off here, inform the tracing code
+#endif
 	bl	schedule
 
 /*
@@ -645,7 +695,6 @@ ret_to_user:
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
-no_work_pending:
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 4c46c54a3..acc1afd5c 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -289,7 +289,7 @@ static struct notifier_block fpsimd_cpu_pm_notifier_block = {
 	.notifier_call = fpsimd_cpu_pm_notifier,
 };
 
-static void fpsimd_pm_init(void)
+static void __init fpsimd_pm_init(void)
 {
 	cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block);
 }
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index c851be795..ebecf9aa3 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -29,12 +29,11 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new,
 
 	/*
 	 * Note:
-	 * Due to modules and __init, code can disappear and change,
-	 * we need to protect against faulting as well as code changing.
-	 * We do this by aarch64_insn_*() which use the probe_kernel_*().
-	 *
-	 * No lock is held here because all the modifications are run
-	 * through stop_machine().
+	 * We are paranoid about modifying text, as if a bug were to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with aarch64_insn_*() which uses
+	 * probe_kernel_*(), and make sure what we read is what we expected it
+	 * to be before modifying it.
 	 */
 	if (validate) {
 		if (aarch64_insn_read((void *)pc, &replaced))
@@ -93,6 +92,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 	return ftrace_modify_code(pc, old, new, true);
 }
 
+void arch_ftrace_update_code(int command)
+{
+	ftrace_modify_all_code(command);
+}
+
 int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
@@ -125,23 +129,20 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	 * on other archs. It's unlikely on AArch64.
 	 */
 	old = *parent;
-	*parent = return_hooker;
 
 	trace.func = self_addr;
 	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		*parent = old;
+	if (!ftrace_graph_entry(&trace))
 		return;
-	}
 
 	err = ftrace_push_return_trace(old, self_addr, &trace.depth,
 				       frame_pointer);
-	if (err == -EBUSY) {
-		*parent = old;
+	if (err == -EBUSY)
 		return;
-	}
+	else
+		*parent = return_hooker;
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b68525792..917d98108 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -415,15 +415,17 @@ ENDPROC(__create_page_tables)
  */
 	.set	initial_sp, init_thread_union + THREAD_START_SP
 __mmap_switched:
-	adr_l	x6, __bss_start
-	adr_l	x7, __bss_stop
-
-1:	cmp	x6, x7
-	b.hs	2f
-	str	xzr, [x6], #8			// Clear BSS
-	b	1b
-2:
+	// Clear BSS
+	adr_l	x0, __bss_start
+	mov	x1, xzr
+	adr_l	x2, __bss_stop
+	sub	x2, x2, x0
+	bl	__pi_memset
+
 	adr_l	sp, initial_sp, x4
+	mov	x4, sp
+	and	x4, x4, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x4			// Save thread_info
 	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
 	str_l	x24, memstart_addr, x6		// Save PHYS_OFFSET
 	mov	x29, #0
@@ -611,6 +613,8 @@ ENDPROC(secondary_startup)
 ENTRY(__secondary_switched)
 	ldr	x0, [x21]			// get secondary_data.stack
 	mov	sp, x0
+	and	x0, x0, #~(THREAD_SIZE - 1)
+	msr	sp_el0, x0			// save thread_info
 	mov	x29, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index bc2abb8b1..352f7abd9 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -65,6 +65,16 @@
 #ifdef CONFIG_EFI
 
 /*
+ * Prevent the symbol aliases below from being emitted into the kallsyms
+ * table, by forcing them to be absolute symbols (which are conveniently
+ * ignored by scripts/kallsyms) rather than section relative symbols.
+ * The distinction is only relevant for partial linking, and only for symbols
+ * that are defined within a section declaration (which is not the case for
+ * the definitions below) so the resulting values will be identical.
+ */
+#define KALLSYMS_HIDE(sym)	ABSOLUTE(sym)
+
+/*
  * The EFI stub has its own symbol namespace prefixed by __efistub_, to
  * isolate it from the kernel proper. The following symbols are legally
  * accessed by the stub, so provide some aliases to make them accessible.
@@ -73,25 +83,26 @@
  * linked at. The routines below are all implemented in assembler in a
  * position independent manner
  */
-__efistub_memcmp		= __pi_memcmp;
-__efistub_memchr		= __pi_memchr;
-__efistub_memcpy		= __pi_memcpy;
-__efistub_memmove		= __pi_memmove;
-__efistub_memset		= __pi_memset;
-__efistub_strlen		= __pi_strlen;
-__efistub_strcmp		= __pi_strcmp;
-__efistub_strncmp		= __pi_strncmp;
-__efistub___flush_dcache_area	= __pi___flush_dcache_area;
+__efistub_memcmp		= KALLSYMS_HIDE(__pi_memcmp);
+__efistub_memchr		= KALLSYMS_HIDE(__pi_memchr);
+__efistub_memcpy		= KALLSYMS_HIDE(__pi_memcpy);
+__efistub_memmove		= KALLSYMS_HIDE(__pi_memmove);
+__efistub_memset		= KALLSYMS_HIDE(__pi_memset);
+__efistub_strlen		= KALLSYMS_HIDE(__pi_strlen);
+__efistub_strnlen		= KALLSYMS_HIDE(__pi_strnlen);
+__efistub_strcmp		= KALLSYMS_HIDE(__pi_strcmp);
+__efistub_strncmp		= KALLSYMS_HIDE(__pi_strncmp);
+__efistub___flush_dcache_area	= KALLSYMS_HIDE(__pi___flush_dcache_area);
 
