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

Pull arm64 updates from Catalin Marinas:

 - Kexec support for arm64

 - Kprobes support

 - Expose MIDR_EL1 and REVIDR_EL1 CPU identification registers to sysfs

 - Trapping of user space cache maintenance operations and emulation in
   the kernel (CPU errata workaround)

 - Clean-up of the early page tables creation (kernel linear mapping,
   EFI run-time maps) to avoid splitting larger blocks (e.g.  pmds) into
   smaller ones (e.g.  ptes)

 - VDSO support for CLOCK_MONOTONIC_RAW in clock_gettime()

 - ARCH_HAS_KCOV enabled for arm64

 - Optimise IP checksum helpers

 - SWIOTLB optimisation to only allocate/initialise the buffer if the
   available RAM is beyond the 32-bit mask

 - Properly handle the "nosmp" command line argument

 - Fix for the initialisation of the CPU debug state during early boot

 - vdso-offsets.h build dependency workaround

 - Build fix when RANDOMIZE_BASE is enabled with MODULES off

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (64 commits)
  arm64: arm: Fix-up the removal of the arm64 regs_query_register_name() prototype
  arm64: Only select ARM64_MODULE_PLTS if MODULES=y
  arm64: mm: run pgtable_page_ctor() on non-swapper translation table pages
  arm64: mm: make create_mapping_late() non-allocating
  arm64: Honor nosmp kernel command line option
  arm64: Fix incorrect per-cpu usage for boot CPU
  arm64: kprobes: Add KASAN instrumentation around stack accesses
  arm64: kprobes: Cleanup jprobe_return
  arm64: kprobes: Fix overflow when saving stack
  arm64: kprobes: WARN if attempting to step with PSTATE.D=1
  arm64: debug: remove unused local_dbg_{enable, disable} macros
  arm64: debug: remove redundant spsr manipulation
  arm64: debug: unmask PSTATE.D earlier
  arm64: localise Image objcopy flags
  arm64: ptrace: remove extra define for CPSR's E bit
  kprobes: Add arm64 case in kprobe example module
  arm64: Add kernel return probes support (kretprobes)
  arm64: Add trampoline code for kretprobes
  arm64: kprobes instruction simulation support
  arm64: Treat all entry code as non-kprobe-able
  ...

7 files changed, 129 insertions, 152 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 50ff9ba3a236..07d7352d7c38 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -52,7 +52,7 @@ ENTRY(__flush_cache_user_range)
 	sub	x3, x2, #1
 	bic	x4, x0, x3
 1:
-USER(9f, dc	cvau, x4	)		// clean D line to PoU
+user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	add	x4, x4, x2
 	cmp	x4, x1
 	b.lo	1b
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index c566ec83719f..f6c55afab3e2 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -19,6 +19,7 @@
 
 #include <linux/gfp.h>
 #include <linux/acpi.h>
+#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -29,6 +30,8 @@
 
 #include <asm/cacheflush.h>
 
+static int swiotlb __read_mostly;
+
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -341,6 +344,13 @@ static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
+static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	if (swiotlb)
+		return swiotlb_dma_supported(hwdev, mask);
+	return 1;
+}
+
 static struct dma_map_ops swiotlb_dma_ops = {
 	.alloc = __dma_alloc,
 	.free = __dma_free,
@@ -354,7 +364,7 @@ static struct dma_map_ops swiotlb_dma_ops = {
 	.sync_single_for_device = __swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
-	.dma_supported = swiotlb_dma_supported,
+	.dma_supported = __swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
 
@@ -513,6 +523,9 @@ EXPORT_SYMBOL(dummy_dma_ops);
 
 static int __init arm64_dma_init(void)
 {
+	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+		swiotlb = 1;
+
 	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);
@@ -848,15 +861,16 @@ static int __iommu_attach_notifier(struct notifier_block *nb,
 {
 	struct iommu_dma_notifier_data *master, *tmp;
 
