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

Pull arm64 updates from Will Deacon:
 "Here is the core arm64 queue for 4.5.  As you might expect, the
  Christmas break resulted in a number of patches not making the final
  cut, so 4.6 is likely to be larger than usual.  There's still some
  useful stuff here, however, and it's detailed below.

  The EFI changes have been Reviewed-by Matt and the memblock change got
  an "OK" from akpm.

  Summary:

   - Support for a separate IRQ stack, although we haven't reduced the
     size of our thread stack just yet since we don't have enough data
     to determine a safe value

   - Refactoring of our EFI initialisation and runtime code into
     drivers/firmware/efi/ so that it can be reused by arch/arm/.

   - Ftrace improvements when unwinding in the function graph tracer

   - Document our silicon errata handling process

   - Cache flushing optimisation when mapping executable pages

   - Support for hugetlb mappings using the contiguous hint in the pte"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (45 commits)
  arm64: head.S: use memset to clear BSS
  efi: stub: define DISABLE_BRANCH_PROFILING for all architectures
  arm64: entry: remove pointless SPSR mode check
  arm64: mm: move pgd_cache initialisation to pgtable_cache_init
  arm64: module: avoid undefined shift behavior in reloc_data()
  arm64: module: fix relocation of movz instruction with negative immediate
  arm64: traps: address fallout from printk -> pr_* conversion
  arm64: ftrace: fix a stack tracer's output under function graph tracer
  arm64: pass a task parameter to unwind_frame()
  arm64: ftrace: modify a stack frame in a safe way
  arm64: remove irq_count and do_softirq_own_stack()
  arm64: hugetlb: add support for PTE contiguous bit
  arm64: Use PoU cache instr for I/D coherency
  arm64: Defer dcache flush in __cpu_copy_user_page
  arm64: reduce stack use in irq_handler
  arm64: mm: ensure that the zero page is visible to the page table walker
  arm64: Documentation: add list of software workarounds for errata
  arm64: mm: place __cpu_setup in .text
  arm64: cmpxchg: Don't incldue linux/mmdebug.h
  arm64: mm: fold alternatives into .init
  ...

19 files changed, 271 insertions, 439 deletions

diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index ab9db0e..d2ee1b2 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/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 937f5e5..3e01207 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/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0669c63..5c90aa4 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/efi.c b/arch/arm64/kernel/efi.c
index 4eeb171..b6abc85 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 7ed3d75..1f7f5a2 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 4c46c54..acc1afd 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 c851be7..ebecf9a 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 23cfc08..ffe9c2b 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
@@ -606,6 +608,8 @@ 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/irq.c b/arch/arm64/kernel/irq.c
index 9f17ec0..2386b26 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 f4bc779..93e9702 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/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 3aa7483..ff46654 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/process.c b/arch/arm64/kernel/process.c
index f75b540..88d742b 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/ptrace.c b/arch/arm64/kernel/ptrace.c
index 1971f49..ff7f132 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -58,6 +58,12 @@
  */
 void ptrace_disable(struct task_struct *child)
 {
+	/*
+	 * This would be better off in core code, but PTRACE_DETACH has
+	 * grown its fair share of arch-specific worts and changing it
+	 * is likely to cause regressions on obscure architectures.
+	 */
+	user_disable_single_step(child);
 }
 
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 6c4fd28..1718706 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 f586f7c..e33fe33 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -173,6 +173,9 @@ 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/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ccb6078..4fad978 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 +37,83 @@
  *	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;
+
+	/*
+	 * Use raw_smp_processor_id() to avoid false-positives from
+	 * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping
+	 * task stacks, we can be pre-empted in this case, so
+	 * {raw_,}smp_processor_id() may give us the wrong value. Sleeping
+	 * tasks can't ever be on an interrupt stack, so regardless of cpu,
+	 * the checks will always fail.
+	 */
+	irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id());
 
 	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);
 
+#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 +121,7 @@ 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 +172,11 @@ 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 13339b6..5977969 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 e9b9b53..cbedd72 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -146,17 +146,15 @@ 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 = IRQ_STACK_PTR(smp_processor_id());
+	int skip;
 
 	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 +166,49 @@ 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 +482,22 @@ 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 71426a7..e3928f5 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)