 #ifdef CONFIG_KASAN
-__efistub___memcpy		= __pi_memcpy;
-__efistub___memmove		= __pi_memmove;
-__efistub___memset		= __pi_memset;
+__efistub___memcpy		= KALLSYMS_HIDE(__pi_memcpy);
+__efistub___memmove		= KALLSYMS_HIDE(__pi_memmove);
+__efistub___memset		= KALLSYMS_HIDE(__pi_memset);
 #endif
 
-__efistub__text			= _text;
-__efistub__end			= _end;
-__efistub__edata		= _edata;
+__efistub__text			= KALLSYMS_HIDE(_text);
+__efistub__end			= KALLSYMS_HIDE(_end);
+__efistub__edata		= KALLSYMS_HIDE(_edata);
 
 #endif
 
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index c08b9ad6f..737145516 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -2,7 +2,7 @@
  * Copyright (C) 2013 Huawei Ltd.
  * Author: Jiang Liu <liuj97@gmail.com>
  *
- * Copyright (C) 2014 Zi Shen Lim <zlim.lnx@gmail.com>
+ * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.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
@@ -363,6 +363,9 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 	u32 immlo, immhi, mask;
 	int shift;
 
+	if (insn == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
 	switch (type) {
 	case AARCH64_INSN_IMM_ADR:
 		shift = 0;
@@ -377,7 +380,7 @@ u32 __kprobes aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
 		if (aarch64_get_imm_shift_mask(type, &mask, &shift) < 0) {
 			pr_err("aarch64_insn_encode_immediate: unknown immediate encoding %d\n",
 			       type);
-			return 0;
+			return AARCH64_BREAK_FAULT;
 		}
 	}
 
@@ -394,9 +397,12 @@ static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
 {
 	int shift;
 
+	if (insn == AARCH64_BREAK_FAULT)
+		return AARCH64_BREAK_FAULT;
+
 	if (reg < AARCH64_INSN_REG_0 || reg > AARCH64_INSN_REG_SP) {
 		pr_err("%s: unknown register encoding %d\n", __func__, reg);
-		return 0;
+		return AARCH64_BREAK_FAULT;
 	}
 
 	switch (type) {
@@ -417,7 +423,7 @@ static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
 	default:
 		pr_err("%s: unknown register type encoding %d\n", __func__,
 		       type);
-		return 0;
+		return AARCH64_BREAK_FAULT;
 	}
 
 	insn &= ~(GENMASK(4, 0) << shift);
@@ -446,7 +452,7 @@ static u32 aarch64_insn_encode_ldst_size(enum aarch64_insn_size_type type,
 		break;
 	default:
 		pr_err("%s: unknown size encoding %d\n", __func__, type);
-		return 0;
+		return AARCH64_BREAK_FAULT;
 	}
 
 	insn &= ~GENMASK(31, 30);
@@ -460,14 +466,17 @@ static inline long branch_imm_common(unsigned long pc, unsigned long addr,
 {
 	long offset;
 
-	/*
-	 * PC: A 64-bit Program Counter holding the address of the current
-	 * instruction. A64 instructions must be word-aligned.
-	 */
-	BUG_ON((pc & 0x3) || (addr & 0x3));
+	if ((pc & 0x3) || (addr & 0x3)) {
+		pr_err("%s: A64 instructions must be word aligned\n", __func__);
+		return range;
+	}
 
 	offset = ((long)addr - (long)pc);
-	BUG_ON(offset < -range || offset >= range);
+
+	if (offset < -range || offset >= range) {
+		pr_err("%s: offset out of range\n", __func__);
+		return range;
+	}
 
 	return offset;
 }
@@ -484,6 +493,8 @@ u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 	 * texts are within +/-128M.
 	 */
 	offset = branch_imm_common(pc, addr, SZ_128M);
+	if (offset >= SZ_128M)
+		return AARCH64_BREAK_FAULT;
 
 	switch (type) {
 	case AARCH64_INSN_BRANCH_LINK:
@@ -493,7 +504,7 @@ u32 __kprobes aarch64_insn_gen_branch_imm(unsigned long pc, unsigned long addr,
 		insn = aarch64_insn_get_b_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -510,6 +521,8 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
 	long offset;
 
 	offset = branch_imm_common(pc, addr, SZ_1M);
+	if (offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
 
 	switch (type) {
 	case AARCH64_INSN_BRANCH_COMP_ZERO:
@@ -519,7 +532,7 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
 		insn = aarch64_insn_get_cbnz_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -530,7 +543,7 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -550,7 +563,10 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 
 	insn = aarch64_insn_get_bcond_value();
 
-	BUG_ON(cond < AARCH64_INSN_COND_EQ || cond > AARCH64_INSN_COND_AL);
+	if (cond < AARCH64_INSN_COND_EQ || cond > AARCH64_INSN_COND_AL) {
+		pr_err("%s: unknown condition encoding %d\n", __func__, cond);
+		return AARCH64_BREAK_FAULT;
+	}
 	insn |= cond;
 