-	if (action != BUS_NOTIFY_ADD_DEVICE)
+	if (action != BUS_NOTIFY_BIND_DRIVER)
 		return 0;
 
 	mutex_lock(&iommu_dma_notifier_lock);
 	list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
-		if (do_iommu_attach(master->dev, master->ops,
-				master->dma_base, master->size)) {
+		if (data == master->dev && do_iommu_attach(master->dev,
+				master->ops, master->dma_base, master->size)) {
 			list_del(&master->list);
 			kfree(master);
+			break;
 		}
 	}
 	mutex_unlock(&iommu_dma_notifier_lock);
@@ -870,17 +884,8 @@ static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
 
 	if (!nb)
 		return -ENOMEM;
-	/*
-	 * The device must be attached to a domain before the driver probe
-	 * routine gets a chance to start allocating DMA buffers. However,
-	 * the IOMMU driver also needs a chance to configure the iommu_group
-	 * via its add_device callback first, so we need to make the attach
-	 * happen between those two points. Since the IOMMU core uses a bus
-	 * notifier with default priority for add_device, do the same but
-	 * with a lower priority to ensure the appropriate ordering.
-	 */
+
 	nb->notifier_call = __iommu_attach_notifier;
-	nb->priority = -100;
 
 	ret = bus_register_notifier(bus, nb);
 	if (ret) {
@@ -904,10 +909,6 @@ static int __init __iommu_dma_init(void)
 	if (!ret)
 		ret = register_iommu_dma_ops_notifier(&pci_bus_type);
 #endif
-
-	/* handle devices queued before this arch_initcall */
-	if (!ret)
-		__iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL);
 	return ret;
 }
 arch_initcall(__iommu_dma_init);
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index ccfde237d6e6..f94b80eb295d 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -27,11 +27,7 @@
 #include <asm/memory.h>
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
-
-struct addr_marker {
-	unsigned long start_address;
-	const char *name;
-};
+#include <asm/ptdump.h>
 
 static const struct addr_marker address_markers[] = {
 #ifdef CONFIG_KASAN
@@ -290,7 +286,8 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 	}
 }
 
-static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start)
+static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
+		     unsigned long start)
 {
 	pgd_t *pgd = pgd_offset(mm, 0UL);
 	unsigned i;
@@ -309,12 +306,13 @@ static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long st
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
+	struct ptdump_info *info = m->private;
 	struct pg_state st = {
 		.seq = m,
-		.marker = address_markers,
+		.marker = info->markers,
 	};
 
-	walk_pgd(&st, &init_mm, VA_START);
+	walk_pgd(&st, info->mm, info->base_addr);
 
 	note_page(&st, 0, 0, 0);
 	return 0;
@@ -322,7 +320,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 
 static int ptdump_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, ptdump_show, NULL);
+	return single_open(file, ptdump_show, inode->i_private);
 }
 
 static const struct file_operations ptdump_fops = {
@@ -332,7 +330,7 @@ static const struct file_operations ptdump_fops = {
 	.release	= single_release,
 };
 
-static int ptdump_init(void)
+int ptdump_register(struct ptdump_info *info, const char *name)
 {
 	struct dentry *pe;
 	unsigned i, j;
@@ -342,8 +340,18 @@ static int ptdump_init(void)
 			for (j = 0; j < pg_level[i].num; j++)
 				pg_level[i].mask |= pg_level[i].bits[j].mask;
 
-	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
-				 &ptdump_fops);
+	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
 	return pe ? 0 : -ENOMEM;
 }
+
+static struct ptdump_info kernel_ptdump_info = {
+	.mm		= &init_mm,
+	.markers	= address_markers,
+	.base_addr	= VA_START,
+};
+
+static int ptdump_init(void)
+{
+	return ptdump_register(&kernel_ptdump_info, "kernel_page_tables");
+}
 device_initcall(ptdump_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 031820d989a8..c8beaa0da7df 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -41,6 +41,28 @@
 
 static const char *fault_name(unsigned int esr);
 
+#ifdef CONFIG_KPROBES
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+	int ret = 0;
+
+	/* kprobe_running() needs smp_processor_id() */
+	if (!user_mode(regs)) {
+		preempt_disable();
+		if (kprobe_running() && kprobe_fault_handler(regs, esr))
+			ret = 1;
+		preempt_enable();
+	}
+
+	return ret;
+}
+#else
+static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
+{
+	return 0;
+}
+#endif
+
 /*
  * Dump out the page tables associated with 'addr' in mm 'mm'.
  */
@@ -202,8 +224,6 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADMAP		0x010000
 #define VM_FAULT_BADACCESS	0x020000
 