 	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn,
@@ -583,7 +599,7 @@ u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
 		insn = aarch64_insn_get_ret_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown branch encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -606,7 +622,7 @@ u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
 		insn = aarch64_insn_get_str_reg_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown load/store encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -645,26 +661,30 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
 		insn = aarch64_insn_get_stp_post_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown load/store encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		/* offset must be multiples of 4 in the range [-256, 252] */
-		BUG_ON(offset & 0x3);
-		BUG_ON(offset < -256 || offset > 252);
+		if ((offset & 0x3) || (offset < -256) || (offset > 252)) {
+			pr_err("%s: offset must be multiples of 4 in the range of [-256, 252] %d\n",
+			       __func__, offset);
+			return AARCH64_BREAK_FAULT;
+		}
 		shift = 2;
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
-		/* offset must be multiples of 8 in the range [-512, 504] */
-		BUG_ON(offset & 0x7);
-		BUG_ON(offset < -512 || offset > 504);
+		if ((offset & 0x7) || (offset < -512) || (offset > 504)) {
+			pr_err("%s: offset must be multiples of 8 in the range of [-512, 504] %d\n",
+			       __func__, offset);
+			return AARCH64_BREAK_FAULT;
+		}
 		shift = 3;
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -702,7 +722,7 @@ u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_subs_imm_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown add/sub encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -713,11 +733,14 @@ u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
-	BUG_ON(imm & ~(SZ_4K - 1));
+	if (imm & ~(SZ_4K - 1)) {
+		pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
+		return AARCH64_BREAK_FAULT;
+	}
 
 	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
 
@@ -746,7 +769,7 @@ u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_sbfm_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown bitfield encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -759,12 +782,18 @@ u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst,
 		mask = GENMASK(5, 0);
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
-	BUG_ON(immr & ~mask);
-	BUG_ON(imms & ~mask);
+	if (immr & ~mask) {
+		pr_err("%s: invalid immr encoding %d\n", __func__, immr);
+		return AARCH64_BREAK_FAULT;
+	}
+	if (imms & ~mask) {
+		pr_err("%s: invalid imms encoding %d\n", __func__, imms);
+		return AARCH64_BREAK_FAULT;
+	}
 
 	insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, dst);
 
@@ -793,23 +822,33 @@ u32 aarch64_insn_gen_movewide(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_movn_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown movewide encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
-	BUG_ON(imm & ~(SZ_64K - 1));
+	if (imm & ~(SZ_64K - 1)) {
+		pr_err("%s: invalid immediate encoding %d\n", __func__, imm);
+		return AARCH64_BREAK_FAULT;
+	}
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		BUG_ON(shift != 0 && shift != 16);
+		if (shift != 0 && shift != 16) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
 		insn |= AARCH64_INSN_SF_BIT;
-		BUG_ON(shift != 0 && shift != 16 && shift != 32 &&
-		       shift != 48);
+		if (shift != 0 && shift != 16 && shift != 32 && shift != 48) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -843,20 +882,28 @@ u32 aarch64_insn_gen_add_sub_shifted_reg(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_subs_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown add/sub encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		BUG_ON(shift & ~(SZ_32 - 1));
+		if (shift & ~(SZ_32 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
 		insn |= AARCH64_INSN_SF_BIT;
-		BUG_ON(shift & ~(SZ_64 - 1));
+		if (shift & ~(SZ_64 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -885,11 +932,15 @@ u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_rev32_value();
 		break;
 	case AARCH64_INSN_DATA1_REVERSE_64:
-		BUG_ON(variant != AARCH64_INSN_VARIANT_64BIT);
+		if (variant != AARCH64_INSN_VARIANT_64BIT) {
+			pr_err("%s: invalid variant for reverse64 %d\n",
+			       __func__, variant);
+			return AARCH64_BREAK_FAULT;
+		}
 		insn = aarch64_insn_get_rev64_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown data1 encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -900,7 +951,7 @@ u32 aarch64_insn_gen_data1(enum aarch64_insn_register dst,
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -937,7 +988,7 @@ u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_rorv_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown data2 encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -948,7 +999,7 @@ u32 aarch64_insn_gen_data2(enum aarch64_insn_register dst,
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -976,7 +1027,7 @@ u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_msub_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown data3 encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -987,7 +1038,7 @@ u32 aarch64_insn_gen_data3(enum aarch64_insn_register dst,
 		insn |= AARCH64_INSN_SF_BIT;
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
@@ -1037,20 +1088,28 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
 		insn = aarch64_insn_get_bics_value();
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown logical encoding %d\n", __func__, type);
 		return AARCH64_BREAK_FAULT;
 	}
 
 	switch (variant) {
 	case AARCH64_INSN_VARIANT_32BIT:
-		BUG_ON(shift & ~(SZ_32 - 1));
+		if (shift & ~(SZ_32 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	case AARCH64_INSN_VARIANT_64BIT:
 		insn |= AARCH64_INSN_SF_BIT;
-		BUG_ON(shift & ~(SZ_64 - 1));
+		if (shift & ~(SZ_64 - 1)) {
+			pr_err("%s: invalid shift encoding %d\n", __func__,
+			       shift);
+			return AARCH64_BREAK_FAULT;
+		}
 		break;
 	default:
-		BUG_ON(1);
+		pr_err("%s: unknown variant encoding %d\n", __func__, variant);
 		return AARCH64_BREAK_FAULT;
 	}
 
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 9f17ec071..2386b26c0 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -30,6 +30,9 @@
 
 unsigned long irq_err_count;
 
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16);
+
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	show_ipi_list(p, prec);
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index f4bc779e6..93e970231 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -30,9 +30,6 @@
 #include <asm/insn.h>
 #include <asm/sections.h>
 
-#define	AARCH64_INSN_IMM_MOVNZ		AARCH64_INSN_IMM_MAX
-#define	AARCH64_INSN_IMM_MOVK		AARCH64_INSN_IMM_16
-
 void *module_alloc(unsigned long size)
 {
 	void *p;
@@ -75,15 +72,18 @@ static u64 do_reloc(enum aarch64_reloc_op reloc_op, void *place, u64 val)
 
 static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len)
 {
-	u64 imm_mask = (1 << len) - 1;
 	s64 sval = do_reloc(op, place, val);
 
 	switch (len) {
 	case 16:
 		*(s16 *)place = sval;
+		if (sval < S16_MIN || sval > U16_MAX)
+			return -ERANGE;
 		break;
 	case 32:
 		*(s32 *)place = sval;
+		if (sval < S32_MIN || sval > U32_MAX)
+			return -ERANGE;
 		break;
 	case 64:
 		*(s64 *)place = sval;
@@ -92,34 +92,23 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len)
 		pr_err("Invalid length (%d) for data relocation\n", len);
 		return 0;
 	}
-
-	/*
-	 * Extract the upper value bits (including the sign bit) and
-	 * shift them to bit 0.
-	 */
-	sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1);
-
-	/*
-	 * Overflow has occurred if the value is not representable in
-	 * len bits (i.e the bottom len bits are not sign-extended and
-	 * the top bits are not all zero).
-	 */
-	if ((u64)(sval + 1) > 2)
-		return -ERANGE;
-
 	return 0;
 }
 
+enum aarch64_insn_movw_imm_type {
+	AARCH64_INSN_IMM_MOVNZ,
+	AARCH64_INSN_IMM_MOVKZ,
+};
+
 static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
-			   int lsb, enum aarch64_insn_imm_type imm_type)
+			   int lsb, enum aarch64_insn_movw_imm_type imm_type)
 {
-	u64 imm, limit = 0;
+	u64 imm;
 	s64 sval;
 	u32 insn = le32_to_cpu(*(u32 *)place);
 
 	sval = do_reloc(op, place, val);
-	sval >>= lsb;
-	imm = sval & 0xffff;
+	imm = sval >> lsb;
 
 	if (imm_type == AARCH64_INSN_IMM_MOVNZ) {
 		/*
@@ -128,7 +117,7 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 		 * immediate is less than zero.
 		 */
 		insn &= ~(3 << 29);
-		if ((s64)imm >= 0) {
+		if (sval >= 0) {
 			/* >=0: Set the instruction to MOVZ (opcode 10b). */
 			insn |= 2 << 29;
 		} else {
@@ -140,29 +129,13 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val,
 			 */
 			imm = ~imm;
 		}
-		imm_type = AARCH64_INSN_IMM_MOVK;
 	}
 
 	/* Update the instruction with the new encoding. */
-	insn = aarch64_insn_encode_immediate(imm_type, insn, imm);
+	insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm);
 	*(u32 *)place = cpu_to_le32(insn);
 
-	/* Shift out the immediate field. */
-	sval >>= 16;
-
-	/*
-	 * For unsigned immediates, the overflow check is straightforward.
-	 * For signed immediates, the sign bit is actually the bit past the
-	 * most significant bit of the field.
-	 * The AARCH64_INSN_IMM_16 immediate type is unsigned.
-	 */
-	if (imm_type != AARCH64_INSN_IMM_16) {
-		sval++;
-		limit++;
-	}
-
-	/* Check the upper bits depending on the sign of the immediate. */
-	if ((u64)sval > limit)
+	if (imm > U16_MAX)
 		return -ERANGE;
 
 	return 0;
@@ -267,25 +240,25 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G1_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G1:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G2_NC:
 			overflow_check = false;
 		case R_AARCH64_MOVW_UABS_G2:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_UABS_G3:
 			/* We're using the top bits so we can't overflow. */
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48,
-					      AARCH64_INSN_IMM_16);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_SABS_G0:
 			ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
@@ -302,7 +275,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_AARCH64_MOVW_PREL_G0_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G0:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0,
@@ -311,7 +284,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_AARCH64_MOVW_PREL_G1_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G1:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16,
@@ -320,7 +293,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_AARCH64_MOVW_PREL_G2_NC:
 			overflow_check = false;
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
-					      AARCH64_INSN_IMM_MOVK);
+					      AARCH64_INSN_IMM_MOVKZ);
 			break;
 		case R_AARCH64_MOVW_PREL_G2:
 			ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32,
diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/paravirt.c
index cf83e61cd..53f371ed4 100644
--- a/arch/arm64/kernel/psci-call.S
+++ b/arch/arm64/kernel/paravirt.c
@@ -8,21 +8,18 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * Copyright (C) 2015 ARM Limited
+ * Copyright (C) 2013 Citrix Systems
  *
- * Author: Will Deacon <will.deacon@arm.com>
+ * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
  */
 
-#include <linux/linkage.h>
+#include <linux/export.h>
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/paravirt.h>
 
-/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_hvc)
-	hvc	#0
-	ret
-ENDPROC(__invoke_psci_fn_hvc)
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
 
-/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */
-ENTRY(__invoke_psci_fn_smc)
-	smc	#0
-	ret
-ENDPROC(__invoke_psci_fn_smc)
+struct pv_time_ops pv_time_ops;
+EXPORT_SYMBOL_GPL(pv_time_ops);
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 3aa74830c..ff4665462 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -164,8 +164,11 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = current->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, callchain_trace, entry);
+	walk_stackframe(current, &frame, callchain_trace, entry);
 }
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 62d3dc60c..f7ab14c4d 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -29,60 +29,74 @@
  * ARMv8 PMUv3 Performance Events handling code.
  * Common event types.
  */
-enum armv8_pmuv3_perf_types {
-	/* Required events. */
-	ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR			= 0x00,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL			= 0x03,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS			= 0x04,
-	ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED			= 0x10,
-	ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES			= 0x11,
-	ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED			= 0x12,
-
-	/* At least one of the following is required. */
-	ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED			= 0x08,
-	ARMV8_PMUV3_PERFCTR_OP_SPEC				= 0x1B,
-
-	/* Common architectural events. */
-	ARMV8_PMUV3_PERFCTR_MEM_READ				= 0x06,
-	ARMV8_PMUV3_PERFCTR_MEM_WRITE				= 0x07,
-	ARMV8_PMUV3_PERFCTR_EXC_TAKEN				= 0x09,
-	ARMV8_PMUV3_PERFCTR_EXC_EXECUTED			= 0x0A,
-	ARMV8_PMUV3_PERFCTR_CID_WRITE				= 0x0B,
-	ARMV8_PMUV3_PERFCTR_PC_WRITE				= 0x0C,
-	ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH			= 0x0D,
-	ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN			= 0x0E,
-	ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS		= 0x0F,
-	ARMV8_PMUV3_PERFCTR_TTBR_WRITE				= 0x1C,
-
-	/* Common microarchitectural events. */
-	ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL			= 0x01,
-	ARMV8_PMUV3_PERFCTR_ITLB_REFILL				= 0x02,
-	ARMV8_PMUV3_PERFCTR_DTLB_REFILL				= 0x05,
-	ARMV8_PMUV3_PERFCTR_MEM_ACCESS				= 0x13,
-	ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS			= 0x14,
-	ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB			= 0x15,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS			= 0x16,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL			= 0x17,
-	ARMV8_PMUV3_PERFCTR_L2_CACHE_WB				= 0x18,
-	ARMV8_PMUV3_PERFCTR_BUS_ACCESS				= 0x19,
-	ARMV8_PMUV3_PERFCTR_MEM_ERROR				= 0x1A,
-	ARMV8_PMUV3_PERFCTR_BUS_CYCLES				= 0x1D,
-};
+
+/* Required events. */
+#define ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR			0x00
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL			0x03
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS			0x04
+#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED			0x10
+#define ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES			0x11
+#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED			0x12
+
+/* At least one of the following is required. */
+#define ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED			0x08
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x1B
+
+/* Common architectural events. */
+#define ARMV8_PMUV3_PERFCTR_MEM_READ				0x06
+#define ARMV8_PMUV3_PERFCTR_MEM_WRITE				0x07
+#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x09
+#define ARMV8_PMUV3_PERFCTR_EXC_EXECUTED			0x0A
+#define ARMV8_PMUV3_PERFCTR_CID_WRITE				0x0B
+#define ARMV8_PMUV3_PERFCTR_PC_WRITE				0x0C
+#define ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH			0x0D
+#define ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN			0x0E
+#define ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS		0x0F
+#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE				0x1C
+#define ARMV8_PMUV3_PERFCTR_CHAIN				0x1E
+#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x21
+
+/* Common microarchitectural events. */
+#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL			0x01
+#define ARMV8_PMUV3_PERFCTR_ITLB_REFILL				0x02
+#define ARMV8_PMUV3_PERFCTR_DTLB_REFILL				0x05
+#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x13
+#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS			0x14
+#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB			0x15
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS			0x16
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL			0x17
+#define ARMV8_PMUV3_PERFCTR_L2_CACHE_WB				0x18
+#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x19
+#define ARMV8_PMUV3_PERFCTR_MEM_ERROR				0x1A
+#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x1D
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x1F
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x20
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x22
+#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x23
+#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x24
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x25
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x26
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x27
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x28
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x29
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x2A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x2B
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x2C
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x2D
+#define ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL			0x2E
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x2F
+#define ARMV8_PMUV3_PERFCTR_L21_TLB				0x30
 
 /* ARMv8 Cortex-A53 specific event types. */
-enum armv8_a53_pmu_perf_types {
-	ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			= 0xC2,
-};
+#define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			0xC2
 
-/* ARMv8 Cortex-A57 specific event types. */
-enum armv8_a57_perf_types {
-	ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD			= 0x40,
-	ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST			= 0x41,
-	ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD			= 0x42,
-	ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST			= 0x43,
-	ARMV8_A57_PERFCTR_DTLB_REFILL_LD			= 0x4c,
-	ARMV8_A57_PERFCTR_DTLB_REFILL_ST			= 0x4d,
-};
+/* ARMv8 Cortex-A57 and Cortex-A72 specific event types. */
+#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD			0x40
+#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST			0x41
+#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD			0x42
+#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST			0x43
+#define ARMV8_A57_PERFCTR_DTLB_REFILL_LD			0x4c
+#define ARMV8_A57_PERFCTR_DTLB_REFILL_ST			0x4d
 
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
@@ -106,6 +120,7 @@ static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
 };
 
+/* ARM Cortex-A57 and Cortex-A72 events mapping. */
 static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
@@ -178,6 +193,137 @@ static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
+#define ARMV8_EVENT_ATTR_RESOLVE(m) #m
+#define ARMV8_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR_STRING(name, armv8_event_attr_##name, \
+			      "event=" ARMV8_EVENT_ATTR_RESOLVE(config))
+
+ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR);
+ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL);
+ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_ITLB_REFILL);
+ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL);
+ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS);
+ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_DTLB_REFILL);
+ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_MEM_READ);
+ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_MEM_WRITE);
+ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED);
+ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN);
+ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_EXECUTED);
+ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE);
+ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE);
+ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH);
+ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN);
+ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS);
+ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED);
+ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES);
+ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED);
+ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS);
+ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS);
+ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB);
+ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS);
+ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2_CACHE_WB);
+ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS);
+ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEM_ERROR);
+ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC);
+ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE);
+ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES);
+ARMV8_EVENT_ATTR(chain, ARMV8_PMUV3_PERFCTR_CHAIN);
+ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED);
+ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED);
+ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND);
+ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND);
+ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB);
+ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB);
+ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE);
+ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE);
+ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL);
+ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE);
+ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB);
+ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL);
+ARMV8_EVENT_ATTR(l21_tlb_refill, ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL);
+ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB);
+ARMV8_EVENT_ATTR(l21_tlb, ARMV8_PMUV3_PERFCTR_L21_TLB);
+
+static struct attribute *armv8_pmuv3_event_attrs[] = {
+	&armv8_event_attr_sw_incr.attr.attr,
+	&armv8_event_attr_l1i_cache_refill.attr.attr,
+	&armv8_event_attr_l1i_tlb_refill.attr.attr,
+	&armv8_event_attr_l1d_cache_refill.attr.attr,
+	&armv8_event_attr_l1d_cache.attr.attr,
+	&armv8_event_attr_l1d_tlb_refill.attr.attr,
+	&armv8_event_attr_ld_retired.attr.attr,
+	&armv8_event_attr_st_retired.attr.attr,
+	&armv8_event_attr_inst_retired.attr.attr,
+	&armv8_event_attr_exc_taken.attr.attr,
+	&armv8_event_attr_exc_return.attr.attr,
+	&armv8_event_attr_cid_write_retired.attr.attr,
+	&armv8_event_attr_pc_write_retired.attr.attr,
+	&armv8_event_attr_br_immed_retired.attr.attr,
+	&armv8_event_attr_br_return_retired.attr.attr,
+	&armv8_event_attr_unaligned_ldst_retired.attr.attr,
+	&armv8_event_attr_br_mis_pred.attr.attr,
+	&armv8_event_attr_cpu_cycles.attr.attr,
+	&armv8_event_attr_br_pred.attr.attr,
+	&armv8_event_attr_mem_access.attr.attr,
+	&armv8_event_attr_l1i_cache.attr.attr,
+	&armv8_event_attr_l1d_cache_wb.attr.attr,
+	&armv8_event_attr_l2d_cache.attr.attr,
+	&armv8_event_attr_l2d_cache_refill.attr.attr,
+	&armv8_event_attr_l2d_cache_wb.attr.attr,
+	&armv8_event_attr_bus_access.attr.attr,
+	&armv8_event_attr_memory_error.attr.attr,
+	&armv8_event_attr_inst_spec.attr.attr,
+	&armv8_event_attr_ttbr_write_retired.attr.attr,
+	&armv8_event_attr_bus_cycles.attr.attr,
+	&armv8_event_attr_chain.attr.attr,
+	&armv8_event_attr_l1d_cache_allocate.attr.attr,
+	&armv8_event_attr_l2d_cache_allocate.attr.attr,
+	&armv8_event_attr_br_retired.attr.attr,
+	&armv8_event_attr_br_mis_pred_retired.attr.attr,
+	&armv8_event_attr_stall_frontend.attr.attr,
+	&armv8_event_attr_stall_backend.attr.attr,
+	&armv8_event_attr_l1d_tlb.attr.attr,
+	&armv8_event_attr_l1i_tlb.attr.attr,
+	&armv8_event_attr_l2i_cache.attr.attr,
+	&armv8_event_attr_l2i_cache_refill.attr.attr,
+	&armv8_event_attr_l3d_cache_allocate.attr.attr,
+	&armv8_event_attr_l3d_cache_refill.attr.attr,
+	&armv8_event_attr_l3d_cache.attr.attr,
+	&armv8_event_attr_l3d_cache_wb.attr.attr,
+	&armv8_event_attr_l2d_tlb_refill.attr.attr,
+	&armv8_event_attr_l21_tlb_refill.attr.attr,
+	&armv8_event_attr_l2d_tlb.attr.attr,
+	&armv8_event_attr_l21_tlb.attr.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_events_attr_group = {
+	.name = "events",
+	.attrs = armv8_pmuv3_event_attrs,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-9");
+
+static struct attribute *armv8_pmuv3_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_format_attr_group = {
+	.name = "format",
+	.attrs = armv8_pmuv3_format_attrs,
+};
+
+static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
+	&armv8_pmuv3_events_attr_group,
+	&armv8_pmuv3_format_attr_group,
+	NULL,
+};
+
 
 /*
  * Perf Events' indices
@@ -643,6 +789,7 @@ static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a53";
 	cpu_pmu->map_event		= armv8_a53_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
@@ -651,6 +798,16 @@ static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a57";
 	cpu_pmu->map_event		= armv8_a57_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	return armv8pmu_probe_num_events(cpu_pmu);
+}
+
+static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv8_pmu_init(cpu_pmu);
+	cpu_pmu->name			= "armv8_cortex_a72";
+	cpu_pmu->map_event		= armv8_a57_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
@@ -658,6 +815,7 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_init},
 	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
 	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
+	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
 	{},
 };
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f75b540bc..88d742ba1 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -344,11 +344,14 @@ unsigned long get_wchan(struct task_struct *p)
 	frame.fp = thread_saved_fp(p);
 	frame.sp = thread_saved_sp(p);
 	frame.pc = thread_saved_pc(p);
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = p->curr_ret_stack;
+#endif
 	stack_page = (unsigned long)task_stack_page(p);
 	do {
 		if (frame.sp < stack_page ||
 		    frame.sp >= stack_page + THREAD_SIZE ||
-		    unwind_frame(&frame))
+		    unwind_frame(p, &frame))
 			return 0;
 		if (!in_sched_functions(frame.pc))
 			return frame.pc;
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 6c4fd2810..1718706fd 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -43,8 +43,11 @@ void *return_address(unsigned int level)
 	frame.fp = (unsigned long)__builtin_frame_address(0);
 	frame.sp = current_stack_pointer;
 	frame.pc = (unsigned long)return_address; /* dummy */
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = current->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, save_return_addr, &data);
+	walk_stackframe(current, &frame, save_return_addr, &data);
 
 	if (!data.level)
 		return data.addr;
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index f586f7c87..fd10eb663 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu)
 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]
@@ -173,6 +177,9 @@ ENTRY(cpu_resume)
 	/* 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
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
new file mode 100644
index 000000000..ae0496fa4
--- /dev/null
+++ b/arch/arm64/kernel/smccc-call.S
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * 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.
+ *
+ */
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+
+	.macro SMCCC instr
+	.cfi_startproc
+	\instr	#0
+	ldr	x4, [sp]
+	stp	x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
+	stp	x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
+	ret
+	.cfi_endproc
+	.endm
+
+/*
+ * void arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_smc)
+	SMCCC	smc
+ENDPROC(arm_smccc_smc)
+
+/*
+ * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2,
+ *		  unsigned long a3, unsigned long a4, unsigned long a5,
+ *		  unsigned long a6, unsigned long a7, struct arm_smccc_res *res)
+ */
+ENTRY(arm_smccc_hvc)
+	SMCCC	hvc
+ENDPROC(arm_smccc_hvc)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ccb6078ed..d9751a476 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -17,9 +17,11 @@
  */
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <linux/ftrace.h>
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 
+#include <asm/irq.h>
 #include <asm/stacktrace.h>
 
 /*
@@ -35,25 +37,82 @@
  *	ldp	x29, x30, [sp]
  *	add	sp, sp, #0x10
  */
-int notrace unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
+	unsigned long irq_stack_ptr;
+
+	/*
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
+	 */
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
 
 	low  = frame->sp;
-	high = ALIGN(low, THREAD_SIZE);
+	/* irq stacks are not THREAD_SIZE aligned */
+	if (on_irq_stack(frame->sp, raw_smp_processor_id()))
+		high = irq_stack_ptr;
+	else
+		high = ALIGN(low, THREAD_SIZE) - 0x20;
 
-	if (fp < low || fp > high - 0x18 || fp & 0xf)
+	if (fp < low || fp > high || fp & 0xf)
 		return -EINVAL;
 
 	frame->sp = fp + 0x10;
-	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
+	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (tsk && tsk->ret_stack &&
+			(frame->pc == (unsigned long)return_to_handler)) {
+		/*
+		 * This is a case where function graph tracer has
+		 * modified a return address (LR) in a stack frame
+		 * to hook a function return.
+		 * So replace it to an original value.
+		 */
+		frame->pc = tsk->ret_stack[frame->graph--].ret;
+	}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+	/*
+	 * Check whether we are going to walk through from interrupt stack
+	 * to task stack.
+	 * If we reach the end of the stack - and its an interrupt stack,
+	 * unpack the dummy frame to find the original elr.
+	 *
+	 * Check the frame->fp we read from the bottom of the irq_stack,
+	 * and the original task stack pointer are both in current->stack.
+	 */
+	if (frame->sp == irq_stack_ptr) {
+		struct pt_regs *irq_args;
+		unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
+
+		if (object_is_on_stack((void *)orig_sp) &&
+		   object_is_on_stack((void *)frame->fp)) {
+			frame->sp = orig_sp;
+
+			/* orig_sp is the saved pt_regs, find the elr */
+			irq_args = (struct pt_regs *)orig_sp;
+			frame->pc = irq_args->pc;
+		} else {
+			/*
+			 * This frame has a non-standard format, and we
+			 * didn't fix it, because the data looked wrong.
+			 * Refuse to output this frame.
+			 */
+			return -EINVAL;
+		}
+	}
 
 	return 0;
 }
 
-void notrace walk_stackframe(struct stackframe *frame,
+void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 		     int (*fn)(struct stackframe *, void *), void *data)
 {
 	while (1) {
@@ -61,7 +120,7 @@ void notrace walk_stackframe(struct stackframe *frame,
 
 		if (fn(frame, data))
 			break;
-		ret = unwind_frame(frame);
+		ret = unwind_frame(tsk, frame);
 		if (ret < 0)
 			break;
 	}
@@ -112,8 +171,11 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)save_stack_trace_tsk;
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = tsk->curr_ret_stack;
+#endif
 
-	walk_stackframe(&frame, save_trace, &data);
+	walk_stackframe(tsk, &frame, save_trace, &data);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index 13339b6ff..59779699a 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -52,8 +52,11 @@ unsigned long profile_pc(struct pt_regs *regs)
 	frame.fp = regs->regs[29];
 	frame.sp = regs->sp;
 	frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = -1; /* no task info */
+#endif
 	do {
-		int ret = unwind_frame(&frame);
+		int ret = unwind_frame(NULL, &frame);
 		if (ret < 0)
 			return 0;
 	} while (in_lock_functions(frame.pc));
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e9b9b5364..c5392081b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -146,17 +146,24 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
+	unsigned long irq_stack_ptr;
+	int skip;
+
+	/*
+	 * Switching between stacks is valid when tracing current and in
+	 * non-preemptible context.
+	 */
+	if (tsk == current && !preemptible())
+		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
+	else
+		irq_stack_ptr = 0;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
 	if (!tsk)
 		tsk = current;
 
-	if (regs) {
-		frame.fp = regs->regs[29];
-		frame.sp = regs->sp;
-		frame.pc = regs->pc;
-	} else if (tsk == current) {
+	if (tsk == current) {
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)dump_backtrace;
@@ -168,21 +175,49 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		frame.sp = thread_saved_sp(tsk);
 		frame.pc = thread_saved_pc(tsk);
 	}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = tsk->curr_ret_stack;
+#endif
 
-	pr_emerg("Call trace:\n");
+	skip = !!regs;
+	printk("Call trace:\n");
 	while (1) {
 		unsigned long where = frame.pc;
 		unsigned long stack;
 		int ret;
 
-		dump_backtrace_entry(where);
-		ret = unwind_frame(&frame);
+		/* skip until specified stack frame */
+		if (!skip) {
+			dump_backtrace_entry(where);
+		} else if (frame.fp == regs->regs[29]) {
+			skip = 0;
+			/*
+			 * Mostly, this is the case where this function is
+			 * called in panic/abort. As exception handler's
+			 * stack frame does not contain the corresponding pc
+			 * at which an exception has taken place, use regs->pc
+			 * instead.
+			 */
+			dump_backtrace_entry(regs->pc);
+		}
+		ret = unwind_frame(tsk, &frame);
 		if (ret < 0)
 			break;
 		stack = frame.sp;
-		if (in_exception_text(where))
+		if (in_exception_text(where)) {
+			/*
+			 * If we switched to the irq_stack before calling this
+			 * exception handler, then the pt_regs will be on the
+			 * task stack. The easiest way to tell is if the large
+			 * pt_regs would overlap with the end of the irq_stack.
+			 */
+			if (stack < irq_stack_ptr &&
+			    (stack + sizeof(struct pt_regs)) > irq_stack_ptr)
+				stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
+
 			dump_mem("", "Exception stack", stack,
 				 stack + sizeof(struct pt_regs), false);
+		}
 	}
 }
 
@@ -456,22 +491,22 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
 
 void __pte_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pte %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
 }
 
 void __pmd_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pmd %016lx.\n", file, line, val);
 }
 
 void __pud_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pud %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pud %016lx.\n", file, line, val);
 }
 
 void __pgd_error(const char *file, int line, unsigned long val)
 {
-	pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val);
+	pr_err("%s:%d: bad pgd %016lx.\n", file, line, val);
 }
 
 /* GENERIC_BUG traps */
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 71426a78d..e3928f578 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -113,7 +113,6 @@ SECTIONS
 		*(.got)			/* Global offset table		*/
 	}
 
-	ALIGN_DEBUG_RO
 	RO_DATA(PAGE_SIZE)
 	EXCEPTION_TABLE(8)
 	NOTES
@@ -128,7 +127,6 @@ SECTIONS
 		ARM_EXIT_KEEP(EXIT_TEXT)
 	}
 
-	ALIGN_DEBUG_RO_MIN(16)
 	.init.data : {
 		INIT_DATA
 		INIT_SETUP(16)
@@ -143,9 +141,6 @@ SECTIONS
 
 	PERCPU_SECTION(L1_CACHE_BYTES)
 
-	. = ALIGN(PAGE_SIZE);
-	__init_end = .;
-
 	. = ALIGN(4);
 	.altinstructions : {
 		__alt_instructions = .;
@@ -157,6 +152,8 @@ SECTIONS
 	}
 
 	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
+
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)