-#define ESR_LNX_EXEC		(1 << 24)
-
 static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
 			   unsigned int mm_flags, unsigned long vm_flags,
 			   struct task_struct *tsk)
@@ -242,14 +262,19 @@ out:
 	return fault;
 }
 
-static inline int permission_fault(unsigned int esr)
+static inline bool is_permission_fault(unsigned int esr)
 {
-	unsigned int ec       = (esr & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT;
+	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
 
 	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
 }
 
+static bool is_el0_instruction_abort(unsigned int esr)
+{
+	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
+}
+
 static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 				   struct pt_regs *regs)
 {
@@ -259,6 +284,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
+	if (notify_page_fault(regs, esr))
+		return 0;
+
 	tsk = current;
 	mm  = tsk->mm;
 
@@ -272,14 +300,14 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	if (user_mode(regs))
 		mm_flags |= FAULT_FLAG_USER;
 
-	if (esr & ESR_LNX_EXEC) {
+	if (is_el0_instruction_abort(esr)) {
 		vm_flags = VM_EXEC;
 	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
 		vm_flags = VM_WRITE;
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
-	if (permission_fault(esr) && (addr < USER_DS)) {
+	if (is_permission_fault(esr) && (addr < USER_DS)) {
 		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
@@ -630,6 +658,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
 
 	return rv;
 }
+NOKPROBE_SYMBOL(do_debug_exception);
 
 #ifdef CONFIG_ARM64_PAN
 void cpu_enable_pan(void *__unused)
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d45f8627012c..2ade7a6a10a7 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -160,12 +160,10 @@ static void __init arm64_memory_present(void)
 static void __init arm64_memory_present(void)
 {
 	struct memblock_region *reg;
-	int nid = 0;
 
 	for_each_memblock(memory, reg) {
-#ifdef CONFIG_NUMA
-		nid = reg->nid;
-#endif
+		int nid = memblock_get_region_node(reg);
+
 		memory_present(nid, memblock_region_memory_base_pfn(reg),
 				memblock_region_memory_end_pfn(reg));
 	}
@@ -403,7 +401,8 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-	swiotlb_init(1);
+	if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+		swiotlb_init(1);
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
@@ -430,9 +429,9 @@ void __init mem_init(void)
 	pr_cont("    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n",
 		MLG(VMALLOC_START, VMALLOC_END));
 	pr_cont("      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(_text, __start_rodata));
+		MLK_ROUNDUP(_text, _etext));
 	pr_cont("    .rodata : 0x%p" " - 0x%p" "   (%6ld KB)\n",
-		MLK_ROUNDUP(__start_rodata, _etext));
+		MLK_ROUNDUP(__start_rodata, __init_begin));
 	pr_cont("      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n",
 		MLK_ROUNDUP(__init_begin, __init_end));
 	pr_cont("      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 0f85a46c3e18..51a558195bb9 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -77,7 +77,6 @@ static phys_addr_t __init early_pgtable_alloc(void)
 	void *ptr;
 
 	phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-	BUG_ON(!phys);
 
 	/*
 	 * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE
@@ -97,24 +96,6 @@ static phys_addr_t __init early_pgtable_alloc(void)
 	return phys;
 }
 
-/*
- * remap a PMD into pages
- */
-static void split_pmd(pmd_t *pmd, pte_t *pte)
-{
-	unsigned long pfn = pmd_pfn(*pmd);
-	int i = 0;
-
-	do {
-		/*
-		 * Need to have the least restrictive permissions available
-		 * permissions will be fixed up later
-		 */
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
-		pfn++;
-	} while (pte++, i++, i < PTRS_PER_PTE);
-}
-
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, unsigned long pfn,
 				  pgprot_t prot,
@@ -122,15 +103,13 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 {
 	pte_t *pte;
 
-	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
+	BUG_ON(pmd_sect(*pmd));
+	if (pmd_none(*pmd)) {
 		phys_addr_t pte_phys;
 		BUG_ON(!pgtable_alloc);
 		pte_phys = pgtable_alloc();
 		pte = pte_set_fixmap(pte_phys);
-		if (pmd_sect(*pmd))
-			split_pmd(pmd, pte);
 		__pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
-		flush_tlb_all();
 		pte_clear_fixmap();
 	}
 	BUG_ON(pmd_bad(*pmd));
@@ -144,41 +123,10 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	pte_clear_fixmap();
 }
 
-static void split_pud(pud_t *old_pud, pmd_t *pmd)
-{
-	unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT;
-	pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr);
-	int i = 0;
-
-	do {
-		set_pmd(pmd, __pmd(addr | pgprot_val(prot)));
-		addr += PMD_SIZE;
-	} while (pmd++, i++, i < PTRS_PER_PMD);
-}
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-
-	/*
-	 * If debug_page_alloc is enabled we must map the linear map
-	 * using pages. However, other mappings created by
-	 * create_mapping_noalloc must use sections in some cases. Allow
-	 * sections to be used in those cases, where no pgtable_alloc
-	 * function is provided.
-	 */
-	return !pgtable_alloc || !debug_pagealloc_enabled();
-}
-#else
-static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void))
-{
-	return true;
-}
-#endif
-
 static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -186,20 +134,13 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	/*
 	 * Check for initial section mappings in the pgd/pud and remove them.
 	 */
-	if (pud_none(*pud) || pud_sect(*pud)) {
+	BUG_ON(pud_sect(*pud));
+	if (pud_none(*pud)) {
 		phys_addr_t pmd_phys;
 		BUG_ON(!pgtable_alloc);
 		pmd_phys = pgtable_alloc();
 		pmd = pmd_set_fixmap(pmd_phys);
-		if (pud_sect(*pud)) {
-			/*
-			 * need to have the 1G of mappings continue to be
-			 * present
-			 */
-			split_pud(pud, pmd);
-		}
 		__pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
-		flush_tlb_all();
 		pmd_clear_fixmap();
 	}
 	BUG_ON(pud_bad(*pud));
@@ -209,7 +150,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
-		      block_mappings_allowed(pgtable_alloc)) {
+		      allow_block_mappings) {
 			pmd_t old_pmd =*pmd;
 			pmd_set_huge(pmd, phys, prot);
 			/*
@@ -248,7 +189,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 
 static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool allow_block_mappings)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -268,8 +210,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 		/*
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
-		if (use_1G_block(addr, next, phys) &&
-		    block_mappings_allowed(pgtable_alloc)) {
+		if (use_1G_block(addr, next, phys) && allow_block_mappings) {
 			pud_t old_pud = *pud;
 			pud_set_huge(pud, phys, prot);
 
@@ -290,7 +231,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 			}
 		} else {
 			alloc_init_pmd(pud, addr, next, phys, prot,
-				       pgtable_alloc);
+				       pgtable_alloc, allow_block_mappings);
 		}
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
@@ -298,15 +239,14 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	pud_clear_fixmap();
 }
 
-/*
- * Create the page directory entries and any necessary page tables for the
- * mapping specified by 'md'.
- */
-static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
-				    phys_addr_t size, pgprot_t prot,
-				    phys_addr_t (*pgtable_alloc)(void))
+static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
+				 unsigned long virt, phys_addr_t size,
+				 pgprot_t prot,
+				 phys_addr_t (*pgtable_alloc)(void),
+				 bool allow_block_mappings)
 {
 	unsigned long addr, length, end, next;
+	pgd_t *pgd = pgd_offset_raw(pgdir, virt);
 
 	/*
 	 * If the virtual and physical address don't have the same offset
@@ -322,29 +262,23 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt,
 	end = addr + length;
 	do {
 		next = pgd_addr_end(addr, end);
-		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc);
+		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
+			       allow_block_mappings);
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
 
-static phys_addr_t late_pgtable_alloc(void)
+static phys_addr_t pgd_pgtable_alloc(void)
 {
 	void *ptr = (void *)__get_free_page(PGALLOC_GFP);
-	BUG_ON(!ptr);
+	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+		BUG();
 
 	/* Ensure the zeroed page is visible to the page table walker */
 	dsb(ishst);
 	return __pa(ptr);
 }
 
-static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
-				 unsigned long virt, phys_addr_t size,
-				 pgprot_t prot,
-				 phys_addr_t (*alloc)(void))
-{
-	init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc);
-}
-
 /*
  * This function can only be used to modify existing table entries,
  * without allocating new levels of table. Note that this permits the
@@ -358,16 +292,17 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 			&phys, virt);
 		return;
 	}
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     NULL);
+	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true);
 }
 
 void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot)
+			       pgprot_t prot, bool allow_block_mappings)
 {
+	BUG_ON(mm == &init_mm);
+
 	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     pgd_pgtable_alloc, allow_block_mappings);
 }
 
 static void create_mapping_late(phys_addr_t phys, unsigned long virt,
@@ -380,51 +315,54 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 	}
 
 	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     late_pgtable_alloc);
+			     NULL, !debug_pagealloc_enabled());
 }
 
 static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
 {
 	unsigned long kernel_start = __pa(_text);
-	unsigned long kernel_end = __pa(_etext);
+	unsigned long kernel_end = __pa(__init_begin);
 
 	/*
 	 * Take care not to create a writable alias for the
 	 * read-only text and rodata sections of the kernel image.
 	 */
 
-	/* No overlap with the kernel text */
+	/* No overlap with the kernel text/rodata */
 	if (end < kernel_start || start >= kernel_end) {
 		__create_pgd_mapping(pgd, start, __phys_to_virt(start),
 				     end - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
+				     early_pgtable_alloc,
+				     !debug_pagealloc_enabled());
 		return;
 	}
 
 	/*
-	 * This block overlaps the kernel text mapping.
+	 * This block overlaps the kernel text/rodata mappings.
 	 * Map the portion(s) which don't overlap.
 	 */
 	if (start < kernel_start)
 		__create_pgd_mapping(pgd, start,
 				     __phys_to_virt(start),
 				     kernel_start - start, PAGE_KERNEL,
-				     early_pgtable_alloc);
+				     early_pgtable_alloc,
+				     !debug_pagealloc_enabled());
 	if (kernel_end < end)
 		__create_pgd_mapping(pgd, kernel_end,
 				     __phys_to_virt(kernel_end),
 				     end - kernel_end, PAGE_KERNEL,
-				     early_pgtable_alloc);
+				     early_pgtable_alloc,
+				     !debug_pagealloc_enabled());
 
 	/*
-	 * Map the linear alias of the [_text, _etext) interval as
+	 * Map the linear alias of the [_text, __init_begin) interval as
 	 * read-only/non-executable. This makes the contents of the
 	 * region accessible to subsystems such as hibernate, but
 	 * protects it from inadvertent modification or execution.
 	 */
 	__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
 			     kernel_end - kernel_start, PAGE_KERNEL_RO,
-			     early_pgtable_alloc);
+			     early_pgtable_alloc, !debug_pagealloc_enabled());
 }
 
 static void __init map_mem(pgd_t *pgd)
@@ -449,14 +387,14 @@ void mark_rodata_ro(void)
 {
 	unsigned long section_size;
 
-	section_size = (unsigned long)__start_rodata - (unsigned long)_text;
+	section_size = (unsigned long)_etext - (unsigned long)_text;
 	create_mapping_late(__pa(_text), (unsigned long)_text,
 			    section_size, PAGE_KERNEL_ROX);
 	/*
-	 * mark .rodata as read only. Use _etext rather than __end_rodata to
-	 * cover NOTES and EXCEPTION_TABLE.
+	 * mark .rodata as read only. Use __init_begin rather than __end_rodata
+	 * to cover NOTES and EXCEPTION_TABLE.
 	 */
-	section_size = (unsigned long)_etext - (unsigned long)__start_rodata;
+	section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
 	create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata,
 			    section_size, PAGE_KERNEL_RO);
 }
@@ -481,7 +419,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(size));
 
 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
-			     early_pgtable_alloc);
+			     early_pgtable_alloc, !debug_pagealloc_enabled());
 
 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;
@@ -499,8 +437,8 @@ static void __init map_kernel(pgd_t *pgd)
 {
 	static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data;
 
-	map_kernel_segment(pgd, _text, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text);
-	map_kernel_segment(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata);
+	map_kernel_segment(pgd, _text, _etext, PAGE_KERNEL_EXEC, &vmlinux_text);
+	map_kernel_segment(pgd, __start_rodata, __init_begin, PAGE_KERNEL, &vmlinux_rodata);
 	map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC,
 			   &vmlinux_init);
 	map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index c4317879b938..5bb61de23201 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -180,6 +180,8 @@ ENTRY(__cpu_setup)
 	msr	cpacr_el1, x0			// Enable FP/ASIMD
 	mov	x0, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x0			// access to the DCC from EL0
+	isb					// Unmask debug exceptions now,
+	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
 	/*
 	 * Memory region attributes for LPAE: