KVM: Don't pre-reserve xarray entries when storing empty/NULL attributesgrafted

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>

44 files changed, 20136 insertions, 0 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
new file mode 100644
index 000000000..3a5364853
--- /dev/null
+++ b/arch/x86/mm/Makefile
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: GPL-2.0
+# Kernel does not boot with instrumentation of tlb.c and mem_encrypt*.c
+KCOV_INSTRUMENT_tlb.o			:= n
+KCOV_INSTRUMENT_mem_encrypt.o		:= n
+KCOV_INSTRUMENT_mem_encrypt_amd.o	:= n
+KCOV_INSTRUMENT_pgprot.o		:= n
+# See the "Disable KCOV" comment in arch/x86/kernel/Makefile.
+KCOV_INSTRUMENT_physaddr.o		:= n
+
+KASAN_SANITIZE_mem_encrypt.o		:= n
+KASAN_SANITIZE_mem_encrypt_amd.o	:= n
+KASAN_SANITIZE_pgprot.o		:= n
+
+# Disable KCSAN entirely, because otherwise we get warnings that some functions
+# reference __initdata sections.
+KCSAN_SANITIZE := n
+# Avoid recursion by not calling KMSAN hooks for CEA code.
+KMSAN_SANITIZE_cpu_entry_area.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_mem_encrypt.o		= -pg
+CFLAGS_REMOVE_mem_encrypt_amd.o		= -pg
+CFLAGS_REMOVE_pgprot.o			= -pg
+endif
+
+obj-y				:=  init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \
+				    pgtable.o physaddr.o tlb.o cpu_entry_area.o maccess.o pgprot.o
+
+obj-y				+= pat/
+
+# Make sure __phys_addr has no stackprotector
+CFLAGS_physaddr.o		:= -fno-stack-protector
+
+obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
+
+obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_PTDUMP)		+= dump_pagetables.o
+obj-$(CONFIG_PTDUMP_DEBUGFS)	+= debug_pagetables.o
+
+KASAN_SANITIZE_kasan_init_$(BITS).o := n
+obj-$(CONFIG_KASAN)		+= kasan_init_$(BITS).o
+
+KMSAN_SANITIZE_kmsan_shadow.o	:= n
+obj-$(CONFIG_KMSAN)		+= kmsan_shadow.o
+
+obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
+mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
+obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
+
+obj-$(CONFIG_NUMA)		+= numa.o
+obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
+obj-$(CONFIG_ACPI_NUMA)		+= srat.o
+
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
+obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)	+= pti.o
+
+obj-$(CONFIG_X86_MEM_ENCRYPT)	+= mem_encrypt.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_amd.o
+
+obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_boot.o
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
new file mode 100644
index 000000000..1cb581bbf
--- /dev/null
+++ b/arch/x86/mm/amdtopology.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD NUMA support.
+ * Discover the memory map and associated nodes.
+ *
+ * This version reads it directly from the AMD northbridge.
+ *
+ * Copyright 2002,2003 Andi Kleen, SuSE Labs.
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/nodemask.h>
+#include <linux/memblock.h>
+#include <linux/numa_memblks.h>
+
+#include <asm/io.h>
+#include <linux/pci_ids.h>
+#include <linux/acpi.h>
+#include <asm/types.h>
+#include <asm/mmzone.h>
+#include <asm/proto.h>
+#include <asm/e820/api.h>
+#include <asm/pci-direct.h>
+#include <asm/numa.h>
+#include <asm/mpspec.h>
+#include <asm/apic.h>
+#include <asm/amd/nb.h>
+
+static unsigned char __initdata nodeids[8];
+
+static __init int find_northbridge(void)
+{
+	int num;
+
+	for (num = 0; num < 32; num++) {
+		u32 header;
+
+		header = read_pci_config(0, num, 0, 0x00);
+		if (header != (PCI_VENDOR_ID_AMD | (0x1100<<16)) &&
+			header != (PCI_VENDOR_ID_AMD | (0x1200<<16)) &&
+			header != (PCI_VENDOR_ID_AMD | (0x1300<<16)))
+			continue;
+
+		header = read_pci_config(0, num, 1, 0x00);
+		if (header != (PCI_VENDOR_ID_AMD | (0x1101<<16)) &&
+			header != (PCI_VENDOR_ID_AMD | (0x1201<<16)) &&
+			header != (PCI_VENDOR_ID_AMD | (0x1301<<16)))
+			continue;
+		return num;
+	}
+
+	return -ENOENT;
+}
+
+int __init amd_numa_init(void)
+{
+	unsigned int numnodes, cores, apicid;
+	u64 prevbase, start = PFN_PHYS(0);
+	u64 end = PFN_PHYS(max_pfn);
+	u32 nodeid, reg;
+	int i, j, nb;
+
+	if (!early_pci_allowed())
+		return -EINVAL;
+
+	nb = find_northbridge();
+	if (nb < 0)
+		return nb;
+
+	pr_info("Scanning NUMA topology in Northbridge %d\n", nb);
+
+	reg = read_pci_config(0, nb, 0, 0x60);
+	numnodes = ((reg >> 4) & 0xF) + 1;
+	if (numnodes <= 1)
+		return -ENOENT;
+
+	pr_info("Number of physical nodes %d\n", numnodes);
+
+	prevbase = 0;
+	for (i = 0; i < 8; i++) {
+		u64 base, limit;
+
+		base = read_pci_config(0, nb, 1, 0x40 + i*8);
+		limit = read_pci_config(0, nb, 1, 0x44 + i*8);
+
+		nodeids[i] = nodeid = limit & 7;
+		if ((base & 3) == 0) {
+			if (i < numnodes)
+				pr_info("Skipping disabled node %d\n", i);
+			continue;
+		}
+		if (nodeid >= numnodes) {
+			pr_info("Ignoring excess node %d (%Lx:%Lx)\n", nodeid,
+				base, limit);
+			continue;
+		}
+
+		if (!limit) {
+			pr_info("Skipping node entry %d (base %Lx)\n",
+				i, base);
+			continue;
+		}
+		if ((base >> 8) & 3 || (limit >> 8) & 3) {
+			pr_err("Node %d using interleaving mode %Lx/%Lx\n",
+			       nodeid, (base >> 8) & 3, (limit >> 8) & 3);
+			return -EINVAL;
+		}
+		if (node_isset(nodeid, numa_nodes_parsed)) {
+			pr_info("Node %d already present, skipping\n",
+				nodeid);
+			continue;
+		}
+
+		limit >>= 16;
+		limit++;
+		limit <<= 24;
+
+		if (limit > end)
+			limit = end;
+		if (limit <= base)
+			continue;
+
+		base >>= 16;
+		base <<= 24;
+
+		if (base < start)
+			base = start;
+		if (limit > end)
+			limit = end;
+		if (limit == base) {
+			pr_err("Empty node %d\n", nodeid);
+			continue;
+		}
+		if (limit < base) {
+			pr_err("Node %d bogus settings %Lx-%Lx.\n",
+			       nodeid, base, limit);
+			continue;
+		}
+
+		/* Could sort here, but pun for now. Should not happen anyroads. */
+		if (prevbase > base) {
+			pr_err("Node map not sorted %Lx,%Lx\n",
+			       prevbase, base);
+			return -EINVAL;
+		}
+
+		pr_info("Node %d MemBase %016Lx Limit %016Lx\n",
+			nodeid, base, limit);
+
+		prevbase = base;
+		numa_add_memblk(nodeid, base, limit);
+	}
+
+	if (nodes_empty(numa_nodes_parsed))
+		return -ENOENT;
+
+	/*
+	 * We seem to have valid NUMA configuration. Map apicids to nodes
+	 * using the size of the core domain in the APIC space.
+	 */
+	cores = topology_get_domain_size(TOPO_CORE_DOMAIN);
+
+	apicid = boot_cpu_physical_apicid;
+	if (apicid > 0)
+		pr_info("BSP APIC ID: %02x\n", apicid);
+
+	for_each_node_mask(i, numa_nodes_parsed) {
+		for (j = 0; j < cores; j++, apicid++)
+			set_apicid_to_node(apicid, i);
+	}
+	return 0;
+}
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
new file mode 100644
index 000000000..575f863f3
--- /dev/null
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/spinlock.h>
+#include <linux/percpu.h>
+#include <linux/kallsyms.h>
+#include <linux/kcore.h>
+#include <linux/pgtable.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/fixmap.h>
+#include <asm/desc.h>
+#include <asm/kasan.h>
+#include <asm/setup.h>
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
+
+#ifdef CONFIG_X86_64
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
+DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
+
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, _cea_offset);
+
+static __always_inline unsigned int cea_offset(unsigned int cpu)
+{
+	return per_cpu(_cea_offset, cpu);
+}
+
+static __init void init_cea_offsets(void)
+{
+	unsigned int max_cea;
+	unsigned int i, j;
+
+	if (!kaslr_enabled()) {
+		for_each_possible_cpu(i)
+			per_cpu(_cea_offset, i) = i;
+		return;
+	}
+
+	max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE;
+
+	/* O(sodding terrible) */
+	for_each_possible_cpu(i) {
+		unsigned int cea;
+
+again:
+		cea = get_random_u32_below(max_cea);
+
+		for_each_possible_cpu(j) {
+			if (cea_offset(j) == cea)
+				goto again;
+
+			if (i == j)
+				break;
+		}
+
+		per_cpu(_cea_offset, i) = cea;
+	}
+}
+#else /* !X86_64 */
+DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack);
+
+static __always_inline unsigned int cea_offset(unsigned int cpu)
+{
+	return cpu;
+}
+static inline void init_cea_offsets(void) { }
+#endif
+
+/* Is called from entry code, so must be noinstr */
+noinstr struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+	unsigned long va = CPU_ENTRY_AREA_PER_CPU + cea_offset(cpu) * CPU_ENTRY_AREA_SIZE;
+	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+	return (struct cpu_entry_area *) va;
+}
+EXPORT_SYMBOL(get_cpu_entry_area);
+
+void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags)
+{
+	unsigned long va = (unsigned long) cea_vaddr;
+	pte_t pte = pfn_pte(pa >> PAGE_SHIFT, flags);
+
+	/*
+	 * The cpu_entry_area is shared between the user and kernel
+	 * page tables.  All of its ptes can safely be global.
+	 * _PAGE_GLOBAL gets reused to help indicate PROT_NONE for
+	 * non-present PTEs, so be careful not to set it in that
+	 * case to avoid confusion.
+	 */
+	if (boot_cpu_has(X86_FEATURE_PGE) &&
+	    (pgprot_val(flags) & _PAGE_PRESENT))
+		pte = pte_set_flags(pte, _PAGE_GLOBAL);
+
+	set_pte_vaddr(va, pte);
+}
+
+static void __init
+cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
+{
+	for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE)
+		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
+}
+
+static void __init percpu_setup_debug_store(unsigned int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+	unsigned int npages;
+	void *cea;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return;
+
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
+	npages = sizeof(struct debug_store) / PAGE_SIZE;
+	BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+	cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
+			     PAGE_KERNEL);
+
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
+	/*
+	 * Force the population of PMDs for not yet allocated per cpu
+	 * memory like debug store buffers.
+	 */
+	npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
+	for (; npages; npages--, cea += PAGE_SIZE)
+		cea_set_pte(cea, 0, PAGE_NONE);
+#endif
+}
+
+#ifdef CONFIG_X86_64
+
+#define cea_map_stack(name) do {					\
+	npages = sizeof(estacks->name## _stack) / PAGE_SIZE;		\
+	cea_map_percpu_pages(cea->estacks.name## _stack,		\
+			estacks->name## _stack, npages, PAGE_KERNEL);	\
+	} while (0)
+
+static void __init percpu_setup_exception_stacks(unsigned int cpu)
+{
+	struct exception_stacks *estacks = per_cpu_ptr(&exception_stacks, cpu);
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+	unsigned int npages;
+
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+
+	per_cpu(cea_exception_stacks, cpu) = &cea->estacks;
+
+	/*
+	 * The exceptions stack mappings in the per cpu area are protected
+	 * by guard pages so each stack must be mapped separately. DB2 is
+	 * not mapped; it just exists to catch triple nesting of #DB.
+	 */
+	cea_map_stack(DF);
+	cea_map_stack(NMI);
+	cea_map_stack(DB);
+	cea_map_stack(MCE);
+
+	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) {
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) {
+			cea_map_stack(VC);
+			cea_map_stack(VC2);
+		}
+	}
+}
+#else
+static void __init percpu_setup_exception_stacks(unsigned int cpu)
+{
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+
+	cea_map_percpu_pages(&cea->doublefault_stack,
+			     &per_cpu(doublefault_stack, cpu), 1, PAGE_KERNEL);
+}
+#endif
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(unsigned int cpu)
+{
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+#ifdef CONFIG_X86_64
+	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
+	pgprot_t gdt_prot = PAGE_KERNEL_RO;
+	pgprot_t tss_prot = PAGE_KERNEL_RO;
+#else
+	/*
+	 * On 32-bit systems, the GDT cannot be read-only because
+	 * our double fault handler uses a task gate, and entering through
+	 * a task gate needs to change an available TSS to busy.  If the
+	 * GDT is read-only, that will triple fault.  The TSS cannot be
+	 * read-only because the CPU writes to it on task switches.
+	 */
+	pgprot_t gdt_prot = PAGE_KERNEL;
+	pgprot_t tss_prot = PAGE_KERNEL;
+#endif
+
+	kasan_populate_shadow_for_vaddr(cea, CPU_ENTRY_AREA_SIZE,
+					early_cpu_to_node(cpu));
+
+	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);
+
+	cea_map_percpu_pages(&cea->entry_stack_page,
+			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
+			     PAGE_KERNEL);
+
+	/*
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	/*
+	 * VMX changes the host TR limit to 0x67 after a VM exit. This is
+	 * okay, since 0x67 covers the size of struct x86_hw_tss. Make sure
+	 * that this is correct.
+	 */
+	BUILD_BUG_ON(offsetof(struct tss_struct, x86_tss) != 0);
+	BUILD_BUG_ON(sizeof(struct x86_hw_tss) != 0x68);
+
+	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
+			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
+
+#ifdef CONFIG_X86_32
+	per_cpu(cpu_entry_area, cpu) = cea;
+#endif
+
+	percpu_setup_exception_stacks(cpu);
+
+	percpu_setup_debug_store(cpu);
+}
+
+static __init void setup_cpu_entry_area_ptes(void)
+{
+#ifdef CONFIG_X86_32
+	unsigned long start, end;
+
+	/* The +1 is for the readonly IDT: */
+	BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE);
+	BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK);
+
+	start = CPU_ENTRY_AREA_BASE;
+	end = start + CPU_ENTRY_AREA_MAP_SIZE;
+
+	/* Careful here: start + PMD_SIZE might wrap around */
+	for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE)
+		populate_extra_pte(start);
+#endif
+}
+
+void __init setup_cpu_entry_areas(void)
+{
+	unsigned int cpu;
+
+	init_cea_offsets();
+
+	setup_cpu_entry_area_ptes();
+
+	for_each_possible_cpu(cpu)
+		setup_cpu_entry_area(cpu);
+
+	/*
+	 * This is the last essential update to swapper_pgdir which needs
+	 * to be synchronized to initial_page_table on 32bit.
+	 */
+	sync_initial_page_table();
+}
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
new file mode 100644
index 000000000..ae5c213a1
--- /dev/null
+++ b/arch/x86/mm/debug_pagetables.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/debugfs.h>
+#include <linux/efi.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/pgtable.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk_pgd_level_debugfs(m, &init_mm, false);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+
+static int ptdump_curknl_show(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd)
+		ptdump_walk_pgd_level_debugfs(m, current->mm, false);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump_curknl);
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+static int ptdump_curusr_show(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd)
+		ptdump_walk_pgd_level_debugfs(m, current->mm, true);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump_curusr);
+#endif
+
+#if defined(CONFIG_EFI) && defined(CONFIG_X86_64)
+static int ptdump_efi_show(struct seq_file *m, void *v)
+{
+	if (efi_mm.pgd)
+		ptdump_walk_pgd_level_debugfs(m, &efi_mm, false);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump_efi);
+#endif
+
+static struct dentry *dir;
+
+static int __init pt_dump_debug_init(void)
+{
+	dir = debugfs_create_dir("page_tables", NULL);
+
+	debugfs_create_file("kernel", 0400, dir, NULL, &ptdump_fops);
+	debugfs_create_file("current_kernel", 0400, dir, NULL,
+			    &ptdump_curknl_fops);
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+	debugfs_create_file("current_user", 0400, dir, NULL,
+			    &ptdump_curusr_fops);
+#endif
+#if defined(CONFIG_EFI) && defined(CONFIG_X86_64)
+	debugfs_create_file("efi", 0400, dir, NULL, &ptdump_efi_fops);
+#endif
+	return 0;
+}
+
+static void __exit pt_dump_debug_exit(void)
+{
+	debugfs_remove_recursive(dir);
+}
+
+module_init(pt_dump_debug_init);
+module_exit(pt_dump_debug_exit);
+MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
+MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables");
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
new file mode 100644
index 000000000..2afa7a233
--- /dev/null
+++ b/arch/x86/mm/dump_pagetables.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Debug helper to dump the current kernel pagetables of the system
+ * so that we can see what the various memory ranges are set to.
+ *
+ * (C) Copyright 2008 Intel Corporation
+ *
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/kasan.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/highmem.h>
+#include <linux/pci.h>
+#include <linux/ptdump.h>
+
+#include <asm/e820/types.h>
+
+/*
+ * The dumper groups pagetable entries of the same type into one, and for
+ * that it needs to keep some state when walking, and flush this state
+ * when a "break" in the continuity is found.
+ */
+struct pg_state {
+	struct ptdump_state ptdump;
+	int level;
+	pgprotval_t current_prot;
+	pgprotval_t effective_prot;
+	pgprotval_t prot_levels[5];
+	unsigned long start_address;
+	const struct addr_marker *marker;
+	unsigned long lines;
+	bool to_dmesg;
+	bool check_wx;
+	unsigned long wx_pages;
+	struct seq_file *seq;
+};
+
+struct addr_marker {
+	unsigned long start_address;
+	const char *name;
+	unsigned long max_lines;
+};
+
+/* Address space markers hints */
+
+#ifdef CONFIG_X86_64
+
+enum address_markers_idx {
+	USER_SPACE_NR = 0,
+	KERNEL_SPACE_NR,
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	LDT_NR,
+#endif
+	LOW_KERNEL_NR,
+	VMALLOC_START_NR,
+	VMEMMAP_START_NR,
+#ifdef CONFIG_KASAN
+	KASAN_SHADOW_START_NR,
+	KASAN_SHADOW_END_NR,
+#endif
+	CPU_ENTRY_AREA_NR,
+#ifdef CONFIG_X86_ESPFIX64
+	ESPFIX_START_NR,
+#endif
+#ifdef CONFIG_EFI
+	EFI_END_NR,
+#endif
+	HIGH_KERNEL_NR,
+	MODULES_VADDR_NR,
+	MODULES_END_NR,
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { (1UL << 63),	"Kernel Space" },
+	[LOW_KERNEL_NR]		= { 0UL,		"Low Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMEMMAP_START_NR]	= { 0UL,		"Vmemmap" },
+#ifdef CONFIG_KASAN
+	/*
+	 * These fields get initialized with the (dynamic)
+	 * KASAN_SHADOW_{START,END} values in pt_dump_init().
+	 */
+	[KASAN_SHADOW_START_NR]	= { 0UL,		"KASAN shadow" },
+	[KASAN_SHADOW_END_NR]	= { 0UL,		"KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { 0UL,		"LDT remap" },
+#endif
+	[CPU_ENTRY_AREA_NR]	= { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
+#ifdef CONFIG_X86_ESPFIX64
+	[ESPFIX_START_NR]	= { ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
+#endif
+#ifdef CONFIG_EFI
+	[EFI_END_NR]		= { EFI_VA_END,		"EFI Runtime Services" },
+#endif
+	[HIGH_KERNEL_NR]	= { __START_KERNEL_map,	"High Kernel Mapping" },
+	[MODULES_VADDR_NR]	= { MODULES_VADDR,	"Modules" },
+	[MODULES_END_NR]	= { MODULES_END,	"End Modules" },
+	[FIXADDR_START_NR]	= { FIXADDR_START,	"Fixmap Area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
+};
+
+#define INIT_PGD	((pgd_t *) &init_top_pgt)
+
+#else /* CONFIG_X86_64 */
+
+enum address_markers_idx {
+	USER_SPACE_NR = 0,
+	KERNEL_SPACE_NR,
+	VMALLOC_START_NR,
+	VMALLOC_END_NR,
+#ifdef CONFIG_HIGHMEM
+	PKMAP_BASE_NR,
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	LDT_NR,
+#endif
+	CPU_ENTRY_AREA_NR,
+	FIXADDR_START_NR,
+	END_OF_SPACE_NR,
+};
+
+static struct addr_marker address_markers[] = {
+	[USER_SPACE_NR]		= { 0,			"User Space" },
+	[KERNEL_SPACE_NR]	= { PAGE_OFFSET,	"Kernel Mapping" },
+	[VMALLOC_START_NR]	= { 0UL,		"vmalloc() Area" },
+	[VMALLOC_END_NR]	= { 0UL,		"vmalloc() End" },
+#ifdef CONFIG_HIGHMEM
+	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { 0UL,		"LDT remap" },
+#endif
+	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
+	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
+	[END_OF_SPACE_NR]	= { -1,			NULL }
+};
+
+#define INIT_PGD	(swapper_pg_dir)
+
+#endif /* !CONFIG_X86_64 */
+
+/* Multipliers for offsets within the PTEs */
+#define PTE_LEVEL_MULT (PAGE_SIZE)
+#define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT)
+#define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
+#define P4D_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
+#define PGD_LEVEL_MULT (PTRS_PER_P4D * P4D_LEVEL_MULT)
+
+#define pt_dump_seq_printf(m, to_dmesg, fmt, args...)		\
+({								\
+	if (to_dmesg)					\
+		printk(KERN_INFO fmt, ##args);			\
+	else							\
+		if (m)						\
+			seq_printf(m, fmt, ##args);		\
+})
+
+#define pt_dump_cont_printf(m, to_dmesg, fmt, args...)		\
+({								\
+	if (to_dmesg)					\
+		printk(KERN_CONT fmt, ##args);			\
+	else							\
+		if (m)						\
+			seq_printf(m, fmt, ##args);		\
+})
+
+/*
+ * Print a readable form of a pgprot_t to the seq_file
+ */
+static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg)
+{
+	static const char * const level_name[] =
+		{ "pgd", "p4d", "pud", "pmd", "pte" };
+
+	if (!(pr & _PAGE_PRESENT)) {
+		/* Not present */
+		pt_dump_cont_printf(m, dmsg, "                              ");
+	} else {
+		if (pr & _PAGE_USER)
+			pt_dump_cont_printf(m, dmsg, "USR ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+		if (pr & _PAGE_RW)
+			pt_dump_cont_printf(m, dmsg, "RW ");
+		else
+			pt_dump_cont_printf(m, dmsg, "ro ");
+		if (pr & _PAGE_PWT)
+			pt_dump_cont_printf(m, dmsg, "PWT ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+		if (pr & _PAGE_PCD)
+			pt_dump_cont_printf(m, dmsg, "PCD ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+
+		/* Bit 7 has a different meaning on level 3 vs 4 */
+		if (level <= 3 && pr & _PAGE_PSE)
+			pt_dump_cont_printf(m, dmsg, "PSE ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+		if ((level == 4 && pr & _PAGE_PAT) ||
+		    ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
+			pt_dump_cont_printf(m, dmsg, "PAT ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+		if (pr & _PAGE_GLOBAL)
+			pt_dump_cont_printf(m, dmsg, "GLB ");
+		else
+			pt_dump_cont_printf(m, dmsg, "    ");
+		if (pr & _PAGE_NX)
+			pt_dump_cont_printf(m, dmsg, "NX ");
+		else
+			pt_dump_cont_printf(m, dmsg, "x  ");
+	}
+	pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
+}
+
+static void note_wx(struct pg_state *st, unsigned long addr)
+{
+	unsigned long npages;
+
+	npages = (addr - st->start_address) / PAGE_SIZE;
+
+#ifdef CONFIG_PCI_BIOS
+	/*
+	 * If PCI BIOS is enabled, the PCI BIOS area is forced to WX.
+	 * Inform about it, but avoid the warning.
+	 */
+	if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN &&
+	    addr <= PAGE_OFFSET + BIOS_END) {
+		pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages);
+		return;
+	}
+#endif
+	/* Account the WX pages */
+	st->wx_pages += npages;
+	WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+		  "x86/mm: Found insecure W+X mapping at address %pS\n",
+		  (void *)st->start_address);
+}
+
+static void effective_prot(struct ptdump_state *pt_st, int level, u64 val)
+{
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	pgprotval_t prot = val & PTE_FLAGS_MASK;
+	pgprotval_t effective;
+
+	if (level > 0) {
+		pgprotval_t higher_prot = st->prot_levels[level - 1];
+
+		effective = (higher_prot & prot & (_PAGE_USER | _PAGE_RW)) |
+			    ((higher_prot | prot) & _PAGE_NX);
+	} else {
+		effective = prot;
+	}
+
+	st->prot_levels[level] = effective;
+}
+
+static void effective_prot_pte(struct ptdump_state *st, pte_t pte)
+{
+	effective_prot(st, 4, pte_val(pte));
+}
+
+static void effective_prot_pmd(struct ptdump_state *st, pmd_t pmd)
+{
+	effective_prot(st, 3, pmd_val(pmd));
+}
+
+static void effective_prot_pud(struct ptdump_state *st, pud_t pud)
+{
+	effective_prot(st, 2, pud_val(pud));
+}
+
+static void effective_prot_p4d(struct ptdump_state *st, p4d_t p4d)
+{
+	effective_prot(st, 1, p4d_val(p4d));
+}
+
+static void effective_prot_pgd(struct ptdump_state *st, pgd_t pgd)
+{
+	effective_prot(st, 0, pgd_val(pgd));
+}
+
+
+/*
+ * This function gets called on a break in a continuous series
+ * of PTE entries; the next one is different so we need to
+ * print what we collected so far.
+ */
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+		      u64 val)
+{
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	pgprotval_t new_prot, new_eff;
+	pgprotval_t cur, eff;
+	static const char units[] = "BKMGTPE";
+	struct seq_file *m = st->seq;
+
+	new_prot = val & PTE_FLAGS_MASK;
+	if (!val)
+		new_eff = 0;
+	else
+		new_eff = st->prot_levels[level];
+
+	/*
+	 * If we have a "break" in the series, we need to flush the state that
+	 * we have now. "break" is either changing perms, levels or
+	 * address space marker.
+	 */
+	cur = st->current_prot;
+	eff = st->effective_prot;
+
+	if (st->level == -1) {
+		/* First entry */
+		st->current_prot = new_prot;
+		st->effective_prot = new_eff;
+		st->level = level;
+		st->marker = address_markers;
+		st->lines = 0;
+		pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+				   st->marker->name);
+	} else if (new_prot != cur || new_eff != eff || level != st->level ||
+		   addr >= st->marker[1].start_address) {
+		const char *unit = units;
+		unsigned long delta;
+		int width = sizeof(unsigned long) * 2;
+
+		if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX))
+			note_wx(st, addr);
+
+		/*
+		 * Now print the actual finished series
+		 */
+		if (!st->marker->max_lines ||
+		    st->lines < st->marker->max_lines) {
+			pt_dump_seq_printf(m, st->to_dmesg,
+					   "0x%0*lx-0x%0*lx   ",
+					   width, st->start_address,
+					   width, addr);
+
+			delta = addr - st->start_address;
+			while (!(delta & 1023) && unit[1]) {
+				delta >>= 10;
+				unit++;
+			}
+			pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ",
+					    delta, *unit);
+			printk_prot(m, st->current_prot, st->level,
+				    st->to_dmesg);
+		}
+		st->lines++;
+
+		/*
+		 * We print markers for special areas of address space,
+		 * such as the start of vmalloc space etc.
+		 * This helps in the interpretation.
+		 */
+		if (addr >= st->marker[1].start_address) {
+			if (st->marker->max_lines &&
+			    st->lines > st->marker->max_lines) {
+				unsigned long nskip =
+					st->lines - st->marker->max_lines;
+				pt_dump_seq_printf(m, st->to_dmesg,
+						   "... %lu entr%s skipped ... \n",
+						   nskip,
+						   nskip == 1 ? "y" : "ies");
+			}
+			st->marker++;
+			st->lines = 0;
+			pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+					   st->marker->name);
+		}
+
+		st->start_address = addr;
+		st->current_prot = new_prot;
+		st->effective_prot = new_eff;
+		st->level = level;
+	}
+}
+
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
+bool ptdump_walk_pgd_level_core(struct seq_file *m,
+				struct mm_struct *mm, pgd_t *pgd,
+				bool checkwx, bool dmesg)
+{
+	const struct ptdump_range ptdump_ranges[] = {
+#ifdef CONFIG_X86_64
+	{0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
+	{GUARD_HOLE_END_ADDR, ~0UL},
+#else
+	{0, ~0UL},
+#endif
+	{0, 0}
+};
+
+	struct pg_state st = {
+		.ptdump = {
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
+			.effective_prot_pte = effective_prot_pte,
+			.effective_prot_pmd = effective_prot_pmd,
+			.effective_prot_pud = effective_prot_pud,
+			.effective_prot_p4d = effective_prot_p4d,
+			.effective_prot_pgd = effective_prot_pgd,
+			.range		= ptdump_ranges
+		},
+		.level = -1,
+		.to_dmesg	= dmesg,
+		.check_wx	= checkwx,
+		.seq		= m
+	};
+
+	ptdump_walk_pgd(&st.ptdump, mm, pgd);
+
+	if (!checkwx)
+		return true;
+	if (st.wx_pages) {
+		pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n",
+			st.wx_pages);
+
+		return false;
+	} else {
+		pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
+
+		return true;
+	}
+}
+
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
+{
+	ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+				   bool user)
+{
+	pgd_t *pgd = mm->pgd;
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+	if (user && boot_cpu_has(X86_FEATURE_PTI))
+		pgd = kernel_to_user_pgdp(pgd);
+#endif
+	ptdump_walk_pgd_level_core(m, mm, pgd, false, false);
+}
+
+void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+	pgd_t *pgd = INIT_PGD;
+
+	if (!(__supported_pte_mask & _PAGE_NX) ||
+	    !boot_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pr_info("x86/mm: Checking user space page tables\n");
+	pgd = kernel_to_user_pgdp(pgd);
+	ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false);
+#endif
+}
+
+bool ptdump_walk_pgd_level_checkwx(void)
+{
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return true;
+
+	return ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
+}
+
+static int __init pt_dump_init(void)
+{
+	/*
+	 * Various markers are not compile-time constants, so assign them
+	 * here.
+	 */
+#ifdef CONFIG_X86_64
+	address_markers[LOW_KERNEL_NR].start_address = PAGE_OFFSET;
+	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+	address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START;
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+#endif
+#ifdef CONFIG_KASAN
+	address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+	address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
+#endif
+#ifdef CONFIG_X86_32
+	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+	address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+# ifdef CONFIG_HIGHMEM
+	address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE;
+# endif
+	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
+	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+	address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
+#endif
+	return 0;
+}
+__initcall(pt_dump_init);
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
new file mode 100644
index 000000000..fa6eebe6a
--- /dev/null
+++ b/arch/x86/mm/extable.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/extable.h>
+#include <linux/uaccess.h>
+#include <linux/sched/debug.h>
+#include <linux/bitfield.h>
+#include <xen/xen.h>
+
+#include <asm/fpu/api.h>
+#include <asm/fred.h>
+#include <asm/sev.h>
+#include <asm/traps.h>
+#include <asm/kdebug.h>
+#include <asm/insn-eval.h>
+#include <asm/sgx.h>
+
+static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr)
+{
+	int reg_offset = pt_regs_offset(regs, nr);
+	static unsigned long __dummy;
+
+	if (WARN_ON_ONCE(reg_offset < 0))
+		return &__dummy;
+
+	return (unsigned long *)((unsigned long)regs + reg_offset);
+}
+
+static inline unsigned long
+ex_fixup_addr(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->fixup + x->fixup;
+}
+
+static bool ex_handler_default(const struct exception_table_entry *e,
+			       struct pt_regs *regs)
+{
+	if (e->data & EX_FLAG_CLEAR_AX)
+		regs->ax = 0;
+	if (e->data & EX_FLAG_CLEAR_DX)
+		regs->dx = 0;
+
+	regs->ip = ex_fixup_addr(e);
+	return true;
+}
+
+/*
+ * This is the *very* rare case where we do a "load_unaligned_zeropad()"
+ * and it's a page crosser into a non-existent page.
+ *
+ * This happens when we optimistically load a pathname a word-at-a-time
+ * and the name is less than the full word and the  next page is not
+ * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC.
+ *
+ * NOTE! The faulting address is always a 'mov mem,reg' type instruction
+ * of size 'long', and the exception fixup must always point to right
+ * after the instruction.
+ */
+static bool ex_handler_zeropad(const struct exception_table_entry *e,
+			       struct pt_regs *regs,
+			       unsigned long fault_addr)
+{
+	struct insn insn;
+	const unsigned long mask = sizeof(long) - 1;
+	unsigned long offset, addr, next_ip, len;
+	unsigned long *reg;
+
+	next_ip = ex_fixup_addr(e);
+	len = next_ip - regs->ip;
+	if (len > MAX_INSN_SIZE)
+		return false;
+
+	if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN))
+		return false;
+	if (insn.length != len)
+		return false;
+
+	if (insn.opcode.bytes[0] != 0x8b)
+		return false;
+	if (insn.opnd_bytes != sizeof(long))
+		return false;
+
+	addr = (unsigned long) insn_get_addr_ref(&insn, regs);
+	if (addr == ~0ul)
+		return false;
+
+	offset = addr & mask;
+	addr = addr & ~mask;
+	if (fault_addr != addr + sizeof(long))
+		return false;
+
+	reg = insn_get_modrm_reg_ptr(&insn, regs);
+	if (!reg)
+		return false;
+
+	*reg = *(unsigned long *)addr >> (offset * 8);
+	return ex_handler_default(e, regs);
+}
+
+static bool ex_handler_fault(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
+{
+	regs->ax = trapnr;
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_sgx(const struct exception_table_entry *fixup,
+			   struct pt_regs *regs, int trapnr)
+{
+	regs->ax = trapnr | SGX_ENCLS_FAULT_FLAG;
+	return ex_handler_default(fixup, regs);
+}
+
+/*
+ * Handler for when we fail to restore a task's FPU state.  We should never get
+ * here because the FPU state of a task using the FPU (struct fpu::fpstate)
+ * should always be valid.  However, past bugs have allowed userspace to set
+ * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
+ * These caused XRSTOR to fail when switching to the task, leaking the FPU
+ * registers of the task previously executing on the CPU.  Mitigate this class
+ * of vulnerability by restoring from the initial state (essentially, zeroing
+ * out all the FPU registers) if we can't restore from the task's FPU state.
+ */
+static bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+				 struct pt_regs *regs)
+{
+	WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
+		  (void *)instruction_pointer(regs));
+
+	fpu_reset_from_exception_fixup();
+
+	return ex_handler_default(fixup, regs);
+}
+
+/*
+ * On x86-64, we end up being imprecise with 'access_ok()', and allow
+ * non-canonical user addresses to make the range comparisons simpler,
+ * and to not have to worry about LAM being enabled.
+ *
+ * In fact, we allow up to one page of "slop" at the sign boundary,
+ * which means that we can do access_ok() by just checking the sign
+ * of the pointer for the common case of having a small access size.
+ */
+static bool gp_fault_address_ok(unsigned long fault_address)
+{
+#ifdef CONFIG_X86_64
+	/* Is it in the "user space" part of the non-canonical space? */
+	if (valid_user_address(fault_address))
+		return true;
+
+	/* .. or just above it? */
+	fault_address -= PAGE_SIZE;
+	if (valid_user_address(fault_address))
+		return true;
+#endif
+	return false;
+}
+
+static bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+			       struct pt_regs *regs, int trapnr,
+			       unsigned long fault_address)
+{
+	WARN_ONCE(trapnr == X86_TRAP_GP && !gp_fault_address_ok(fault_address),
+		"General protection fault in user access. Non-canonical address?");
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_msr(const struct exception_table_entry *fixup,
+			   struct pt_regs *regs, bool wrmsr, bool safe, int reg)
+{
+	if (__ONCE_LITE_IF(!safe && wrmsr)) {
+		pr_warn("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
+			(unsigned int)regs->cx, (unsigned int)regs->dx,
+			(unsigned int)regs->ax,  regs->ip, (void *)regs->ip);
+		show_stack_regs(regs);
+	}
+
+	if (__ONCE_LITE_IF(!safe && !wrmsr)) {
+		pr_warn("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
+			(unsigned int)regs->cx, regs->ip, (void *)regs->ip);
+		show_stack_regs(regs);
+	}
+
+	if (!wrmsr) {
+		/* Pretend that the read succeeded and returned 0. */
+		regs->ax = 0;
+		regs->dx = 0;
+	}
+
+	if (safe)
+		*pt_regs_nr(regs, reg) = -EIO;
+
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
+				struct pt_regs *regs)
+{
+	if (cpu_feature_enabled(X86_BUG_NULL_SEG))
+		asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
+	asm volatile ("mov %0, %%fs" : : "rm" (0));
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_imm_reg(const struct exception_table_entry *fixup,
+			       struct pt_regs *regs, int reg, int imm)
+{
+	*pt_regs_nr(regs, reg) = (long)imm;
+	return ex_handler_default(fixup, regs);
+}
+
+static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup,
+				  struct pt_regs *regs, int trapnr,
+				  unsigned long fault_address,
+				  int reg, int imm)
+{
+	regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg);
+	return ex_handler_uaccess(fixup, regs, trapnr, fault_address);
+}
+
+#ifdef CONFIG_X86_FRED
+static bool ex_handler_eretu(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, unsigned long error_code)
+{
+	struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax));
+	unsigned short ss = uregs->ss;
+	unsigned short cs = uregs->cs;
+
+	/*
+	 * Move the NMI bit from the invalid stack frame, which caused ERETU
+	 * to fault, to the fault handler's stack frame, thus to unblock NMI
+	 * with the fault handler's ERETS instruction ASAP if NMI is blocked.
+	 */
+	regs->fred_ss.nmi = uregs->fred_ss.nmi;
+
+	/*
+	 * Sync event information to uregs, i.e., the ERETU return frame, but
+	 * is it safe to write to the ERETU return frame which is just above
+	 * current event stack frame?
+	 *
+	 * The RSP used by FRED to push a stack frame is not the value in %rsp,
+	 * it is calculated from %rsp with the following 2 steps:
+	 * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0)	// Reserve N*64 bytes
+	 * 2) RSP = RSP & ~0x3f		// Align to a 64-byte cache line
+	 * when an event delivery doesn't trigger a stack level change.
+	 *
+	 * Here is an example with N*64 (N=1) bytes reserved:
+	 *
+	 *  64-byte cache line ==>  ______________
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETU return frame
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *  64-byte cache line ==> |______________| <== RSP after step 1) and 2)
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETS return frame
+	 *
+	 * Thus a new FRED stack frame will always be pushed below a previous
+	 * FRED stack frame ((N*64) bytes may be reserved between), and it is
+	 * safe to write to a previous FRED stack frame as they never overlap.
+	 */
+	fred_info(uregs)->edata = fred_event_data(regs);
+	uregs->ssx = regs->ssx;
+	uregs->fred_ss.ss = ss;
+	/* The NMI bit was moved away above */
+	uregs->fred_ss.nmi = 0;
+	uregs->csx = regs->csx;
+	uregs->fred_cs.sl = 0;
+	uregs->fred_cs.wfe = 0;
+	uregs->cs = cs;
+	uregs->orig_ax = error_code;
+
+	return ex_handler_default(fixup, regs);
+}
+#endif
+
+int ex_get_fixup_type(unsigned long ip)
+{
+	const struct exception_table_entry *e = search_exception_tables(ip);
+
+	return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE;
+}
+
+int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
+		    unsigned long fault_addr)
+{
+	const struct exception_table_entry *e;
+	int type, reg, imm;
+
+#ifdef CONFIG_PNPBIOS
+	if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
+		extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
+		extern u32 pnp_bios_is_utter_crap;
+		pnp_bios_is_utter_crap = 1;
+		printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n");
+		__asm__ volatile(
+			"movl %0, %%esp\n\t"
+			"jmp *%1\n\t"
+			: : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip));
+		panic("do_trap: can't hit this");
+	}
+#endif
+
+	e = search_exception_tables(regs->ip);
+	if (!e)
+		return 0;
+
+	type = FIELD_GET(EX_DATA_TYPE_MASK, e->data);
+	reg  = FIELD_GET(EX_DATA_REG_MASK,  e->data);
+	imm  = FIELD_GET_SIGNED(EX_DATA_IMM_MASK, e->data);
+
+	switch (type) {
+	case EX_TYPE_DEFAULT:
+	case EX_TYPE_DEFAULT_MCE_SAFE:
+		return ex_handler_default(e, regs);
+	case EX_TYPE_FAULT:
+	case EX_TYPE_FAULT_MCE_SAFE:
+		return ex_handler_fault(e, regs, trapnr);
+	case EX_TYPE_UACCESS:
+		return ex_handler_uaccess(e, regs, trapnr, fault_addr);
+	case EX_TYPE_CLEAR_FS:
+		return ex_handler_clear_fs(e, regs);
+	case EX_TYPE_FPU_RESTORE:
+		return ex_handler_fprestore(e, regs);
+	case EX_TYPE_BPF:
+		return ex_handler_bpf(e, regs);
+	case EX_TYPE_WRMSR:
+		return ex_handler_msr(e, regs, true, false, reg);
+	case EX_TYPE_RDMSR:
+		return ex_handler_msr(e, regs, false, false, reg);
+	case EX_TYPE_WRMSR_SAFE:
+		return ex_handler_msr(e, regs, true, true, reg);
+	case EX_TYPE_RDMSR_SAFE:
+		return ex_handler_msr(e, regs, false, true, reg);
+	case EX_TYPE_WRMSR_IN_MCE:
+		ex_handler_msr_mce(regs, true);
+		break;
+	case EX_TYPE_RDMSR_IN_MCE:
+		ex_handler_msr_mce(regs, false);
+		break;
+	case EX_TYPE_POP_REG:
+		regs->sp += sizeof(long);
+		fallthrough;
+	case EX_TYPE_IMM_REG:
+		return ex_handler_imm_reg(e, regs, reg, imm);
+	case EX_TYPE_FAULT_SGX:
+		return ex_handler_sgx(e, regs, trapnr);
+	case EX_TYPE_UCOPY_LEN:
+		return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm);
+	case EX_TYPE_ZEROPAD:
+		return ex_handler_zeropad(e, regs, fault_addr);
+#ifdef CONFIG_X86_FRED
+	case EX_TYPE_ERETU:
+		return ex_handler_eretu(e, regs, error_code);
+#endif
+	}
+	BUG();
+}
+
+extern unsigned int early_recursion_flag;
+
+/* Restricted version used during very early boot */
+void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
+{
+	/* Ignore early NMIs. */
+	if (trapnr == X86_TRAP_NMI)
+		return;
+
+	if (early_recursion_flag > 2)
+		goto halt_loop;
+
+	/*
+	 * Old CPUs leave the high bits of CS on the stack
+	 * undefined.  I'm not sure which CPUs do this, but at least
+	 * the 486 DX works this way.
+	 * Xen pv domains are not using the default __KERNEL_CS.
+	 */
+	if (!xen_pv_domain() && regs->cs != __KERNEL_CS)
+		goto fail;
+
+	/*
+	 * The full exception fixup machinery is available as soon as
+	 * the early IDT is loaded.  This means that it is the
+	 * responsibility of extable users to either function correctly
+	 * when handlers are invoked early or to simply avoid causing
+	 * exceptions before they're ready to handle them.
+	 *
+	 * This is better than filtering which handlers can be used,
+	 * because refusing to call a handler here is guaranteed to
+	 * result in a hard-to-debug panic.
+	 *
+	 * Keep in mind that not all vectors actually get here.  Early
+	 * page faults, for example, are special.
+	 */
+	if (fixup_exception(regs, trapnr, regs->orig_ax, 0))
+		return;
+
+	if (trapnr == X86_TRAP_UD) {
+		if (handle_bug(regs))
+			return;
+
+		/*
+		 * If this was a BUG and handle_bug returns or if this
+		 * was just a normal #UD, we want to continue onward and
+		 * crash.
+		 */
+	}
+
+fail:
+	early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n",
+		     (unsigned)trapnr, (unsigned long)regs->cs, regs->ip,
+		     regs->orig_ax, read_cr2());
+
+	show_regs(regs);
+
+halt_loop:
+	while (true)
+		halt();
+}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
new file mode 100644
index 000000000..aa88370ce
--- /dev/null
+++ b/arch/x86/mm/fault.c
@@ -0,0 +1,1540 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 1995  Linus Torvalds
+ *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
+ *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
+ */
+#include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
+#include <linux/kdebug.h>		/* oops_begin/end, ...		*/
+#include <linux/memblock.h>		/* max_low_pfn			*/
+#include <linux/bpf_defs.h>		/* bpf_arena_handle_page_fault	*/
+#include <linux/kfence.h>		/* kfence_handle_page_fault	*/
+#include <linux/kprobes.h>		/* NOKPROBE_SYMBOL, ...		*/
+#include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
+#include <linux/perf_event.h>		/* perf_sw_event		*/
+#include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
+#include <linux/context_tracking.h>	/* exception_enter(), ...	*/
+#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
+#include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
+#include <linux/mm_types.h>
+#include <linux/mm.h>			/* find_and_lock_vma() */
+#include <linux/vmalloc.h>
+
+#include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
+#include <asm/traps.h>			/* dotraplinkage, ...		*/
+#include <asm/fixmap.h>			/* VSYSCALL_ADDR		*/
+#include <asm/vsyscall.h>		/* emulate_vsyscall		*/
+#include <asm/vm86.h>			/* struct vm86			*/
+#include <asm/mmu_context.h>		/* vma_pkey()			*/
+#include <asm/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
+#include <asm/desc.h>			/* store_idt(), ...		*/
+#include <asm/cpu_entry_area.h>		/* exception stack		*/
+#include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
+#include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
+#include <asm/vdso.h>			/* fixup_vdso_exception()	*/
+#include <asm/irq_stack.h>
+#include <asm/fred.h>
+#include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/exceptions.h>
+
+/*
+ * Returns 0 if mmiotrace is disabled, or if the fault is not
+ * handled by mmiotrace:
+ */
+static nokprobe_inline int
+kmmio_fault(struct pt_regs *regs, unsigned long addr)
+{
+	if (unlikely(is_kmmio_active()))
+		if (kmmio_handler(regs, addr) == 1)
+			return -1;
+	return 0;
+}
+
+/*
+ * Prefetch quirks:
+ *
+ * 32-bit mode:
+ *
+ *   Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ *   Check that here and ignore it.  This is AMD erratum #91.
+ *
+ * 64-bit mode:
+ *
+ *   Sometimes the CPU reports invalid exceptions on prefetch.
+ *   Check that here and ignore it.
+ *
+ * Opcode checker based on code by Richard Brunner.
+ */
+static inline int
+check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
+		      unsigned char opcode, int *prefetch)
+{
+	unsigned char instr_hi = opcode & 0xf0;
+	unsigned char instr_lo = opcode & 0x0f;
+
+	switch (instr_hi) {
+	case 0x20:
+	case 0x30:
+		/*
+		 * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
+		 * In X86_64 long mode, the CPU will signal invalid
+		 * opcode if some of these prefixes are present so
+		 * X86_64 will never get here anyway
+		 */
+		return ((instr_lo & 7) == 0x6);
+#ifdef CONFIG_X86_64
+	case 0x40:
+		/*
+		 * In 64-bit mode 0x40..0x4F are valid REX prefixes
+		 */
+		return (!user_mode(regs) || user_64bit_mode(regs));
+#endif
+	case 0x60:
+		/* 0x64 thru 0x67 are valid prefixes in all modes. */
+		return (instr_lo & 0xC) == 0x4;
+	case 0xF0:
+		/* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
+		return !instr_lo || (instr_lo>>1) == 1;
+	case 0x00:
+		/* Prefetch instruction is 0x0F0D or 0x0F18 */
+		if (get_kernel_nofault(opcode, instr))
+			return 0;
+
+		*prefetch = (instr_lo == 0xF) &&
+			(opcode == 0x0D || opcode == 0x18);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static bool is_amd_k8_pre_npt(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	return unlikely(IS_ENABLED(CONFIG_CPU_SUP_AMD) &&
+			c->x86_vendor == X86_VENDOR_AMD &&
+			c->x86 == 0xf && c->x86_model < 0x40);
+}
+
+static int
+is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
+{
+	unsigned char *max_instr;
+	unsigned char *instr;
+	int prefetch = 0;
+
+	/* Erratum #91 affects AMD K8, pre-NPT CPUs */
+	if (!is_amd_k8_pre_npt())
+		return 0;
+
+	/*
+	 * If it was a exec (instruction fetch) fault on NX page, then
+	 * do not ignore the fault:
+	 */
+	if (error_code & X86_PF_INSTR)
+		return 0;
+
+	instr = (void *)convert_ip_to_linear(current, regs);
+	max_instr = instr + 15;
+
+	/*
+	 * This code has historically always bailed out if IP points to a
+	 * not-present page (e.g. due to a race).  No one has ever
+	 * complained about this.
+	 */
+	pagefault_disable();
+
+	while (instr < max_instr) {
+		unsigned char opcode;
+
+		if (user_mode(regs)) {
+			if (get_user(opcode, (unsigned char __user *) instr))
+				break;
+		} else {
+			if (get_kernel_nofault(opcode, instr))
+				break;
+		}
+
+		instr++;
+
+		if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
+			break;
+	}
+
+	pagefault_enable();
+	return prefetch;
+}
+
+DEFINE_SPINLOCK(pgd_lock);
+/*
+ * List of all process' PGD pages (excluding init_mm and some other special
+ * system-wide PGDs). Mainly used to keep the kernel portion of the address
+ * space in sync across mms.
+ */
+LIST_HEAD(pgd_list);
+
+#ifdef CONFIG_X86_32
+static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
+{
+	unsigned index = pgd_index(address);
+	pgd_t *pgd_k;
+	p4d_t *p4d, *p4d_k;
+	pud_t *pud, *pud_k;
+	pmd_t *pmd, *pmd_k;
+
+	pgd += index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(*pgd_k))
+		return NULL;
+
+	/*
+	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
+	 * and redundant with the set_pmd() on non-PAE. As would
+	 * set_p4d/set_pud.
+	 */
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (!p4d_present(*p4d_k))
+		return NULL;
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
+	if (!pud_present(*pud_k))
+		return NULL;
+
+	pmd = pmd_offset(pud, address);
+	pmd_k = pmd_offset(pud_k, address);
+
+	if (pmd_present(*pmd) != pmd_present(*pmd_k))
+		set_pmd(pmd, *pmd_k);
+
+	if (!pmd_present(*pmd_k))
+		return NULL;
+	else
+		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
+
+	return pmd_k;
+}
+
+/*
+ *   Handle a fault on the vmalloc or module mapping area
+ *
+ *   This is needed because there is a race condition between the time
+ *   when the vmalloc mapping code updates the PMD to the point in time
+ *   where it synchronizes this update with the other page-tables in the
+ *   system.
+ *
+ *   In this race window another thread/CPU can map an area on the same
+ *   PMD, finds it already present and does not synchronize it with the
+ *   rest of the system yet. As a result v[mz]alloc might return areas
+ *   which are not mapped in every page-table in the system, causing an
+ *   unhandled page-fault when they are accessed.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+	unsigned long pgd_paddr;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "current" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	pgd_paddr = read_cr3_pa();
+	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+	if (!pmd_k)
+		return -1;
+
+	if (pmd_leaf(*pmd_k))
+		return 0;
+
+	pte_k = pte_offset_kernel(pmd_k, address);
+	if (!pte_present(*pte_k))
+		return -1;
+
+	return 0;
+}
+NOKPROBE_SYMBOL(vmalloc_fault);
+
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = start & PMD_MASK;
+	     addr >= TASK_SIZE_MAX && addr < VMALLOC_END;
+	     addr += PMD_SIZE) {
+		struct ptdesc *ptdesc;
+
+		spin_lock(&pgd_lock);
+		list_for_each_entry(ptdesc, &pgd_list, pt_list) {
+			spinlock_t *pgt_lock;
+
+			/* the pgt_lock only for Xen */
+			pgt_lock = &pgd_page_get_mm(ptdesc)->page_table_lock;
+
+			spin_lock(pgt_lock);
+			vmalloc_sync_one(ptdesc_address(ptdesc), addr);
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock(&pgd_lock);
+	}
+}
+
+static bool low_pfn(unsigned long pfn)
+{
+	return pfn < max_low_pfn;
+}
+
+static void dump_pagetable(unsigned long address)
+{
+	pgd_t *base = __va(read_cr3_pa());
+	pgd_t *pgd = &base[pgd_index(address)];
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+#ifdef CONFIG_X86_PAE
+	pr_info("*pdpt = %016Lx ", pgd_val(*pgd));
+	if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd))
+		goto out;
+#define pr_pde pr_cont
+#else
+#define pr_pde pr_info
+#endif
+	p4d = p4d_offset(pgd, address);
+	pud = pud_offset(p4d, address);
+	pmd = pmd_offset(pud, address);
+	pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd));
+#undef pr_pde
+
+	/*
+	 * We must not directly access the pte in the highpte
+	 * case if the page table is located in highmem.
+	 * And let's rather not kmap-atomic the pte, just in case
+	 * it's allocated already:
+	 */
+	if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	pte = pte_offset_kernel(pmd, address);
+	pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte));
+out:
+	pr_cont("\n");
+}
+
+#else /* CONFIG_X86_64: */
+
+#ifdef CONFIG_CPU_SUP_AMD
+static const char errata93_warning[] =
+KERN_ERR 
+"******* Your BIOS seems to not contain a fix for K8 errata #93\n"
+"******* Working around it, but it may cause SEGVs or burn power.\n"
+"******* Please consider a BIOS update.\n"
+"******* Disabling USB legacy in the BIOS may also help.\n";
+#endif
+
+static int bad_address(void *p)
+{
+	unsigned long dummy;
+
+	return get_kernel_nofault(dummy, (unsigned long *)p);
+}
+
+static void dump_pagetable(unsigned long address)
+{
+	pgd_t *base = __va(read_cr3_pa());
+	pgd_t *pgd = base + pgd_index(address);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (bad_address(pgd))
+		goto bad;
+
+	pr_info("PGD %lx ", pgd_val(*pgd));
+
+	if (!pgd_present(*pgd))
+		goto out;
+
+	p4d = p4d_offset(pgd, address);
+	if (bad_address(p4d))
+		goto bad;
+
+	pr_cont("P4D %lx ", p4d_val(*p4d));
+	if (!p4d_present(*p4d) || p4d_leaf(*p4d))
+		goto out;
+
+	pud = pud_offset(p4d, address);
+	if (bad_address(pud))
+		goto bad;
+
+	pr_cont("PUD %lx ", pud_val(*pud));
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	if (bad_address(pmd))
+		goto bad;
+
+	pr_cont("PMD %lx ", pmd_val(*pmd));
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	pte = pte_offset_kernel(pmd, address);
+	if (bad_address(pte))
+		goto bad;
+
+	pr_cont("PTE %lx", pte_val(*pte));
+out:
+	pr_cont("\n");
+	return;
+bad:
+	pr_info("BAD\n");
+}
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Workaround for K8 erratum #93 & buggy BIOS.
+ *
+ * BIOS SMM functions are required to use a specific workaround
+ * to avoid corruption of the 64bit RIP register on C stepping K8.
+ *
+ * A lot of BIOS that didn't get tested properly miss this.
+ *
+ * The OS sees this as a page fault with the upper 32bits of RIP cleared.
+ * Try to work around it here.
+ *
+ * Note we only handle faults in kernel here.
+ * Does nothing on 32-bit.
+ */
+static int is_errata93(struct pt_regs *regs, unsigned long address)
+{
+#if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD)
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD
+	    || boot_cpu_data.x86 != 0xf)
+		return 0;
+
+	if (user_mode(regs))
+		return 0;
+
+	if (address != regs->ip)
+		return 0;
+
+	if ((address >> 32) != 0)
+		return 0;
+
+	address |= 0xffffffffUL << 32;
+	if ((address >= (u64)_stext && address <= (u64)_etext) ||
+	    (address >= MODULES_VADDR && address <= MODULES_END)) {
+		printk_once(errata93_warning);
+		regs->ip = address;
+		return 1;
+	}
+#endif
+	return 0;
+}
+
+/*
+ * Work around K8 erratum #100 K8 in compat mode occasionally jumps
+ * to illegal addresses >4GB.
+ *
+ * We catch this in the page fault handler because these addresses
+ * are not reachable. Just detect this case and return.  Any code
+ * segment in LDT is compatibility mode.
+ */
+static int is_errata100(struct pt_regs *regs, unsigned long address)
+{
+#ifdef CONFIG_X86_64
+	if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
+		return 1;
+#endif
+	return 0;
+}
+
+/* Pentium F0 0F C7 C8 bug workaround: */
+static int is_f00f_bug(struct pt_regs *regs, unsigned long error_code,
+		       unsigned long address)
+{
+#ifdef CONFIG_X86_F00F_BUG
+	if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) &&
+	    idt_is_f00f_address(address)) {
+		handle_invalid_op(regs);
+		return 1;
+	}
+#endif
+	return 0;
+}
+
+static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
+{
+	u32 offset = (index >> 3) * sizeof(struct desc_struct);
+	unsigned long addr;
+	struct ldttss_desc desc;
+
+	if (index == 0) {
+		pr_alert("%s: NULL\n", name);
+		return;
+	}
+
+	if (offset + sizeof(struct ldttss_desc) >= gdt->size) {
+		pr_alert("%s: 0x%hx -- out of bounds\n", name, index);
+		return;
+	}
+
+	if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
+			      sizeof(struct ldttss_desc))) {
+		pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
+			 name, index);
+		return;
+	}
+
+	addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24);
+#ifdef CONFIG_X86_64
+	addr |= ((u64)desc.base3 << 32);
+#endif
+	pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n",
+		 name, index, addr, (desc.limit0 | (desc.limit1 << 16)));
+}
+
+static void
+show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+{
+	if (!oops_may_print())
+		return;
+
+	if (error_code & X86_PF_INSTR) {
+		unsigned int level;
+		bool nx, rw;
+		pgd_t *pgd;
+		pte_t *pte;
+
+		pgd = __va(read_cr3_pa());
+		pgd += pgd_index(address);
+
+		pte = lookup_address_in_pgd_attr(pgd, address, &level, &nx, &rw);
+
+		if (pte && pte_present(*pte) && (!pte_exec(*pte) || nx))
+			pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
+				from_kuid(&init_user_ns, current_uid()));
+		if (pte && pte_present(*pte) && pte_exec(*pte) && !nx &&
+				(pgd_flags(*pgd) & _PAGE_USER) &&
+				(__read_cr4() & X86_CR4_SMEP))
+			pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
+				from_kuid(&init_user_ns, current_uid()));
+	}
+
+	if (address < PAGE_SIZE && !user_mode(regs))
+		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
+			(void *)address);
+	else
+		pr_alert("BUG: unable to handle page fault for address: %px\n",
+			(void *)address);
+
+	pr_alert("#PF: %s %s in %s mode\n",
+		 (error_code & X86_PF_USER)  ? "user" : "supervisor",
+		 (error_code & X86_PF_INSTR) ? "instruction fetch" :
+		 (error_code & X86_PF_WRITE) ? "write access" :
+					       "read access",
+			     user_mode(regs) ? "user" : "kernel");
+	pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code,
+		 !(error_code & X86_PF_PROT) ? "not-present page" :
+		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
+		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+		 (error_code & X86_PF_RMP)   ? "RMP violation" :
+					       "permissions violation");
+
+	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
+		struct desc_ptr idt, gdt;
+		u16 ldtr, tr;
+
+		/*
+		 * This can happen for quite a few reasons.  The more obvious
+		 * ones are faults accessing the GDT, or LDT.  Perhaps
+		 * surprisingly, if the CPU tries to deliver a benign or
+		 * contributory exception from user code and gets a page fault
+		 * during delivery, the page fault can be delivered as though
+		 * it originated directly from user code.  This could happen
+		 * due to wrong permissions on the IDT, GDT, LDT, TSS, or
+		 * kernel or IST stack.
+		 */
+		store_idt(&idt);
+
+		/* Usable even on Xen PV -- it's just slow. */
+		native_store_gdt(&gdt);
+
+		pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n",
+			 idt.address, idt.size, gdt.address, gdt.size);
+
+		store_ldt(ldtr);
+		show_ldttss(&gdt, "LDTR", ldtr);
+
+		store_tr(tr);
+		show_ldttss(&gdt, "TR", tr);
+	}
+
+	dump_pagetable(address);
+
+	if (error_code & X86_PF_RMP)
+		snp_dump_hva_rmpentry(address);
+}
+
+static noinline void
+pgtable_bad(struct pt_regs *regs, unsigned long error_code,
+	    unsigned long address)
+{
+	struct task_struct *tsk;
+	unsigned long flags;
+	int sig;
+
+	flags = oops_begin();
+	tsk = current;
+	sig = SIGKILL;
+
+	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
+	       tsk->comm, address);
+	dump_pagetable(address);
+
+	if (__die("Bad pagetable", regs, error_code))
+		sig = 0;
+
+	oops_end(flags, regs, sig);
+}
+
+static void sanitize_error_code(unsigned long address,
+				unsigned long *error_code)
+{
+	/*
+	 * To avoid leaking information about the kernel page
+	 * table layout, pretend that user-mode accesses to
+	 * kernel addresses are always protection faults.
+	 *
+	 * NB: This means that failed vsyscalls with vsyscall=none
+	 * will have the PROT bit.  This doesn't leak any
+	 * information and does not appear to cause any problems.
+	 */
+	if (address >= TASK_SIZE_MAX)
+		*error_code |= X86_PF_PROT;
+}
+
+static void set_signal_archinfo(unsigned long address,
+				unsigned long error_code)
+{
+	struct task_struct *tsk = current;
+
+	tsk->thread.trap_nr = X86_TRAP_PF;
+	tsk->thread.error_code = error_code | X86_PF_USER;
+	tsk->thread.cr2 = address;
+}
+
+static noinline void
+page_fault_oops(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
+{
+#ifdef CONFIG_VMAP_STACK
+	struct stack_info info;
+#endif
+	unsigned long flags;
+	int sig;
+
+	if (user_mode(regs)) {
+		/*
+		 * Implicit kernel access from user mode?  Skip the stack
+		 * overflow and EFI special cases.
+		 */
+		goto oops;
+	}
+
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * Stack overflow?  During boot, we can fault near the initial
+	 * stack in the direct map, but that's not an overflow -- check
+	 * that we're in vmalloc space to avoid this.
+	 */
+	if (is_vmalloc_addr((void *)address) &&
+	    get_stack_guard_info((void *)address, &info)) {
+		/*
+		 * We're likely to be running with very little stack space
+		 * left.  It's plausible that we'd hit this condition but
+		 * double-fault even before we get this far, in which case
+		 * we're fine: the double-fault handler will deal with it.
+		 *
+		 * We don't want to make it all the way into the oops code
+		 * and then double-fault, though, because we're likely to
+		 * break the console driver and lose most of the stack dump.
+		 */
+		call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*),
+			      handle_stack_overflow,
+			      ASM_CALL_ARG3,
+			      , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
+
+		BUG();
+	}
+#endif
+
+	/*
+	 * Buggy firmware could access regions which might page fault.  If
+	 * this happens, EFI has a special OOPS path that will try to
+	 * avoid hanging the system.
+	 */
+	if (IS_ENABLED(CONFIG_EFI))
+		efi_crash_gracefully_on_page_fault(address, regs);
+
+	/* Only not-present faults should be handled by KFENCE or BPF arena. */
+	if (!(error_code & X86_PF_PROT)) {
+		if (kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs))
+			return;
+		if (bpf_arena_handle_page_fault(address, error_code & X86_PF_WRITE, regs->ip))
+			return;
+	}
+
+oops:
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice:
+	 */
+	flags = oops_begin();
+
+	show_fault_oops(regs, error_code, address);
+
+	if (task_stack_end_corrupted(current))
+		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
+
+	sig = SIGKILL;
+	if (__die("Oops", regs, error_code))
+		sig = 0;
+
+	/* Executive summary in case the body of the oops scrolled away */
+	printk(KERN_DEFAULT "CR2: %016lx\n", address);
+
+	oops_end(flags, regs, sig);
+}
+
+static noinline void
+kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
+			 unsigned long address, int signal, int si_code,
+			 u32 pkey)
+{
+	WARN_ON_ONCE(user_mode(regs));
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs, X86_TRAP_PF, error_code, address))
+		return;
+
+	/*
+	 * AMD erratum #91 manifests as a spurious page fault on a PREFETCH
+	 * instruction.
+	 */
+	if (is_prefetch(regs, error_code, address))
+		return;
+
+	page_fault_oops(regs, error_code, address);
+}
+
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address, struct task_struct *tsk)
+{
+	const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
+	/* This is a racy snapshot, but it's better than nothing. */
+	int cpu = raw_smp_processor_id();
+
+	if (!unhandled_signal(tsk, SIGSEGV))
+		return;
+
+	if (!printk_ratelimit())
+		return;
+
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
+		loglvl, tsk->comm, task_pid_nr(tsk), address,
+		(void *)regs->ip, (void *)regs->sp, error_code);
+
+	print_vma_addr(KERN_CONT " in ", regs->ip);
+
+	/*
+	 * Dump the likely CPU where the fatal segfault happened.
+	 * This can help identify faulty hardware.
+	 */
+	printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu,
+	       topology_core_id(cpu), topology_physical_package_id(cpu));
+
+
+	printk(KERN_CONT "\n");
+
+	show_opcodes(regs, loglvl);
+}
+
+static void
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+		       unsigned long address, u32 pkey, int si_code)
+{
+	struct task_struct *tsk = current;
+
+	if (!user_mode(regs)) {
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGSEGV, si_code, pkey);
+		return;
+	}
+
+	if (!(error_code & X86_PF_USER)) {
+		/* Implicit user access to kernel memory -- just oops */
+		page_fault_oops(regs, error_code, address);
+		return;
+	}
+
+	/*
+	 * User mode accesses just cause a SIGSEGV.
+	 * It's possible to have interrupts off here:
+	 */
+	local_irq_enable();
+
+	/*
+	 * Valid to do another page fault here because this one came
+	 * from user space:
+	 */
+	if (is_prefetch(regs, error_code, address))
+		return;
+
+	if (is_errata100(regs, address))
+		return;
+
+	sanitize_error_code(address, &error_code);
+
+	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
+		return;
+
+	if (likely(show_unhandled_signals))
+		show_signal_msg(regs, error_code, address, tsk);
+
+	set_signal_archinfo(address, error_code);
+
+	if (si_code == SEGV_PKUERR)
+		force_sig_pkuerr((void __user *)address, pkey);
+	else
+		force_sig_fault(SIGSEGV, si_code, (void __user *)address);
+}
+
+static noinline void
+bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+		     unsigned long address)
+{
+	__bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR);
+}
+
+static void
+__bad_area(struct pt_regs *regs, unsigned long error_code,
+	   unsigned long address, struct mm_struct *mm,
+	   struct vm_area_struct *vma, u32 pkey, int si_code)
+{
+	/*
+	 * Something tried to access memory that isn't in our memory map..
+	 * Fix it, but check if it's kernel or user first..
+	 */
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
+
+	__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
+}
+
+static inline bool bad_area_access_from_pkeys(unsigned long error_code,
+		struct vm_area_struct *vma)
+{
+	/* This code is always called on the current mm */
+	bool foreign = false;
+
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return false;
+	if (error_code & X86_PF_PK)
+		return true;
+	/* this checks permission keys on the VMA: */
+	if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE),
+				       (error_code & X86_PF_INSTR), foreign))
+		return true;
+	return false;
+}
+
+static noinline void
+bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
+		      unsigned long address, struct mm_struct *mm,
+		      struct vm_area_struct *vma)
+{
+	/*
+	 * This OSPKE check is not strictly necessary at runtime.
+	 * But, doing it this way allows compiler optimizations
+	 * if pkeys are compiled out.
+	 */
+	if (bad_area_access_from_pkeys(error_code, vma)) {
+		/*
+		 * A protection key fault means that the PKRU value did not allow
+		 * access to some PTE.  Userspace can figure out what PKRU was
+		 * from the XSAVE state.  This function captures the pkey from
+		 * the vma and passes it to userspace so userspace can discover
+		 * which protection key was set on the PTE.
+		 *
+		 * If we get here, we know that the hardware signaled a X86_PF_PK
+		 * fault and that there was a VMA once we got in the fault
+		 * handler.  It does *not* guarantee that the VMA we find here
+		 * was the one that we faulted on.
+		 *
+		 * 1. T1   : mprotect_key(foo, PAGE_SIZE, pkey=4);
+		 * 2. T1   : set PKRU to deny access to pkey=4, touches page
+		 * 3. T1   : faults...
+		 * 4.    T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
+		 * 5. T1   : enters fault handler, takes mmap_lock, etc...
+		 * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
+		 *	     faulted on a pte with its pkey=4.
+		 */
+		u32 pkey = vma_pkey(vma);
+
+		__bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR);
+	} else {
+		__bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR);
+	}
+}
+
+static void
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
+	  vm_fault_t fault)
+{
+	/* Kernel mode? Handle exceptions or die: */
+	if (!user_mode(regs)) {
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY);
+		return;
+	}
+
+	/* User-space => ok to do another page fault: */
+	if (is_prefetch(regs, error_code, address))
+		return;
+
+	sanitize_error_code(address, &error_code);
+
+	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
+		return;
+
+	set_signal_archinfo(address, error_code);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+		struct task_struct *tsk = current;
+		unsigned lsb = 0;
+
+		pr_err(
+	"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+			tsk->comm, tsk->pid, address);
+		if (fault & VM_FAULT_HWPOISON_LARGE)
+			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+		if (fault & VM_FAULT_HWPOISON)
+			lsb = PAGE_SHIFT;
+		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
+		return;
+	}
+#endif
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
+}
+
+static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
+{
+	if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
+		return 0;
+
+	if ((error_code & X86_PF_INSTR) && !pte_exec(*pte))
+		return 0;
+
+	return 1;
+}
+
+/*
+ * Handle a spurious fault caused by a stale TLB entry.
+ *
+ * This allows us to lazily refresh the TLB when increasing the
+ * permissions of a kernel page (RO -> RW or NX -> X).  Doing it
+ * eagerly is very expensive since that implies doing a full
+ * cross-processor TLB flush, even if no stale TLB entries exist
+ * on other processors.
+ *
+ * Spurious faults may only occur if the TLB contains an entry with
+ * fewer permission than the page table entry.  Non-present (P = 0)
+ * and reserved bit (R = 1) faults are never spurious.
+ *
+ * There are no security implications to leaving a stale TLB when
+ * increasing the permissions on a page.
+ *
+ * Returns non-zero if a spurious fault was handled, zero otherwise.
+ *
+ * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3
+ * (Optional Invalidation).
+ */
+static noinline int
+spurious_kernel_fault(unsigned long error_code, unsigned long address)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	int ret;
+
+	/*
+	 * Only writes to RO or instruction fetches from NX may cause
+	 * spurious faults.
+	 *
+	 * These could be from user or supervisor accesses but the TLB
+	 * is only lazily flushed after a kernel mapping protection
+	 * change, so user accesses are not expected to cause spurious
+	 * faults.
+	 */
+	if (error_code != (X86_PF_WRITE | X86_PF_PROT) &&
+	    error_code != (X86_PF_INSTR | X86_PF_PROT))
+		return 0;
+
+	pgd = init_mm.pgd + pgd_index(address);
+	if (!pgd_present(*pgd))
+		return 0;
+
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		return 0;
+
+	if (p4d_leaf(*p4d))
+		return spurious_kernel_fault_check(error_code, (pte_t *) p4d);
+
+	pud = pud_offset(p4d, address);
+	if (!pud_present(*pud))
+		return 0;
+
+	if (pud_leaf(*pud))
+		return spurious_kernel_fault_check(error_code, (pte_t *) pud);
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(*pmd))
+		return 0;
+
+	if (pmd_leaf(*pmd))
+		return spurious_kernel_fault_check(error_code, (pte_t *) pmd);
+
+	pte = pte_offset_kernel(pmd, address);
+	if (!pte_present(*pte))
+		return 0;
+
+	ret = spurious_kernel_fault_check(error_code, pte);
+	if (!ret)
+		return 0;
+
+	/*
+	 * Make sure we have permissions in PMD.
+	 * If not, then there's a bug in the page tables:
+	 */
+	ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd);
+	WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
+
+	return ret;
+}
+NOKPROBE_SYMBOL(spurious_kernel_fault);
+
+int show_unhandled_signals = 1;
+
+static inline int
+access_error(unsigned long error_code, struct vm_area_struct *vma)
+{
+	/* This is only called for the current mm, so: */
+	bool foreign = false;
+
+	/*
+	 * Read or write was blocked by protection keys.  This is
+	 * always an unconditional error and can never result in
+	 * a follow-up action to resolve the fault, like a COW.
+	 */
+	if (error_code & X86_PF_PK)
+		return 1;
+
+	/*
+	 * SGX hardware blocked the access.  This usually happens
+	 * when the enclave memory contents have been destroyed, like
+	 * after a suspend/resume cycle. In any case, the kernel can't
+	 * fix the cause of the fault.  Handle the fault as an access
+	 * error even in cases where no actual access violation
+	 * occurred.  This allows userspace to rebuild the enclave in
+	 * response to the signal.
+	 */
+	if (unlikely(error_code & X86_PF_SGX))
+		return 1;
+
+	/*
+	 * Make sure to check the VMA so that we do not perform
+	 * faults just to hit a X86_PF_PK as soon as we fill in a
+	 * page.
+	 */
+	if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE),
+				       (error_code & X86_PF_INSTR), foreign))
+		return 1;
+
+	/*
+	 * Shadow stack accesses (PF_SHSTK=1) are only permitted to
+	 * shadow stack VMAs. All other accesses result in an error.
+	 */
+	if (error_code & X86_PF_SHSTK) {
+		if (unlikely(!(vma->vm_flags & VM_SHADOW_STACK)))
+			return 1;
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
+			return 1;
+		return 0;
+	}
+
+	if (error_code & X86_PF_WRITE) {
+		/* write, present and write, not present: */
+		if (unlikely(vma->vm_flags & VM_SHADOW_STACK))
+			return 1;
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
+			return 1;
+		return 0;
+	}
+
+	/* read, present: */
+	if (unlikely(error_code & X86_PF_PROT))
+		return 1;
+
+	/* read, not present: */
+	if (unlikely(!vma_is_accessible(vma)))
+		return 1;
+
+	return 0;
+}
+
+bool fault_in_kernel_space(unsigned long address)
+{
+	/*
+	 * On 64-bit systems, the vsyscall page is at an address above
+	 * TASK_SIZE_MAX, but is not considered part of the kernel
+	 * address space.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address))
+		return false;
+
+	return address >= TASK_SIZE_MAX;
+}
+
+/*
+ * Called for all faults where 'address' is part of the kernel address
+ * space.  Might get called for faults that originate from *code* that
+ * ran in userspace or the kernel.
+ */
+static void
+do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
+		   unsigned long address)
+{
+	/*
+	 * Protection keys exceptions only happen on user pages.  We
+	 * have no user pages in the kernel portion of the address
+	 * space, so do not expect them here.
+	 */
+	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
+
+#ifdef CONFIG_X86_32
+	/*
+	 * We can fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * Before doing this on-demand faulting, ensure that the
+	 * fault is not any of the following:
+	 * 1. A fault on a PTE with a reserved bit set.
+	 * 2. A fault caused by a user-mode access.  (Do not demand-
+	 *    fault kernel memory due to user-mode accesses).
+	 * 3. A fault caused by a page-level protection violation.
+	 *    (A demand fault would be on a non-present page which
+	 *     would have X86_PF_PROT==0).
+	 *
+	 * This is only needed to close a race condition on x86-32 in
+	 * the vmalloc mapping/unmapping code. See the comment above
+	 * vmalloc_fault() for details. On x86-64 the race does not
+	 * exist as the vmalloc mappings don't need to be synchronized
+	 * there.
+	 */
+	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+		if (vmalloc_fault(address) >= 0)
+			return;
+	}
+#endif
+
+	if (is_f00f_bug(regs, hw_error_code, address))
+		return;
+
+	/* Was the fault spurious, caused by lazy TLB invalidation? */
+	if (spurious_kernel_fault(hw_error_code, address))
+		return;
+
+	/* kprobes don't want to hook the spurious faults: */
+	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
+		return;
+
+	/*
+	 * Note, despite being a "bad area", there are quite a few
+	 * acceptable reasons to get here, such as erratum fixups
+	 * and handling kernel code that can fault, like get_user().
+	 *
+	 * Don't take the mm semaphore here. If we fixup a prefetch
+	 * fault we could otherwise deadlock:
+	 */
+	bad_area_nosemaphore(regs, hw_error_code, address);
+}
+NOKPROBE_SYMBOL(do_kern_addr_fault);
+
+/*
+ * Handle faults in the user portion of the address space.  Nothing in here
+ * should check X86_PF_USER without a specific justification: for almost
+ * all purposes, we should treat a normal kernel access to user memory
+ * (e.g. get_user(), put_user(), etc.) the same as the WRUSS instruction.
+ * The one exception is AC flag handling, which is, per the x86
+ * architecture, special for WRUSS.
+ */
+static inline
+void do_user_addr_fault(struct pt_regs *regs,
+			unsigned long error_code,
+			unsigned long address)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+	struct mm_struct *mm;
+	vm_fault_t fault;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+
+	tsk = current;
+	mm = tsk->mm;
+
+	if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) {
+		/*
+		 * Whoops, this is kernel mode code trying to execute from
+		 * user memory.  Unless this is AMD erratum #93, which
+		 * corrupts RIP such that it looks like a user address,
+		 * this is unrecoverable.  Don't even try to look up the
+		 * VMA or look for extable entries.
+		 */
+		if (is_errata93(regs, address))
+			return;
+
+		page_fault_oops(regs, error_code, address);
+		return;
+	}
+
+	/* kprobes don't want to hook the spurious faults: */
+	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
+		return;
+
+	/*
+	 * Reserved bits are never expected to be set on
+	 * entries in the user portion of the page tables.
+	 */
+	if (unlikely(error_code & X86_PF_RSVD))
+		pgtable_bad(regs, error_code, address);
+
+	/*
+	 * If SMAP is on, check for invalid kernel (supervisor) access to user
+	 * pages in the user address space.  The odd case here is WRUSS,
+	 * which, according to the preliminary documentation, does not respect
+	 * SMAP and will have the USER bit set so, in all cases, SMAP
+	 * enforcement appears to be consistent with the USER bit.
+	 */
+	if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) &&
+		     !(error_code & X86_PF_USER) &&
+		     !(regs->flags & X86_EFLAGS_AC))) {
+		/*
+		 * No extable entry here.  This was a kernel access to an
+		 * invalid pointer.  get_kernel_nofault() will not get here.
+		 */
+		page_fault_oops(regs, error_code, address);
+		return;
+	}
+
+	/*
+	 * If we're in an interrupt, have no user context or are running
+	 * in a region with pagefaults disabled then we must not take the fault
+	 */
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
+	}
+
+	/* Legacy check - remove this after verifying that it doesn't trigger */
+	if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
+	}
+
+	local_irq_enable();
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
+	/*
+	 * Read-only permissions can not be expressed in shadow stack PTEs.
+	 * Treat all shadow stack accesses as WRITE faults. This ensures
+	 * that the MM will prepare everything (e.g., break COW) such that
+	 * maybe_mkwrite() can create a proper shadow stack PTE.
+	 */
+	if (error_code & X86_PF_SHSTK)
+		flags |= FAULT_FLAG_WRITE;
+	if (error_code & X86_PF_WRITE)
+		flags |= FAULT_FLAG_WRITE;
+	if (error_code & X86_PF_INSTR)
+		flags |= FAULT_FLAG_INSTRUCTION;
+
+	/*
+	 * We set FAULT_FLAG_USER based on the register state, not
+	 * based on X86_PF_USER. User space accesses that cause
+	 * system page faults are still user accesses.
+	 */
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Faults in the vsyscall page might need emulation.  The
+	 * vsyscall page is at a high address (>PAGE_OFFSET), but is
+	 * considered to be part of the user address space.
+	 *
+	 * The vsyscall page does not have a "real" VMA, so do this
+	 * emulation before we go searching for VMAs.
+	 *
+	 * PKRU never rejects instruction fetches, so we don't need
+	 * to consider the PF_PK bit.
+	 */
+	if (is_vsyscall_vaddr(address)) {
+		if (emulate_vsyscall_pf(error_code, regs, address))
+			return;
+	}
+#endif
+
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, address);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(error_code, vma))) {
+		bad_area_access_error(regs, error_code, address, NULL, vma);
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		return;
+	}
+	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
+	/* Quick path to respond to signals */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
+		return;
+	}
+lock_mmap:
+
+retry:
+	vma = lock_mm_and_find_vma(mm, address, regs);
+	if (unlikely(!vma)) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
+	}
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it..
+	 */
+	if (unlikely(access_error(error_code, vma))) {
+		bad_area_access_error(regs, error_code, address, mm, vma);
+		return;
+	}
+
+	/*
+	 * If for any reason at all we couldn't handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.  Since we never set FAULT_FLAG_RETRY_NOWAIT, if
+	 * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked.
+	 *
+	 * Note that handle_userfault() may also release and reacquire mmap_lock
+	 * (and not return with VM_FAULT_RETRY), when returning to userland to
+	 * repeat the page fault later with a VM_FAULT_NOPAGE retval
+	 * (potentially after handling any pending signal during the return to
+	 * userland). The return to userland is identified whenever
+	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
+	 */
+	fault = handle_mm_fault(vma, address, flags, regs);
+
+	if (fault_signal_pending(fault, regs)) {
+		/*
+		 * Quick path to respond to signals.  The core mm code
+		 * has unlocked the mm for us if we get here.
+		 */
+		if (!user_mode(regs))
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR,
+						 ARCH_DEFAULT_PKEY);
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	/*
+	 * If we need to retry the mmap_lock has already been released,
+	 * and if there is a fatal signal pending there is no guarantee
+	 * that we made any progress. Handle this case first.
+	 */
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+		goto retry;
+	}
+
+	mmap_read_unlock(mm);
+done:
+	if (likely(!(fault & VM_FAULT_ERROR)))
+		return;
+
+	if (fatal_signal_pending(current) && !user_mode(regs)) {
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 0, 0, ARCH_DEFAULT_PKEY);
+		return;
+	}
+
+	if (fault & VM_FAULT_OOM) {
+		/* Kernel mode? Handle exceptions or die: */
+		if (!user_mode(regs)) {
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGSEGV, SEGV_MAPERR,
+						 ARCH_DEFAULT_PKEY);
+			return;
+		}
+
+		/*
+		 * We ran out of memory, call the OOM killer, and return the
+		 * userspace (which will retry the fault, or kill us if we got
+		 * oom-killed):
+		 */
+		pagefault_out_of_memory();
+	} else {
+		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+			     VM_FAULT_HWPOISON_LARGE))
+			do_sigbus(regs, error_code, address, fault);
+		else if (fault & VM_FAULT_SIGSEGV)
+			bad_area_nosemaphore(regs, error_code, address);
+		else
+			BUG();
+	}
+}
+NOKPROBE_SYMBOL(do_user_addr_fault);
+
+static __always_inline void
+trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
+			 unsigned long address)
+{
+	if (user_mode(regs))
+		trace_page_fault_user(address, regs, error_code);
+	else
+		trace_page_fault_kernel(address, regs, error_code);
+}
+
+static __always_inline void
+handle_page_fault(struct pt_regs *regs, unsigned long error_code,
+			      unsigned long address)
+{
+	trace_page_fault_entries(regs, error_code, address);
+
+	if (unlikely(kmmio_fault(regs, address)))
+		return;
+
+	/* Was the fault on kernel-controlled part of the address space? */
+	if (unlikely(fault_in_kernel_space(address))) {
+		do_kern_addr_fault(regs, error_code, address);
+	} else {
+		do_user_addr_fault(regs, error_code, address);
+	}
+	/*
+	 * page fault handling might have reenabled interrupts,
+	 * make sure to disable them again.
+	 */
+	local_irq_disable();
+}
+
+DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
+{
+	irqentry_state_t state;
+	unsigned long address;
+
+	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
+
+	/*
+	 * KVM uses #PF vector to deliver 'page not present' events to guests
+	 * (asynchronous page fault mechanism). The event happens when a
+	 * userspace task is trying to access some valid (from guest's point of
+	 * view) memory which is not currently mapped by the host (e.g. the
+	 * memory is swapped out). Note, the corresponding "page ready" event
+	 * which is injected when the memory becomes available, is delivered via
+	 * an interrupt mechanism and not a #PF exception
+	 * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()).
+	 *
+	 * We are relying on the interrupted context being sane (valid RSP,
+	 * relevant locks not held, etc.), which is fine as long as the
+	 * interrupted context had IF=1.  We are also relying on the KVM
+	 * async pf type field and CR2 being read consistently instead of
+	 * getting values from real and async page faults mixed up.
+	 *
+	 * Fingers crossed.
+	 *
+	 * The async #PF handling code takes care of idtentry handling
+	 * itself.
+	 */
+	if (kvm_handle_async_pf(regs, (u32)address))
+		return;
+
+	/*
+	 * Entry handling for valid #PF from kernel mode is slightly
+	 * different: RCU is already watching and ct_irq_enter() must not
+	 * be invoked because a kernel fault on a user space address might
+	 * sleep.
+	 *
+	 * In case the fault hit a RCU idle region the conditional entry
+	 * code reenabled RCU to avoid subsequent wreckage which helps
+	 * debuggability.
+	 */
+	state = irqentry_enter(regs);
+
+	instrumentation_begin();
+	handle_page_fault(regs, error_code, address);
+	instrumentation_end();
+
+	irqentry_exit(regs, state);
+}
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
new file mode 100644
index 000000000..3b26621c9
--- /dev/null
+++ b/arch/x86/mm/hugetlbpage.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * IA-32 Huge TLB Page Support for Kernel.
+ *
+ * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
+ */
+
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/sched/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/err.h>
+#include <linux/sysctl.h>
+#include <linux/compat.h>
+#include <asm/mman.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/elf.h>
+
+
+#ifdef CONFIG_X86_64
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	if (size == PMD_SIZE)
+		return true;
+	else if (size == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES))
+		return true;
+	else
+		return false;
+}
+
+#ifdef CONFIG_CONTIG_ALLOC
+static __init int gigantic_pages_init(void)
+{
+	/* With compaction or CMA we can allocate gigantic pages at runtime */
+	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	return 0;
+}
+arch_initcall(gigantic_pages_init);
+#endif
+#endif
+
+unsigned int __init arch_hugetlb_cma_order(void)
+{
+	if (boot_cpu_has(X86_FEATURE_GBPAGES))
+		return PUD_SHIFT - PAGE_SHIFT;
+
+	return 0;
+}
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
new file mode 100644
index 000000000..5a15bffe6
--- /dev/null
+++ b/arch/x86/mm/ident_map.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Helper routines for building identity mapping page tables. This is
+ * included by both the compressed kernel and the regular kernel.
+ */
+
+static void free_pte(struct x86_mapping_info *info, pmd_t *pmd)
+{
+	pte_t *pte = pte_offset_kernel(pmd, 0);
+
+	info->free_pgt_page(pte, info->context);
+}
+
+static void free_pmd(struct x86_mapping_info *info, pud_t *pud)
+{
+	pmd_t *pmd = pmd_offset(pud, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_present(pmd[i]))
+			continue;
+
+		if (pmd_leaf(pmd[i]))
+			continue;
+
+		free_pte(info, &pmd[i]);
+	}
+
+	info->free_pgt_page(pmd, info->context);
+}
+
+static void free_pud(struct x86_mapping_info *info, p4d_t *p4d)
+{
+	pud_t *pud = pud_offset(p4d, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		if (!pud_present(pud[i]))
+			continue;
+
+		if (pud_leaf(pud[i]))
+			continue;
+
+		free_pmd(info, &pud[i]);
+	}
+
+	info->free_pgt_page(pud, info->context);
+}
+
+static void free_p4d(struct x86_mapping_info *info, pgd_t *pgd)
+{
+	p4d_t *p4d = p4d_offset(pgd, 0);
+	int i;
+
+	for (i = 0; i < PTRS_PER_P4D; i++) {
+		if (!p4d_present(p4d[i]))
+			continue;
+
+		free_pud(info, &p4d[i]);
+	}
+
+	if (pgtable_l5_enabled())
+		info->free_pgt_page(p4d, info->context);
+}
+
+void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		if (!pgd_present(pgd[i]))
+			continue;
+
+		free_p4d(info, &pgd[i]);
+	}
+
+	info->free_pgt_page(pgd, info->context);
+}
+
+static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
+			   unsigned long addr, unsigned long end)
+{
+	addr &= PMD_MASK;
+	for (; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+
+		if (pmd_present(*pmd))
+			continue;
+
+		set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
+	}
+}
+
+static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+		bool use_gbpage;
+
+		next = pud_addr_end(addr, end);
+
+		/* if this is already a gbpage, this portion is already mapped */
+		if (pud_leaf(*pud))
+			continue;
+
+		/* Is using a gbpage allowed? */
+		use_gbpage = info->direct_gbpages;
+
+		/* Don't use gbpage if it maps more than the requested region. */
+		/* at the beginning: */
+		use_gbpage &= ((addr & ~PUD_MASK) == 0);
+		/* ... or at the end: */
+		use_gbpage &= ((next & ~PUD_MASK) == 0);
+
+		/* Never overwrite existing mappings */
+		use_gbpage &= !pud_present(*pud);
+
+		if (use_gbpage) {
+			pud_t pudval;
+
+			pudval = __pud((addr - info->offset) | info->page_flag);
+			set_pud(pud, pudval);
+			continue;
+		}
+
+		if (pud_present(*pud)) {
+			pmd = pmd_offset(pud, 0);
+			ident_pmd_init(info, pmd, addr, next);
+			continue;
+		}
+		pmd = (pmd_t *)info->alloc_pgt_page(info->context);
+		if (!pmd)
+			return -ENOMEM;
+		ident_pmd_init(info, pmd, addr, next);
+		set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag));
+	}
+
+	return 0;
+}
+
+static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
+			  unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	int result;
+
+	for (; addr < end; addr = next) {
+		p4d_t *p4d = p4d_page + p4d_index(addr);
+		pud_t *pud;
+
+		next = p4d_addr_end(addr, end);
+		if (p4d_present(*p4d)) {
+			pud = pud_offset(p4d, 0);
+			result = ident_pud_init(info, pud, addr, next);
+			if (result)
+				return result;
+
+			continue;
+		}
+		pud = (pud_t *)info->alloc_pgt_page(info->context);
+		if (!pud)
+			return -ENOMEM;
+
+		result = ident_pud_init(info, pud, addr, next);
+		if (result)
+			return result;
+
+		set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
+	}
+
+	return 0;
+}
+
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+			      unsigned long pstart, unsigned long pend)
+{
+	unsigned long addr = pstart + info->offset;
+	unsigned long end = pend + info->offset;
+	unsigned long next;
+	int result;
+
+	/* Set the default pagetable flags if not supplied */
+	if (!info->kernpg_flag)
+		info->kernpg_flag = _KERNPG_TABLE;
+
+	/* Filter out unsupported __PAGE_KERNEL_* bits: */
+	info->kernpg_flag &= __default_kernel_pte_mask;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_page + pgd_index(addr);
+		p4d_t *p4d;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_present(*pgd)) {
+			p4d = p4d_offset(pgd, 0);
+			result = ident_p4d_init(info, p4d, addr, next);
+			if (result)
+				return result;
+			continue;
+		}
+
+		p4d = (p4d_t *)info->alloc_pgt_page(info->context);
+		if (!p4d)
+			return -ENOMEM;
+		result = ident_p4d_init(info, p4d, addr, next);
+		if (result)
+			return result;
+		if (pgtable_l5_enabled()) {
+			set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag | _PAGE_NOPTISHADOW));
+		} else {
+			/*
+			 * With p4d folded, pgd is equal to p4d.
+			 * The pgd entry has to point to the pud page table in this case.
+			 */
+			pud_t *pud = pud_offset(p4d, 0);
+			set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag | _PAGE_NOPTISHADOW));
+		}
+	}
+
+	return 0;
+}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
new file mode 100644
index 000000000..079f8c7e9
--- /dev/null
+++ b/arch/x86/mm/init.c
@@ -0,0 +1,1128 @@
+#include <linux/gfp.h>
+#include <linux/initrd.h>
+#include <linux/ioport.h>
+#include <linux/swap.h>
+#include <linux/memblock.h>
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
+#include <linux/kmemleak.h>
+#include <linux/sched/task.h>
+#include <linux/execmem.h>
+
+#include <asm/set_memory.h>
+#include <asm/cpu_device_id.h>
+#include <asm/e820/api.h>
+#include <asm/init.h>
+#include <asm/page.h>
+#include <asm/page_types.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+#include <asm/proto.h>
+#include <asm/dma.h>		/* for MAX_DMA_PFN */
+#include <asm/kaslr.h>
+#include <asm/hypervisor.h>
+#include <asm/cpufeature.h>
+#include <asm/pti.h>
+#include <asm/text-patching.h>
+#include <asm/memtype.h>
+#include <asm/mmu_context.h>
+
+/*
+ * We need to define the tracepoints somewhere, and tlb.c
+ * is only compiled when SMP=y.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/tlb.h>
+
+#include "mm_internal.h"
+
+/*
+ * Tables translating between page_cache_type_t and pte encoding.
+ *
+ * The default values are defined statically as minimal supported mode;
+ * WC and WT fall back to UC-.  pat_init() updates these values to support
+ * more cache modes, WC and WT, when it is safe to do so.  See pat_init()
+ * for the details.  Note, __early_ioremap() used during early boot-time
+ * takes pgprot_t (pte encoding) and does not use these tables.
+ *
+ *   Index into __cachemode2pte_tbl[] is the cachemode.
+ *
+ *   Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte
+ *   (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2.
+ */
+static uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
+	[_PAGE_CACHE_MODE_WB      ]	= 0         | 0        ,
+	[_PAGE_CACHE_MODE_WC      ]	= 0         | _PAGE_PCD,
+	[_PAGE_CACHE_MODE_UC_MINUS]	= 0         | _PAGE_PCD,
+	[_PAGE_CACHE_MODE_UC      ]	= _PAGE_PWT | _PAGE_PCD,
+	[_PAGE_CACHE_MODE_WT      ]	= 0         | _PAGE_PCD,
+	[_PAGE_CACHE_MODE_WP      ]	= 0         | _PAGE_PCD,
+};
+
+unsigned long cachemode2protval(enum page_cache_mode pcm)
+{
+	if (likely(pcm == 0))
+		return 0;
+	return __cachemode2pte_tbl[pcm];
+}
+EXPORT_SYMBOL(cachemode2protval);
+
+static uint8_t __pte2cachemode_tbl[8] = {
+	[__pte2cm_idx( 0        | 0         | 0        )] = _PAGE_CACHE_MODE_WB,
+	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx( 0        | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC,
+	[__pte2cm_idx( 0        | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
+	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx(0         | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
+	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
+};
+
+/*
+ * Check that the write-protect PAT entry is set for write-protect.
+ * To do this without making assumptions how PAT has been set up (Xen has
+ * another layout than the kernel), translate the _PAGE_CACHE_MODE_WP cache
+ * mode via the __cachemode2pte_tbl[] into protection bits (those protection
+ * bits will select a cache mode of WP or better), and then translate the
+ * protection bits back into the cache mode using __pte2cm_idx() and the
+ * __pte2cachemode_tbl[] array. This will return the really used cache mode.
+ */
+bool x86_has_pat_wp(void)
+{
+	uint16_t prot = __cachemode2pte_tbl[_PAGE_CACHE_MODE_WP];
+
+	return __pte2cachemode_tbl[__pte2cm_idx(prot)] == _PAGE_CACHE_MODE_WP;
+}
+
+enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
+{
+	unsigned long masked;
+
+	masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK;
+	if (likely(masked == 0))
+		return 0;
+	return __pte2cachemode_tbl[__pte2cm_idx(masked)];
+}
+
+static unsigned long __initdata pgt_buf_start;
+static unsigned long __initdata pgt_buf_end;
+static unsigned long __initdata pgt_buf_top;
+
+static unsigned long min_pfn_mapped;
+
+static bool __initdata can_use_brk_pgt = true;
+
+/*
+ * Pages returned are already directly mapped.
+ *
+ * Changing that is likely to break Xen, see commit:
+ *
+ *    279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve
+ *
+ * for detailed information.
+ */
+__ref void *alloc_low_pages(unsigned int num)
+{
+	unsigned long pfn;
+	int i;
+
+	if (after_bootmem) {
+		unsigned int order;
+
+		order = get_order((unsigned long)num << PAGE_SHIFT);
+		return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
+	}
+
+	if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
+		unsigned long ret = 0;
+
+		if (min_pfn_mapped < max_pfn_mapped) {
+			ret = memblock_phys_alloc_range(
+					PAGE_SIZE * num, PAGE_SIZE,
+					min_pfn_mapped << PAGE_SHIFT,
+					max_pfn_mapped << PAGE_SHIFT);
+		}
+		if (!ret && can_use_brk_pgt)
+			ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE));
+
+		if (!ret)
+			panic("alloc_low_pages: can not alloc memory");
+
+		pfn = ret >> PAGE_SHIFT;
+	} else {
+		pfn = pgt_buf_end;
+		pgt_buf_end += num;
+	}
+
+	for (i = 0; i < num; i++) {
+		void *adr;
+
+		adr = __va((pfn + i) << PAGE_SHIFT);
+		clear_page(adr);
+	}
+
+	return __va(pfn << PAGE_SHIFT);
+}
+
+/*
+ * By default need to be able to allocate page tables below PGD firstly for
+ * the 0-ISA_END_ADDRESS range and secondly for the initial PMD_SIZE mapping.
+ * With KASLR memory randomization, depending on the machine e820 memory and the
+ * PUD alignment, twice that many pages may be needed when KASLR memory
+ * randomization is enabled.
+ */
+
+#define INIT_PGD_PAGE_TABLES    4
+
+#ifndef CONFIG_RANDOMIZE_MEMORY
+#define INIT_PGD_PAGE_COUNT      (2 * INIT_PGD_PAGE_TABLES)
+#else
+#define INIT_PGD_PAGE_COUNT      (4 * INIT_PGD_PAGE_TABLES)
+#endif
+
+#define INIT_PGT_BUF_SIZE	(INIT_PGD_PAGE_COUNT * PAGE_SIZE)
+RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
+void  __init early_alloc_pgt_buf(void)
+{
+	unsigned long tables = INIT_PGT_BUF_SIZE;
+	phys_addr_t base;
+
+	base = __pa(extend_brk(tables, PAGE_SIZE));
+
+	pgt_buf_start = base >> PAGE_SHIFT;
+	pgt_buf_end = pgt_buf_start;
+	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
+}
+
+int after_bootmem;
+
+early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES);
+
+struct map_range {
+	unsigned long start;
+	unsigned long end;
+	unsigned page_size_mask;
+};
+
+static int page_size_mask;
+
+/*
+ * Save some of cr4 feature set we're using (e.g.  Pentium 4MB
+ * enable and PPro Global page enable), so that any CPU's that boot
+ * up after us can get the correct flags. Invoked on the boot CPU.
+ */
+static inline void cr4_set_bits_and_update_boot(unsigned long mask)
+{
+	mmu_cr4_features |= mask;
+	if (trampoline_cr4_features)
+		*trampoline_cr4_features = mmu_cr4_features;
+	cr4_set_bits(mask);
+}
+
+static void __init probe_page_size_mask(void)
+{
+	/*
+	 * For pagealloc debugging, identity mapping will use small pages.
+	 * This will simplify cpa(), which otherwise needs to support splitting
+	 * large pages into small in interrupt context, etc.
+	 */
+	if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
+		page_size_mask |= 1 << PG_LEVEL_2M;
+	else
+		direct_gbpages = 0;
+
+	/* Enable PSE if available */
+	if (boot_cpu_has(X86_FEATURE_PSE))
+		cr4_set_bits_and_update_boot(X86_CR4_PSE);
+
+	/* Enable PGE if available */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
+		cr4_set_bits_and_update_boot(X86_CR4_PGE);
+		__supported_pte_mask |= _PAGE_GLOBAL;
+	}
+
+	/* By the default is everything supported: */
+	__default_kernel_pte_mask = __supported_pte_mask;
+	/* Except when with PTI where the kernel is mostly non-Global: */
+	if (cpu_feature_enabled(X86_FEATURE_PTI))
+		__default_kernel_pte_mask &= ~_PAGE_GLOBAL;
+
+	/* Enable 1 GB linear kernel mappings if available: */
+	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
+		printk(KERN_INFO "Using GB pages for direct mapping\n");
+		page_size_mask |= 1 << PG_LEVEL_1G;
+	} else {
+		direct_gbpages = 0;
+	}
+}
+
+/*
+ * INVLPG may not properly flush Global entries on
+ * these CPUs.  New microcode fixes the issue.
+ */
+static const struct x86_cpu_id invlpg_miss_ids[] = {
+	X86_MATCH_VFM(INTEL_ALDERLAKE,	    0x2e),
+	X86_MATCH_VFM(INTEL_ALDERLAKE_L,    0x42c),
+	X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, 0x11),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE,	    0x118),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_P,   0x4117),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,   0x2e),
+	{}
+};
+
+static void setup_pcid(void)
+{
+	const struct x86_cpu_id *invlpg_miss_match;
+
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_PCID))
+		return;
+
+	invlpg_miss_match = x86_match_cpu(invlpg_miss_ids);
+
+	if (invlpg_miss_match &&
+	    boot_cpu_data.microcode < invlpg_miss_match->driver_data) {
+		pr_info("Incomplete global flushes, disabling PCID");
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
+		return;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
+		/*
+		 * This can't be cr4_set_bits_and_update_boot() -- the
+		 * trampoline code can't handle CR4.PCIDE and it wouldn't
+		 * do any good anyway.  Despite the name,
+		 * cr4_set_bits_and_update_boot() doesn't actually cause
+		 * the bits in question to remain set all the way through
+		 * the secondary boot asm.
+		 *
+		 * Instead, we brute-force it and set CR4.PCIDE manually in
+		 * start_secondary().
+		 */
+		cr4_set_bits(X86_CR4_PCIDE);
+	} else {
+		/*
+		 * flush_tlb_all(), as currently implemented, won't work if
+		 * PCID is on but PGE is not.  Since that combination
+		 * doesn't exist on real hardware, there's no reason to try
+		 * to fully support it, but it's polite to avoid corrupting
+		 * data if we're on an improperly configured VM.
+		 */
+		setup_clear_cpu_cap(X86_FEATURE_PCID);
+	}
+}
+
+#ifdef CONFIG_X86_32
+#define NR_RANGE_MR 3
+#else /* CONFIG_X86_64 */
+#define NR_RANGE_MR 5
+#endif
+
+static int __meminit save_mr(struct map_range *mr, int nr_range,
+			     unsigned long start_pfn, unsigned long end_pfn,
+			     unsigned long page_size_mask)
+{
+	if (start_pfn < end_pfn) {
+		if (nr_range >= NR_RANGE_MR)
+			panic("run out of range for init_memory_mapping\n");
+		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
+		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
+		mr[nr_range].page_size_mask = page_size_mask;
+		nr_range++;
+	}
+
+	return nr_range;
+}
+
+/*
+ * adjust the page_size_mask for small range to go with
+ *	big page size instead small one if nearby are ram too.
+ */
+static void __ref adjust_range_page_size_mask(struct map_range *mr,
+							 int nr_range)
+{
+	int i;
+
+	for (i = 0; i < nr_range; i++) {
+		if ((page_size_mask & (1<<PG_LEVEL_2M)) &&
+		    !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) {
+			unsigned long start = round_down(mr[i].start, PMD_SIZE);
+			unsigned long end = round_up(mr[i].end, PMD_SIZE);
+
+#ifdef CONFIG_X86_32
+			if ((end >> PAGE_SHIFT) > max_low_pfn)
+				continue;
+#endif
+
+			if (memblock_is_region_memory(start, end - start))
+				mr[i].page_size_mask |= 1<<PG_LEVEL_2M;
+		}
+		if ((page_size_mask & (1<<PG_LEVEL_1G)) &&
+		    !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) {
+			unsigned long start = round_down(mr[i].start, PUD_SIZE);
+			unsigned long end = round_up(mr[i].end, PUD_SIZE);
+
+			if (memblock_is_region_memory(start, end - start))
+				mr[i].page_size_mask |= 1<<PG_LEVEL_1G;
+		}
+	}
+}
+
+static const char *page_size_string(struct map_range *mr)
+{
+	static const char str_1g[] = "1G";
+	static const char str_2m[] = "2M";
+	static const char str_4m[] = "4M";
+	static const char str_4k[] = "4k";
+
+	if (mr->page_size_mask & (1<<PG_LEVEL_1G))
+		return str_1g;
+	/*
+	 * 32-bit without PAE has a 4M large page size.
+	 * PG_LEVEL_2M is misnamed, but we can at least
+	 * print out the right size in the string.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32) &&
+	    !IS_ENABLED(CONFIG_X86_PAE) &&
+	    mr->page_size_mask & (1<<PG_LEVEL_2M))
+		return str_4m;
+
+	if (mr->page_size_mask & (1<<PG_LEVEL_2M))
+		return str_2m;
+
+	return str_4k;
+}
+
+static int __meminit split_mem_range(struct map_range *mr, int nr_range,
+				     unsigned long start,
+				     unsigned long end)
+{
+	unsigned long start_pfn, end_pfn, limit_pfn;
+	unsigned long pfn;
+	int i;
+
+	limit_pfn = PFN_DOWN(end);
+
+	/* head if not big page alignment ? */
+	pfn = start_pfn = PFN_DOWN(start);
+#ifdef CONFIG_X86_32
+	/*
+	 * Don't use a large page for the first 2/4MB of memory
+	 * because there are often fixed size MTRRs in there
+	 * and overlapping MTRRs into large pages can cause
+	 * slowdowns.
+	 */
+	if (pfn == 0)
+		end_pfn = PFN_DOWN(PMD_SIZE);
+	else
+		end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
+#else /* CONFIG_X86_64 */
+	end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
+#endif
+	if (end_pfn > limit_pfn)
+		end_pfn = limit_pfn;
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+		pfn = end_pfn;
+	}
+
+	/* big page (2M) range */
+	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
+#ifdef CONFIG_X86_32
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
+#else /* CONFIG_X86_64 */
+	end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
+	if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE)))
+		end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
+#endif
+
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pfn = end_pfn;
+	}
+
+#ifdef CONFIG_X86_64
+	/* big page (1G) range */
+	start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE));
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask &
+				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+		pfn = end_pfn;
+	}
+
+	/* tail is not big page (1G) alignment */
+	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
+	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pfn = end_pfn;
+	}
+#endif
+
+	/* tail is not big page (2M) alignment */
+	start_pfn = pfn;
+	end_pfn = limit_pfn;
+	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+
+	if (!after_bootmem)
+		adjust_range_page_size_mask(mr, nr_range);
+
+	/* try to merge same page size and continuous */
+	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
+		unsigned long old_start;
+		if (mr[i].end != mr[i+1].start ||
+		    mr[i].page_size_mask != mr[i+1].page_size_mask)
+			continue;
+		/* move it */
+		old_start = mr[i].start;
+		memmove(&mr[i], &mr[i+1],
+			(nr_range - 1 - i) * sizeof(struct map_range));
+		mr[i--].start = old_start;
+		nr_range--;
+	}
+
+	for (i = 0; i < nr_range; i++)
+		pr_debug(" [mem %#010lx-%#010lx] page %s\n",
+				mr[i].start, mr[i].end - 1,
+				page_size_string(&mr[i]));
+
+	return nr_range;
+}
+
+struct range pfn_mapped[E820_MAX_ENTRIES];
+int nr_pfn_mapped;
+
+static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES,
+					     nr_pfn_mapped, start_pfn, end_pfn);
+	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES);
+
+	max_pfn_mapped = max(max_pfn_mapped, end_pfn);
+
+	if (start_pfn < (1UL<<(32-PAGE_SHIFT)))
+		max_low_pfn_mapped = max(max_low_pfn_mapped,
+					 min(end_pfn, 1UL<<(32-PAGE_SHIFT)));
+}
+
+bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_pfn_mapped; i++)
+		if ((start_pfn >= pfn_mapped[i].start) &&
+		    (end_pfn <= pfn_mapped[i].end))
+			return true;
+
+	return false;
+}
+
+/*
+ * Setup the direct mapping of the physical memory at PAGE_OFFSET.
+ * This runs before bootmem is initialized and gets pages directly from
+ * the physical memory. To access them they are temporarily mapped.
+ */
+unsigned long __ref init_memory_mapping(unsigned long start,
+					unsigned long end, pgprot_t prot)
+{
+	struct map_range mr[NR_RANGE_MR];
+	unsigned long ret = 0;
+	int nr_range, i;
+
+	pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n",
+	       start, end - 1);
+
+	memset(mr, 0, sizeof(mr));
+	nr_range = split_mem_range(mr, 0, start, end);
+
+	for (i = 0; i < nr_range; i++)
+		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
+						   mr[i].page_size_mask,
+						   prot);
+
+	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);
+
+	return ret >> PAGE_SHIFT;
+}
+
+/*
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
+ */
+static unsigned long __init init_range_memory_mapping(
+					   unsigned long r_start,
+					   unsigned long r_end)
+{
+	unsigned long start_pfn, end_pfn;
+	unsigned long mapped_ram_size = 0;
+	int i;
+
+	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+		u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end);
+		u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end);
+		if (start >= end)
+			continue;
+
+		/*
+		 * if it is overlapping with brk pgt, we need to
+		 * alloc pgt buf from memblock instead.
+		 */
+		can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >=
+				    min(end, (u64)pgt_buf_top<<PAGE_SHIFT);
+		init_memory_mapping(start, end, PAGE_KERNEL);
+		mapped_ram_size += end - start;
+		can_use_brk_pgt = true;
+	}
+
+	return mapped_ram_size;
+}
+
+static unsigned long __init get_new_step_size(unsigned long step_size)
+{
+	/*
+	 * Initial mapped size is PMD_SIZE (2M).
+	 * We can not set step_size to be PUD_SIZE (1G) yet.
+	 * In worse case, when we cross the 1G boundary, and
+	 * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
+	 * to map 1G range with PTE. Hence we use one less than the
+	 * difference of page table level shifts.
+	 *
+	 * Don't need to worry about overflow in the top-down case, on 32bit,
+	 * when step_size is 0, round_down() returns 0 for start, and that
+	 * turns it into 0x100000000ULL.
+	 * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+	 * needs to be taken into consideration by the code below.
+	 */
+	return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
+}
+
+/**
+ * memory_map_top_down - Map [map_start, map_end) top down
+ * @map_start: start address of the target memory range
+ * @map_end: end address of the target memory range
+ *
+ * This function will setup direct mapping for memory range
+ * [map_start, map_end) in top-down. That said, the page tables
+ * will be allocated at the end of the memory, and we map the
+ * memory in top-down.
+ */
+static void __init memory_map_top_down(unsigned long map_start,
+				       unsigned long map_end)
+{
+	unsigned long real_end, last_start;
+	unsigned long step_size;
+	unsigned long addr;
+	unsigned long mapped_ram_size = 0;
+
+	/*
+	 * Systems that have many reserved areas near top of the memory,
+	 * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will
+	 * require lots of 4K mappings which may exhaust pgt_buf.
+	 * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure
+	 * there is enough mapped memory that can be allocated from
+	 * memblock.
+	 */
+	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
+					 map_end);
+	if (!addr) {
+		pr_warn("Failed to release memory for alloc_low_pages()");
+		real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE));
+	} else {
+		memblock_phys_free(addr, PMD_SIZE);
+		real_end = addr + PMD_SIZE;
+	}
+
+	/* step_size need to be small so pgt_buf from BRK could cover it */
+	step_size = PMD_SIZE;
+	max_pfn_mapped = 0; /* will get exact value next */
+	min_pfn_mapped = real_end >> PAGE_SHIFT;
+	last_start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
+	while (last_start > map_start) {
+		unsigned long start;
+
+		if (last_start > step_size) {
+			start = round_down(last_start - 1, step_size);
+			if (start < map_start)
+				start = map_start;
+		} else
+			start = map_start;
+		mapped_ram_size += init_range_memory_mapping(start,
+							last_start);
+		last_start = start;
+		min_pfn_mapped = last_start >> PAGE_SHIFT;
+		if (mapped_ram_size >= step_size)
+			step_size = get_new_step_size(step_size);
+	}
+
+	if (real_end < map_end)
+		init_range_memory_mapping(real_end, map_end);
+}
+
+/**
+ * memory_map_bottom_up - Map [map_start, map_end) bottom up
+ * @map_start: start address of the target memory range
+ * @map_end: end address of the target memory range
+ *
+ * This function will setup direct mapping for memory range
+ * [map_start, map_end) in bottom-up. Since we have limited the
+ * bottom-up allocation above the kernel, the page tables will
+ * be allocated just above the kernel and we map the memory
+ * in [map_start, map_end) in bottom-up.
+ */
+static void __init memory_map_bottom_up(unsigned long map_start,
+					unsigned long map_end)
+{
+	unsigned long next, start;
+	unsigned long mapped_ram_size = 0;
+	/* step_size need to be small so pgt_buf from BRK could cover it */
+	unsigned long step_size = PMD_SIZE;
+
+	start = map_start;
+	min_pfn_mapped = start >> PAGE_SHIFT;
+
+	/*
+	 * We start from the bottom (@map_start) and go to the top (@map_end).
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
+	while (start < map_end) {
+		if (step_size && map_end - start > step_size) {
+			next = round_up(start + 1, step_size);
+			if (next > map_end)
+				next = map_end;
+		} else {
+			next = map_end;
+		}
+
+		mapped_ram_size += init_range_memory_mapping(start, next);
+		start = next;
+
+		if (mapped_ram_size >= step_size)
+			step_size = get_new_step_size(step_size);
+	}
+}
+
+/*
+ * The real mode trampoline, which is required for bootstrapping CPUs
+ * occupies only a small area under the low 1MB.  See reserve_real_mode()
+ * for details.
+ *
+ * If KASLR is disabled the first PGD entry of the direct mapping is copied
+ * to map the real mode trampoline.
+ *
+ * If KASLR is enabled, copy only the PUD which covers the low 1MB
+ * area. This limits the randomization granularity to 1GB for both 4-level
+ * and 5-level paging.
+ */
+static void __init init_trampoline(void)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * The code below will alias kernel page-tables in the user-range of the
+	 * address space, including the Global bit. So global TLB entries will
+	 * be created when using the trampoline page-table.
+	 */
+	if (!kaslr_memory_enabled())
+		trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
+	else
+		init_trampoline_kaslr();
+#endif
+}
+
+void __init init_mem_mapping(void)
+{
+	unsigned long end;
+
+	pti_check_boottime_disable();
+	probe_page_size_mask();
+	setup_pcid();
+
+#ifdef CONFIG_X86_64
+	end = max_pfn << PAGE_SHIFT;
+#else
+	end = max_low_pfn << PAGE_SHIFT;
+#endif
+
+	/* the ISA range is always mapped regardless of memory holes */
+	init_memory_mapping(0, ISA_END_ADDRESS, PAGE_KERNEL);
+
+	/* Init the trampoline, possibly with KASLR memory offset */
+	init_trampoline();
+
+	/*
+	 * If the allocation is in bottom-up direction, we setup direct mapping
+	 * in bottom-up, otherwise we setup direct mapping in top-down.
+	 */
+	if (memblock_bottom_up()) {
+		unsigned long kernel_end = __pa_symbol(_end);
+
+		/*
+		 * we need two separate calls here. This is because we want to
+		 * allocate page tables above the kernel. So we first map
+		 * [kernel_end, end) to make memory above the kernel be mapped
+		 * as soon as possible. And then use page tables allocated above
+		 * the kernel to map [ISA_END_ADDRESS, kernel_end).
+		 */
+		memory_map_bottom_up(kernel_end, end);
+		memory_map_bottom_up(ISA_END_ADDRESS, kernel_end);
+	} else {
+		memory_map_top_down(ISA_END_ADDRESS, end);
+	}
+
+#ifdef CONFIG_X86_64
+	if (max_pfn > max_low_pfn) {
+		/* can we preserve max_low_pfn ?*/
+		max_low_pfn = max_pfn;
+	}
+#else
+	early_ioremap_page_table_range_init();
+#endif
+
+	load_cr3(swapper_pg_dir);
+	__flush_tlb_all();
+
+	x86_init.hyper.init_mem_mapping();
+
+	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
+}
+
+/*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	text_poke_mm = mm_alloc();
+	BUG_ON(!text_poke_mm);
+
+	/* Xen PV guests need the PGD to be pinned. */
+	paravirt_enter_mmap(text_poke_mm);
+
+	set_notrack_mm(text_poke_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	text_poke_mm_addr = TASK_UNMAPPED_BASE;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		text_poke_mm_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((text_poke_mm_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		text_poke_mm_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
+/*
+ * devmem_is_allowed() checks to see if /dev/mem access to a certain address
+ * is valid. The argument is a physical page number.
+ *
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
+ */
+int devmem_is_allowed(unsigned long pagenr)
+{
+	if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE,
+				IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
+			!= REGION_DISJOINT) {
+		/*
+		 * For disallowed memory regions in the low 1MB range,
+		 * request that the page be shown as all zeros.
+		 */
+		if (pagenr < 256)
+			return 2;
+
+		return 0;
+	}
+
+	/*
+	 * This must follow RAM test, since System RAM is considered a
+	 * restricted resource under CONFIG_STRICT_DEVMEM.
+	 */
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+		/* Low 1MB bypasses iomem restrictions. */
+		if (pagenr < 256)
+			return 1;
+
+		return 0;
+	}
+
+	return 1;
+}
+
+void free_init_pages(const char *what, unsigned long begin, unsigned long end)
+{
+	unsigned long begin_aligned, end_aligned;
+
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	if (begin >= end)
+		return;
+
+	/*
+	 * If debugging page accesses then do not free this memory but
+	 * mark them not present - any buggy init-section access will
+	 * create a kernel page fault:
+	 */
+	if (debug_pagealloc_enabled()) {
+		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
+			begin, end - 1);
+		/*
+		 * Inform kmemleak about the hole in the memory since the
+		 * corresponding pages will be unmapped.
+		 */
+		kmemleak_free_part((void *)begin, end - begin);
+		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+	} else {
+		/*
+		 * We just marked the kernel text read only above, now that
+		 * we are going to free part of that, we need to make that
+		 * writeable and non-executable first.
+		 */
+		set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
+		set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
+
+		free_reserved_area((void *)begin, (void *)end,
+				   POISON_FREE_INITMEM, what);
+	}
+}
+
+/*
+ * begin/end can be in the direct map or the "high kernel mapping"
+ * used for the kernel image only.  free_init_pages() will do the
+ * right thing for either kind of address.
+ */
+void free_kernel_image_pages(const char *what, void *begin, void *end)
+{
+	unsigned long begin_ul = (unsigned long)begin;
+	unsigned long end_ul = (unsigned long)end;
+	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
+
+	free_init_pages(what, begin_ul, end_ul);
+
+	/*
+	 * PTI maps some of the kernel into userspace.  For performance,
+	 * this includes some kernel areas that do not contain secrets.
+	 * Those areas might be adjacent to the parts of the kernel image
+	 * being freed, which may contain secrets.  Remove the "high kernel
+	 * image mapping" for these freed areas, ensuring they are not even
+	 * potentially vulnerable to Meltdown regardless of the specific
+	 * optimizations PTI is currently using.
+	 *
+	 * The "noalias" prevents unmapping the direct map alias which is
+	 * needed to access the freed pages.
+	 *
+	 * This is only valid for 64bit kernels. 32bit has only one mapping
+	 * which can't be treated in this way for obvious reasons.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
+		set_memory_np_noalias(begin_ul, len_pages);
+}
+
+void __ref free_initmem(void)
+{
+	e820__reallocate_tables();
+
+	mem_encrypt_free_decrypted_mem();
+
+	free_kernel_image_pages("unused kernel image (initmem)",
+				&__init_begin, &__init_end);
+}
+
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompressor could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd", start, PAGE_ALIGN(end));
+}
+#endif
+
+void __init arch_zone_limits_init(unsigned long *max_zone_pfns)
+{
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA]		= min(MAX_DMA_PFN, max_low_pfn);
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	max_zone_pfns[ZONE_DMA32]	= min(MAX_DMA32_PFN, max_low_pfn);
+#endif
+	max_zone_pfns[ZONE_NORMAL]	= max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+	max_zone_pfns[ZONE_HIGHMEM]	= max_pfn;
+#endif
+}
+
+__visible DEFINE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+	.loaded_mm = &init_mm,
+	.next_asid = 1,
+	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
+};
+
+#ifdef CONFIG_ADDRESS_MASKING
+DEFINE_PER_CPU(u64, tlbstate_untag_mask);
+EXPORT_PER_CPU_SYMBOL(tlbstate_untag_mask);
+#endif
+
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
+{
+	/* entry 0 MUST be WB (hardwired to speed up translations) */
+	BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB);
+
+	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
+	__pte2cachemode_tbl[entry] = cache;
+}
+
+#ifdef CONFIG_SWAP
+unsigned long arch_max_swapfile_size(void)
+{
+	unsigned long pages;
+
+	pages = generic_max_swapfile_size();
+
+	if (boot_cpu_has_bug(X86_BUG_L1TF) && l1tf_mitigation != L1TF_MITIGATION_OFF) {
+		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+		unsigned long long l1tf_limit = l1tf_pfn_limit();
+		/*
+		 * We encode swap offsets also with 3 bits below those for pfn
+		 * which makes the usable limit higher.
+		 */
+#if CONFIG_PGTABLE_LEVELS > 2
+		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+		pages = min_t(unsigned long long, l1tf_limit, pages);
+	}
+	return pages;
+}
+#endif
+
+#ifdef CONFIG_EXECMEM
+static struct execmem_info execmem_info __ro_after_init;
+
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
+void execmem_fill_trapping_insns(void *ptr, size_t size)
+{
+	memset(ptr, INT3_INSN_OPCODE, size);
+}
+#endif
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	unsigned long start, offset = 0;
+	enum execmem_range_flags flags;
+	pgprot_t pgprot;
+
+	if (kaslr_enabled())
+		offset = get_random_u32_inclusive(1, 1024) * PAGE_SIZE;
+
+	start = MODULES_VADDR + offset;
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) &&
+	    cpu_feature_enabled(X86_FEATURE_PSE)) {
+		pgprot = PAGE_KERNEL_ROX;
+		flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE;
+	} else {
+		pgprot = PAGE_KERNEL;
+		flags = EXECMEM_KASAN_SHADOW;
+	}
+
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_MODULE_TEXT] = {
+				.flags	= flags,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= pgprot,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_KPROBES] = {
+				.flags	= flags,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL_ROX,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_FTRACE] = {
+				.flags	= flags,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= pgprot,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_BPF] = {
+				.flags	= flags,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= pgprot,
+				.alignment = MODULE_ALIGN,
+			},
+			[EXECMEM_MODULE_DATA] = {
+				.flags	= EXECMEM_KASAN_SHADOW,
+				.start	= start,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = MODULE_ALIGN,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
+#endif /* CONFIG_EXECMEM */
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
new file mode 100644
index 000000000..0908c44d5
--- /dev/null
+++ b/arch/x86/mm/init_32.c
@@ -0,0 +1,759 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ *
+ *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/pci.h>
+#include <linux/pfn.h>
+#include <linux/poison.h>
+#include <linux/memblock.h>
+#include <linux/proc_fs.h>
+#include <linux/memory_hotplug.h>
+#include <linux/initrd.h>
+#include <linux/cpumask.h>
+#include <linux/gfp.h>
+
+#include <asm/asm.h>
+#include <asm/bios_ebda.h>
+#include <asm/processor.h>
+#include <linux/uaccess.h>
+#include <asm/dma.h>
+#include <asm/fixmap.h>
+#include <asm/e820/api.h>
+#include <asm/apic.h>
+#include <asm/bugs.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/olpc_ofw.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/set_memory.h>
+#include <asm/page_types.h>
+#include <asm/cpu_entry_area.h>
+#include <asm/init.h>
+#include <asm/pgtable_areas.h>
+#include <asm/numa.h>
+
+#include "mm_internal.h"
+
+unsigned long highstart_pfn, highend_pfn;
+
+bool __read_mostly __vmalloc_start_set = false;
+
+/*
+ * Creates a middle page table and puts a pointer to it in the
+ * given global directory entry. This only returns the gd entry
+ * in non-PAE compilation mode, since the middle layer is folded.
+ */
+static pmd_t * __init one_md_table_init(pgd_t *pgd)
+{
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd_table;
+
+#ifdef CONFIG_X86_PAE
+	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
+		pmd_table = (pmd_t *)alloc_low_page();
+		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
+		p4d = p4d_offset(pgd, 0);
+		pud = pud_offset(p4d, 0);
+		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
+	}
+#endif
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
+	pmd_table = pmd_offset(pud, 0);
+
+	return pmd_table;
+}
+
+/*
+ * Create a page table and place a pointer to it in a middle page
+ * directory entry:
+ */
+static pte_t * __init one_page_table_init(pmd_t *pmd)
+{
+	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
+		pte_t *page_table = (pte_t *)alloc_low_page();
+
+		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
+		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
+	}
+
+	return pte_offset_kernel(pmd, 0);
+}
+
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	int pgd_idx = pgd_index(vaddr);
+	int pmd_idx = pmd_index(vaddr);
+
+	return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx;
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	int pte_idx = pte_index(vaddr);
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return one_page_table_init(pmd) + pte_idx;
+}
+
+static unsigned long __init
+page_table_range_init_count(unsigned long start, unsigned long end)
+{
+	unsigned long count = 0;
+#ifdef CONFIG_HIGHMEM
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+	int pgd_idx, pmd_idx;
+	unsigned long vaddr;
+
+	if (pmd_idx_kmap_begin == pmd_idx_kmap_end)
+		return 0;
+
+	vaddr = start;
+	pgd_idx = pgd_index(vaddr);
+	pmd_idx = pmd_index(vaddr);
+
+	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
+		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
+							pmd_idx++) {
+			if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin &&
+			    (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end)
+				count++;
+			vaddr += PMD_SIZE;
+		}
+		pmd_idx = 0;
+	}
+#endif
+	return count;
+}
+
+static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
+					   unsigned long vaddr, pte_t *lastpte,
+					   void **adr)
+{
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * Something (early fixmap) may already have put a pte
+	 * page here, which causes the page table allocation
+	 * to become nonlinear. Attempt to fix it, and if it
+	 * is still nonlinear then we have to bug.
+	 */
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+
+	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
+	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
+	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) {
+		pte_t *newpte;
+		int i;
+
+		BUG_ON(after_bootmem);
+		newpte = *adr;
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			set_pte(newpte + i, pte[i]);
+		*adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE);
+
+		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
+		BUG_ON(newpte != pte_offset_kernel(pmd, 0));
+		__flush_tlb_all();
+
+		pte = newpte;
+	}
+	BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
+	       && vaddr > fix_to_virt(FIX_KMAP_END)
+	       && lastpte && lastpte + PTRS_PER_PTE != pte);
+#endif
+	return pte;
+}
+
+/*
+ * This function initializes a certain range of kernel virtual memory
+ * with new bootmem page tables, everywhere page tables are missing in
+ * the given range.
+ *
+ * NOTE: The pagetables are allocated contiguous on the physical space
+ * so we can cache the place of the first one and move around without
+ * checking the pgd every time.
+ */
+static void __init
+page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
+{
+	int pgd_idx, pmd_idx;
+	unsigned long vaddr;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte = NULL;
+	unsigned long count = page_table_range_init_count(start, end);
+	void *adr = NULL;
+
+	if (count)
+		adr = alloc_low_pages(count);
+
+	vaddr = start;
+	pgd_idx = pgd_index(vaddr);
+	pmd_idx = pmd_index(vaddr);
+	pgd = pgd_base + pgd_idx;
+
+	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
+		pmd = one_md_table_init(pgd);
+		pmd = pmd + pmd_index(vaddr);
+		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
+							pmd++, pmd_idx++) {
+			pte = page_table_kmap_check(one_page_table_init(pmd),
+						    pmd, vaddr, pte, &adr);
+
+			vaddr += PMD_SIZE;
+		}
+		pmd_idx = 0;
+	}
+}
+
+static inline int is_x86_32_kernel_text(unsigned long addr)
+{
+	if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
+		return 1;
+	return 0;
+}
+
+/*
+ * This maps the physical memory to kernel virtual address space, a total
+ * of max_low_pfn pages, by creating page tables starting from address
+ * PAGE_OFFSET:
+ */
+unsigned long __init
+kernel_physical_mapping_init(unsigned long start,
+			     unsigned long end,
+			     unsigned long page_size_mask,
+			     pgprot_t prot)
+{
+	int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+	unsigned long last_map_addr = end;
+	unsigned long start_pfn, end_pfn;
+	pgd_t *pgd_base = swapper_pg_dir;
+	int pgd_idx, pmd_idx, pte_ofs;
+	unsigned long pfn;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned pages_2m, pages_4k;
+	int mapping_iter;
+
+	start_pfn = start >> PAGE_SHIFT;
+	end_pfn = end >> PAGE_SHIFT;
+
+	/*
+	 * First iteration will setup identity mapping using large/small pages
+	 * based on use_pse, with other attributes same as set by
+	 * the early code in head_32.S
+	 *
+	 * Second iteration will setup the appropriate attributes (NX, GLOBAL..)
+	 * as desired for the kernel identity mapping.
+	 *
+	 * This two pass mechanism conforms to the TLB app note which says:
+	 *
+	 *     "Software should not write to a paging-structure entry in a way
+	 *      that would change, for any linear address, both the page size
+	 *      and either the page frame or attributes."
+	 */
+	mapping_iter = 1;
+
+	if (!boot_cpu_has(X86_FEATURE_PSE))
+		use_pse = 0;
+
+repeat:
+	pages_2m = pages_4k = 0;
+	pfn = start_pfn;
+	pgd_idx = pgd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
+	pgd = pgd_base + pgd_idx;
+	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
+		pmd = one_md_table_init(pgd);
+
+		if (pfn >= end_pfn)
+			continue;
+#ifdef CONFIG_X86_PAE
+		pmd_idx = pmd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
+		pmd += pmd_idx;
+#else
+		pmd_idx = 0;
+#endif
+		for (; pmd_idx < PTRS_PER_PMD && pfn < end_pfn;
+		     pmd++, pmd_idx++) {
+			unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET;
+
+			/*
+			 * Map with big pages if possible, otherwise
+			 * create normal page tables:
+			 */
+			if (use_pse) {
+				unsigned int addr2;
+				pgprot_t prot = PAGE_KERNEL_LARGE;
+				/*
+				 * first pass will use the same initial
+				 * identity mapping attribute + _PAGE_PSE.
+				 */
+				pgprot_t init_prot =
+					__pgprot(PTE_IDENT_ATTR |
+						 _PAGE_PSE);
+
+				pfn &= PMD_MASK >> PAGE_SHIFT;
+				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
+					PAGE_OFFSET + PAGE_SIZE-1;
+
+				if (is_x86_32_kernel_text(addr) ||
+				    is_x86_32_kernel_text(addr2))
+					prot = PAGE_KERNEL_LARGE_EXEC;
+
+				pages_2m++;
+				if (mapping_iter == 1)
+					set_pmd(pmd, pfn_pmd(pfn, init_prot));
+				else
+					set_pmd(pmd, pfn_pmd(pfn, prot));
+
+				pfn += PTRS_PER_PTE;
+				continue;
+			}
+			pte = one_page_table_init(pmd);
+
+			pte_ofs = pte_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
+			pte += pte_ofs;
+			for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn;
+			     pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) {
+				pgprot_t prot = PAGE_KERNEL;
+				/*
+				 * first pass will use the same initial
+				 * identity mapping attribute.
+				 */
+				pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR);
+
+				if (is_x86_32_kernel_text(addr))
+					prot = PAGE_KERNEL_EXEC;
+
+				pages_4k++;
+				if (mapping_iter == 1) {
+					set_pte(pte, pfn_pte(pfn, init_prot));
+					last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+				} else
+					set_pte(pte, pfn_pte(pfn, prot));
+			}
+		}
+	}
+	if (mapping_iter == 1) {
+		/*
+		 * update direct mapping page count only in the first
+		 * iteration.
+		 */
+		update_page_count(PG_LEVEL_2M, pages_2m);
+		update_page_count(PG_LEVEL_4K, pages_4k);
+
+		/*
+		 * local global flush tlb, which will flush the previous
+		 * mappings present in both small and large page TLB's.
+		 */
+		__flush_tlb_all();
+
+		/*
+		 * Second iteration will set the actual desired PTE attributes.
+		 */
+		mapping_iter = 2;
+		goto repeat;
+	}
+	return last_map_addr;
+}
+
+#ifdef CONFIG_HIGHMEM
+static void __init permanent_kmaps_init(pgd_t *pgd_base)
+{
+	unsigned long vaddr = PKMAP_BASE;
+
+	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
+
+	pkmap_page_table = virt_to_kpte(vaddr);
+}
+#else
+static inline void permanent_kmaps_init(pgd_t *pgd_base)
+{
+}
+#endif /* CONFIG_HIGHMEM */
+
+void __init sync_initial_page_table(void)
+{
+	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+}
+
+void __init native_pagetable_init(void)
+{
+	unsigned long pfn, va;
+	pgd_t *pgd, *base = swapper_pg_dir;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	/*
+	 * Remove any mappings which extend past the end of physical
+	 * memory from the boot time page table.
+	 * In virtual address space, we should have at least two pages
+	 * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END
+	 * definition. And max_low_pfn is set to VMALLOC_END physical
+	 * address. If initial memory mapping is doing right job, we
+	 * should have pte used near max_low_pfn or one pmd is not present.
+	 */
+	for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
+		va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
+		pgd = base + pgd_index(va);
+		if (!pgd_present(*pgd))
+			break;
+
+		p4d = p4d_offset(pgd, va);
+		pud = pud_offset(p4d, va);
+		pmd = pmd_offset(pud, va);
+		if (!pmd_present(*pmd))
+			break;
+
+		/* should not be large page here */
+		if (pmd_leaf(*pmd)) {
+			pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n",
+				pfn, pmd, __pa(pmd));
+			BUG_ON(1);
+		}
+
+		pte = pte_offset_kernel(pmd, va);
+		if (!pte_present(*pte))
+			break;
+
+		printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n",
+				pfn, pmd, __pa(pmd), pte, __pa(pte));
+		pte_clear(NULL, va, pte);
+	}
+	paging_init();
+}
+
+/*
+ * Build a proper pagetable for the kernel mappings.  Up until this
+ * point, we've been running on some set of pagetables constructed by
+ * the boot process.
+ *
+ * This will be a pagetable constructed in arch/x86/kernel/head_32.S.
+ * The root of the pagetable will be swapper_pg_dir.
+ *
+ * In general, pagetable_init() assumes that the pagetable may already
+ * be partially populated, and so it avoids stomping on any existing
+ * mappings.
+ */
+void __init early_ioremap_page_table_range_init(void)
+{
+	pgd_t *pgd_base = swapper_pg_dir;
+	unsigned long vaddr, end;
+
+	/*
+	 * Fixed mappings, only the page table structure has to be
+	 * created - mappings will be set by set_fixmap():
+	 */
+	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
+	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
+	page_table_range_init(vaddr, end, pgd_base);
+	early_ioremap_reset();
+}
+
+static void __init pagetable_init(void)
+{
+	pgd_t *pgd_base = swapper_pg_dir;
+
+	permanent_kmaps_init(pgd_base);
+}
+
+#define DEFAULT_PTE_MASK ~(_PAGE_NX | _PAGE_GLOBAL)
+/* Bits supported by the hardware: */
+pteval_t __supported_pte_mask __read_mostly = DEFAULT_PTE_MASK;
+/* Bits allowed in normal kernel mappings: */
+pteval_t __default_kernel_pte_mask __read_mostly = DEFAULT_PTE_MASK;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
+EXPORT_SYMBOL(__default_kernel_pte_mask);
+
+/* user-defined highmem size */
+static unsigned int highmem_pages = -1;
+
+/*
+ * highmem=size forces highmem to be exactly 'size' bytes.
+ * This works even on boxes that have no highmem otherwise.
+ * This also works to reduce highmem size on bigger boxes.
+ */
+static int __init parse_highmem(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT;
+	return 0;
+}
+early_param("highmem", parse_highmem);
+
+#define MSG_HIGHMEM_TOO_BIG \
+	"highmem size (%luMB) is bigger than pages available (%luMB)!\n"
+
+#define MSG_LOWMEM_TOO_SMALL \
+	"highmem size (%luMB) results in <64MB lowmem, ignoring it!\n"
+/*
+ * All of RAM fits into lowmem - but if user wants highmem
+ * artificially via the highmem=x boot parameter then create
+ * it:
+ */
+static void __init lowmem_pfn_init(void)
+{
+	/* max_low_pfn is 0, we already have early_res support */
+	max_low_pfn = max_pfn;
+
+	if (highmem_pages == -1)
+		highmem_pages = 0;
+#ifdef CONFIG_HIGHMEM
+	if (highmem_pages >= max_pfn) {
+		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
+			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
+		highmem_pages = 0;
+	}
+	if (highmem_pages) {
+		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
+			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
+				pages_to_mb(highmem_pages));
+			highmem_pages = 0;
+		}
+		max_low_pfn -= highmem_pages;
+	}
+#else
+	if (highmem_pages)
+		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
+#endif
+}
+
+#define MSG_HIGHMEM_TOO_SMALL \
+	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
+
+#define MSG_HIGHMEM_TRIMMED \
+	"Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n"
+/*
+ * We have more RAM than fits into lowmem - we try to put it into
+ * highmem, also taking the highmem=x boot parameter into account:
+ */
+static void __init highmem_pfn_init(void)
+{
+	max_low_pfn = MAXMEM_PFN;
+
+	if (highmem_pages == -1)
+		highmem_pages = max_pfn - MAXMEM_PFN;
+
+	if (highmem_pages + MAXMEM_PFN < max_pfn)
+		max_pfn = MAXMEM_PFN + highmem_pages;
+
+	if (highmem_pages + MAXMEM_PFN > max_pfn) {
+		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
+			pages_to_mb(max_pfn - MAXMEM_PFN),
+			pages_to_mb(highmem_pages));
+		highmem_pages = 0;
+	}
+#ifndef CONFIG_HIGHMEM
+	/* Maximum memory usable is what is directly addressable */
+	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
+	printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	max_pfn = MAXMEM_PFN;
+#else /* !CONFIG_HIGHMEM */
+	if (max_pfn > MAX_NONPAE_PFN) {
+		max_pfn = MAX_NONPAE_PFN;
+		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
+	}
+#endif /* !CONFIG_HIGHMEM */
+}
+
+/*
+ * Determine low and high memory ranges:
+ */
+void __init find_low_pfn_range(void)
+{
+	/* it could update max_pfn */
+
+	if (max_pfn <= MAXMEM_PFN)
+		lowmem_pfn_init();
+	else
+		highmem_pfn_init();
+}
+
+void __init initmem_init(void)
+{
+#ifdef CONFIG_HIGHMEM
+	highstart_pfn = highend_pfn = max_pfn;
+	if (max_pfn > max_low_pfn)
+		highstart_pfn = max_low_pfn;
+	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
+		pages_to_mb(highend_pfn - highstart_pfn));
+	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
+#else
+	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
+#endif
+
+	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
+
+	__vmalloc_start_set = true;
+
+	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
+			pages_to_mb(max_low_pfn));
+
+	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
+		 max_pfn_mapped<<PAGE_SHIFT);
+	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
+}
+
+/*
+ * paging_init() sets up the page tables - note that the first 8MB are
+ * already mapped by head.S.
+ *
+ * This routines also unmaps the page at virtual kernel address 0, so
+ * that we can trap those pesky NULL-reference errors in the kernel.
+ */
+void __init paging_init(void)
+{
+	pagetable_init();
+
+	__flush_tlb_all();
+
+	/*
+	 * NOTE: at this point the bootmem allocator is fully available.
+	 */
+	olpc_dt_build_devicetree();
+}
+
+/*
+ * Test if the WP bit works in supervisor mode. It isn't supported on 386's
+ * and also on some strange 486's. All 586+'s are OK. This used to involve
+ * black magic jumps to work around some nasty CPU bugs, but fortunately the
+ * switch to using exceptions got rid of all that.
+ */
+static void __init test_wp_bit(void)
+{
+	char z = 0;
+
+	printk(KERN_INFO "Checking if this processor honours the WP bit even in supervisor mode...");
+
+	__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
+
+	if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+		clear_fixmap(FIX_WP_TEST);
+		printk(KERN_CONT "Ok.\n");
+		return;
+	}
+
+	printk(KERN_CONT "No.\n");
+	panic("Linux doesn't support CPUs with broken WP.");
+}
+
+void __init arch_mm_preinit(void)
+{
+	pci_iommu_alloc();
+
+#ifdef CONFIG_FLATMEM
+	BUG_ON(!mem_map);
+#endif
+}
+
+void __init mem_init(void)
+{
+	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
+
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
+	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
+
+#ifdef CONFIG_HIGHMEM
+	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
+	BUG_ON(VMALLOC_END				> PKMAP_BASE);
+#endif
+	BUG_ON(VMALLOC_START				>= VMALLOC_END);
+	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
+
+	test_wp_bit();
+}
+
+int kernel_set_to_readonly __read_mostly;
+
+static void mark_nxdata_nx(void)
+{
+	/*
+	 * When this called, init has already been executed and released,
+	 * so everything past _etext should be NX.
+	 */
+	unsigned long start = PFN_ALIGN(_etext);
+	/*
+	 * This comes from is_x86_32_kernel_text upper limit. Also HPAGE where used:
+	 */
+	unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;
+
+	if (__supported_pte_mask & _PAGE_NX)
+		printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10);
+	set_memory_nx(start, size >> PAGE_SHIFT);
+}
+
+void mark_rodata_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = (unsigned long)__end_rodata - start;
+
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+	pr_info("Write protecting kernel text and read-only data: %luk\n",
+		size >> 10);
+
+	kernel_set_to_readonly = 1;
+
+#ifdef CONFIG_CPA_DEBUG
+	pr_info("Testing CPA: Reverting %lx-%lx\n", start, start + size);
+	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+
+	pr_info("Testing CPA: write protecting again\n");
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+#endif
+	mark_nxdata_nx();
+}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
new file mode 100644
index 000000000..70e682180
--- /dev/null
+++ b/arch/x86/mm/init_64.c
@@ -0,0 +1,1557 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  linux/arch/x86_64/mm/init.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ *  Copyright (C) 2000  Pavel Machek <pavel@ucw.cz>
+ *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/initrd.h>
+#include <linux/pagemap.h>
+#include <linux/memblock.h>
+#include <linux/proc_fs.h>
+#include <linux/pci.h>
+#include <linux/pfn.h>
+#include <linux/poison.h>
+#include <linux/dma-mapping.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+#include <linux/memremap.h>
+#include <linux/nmi.h>
+#include <linux/gfp.h>
+#include <linux/kcore.h>
+
+#include <asm/processor.h>
+#include <asm/bios_ebda.h>
+#include <linux/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/fixmap.h>
+#include <asm/e820/api.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+#include <asm/mmu_context.h>
+#include <asm/proto.h>
+#include <asm/smp.h>
+#include <asm/sections.h>
+#include <asm/kdebug.h>
+#include <asm/numa.h>
+#include <asm/set_memory.h>
+#include <asm/init.h>
+#include <asm/uv/uv.h>
+#include <asm/setup.h>
+#include <asm/ftrace.h>
+
+#include "mm_internal.h"
+
+#include "ident_map.c"
+
+#define DEFINE_POPULATE(fname, type1, type2, init)		\
+static inline void fname##_init(struct mm_struct *mm,		\
+		type1##_t *arg1, type2##_t *arg2, bool init)	\
+{								\
+	if (init)						\
+		fname##_safe(mm, arg1, arg2);			\
+	else							\
+		fname(mm, arg1, arg2);				\
+}
+
+DEFINE_POPULATE(p4d_populate, p4d, pud, init)
+DEFINE_POPULATE(pgd_populate, pgd, p4d, init)
+DEFINE_POPULATE(pud_populate, pud, pmd, init)
+DEFINE_POPULATE(pmd_populate_kernel, pmd, pte, init)
+
+#define DEFINE_ENTRY(type1, type2, init)			\
+static inline void set_##type1##_init(type1##_t *arg1,		\
+			type2##_t arg2, bool init)		\
+{								\
+	if (init)						\
+		set_##type1##_safe(arg1, arg2);			\
+	else							\
+		set_##type1(arg1, arg2);			\
+}
+
+DEFINE_ENTRY(p4d, p4d, init)
+DEFINE_ENTRY(pud, pud, init)
+DEFINE_ENTRY(pmd, pmd, init)
+DEFINE_ENTRY(pte, pte, init)
+
+static inline pgprot_t prot_sethuge(pgprot_t prot)
+{
+	WARN_ON_ONCE(pgprot_val(prot) & _PAGE_PAT);
+
+	return __pgprot(pgprot_val(prot) | _PAGE_PSE);
+}
+
+/*
+ * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
+ * physical space so we can cache the place of the first one and move
+ * around without checking the pgd every time.
+ */
+
+/* Bits supported by the hardware: */
+pteval_t __supported_pte_mask __read_mostly = ~0;
+/* Bits allowed in normal kernel mappings: */
+pteval_t __default_kernel_pte_mask __read_mostly = ~0;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+/* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */
+EXPORT_SYMBOL(__default_kernel_pte_mask);
+
+int force_personality32;
+
+/*
+ * noexec32=on|off
+ * Control non executable heap for 32bit processes.
+ *
+ * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
+ * off	PROT_READ implies PROT_EXEC
+ */
+static int __init nonx32_setup(char *str)
+{
+	if (!strcmp(str, "on"))
+		force_personality32 &= ~READ_IMPLIES_EXEC;
+	else if (!strcmp(str, "off"))
+		force_personality32 |= READ_IMPLIES_EXEC;
+	return 1;
+}
+__setup("noexec32=", nonx32_setup);
+
+static void sync_global_pgds_l5(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		const pgd_t *pgd_ref = pgd_offset_k(addr);
+		struct ptdesc *ptdesc;
+
+		/* Check for overflow */
+		if (addr < start)
+			break;
+
+		if (pgd_none(*pgd_ref))
+			continue;
+
+		spin_lock(&pgd_lock);
+		list_for_each_entry(ptdesc, &pgd_list, pt_list) {
+			pgd_t *pgd;
+			spinlock_t *pgt_lock;
+
+			pgd = (pgd_t *)ptdesc_address(ptdesc) + pgd_index(addr);
+			/* the pgt_lock only for Xen */
+			pgt_lock = &pgd_page_get_mm(ptdesc)->page_table_lock;
+			spin_lock(pgt_lock);
+
+			if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
+				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+
+			if (pgd_none(*pgd))
+				set_pgd(pgd, *pgd_ref);
+
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock(&pgd_lock);
+	}
+}
+
+static void sync_global_pgds_l4(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		pgd_t *pgd_ref = pgd_offset_k(addr);
+		const p4d_t *p4d_ref;
+		struct ptdesc *ptdesc;
+
+		/*
+		 * With folded p4d, pgd_none() is always false, we need to
+		 * handle synchronization on p4d level.
+		 */
+		MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
+		p4d_ref = p4d_offset(pgd_ref, addr);
+
+		if (p4d_none(*p4d_ref))
+			continue;
+
+		spin_lock(&pgd_lock);
+		list_for_each_entry(ptdesc, &pgd_list, pt_list) {
+			pgd_t *pgd;
+			p4d_t *p4d;
+			spinlock_t *pgt_lock;
+
+			pgd = (pgd_t *)ptdesc_address(ptdesc) + pgd_index(addr);
+			p4d = p4d_offset(pgd, addr);
+			/* the pgt_lock only for Xen */
+			pgt_lock = &pgd_page_get_mm(ptdesc)->page_table_lock;
+			spin_lock(pgt_lock);
+
+			if (!p4d_none(*p4d_ref) && !p4d_none(*p4d))
+				BUG_ON(p4d_pgtable(*p4d)
+				       != p4d_pgtable(*p4d_ref));
+
+			if (p4d_none(*p4d))
+				set_p4d(p4d, *p4d_ref);
+
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock(&pgd_lock);
+	}
+}
+
+/*
+ * When memory was added make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+static void sync_global_pgds(unsigned long start, unsigned long end)
+{
+	if (pgtable_l5_enabled())
+		sync_global_pgds_l5(start, end);
+	else
+		sync_global_pgds_l4(start, end);
+}
+
+/*
+ * Make kernel mappings visible in all page tables in the system.
+ * This is necessary except when the init task populates kernel mappings
+ * during the boot process. In that case, all processes originating from
+ * the init task copies the kernel mappings, so there is no issue.
+ * Otherwise, missing synchronization could lead to kernel crashes due
+ * to missing page table entries for certain kernel mappings.
+ *
+ * Synchronization is performed at the top level, which is the PGD in
+ * 5-level paging systems. But in 4-level paging systems, however,
+ * pgd_populate() is a no-op, so synchronization is done at the P4D level.
+ * sync_global_pgds() handles this difference between paging levels.
+ */
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	sync_global_pgds(start, end);
+}
+
+/*
+ * NOTE: This function is marked __ref because it calls __init function
+ * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
+ */
+static __ref void *spp_getpage(void)
+{
+	void *ptr;
+
+	if (after_bootmem)
+		ptr = (void *) get_zeroed_page(GFP_ATOMIC);
+	else
+		ptr = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+
+	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
+		panic("set_pte_phys: cannot allocate page data %s\n",
+			after_bootmem ? "after bootmem" : "");
+	}
+
+	pr_debug("spp_getpage %p\n", ptr);
+
+	return ptr;
+}
+
+static p4d_t *fill_p4d(pgd_t *pgd, unsigned long vaddr)
+{
+	if (pgd_none(*pgd)) {
+		p4d_t *p4d = (p4d_t *)spp_getpage();
+		pgd_populate(&init_mm, pgd, p4d);
+		if (p4d != p4d_offset(pgd, 0))
+			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
+			       p4d, p4d_offset(pgd, 0));
+	}
+	return p4d_offset(pgd, vaddr);
+}
+
+static pud_t *fill_pud(p4d_t *p4d, unsigned long vaddr)
+{
+	if (p4d_none(*p4d)) {
+		pud_t *pud = (pud_t *)spp_getpage();
+		p4d_populate(&init_mm, p4d, pud);
+		if (pud != pud_offset(p4d, 0))
+			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
+			       pud, pud_offset(p4d, 0));
+	}
+	return pud_offset(p4d, vaddr);
+}
+
+static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
+{
+	if (pud_none(*pud)) {
+		pmd_t *pmd = (pmd_t *) spp_getpage();
+		pud_populate(&init_mm, pud, pmd);
+		if (pmd != pmd_offset(pud, 0))
+			printk(KERN_ERR "PAGETABLE BUG #02! %p <-> %p\n",
+			       pmd, pmd_offset(pud, 0));
+	}
+	return pmd_offset(pud, vaddr);
+}
+
+static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
+{
+	if (pmd_none(*pmd)) {
+		pte_t *pte = (pte_t *) spp_getpage();
+		pmd_populate_kernel(&init_mm, pmd, pte);
+		if (pte != pte_offset_kernel(pmd, 0))
+			printk(KERN_ERR "PAGETABLE BUG #03!\n");
+	}
+	return pte_offset_kernel(pmd, vaddr);
+}
+
+static void __set_pte_vaddr(pud_t *pud, unsigned long vaddr, pte_t new_pte)
+{
+	pmd_t *pmd = fill_pmd(pud, vaddr);
+	pte_t *pte = fill_pte(pmd, vaddr);
+
+	set_pte(pte, new_pte);
+
+	/*
+	 * It's enough to flush this one mapping.
+	 * (PGE mappings get flushed as well)
+	 */
+	flush_tlb_one_kernel(vaddr);
+}
+
+void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte)
+{
+	p4d_t *p4d = p4d_page + p4d_index(vaddr);
+	pud_t *pud = fill_pud(p4d, vaddr);
+
+	__set_pte_vaddr(pud, vaddr, new_pte);
+}
+
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+{
+	pud_t *pud = pud_page + pud_index(vaddr);
+
+	__set_pte_vaddr(pud, vaddr, new_pte);
+}
+
+void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
+{
+	pgd_t *pgd;
+	p4d_t *p4d_page;
+
+	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));
+
+	pgd = pgd_offset_k(vaddr);
+	if (pgd_none(*pgd)) {
+		printk(KERN_ERR
+			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
+		return;
+	}
+
+	p4d_page = p4d_offset(pgd, 0);
+	set_pte_vaddr_p4d(p4d_page, vaddr, pteval);
+}
+
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(vaddr);
+	p4d = fill_p4d(pgd, vaddr);
+	pud = fill_pud(p4d, vaddr);
+	return fill_pmd(pud, vaddr);
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return fill_pte(pmd, vaddr);
+}
+
+/*
+ * Create large page table mappings for a range of physical addresses.
+ */
+static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
+					enum page_cache_mode cache)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pgprot_t prot;
+
+	pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) |
+		protval_4k_2_large(cachemode2protval(cache));
+	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
+	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
+		pgd = pgd_offset_k((unsigned long)__va(phys));
+		if (pgd_none(*pgd)) {
+			p4d = (p4d_t *) spp_getpage();
+			set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		p4d = p4d_offset(pgd, (unsigned long)__va(phys));
+		if (p4d_none(*p4d)) {
+			pud = (pud_t *) spp_getpage();
+			set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		pud = pud_offset(p4d, (unsigned long)__va(phys));
+		if (pud_none(*pud)) {
+			pmd = (pmd_t *) spp_getpage();
+			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		pmd = pmd_offset(pud, phys);
+		BUG_ON(!pmd_none(*pmd));
+		set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
+	}
+}
+
+void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
+{
+	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB);
+}
+
+void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
+{
+	__init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC);
+}
+
+/*
+ * The head.S code sets up the kernel high mapping:
+ *
+ *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
+ *
+ * phys_base holds the negative offset to the kernel, which is added
+ * to the compile time generated pmds. This results in invalid pmds up
+ * to the point where we hit the physaddr 0 mapping.
+ *
+ * We limit the mappings to the region from _text to _brk_end.  _brk_end
+ * is rounded up to the 2MB boundary. This catches the invalid pmds as
+ * well, as they are located before _text:
+ */
+void __init cleanup_highmap(void)
+{
+	unsigned long vaddr = __START_KERNEL_map;
+	unsigned long vaddr_end = __START_KERNEL_map + KERNEL_IMAGE_SIZE;
+	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+	pmd_t *pmd = level2_kernel_pgt;
+
+	/*
+	 * Native path, max_pfn_mapped is not set yet.
+	 * Xen has valid max_pfn_mapped set in
+	 *	arch/x86/xen/mmu.c:xen_setup_kernel_pagetable().
+	 */
+	if (max_pfn_mapped)
+		vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
+
+	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
+		if (pmd_none(*pmd))
+			continue;
+		if (vaddr < (unsigned long) _text || vaddr > end)
+			set_pmd(pmd, __pmd(0));
+	}
+}
+
+/*
+ * Create PTE level page table mapping for physical addresses.
+ * It returns the last physical address mapped.
+ */
+static unsigned long __meminit
+phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end,
+	      pgprot_t prot, bool init)
+{
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
+	pte_t *pte;
+	int i;
+
+	pte = pte_page + pte_index(paddr);
+	i = pte_index(paddr);
+
+	for (; i < PTRS_PER_PTE; i++, paddr = paddr_next, pte++) {
+		paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE;
+		if (paddr >= paddr_end) {
+			if (!after_bootmem &&
+			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PAGE_MASK, paddr_next,
+					     E820_TYPE_ACPI))
+				set_pte_init(pte, __pte(0), init);
+			continue;
+		}
+
+		/*
+		 * We will re-use the existing mapping.
+		 * Xen for example has some special requirements, like mapping
+		 * pagetable pages as RO. So assume someone who pre-setup
+		 * these mappings are more intelligent.
+		 */
+		if (!pte_none(*pte)) {
+			if (!after_bootmem)
+				pages++;
+			continue;
+		}
+
+		pages++;
+		set_pte_init(pte, pfn_pte(paddr >> PAGE_SHIFT, prot), init);
+		paddr_last = (paddr & PAGE_MASK) + PAGE_SIZE;
+	}
+
+	update_page_count(PG_LEVEL_4K, pages);
+
+	return paddr_last;
+}
+
+/*
+ * Create PMD level page table mapping for physical addresses. The virtual
+ * and physical address have to be aligned at this level.
+ * It returns the last physical address mapped.
+ */
+static unsigned long __meminit
+phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end,
+	      unsigned long page_size_mask, pgprot_t prot, bool init)
+{
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
+
+	int i = pmd_index(paddr);
+
+	for (; i < PTRS_PER_PMD; i++, paddr = paddr_next) {
+		pmd_t *pmd = pmd_page + pmd_index(paddr);
+		pte_t *pte;
+		pgprot_t new_prot = prot;
+
+		paddr_next = (paddr & PMD_MASK) + PMD_SIZE;
+		if (paddr >= paddr_end) {
+			if (!after_bootmem &&
+			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PMD_MASK, paddr_next,
+					     E820_TYPE_ACPI))
+				set_pmd_init(pmd, __pmd(0), init);
+			continue;
+		}
+
+		if (!pmd_none(*pmd)) {
+			if (!pmd_leaf(*pmd)) {
+				spin_lock(&init_mm.page_table_lock);
+				pte = (pte_t *)pmd_page_vaddr(*pmd);
+				paddr_last = phys_pte_init(pte, paddr,
+							   paddr_end, prot,
+							   init);
+				spin_unlock(&init_mm.page_table_lock);
+				continue;
+			}
+			/*
+			 * If we are ok with PG_LEVEL_2M mapping, then we will
+			 * use the existing mapping,
+			 *
+			 * Otherwise, we will split the large page mapping but
+			 * use the same existing protection bits except for
+			 * large page, so that we don't violate Intel's TLB
+			 * Application note (317080) which says, while changing
+			 * the page sizes, new and old translations should
+			 * not differ with respect to page frame and
+			 * attributes.
+			 */
+			if (page_size_mask & (1 << PG_LEVEL_2M)) {
+				if (!after_bootmem)
+					pages++;
+				paddr_last = paddr_next;
+				continue;
+			}
+			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
+		}
+
+		if (page_size_mask & (1<<PG_LEVEL_2M)) {
+			pages++;
+			spin_lock(&init_mm.page_table_lock);
+			set_pmd_init(pmd,
+				     pfn_pmd(paddr >> PAGE_SHIFT, prot_sethuge(prot)),
+				     init);
+			spin_unlock(&init_mm.page_table_lock);
+			paddr_last = paddr_next;
+			continue;
+		}
+
+		pte = alloc_low_page();
+		paddr_last = phys_pte_init(pte, paddr, paddr_end, new_prot, init);
+
+		spin_lock(&init_mm.page_table_lock);
+		pmd_populate_kernel_init(&init_mm, pmd, pte, init);
+		spin_unlock(&init_mm.page_table_lock);
+	}
+	update_page_count(PG_LEVEL_2M, pages);
+	return paddr_last;
+}
+
+/*
+ * Create PUD level page table mapping for physical addresses. The virtual
+ * and physical address do not have to be aligned at this level. KASLR can
+ * randomize virtual addresses up to this level.
+ * It returns the last physical address mapped.
+ */
+static unsigned long __meminit
+phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end,
+	      unsigned long page_size_mask, pgprot_t _prot, bool init)
+{
+	unsigned long pages = 0, paddr_next;
+	unsigned long paddr_last = paddr_end;
+	unsigned long vaddr = (unsigned long)__va(paddr);
+	int i = pud_index(vaddr);
+
+	for (; i < PTRS_PER_PUD; i++, paddr = paddr_next) {
+		pud_t *pud;
+		pmd_t *pmd;
+		pgprot_t prot = _prot;
+
+		vaddr = (unsigned long)__va(paddr);
+		pud = pud_page + pud_index(vaddr);
+		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
+
+		if (paddr >= paddr_end) {
+			if (!after_bootmem &&
+			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & PUD_MASK, paddr_next,
+					     E820_TYPE_ACPI))
+				set_pud_init(pud, __pud(0), init);
+			continue;
+		}
+
+		if (!pud_none(*pud)) {
+			if (!pud_leaf(*pud)) {
+				pmd = pmd_offset(pud, 0);
+				paddr_last = phys_pmd_init(pmd, paddr,
+							   paddr_end,
+							   page_size_mask,
+							   prot, init);
+				continue;
+			}
+			/*
+			 * If we are ok with PG_LEVEL_1G mapping, then we will
+			 * use the existing mapping.
+			 *
+			 * Otherwise, we will split the gbpage mapping but use
+			 * the same existing protection  bits except for large
+			 * page, so that we don't violate Intel's TLB
+			 * Application note (317080) which says, while changing
+			 * the page sizes, new and old translations should
+			 * not differ with respect to page frame and
+			 * attributes.
+			 */
+			if (page_size_mask & (1 << PG_LEVEL_1G)) {
+				if (!after_bootmem)
+					pages++;
+				paddr_last = paddr_next;
+				continue;
+			}
+			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
+		}
+
+		if (page_size_mask & (1<<PG_LEVEL_1G)) {
+			pages++;
+			spin_lock(&init_mm.page_table_lock);
+			set_pud_init(pud,
+				     pfn_pud(paddr >> PAGE_SHIFT, prot_sethuge(prot)),
+				     init);
+			spin_unlock(&init_mm.page_table_lock);
+			paddr_last = paddr_next;
+			continue;
+		}
+
+		pmd = alloc_low_page();
+		paddr_last = phys_pmd_init(pmd, paddr, paddr_end,
+					   page_size_mask, prot, init);
+
+		spin_lock(&init_mm.page_table_lock);
+		pud_populate_init(&init_mm, pud, pmd, init);
+		spin_unlock(&init_mm.page_table_lock);
+	}
+
+	update_page_count(PG_LEVEL_1G, pages);
+
+	return paddr_last;
+}
+
+static unsigned long __meminit
+phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
+	      unsigned long page_size_mask, pgprot_t prot, bool init)
+{
+	unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last;
+
+	paddr_last = paddr_end;
+	vaddr = (unsigned long)__va(paddr);
+	vaddr_end = (unsigned long)__va(paddr_end);
+
+	if (!pgtable_l5_enabled())
+		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end,
+				     page_size_mask, prot, init);
+
+	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+		p4d_t *p4d = p4d_page + p4d_index(vaddr);
+		pud_t *pud;
+
+		vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE;
+		paddr = __pa(vaddr);
+
+		if (paddr >= paddr_end) {
+			paddr_next = __pa(vaddr_next);
+			if (!after_bootmem &&
+			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
+					     E820_TYPE_RAM) &&
+			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
+					     E820_TYPE_ACPI))
+				set_p4d_init(p4d, __p4d(0), init);
+			continue;
+		}
+
+		if (!p4d_none(*p4d)) {
+			pud = pud_offset(p4d, 0);
+			paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
+					page_size_mask, prot, init);
+			continue;
+		}
+
+		pud = alloc_low_page();
+		paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
+					   page_size_mask, prot, init);
+
+		spin_lock(&init_mm.page_table_lock);
+		p4d_populate_init(&init_mm, p4d, pud, init);
+		spin_unlock(&init_mm.page_table_lock);
+	}
+
+	return paddr_last;
+}
+
+static unsigned long __meminit
+__kernel_physical_mapping_init(unsigned long paddr_start,
+			       unsigned long paddr_end,
+			       unsigned long page_size_mask,
+			       pgprot_t prot, bool init)
+{
+	bool pgd_changed = false;
+	unsigned long vaddr, vaddr_start, vaddr_end, vaddr_next, paddr_last;
+
+	paddr_last = paddr_end;
+	vaddr = (unsigned long)__va(paddr_start);
+	vaddr_end = (unsigned long)__va(paddr_end);
+	vaddr_start = vaddr;
+
+	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+		pgd_t *pgd = pgd_offset_k(vaddr);
+		p4d_t *p4d;
+
+		vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE;
+
+		if (pgd_val(*pgd)) {
+			p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+			paddr_last = phys_p4d_init(p4d, __pa(vaddr),
+						   __pa(vaddr_end),
+						   page_size_mask,
+						   prot, init);
+			continue;
+		}
+
+		p4d = alloc_low_page();
+		paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end),
+					   page_size_mask, prot, init);
+
+		spin_lock(&init_mm.page_table_lock);
+		if (pgtable_l5_enabled())
+			pgd_populate_init(&init_mm, pgd, p4d, init);
+		else
+			p4d_populate_init(&init_mm, p4d_offset(pgd, vaddr),
+					  (pud_t *) p4d, init);
+
+		spin_unlock(&init_mm.page_table_lock);
+		pgd_changed = true;
+	}
+
+	if (pgd_changed)
+		sync_global_pgds(vaddr_start, vaddr_end - 1);
+
+	return paddr_last;
+}
+
+
+/*
+ * Create page table mapping for the physical memory for specific physical
+ * addresses. Note that it can only be used to populate non-present entries.
+ * The virtual and physical addresses have to be aligned on PMD level
+ * down. It returns the last physical address mapped.
+ */
+unsigned long __meminit
+kernel_physical_mapping_init(unsigned long paddr_start,
+			     unsigned long paddr_end,
+			     unsigned long page_size_mask, pgprot_t prot)
+{
+	return __kernel_physical_mapping_init(paddr_start, paddr_end,
+					      page_size_mask, prot, true);
+}
+
+/*
+ * This function is similar to kernel_physical_mapping_init() above with the
+ * exception that it uses set_{pud,pmd}() instead of the set_{pud,pte}_safe()
+ * when updating the mapping. The caller is responsible to flush the TLBs after
+ * the function returns.
+ */
+unsigned long __meminit
+kernel_physical_mapping_change(unsigned long paddr_start,
+			       unsigned long paddr_end,
+			       unsigned long page_size_mask)
+{
+	return __kernel_physical_mapping_init(paddr_start, paddr_end,
+					      page_size_mask, PAGE_KERNEL,
+					      false);
+}
+
+#ifndef CONFIG_NUMA
+static __always_inline void x86_numa_init(void)
+{
+	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
+}
+#endif
+
+void __init initmem_init(void)
+{
+	x86_numa_init();
+}
+
+void __init paging_init(void)
+{
+	/*
+	 * clear the default setting with node 0
+	 * note: don't use nodes_clear here, that is really clearing when
+	 *	 numa support is not compiled in, and later node_set_state
+	 *	 will not set it back.
+	 */
+	node_clear_state(0, N_MEMORY);
+	node_clear_state(0, N_NORMAL_MEMORY);
+}
+
+#define PAGE_UNUSED 0xFD
+
+/*
+ * The unused vmemmap range, which was not yet memset(PAGE_UNUSED), ranges
+ * from unused_pmd_start to next PMD_SIZE boundary.
+ */
+static unsigned long unused_pmd_start __meminitdata;
+
+static void __meminit vmemmap_flush_unused_pmd(void)
+{
+	if (!unused_pmd_start)
+		return;
+	/*
+	 * Clears (unused_pmd_start, PMD_END]
+	 */
+	memset((void *)unused_pmd_start, PAGE_UNUSED,
+	       ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
+	unused_pmd_start = 0;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+/* Returns true if the PMD is completely unused and thus it can be freed */
+static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	/*
+	 * Flush the unused range cache to ensure that memchr_inv() will work
+	 * for the whole range.
+	 */
+	vmemmap_flush_unused_pmd();
+	memset((void *)addr, PAGE_UNUSED, end - addr);
+
+	return !memchr_inv((void *)start, PAGE_UNUSED, PMD_SIZE);
+}
+#endif
+
+static void __meminit __vmemmap_use_sub_pmd(unsigned long start)
+{
+	/*
+	 * As we expect to add in the same granularity as we remove, it's
+	 * sufficient to mark only some piece used to block the memmap page from
+	 * getting removed when removing some other adjacent memmap (just in
+	 * case the first memmap never gets initialized e.g., because the memory
+	 * block never gets onlined).
+	 */
+	memset((void *)start, 0, sizeof(struct page));
+}
+
+static void __meminit vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+{
+	/*
+	 * We only optimize if the new used range directly follows the
+	 * previously unused range (esp., when populating consecutive sections).
+	 */
+	if (unused_pmd_start == start) {
+		if (likely(IS_ALIGNED(end, PMD_SIZE)))
+			unused_pmd_start = 0;
+		else
+			unused_pmd_start = end;
+		return;
+	}
+
+	/*
+	 * If the range does not contiguously follows previous one, make sure
+	 * to mark the unused range of the previous one so it can be removed.
+	 */
+	vmemmap_flush_unused_pmd();
+	__vmemmap_use_sub_pmd(start);
+}
+
+
+static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
+{
+	const unsigned long page = ALIGN_DOWN(start, PMD_SIZE);
+
+	vmemmap_flush_unused_pmd();
+
+	/*
+	 * Could be our memmap page is filled with PAGE_UNUSED already from a
+	 * previous remove. Make sure to reset it.
+	 */
+	__vmemmap_use_sub_pmd(start);
+
+	/*
+	 * Mark with PAGE_UNUSED the unused parts of the new memmap range
+	 */
+	if (!IS_ALIGNED(start, PMD_SIZE))
+		memset((void *)page, PAGE_UNUSED, start - page);
+
+	/*
+	 * We want to avoid memset(PAGE_UNUSED) when populating the vmemmap of
+	 * consecutive sections. Remember for the last added PMD where the
+	 * unused range begins.
+	 */
+	if (!IS_ALIGNED(end, PMD_SIZE))
+		unused_pmd_start = end;
+}
+
+/*
+ * Memory hotplug specific functions
+ */
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
+ * updating.
+ */
+static void update_end_of_memory_vars(u64 start, u64 size)
+{
+	unsigned long end_pfn = PFN_UP(start + size);
+
+	if (end_pfn > max_pfn) {
+		max_pfn = end_pfn;
+		max_low_pfn = end_pfn;
+		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	}
+}
+
+int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
+	      struct mhp_params *params)
+{
+	unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
+	int ret;
+
+	if (WARN_ON_ONCE(end > DIRECT_MAP_PHYSMEM_END))
+		return -ERANGE;
+
+	ret = __add_pages(nid, start_pfn, nr_pages, params);
+	WARN_ON_ONCE(ret);
+
+	/*
+	 * Special case: add_pages() is called by memremap_pages() for adding device
+	 * private pages. Do not bump up max_pfn in the device private path,
+	 * because max_pfn changes affect dma_addressing_limited().
+	 *
+	 * dma_addressing_limited() returning true when max_pfn is the device's
+	 * addressable memory can force device drivers to use bounce buffers
+	 * and impact their performance negatively:
+	 */
+	if (!params->pgmap)
+		/* update max_pfn, max_low_pfn and high_memory */
+		update_end_of_memory_vars(start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
+
+	return ret;
+}
+
+int arch_add_memory(int nid, u64 start, u64 size,
+		    struct mhp_params *params)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	init_memory_mapping(start, start + size, params->pgprot);
+
+	return add_pages(nid, start_pfn, nr_pages, params);
+}
+
+static void __meminit free_pagetable(struct page *page)
+{
+	if (PageReserved(page))
+		free_reserved_page(page);
+	else
+		pagetable_free(page_ptdesc(page));
+}
+
+static void __meminit free_vmemmap_pages(struct page *page, unsigned int order,
+		struct vmem_altmap *altmap)
+{
+	unsigned long nr_pages = 1u << order;
+
+	if (altmap)
+		vmem_altmap_free(altmap, nr_pages);
+	else if (PageReserved(page))
+		free_reserved_pages(page, order);
+	else
+		__free_pages(page, order);
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+	pte_t *pte;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte = pte_start + i;
+		if (!pte_none(*pte))
+			return;
+	}
+
+	/* free a pte table */
+	free_pagetable(pmd_page(*pmd));
+	spin_lock(&init_mm.page_table_lock);
+	pmd_clear(pmd);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+	pmd_t *pmd;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd = pmd_start + i;
+		if (!pmd_none(*pmd))
+			return;
+	}
+
+	/* free a pmd table */
+	free_pagetable(pud_page(*pud));
+	spin_lock(&init_mm.page_table_lock);
+	pud_clear(pud);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
+{
+	pud_t *pud;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (!pud_none(*pud))
+			return;
+	}
+
+	/* free a pud table */
+	free_pagetable(p4d_page(*p4d));
+	spin_lock(&init_mm.page_table_lock);
+	p4d_clear(p4d);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit
+remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pte_t *pte;
+	phys_addr_t phys_addr;
+
+	pte = pte_start + pte_index(addr);
+	for (; addr < end; addr = next, pte++) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		if (next > end)
+			next = end;
+
+		if (!pte_present(*pte))
+			continue;
+
+		/*
+		 * We mapped [0,1G) memory as identity mapping when
+		 * initializing, in arch/x86/kernel/head_64.S. These
+		 * pagetables cannot be removed.
+		 */
+		phys_addr = pte_val(*pte) + (addr & PAGE_MASK);
+		if (phys_addr < (phys_addr_t)0x40000000)
+			return;
+
+		if (!direct)
+			/* We never populate base pages from the altmap. */
+			free_vmemmap_pages(pte_page(*pte), 0, NULL);
+
+		spin_lock(&init_mm.page_table_lock);
+		pte_clear(&init_mm, addr, pte);
+		spin_unlock(&init_mm.page_table_lock);
+
+		/* For non-direct mapping, pages means nothing. */
+		pages++;
+	}
+
+	/* Call free_pte_table() in remove_pmd_table(). */
+	flush_tlb_all();
+	if (direct)
+		update_page_count(PG_LEVEL_4K, -pages);
+}
+
+static void __meminit
+remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
+		 bool direct, struct vmem_altmap *altmap)
+{
+	unsigned long next, pages = 0;
+	pte_t *pte_base;
+	pmd_t *pmd;
+
+	pmd = pmd_start + pmd_index(addr);
+	for (; addr < end; addr = next, pmd++) {
+		next = pmd_addr_end(addr, end);
+
+		if (!pmd_present(*pmd))
+			continue;
+
+		if (pmd_leaf(*pmd)) {
+			if (IS_ALIGNED(addr, PMD_SIZE) &&
+			    IS_ALIGNED(next, PMD_SIZE)) {
+				if (!direct)
+					free_vmemmap_pages(pmd_page(*pmd),
+							   PMD_ORDER, altmap);
+
+				spin_lock(&init_mm.page_table_lock);
+				pmd_clear(pmd);
+				spin_unlock(&init_mm.page_table_lock);
+				pages++;
+			} else if (vmemmap_pmd_is_unused(addr, next)) {
+				free_vmemmap_pages(pmd_page(*pmd), PMD_ORDER,
+						   altmap);
+				spin_lock(&init_mm.page_table_lock);
+				pmd_clear(pmd);
+				spin_unlock(&init_mm.page_table_lock);
+			}
+			continue;
+		}
+
+		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
+		remove_pte_table(pte_base, addr, next, direct);
+		free_pte_table(pte_base, pmd);
+	}
+
+	/* Call free_pmd_table() in remove_pud_table(). */
+	if (direct)
+		update_page_count(PG_LEVEL_2M, -pages);
+}
+
+static void __meminit
+remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
+		 struct vmem_altmap *altmap, bool direct)
+{
+	unsigned long next, pages = 0;
+	pmd_t *pmd_base;
+	pud_t *pud;
+
+	pud = pud_start + pud_index(addr);
+	for (; addr < end; addr = next, pud++) {
+		next = pud_addr_end(addr, end);
+
+		if (!pud_present(*pud))
+			continue;
+
+		if (pud_leaf(*pud) &&
+		    IS_ALIGNED(addr, PUD_SIZE) &&
+		    IS_ALIGNED(next, PUD_SIZE)) {
+			spin_lock(&init_mm.page_table_lock);
+			pud_clear(pud);
+			spin_unlock(&init_mm.page_table_lock);
+			pages++;
+			continue;
+		}
+
+		pmd_base = pmd_offset(pud, 0);
+		remove_pmd_table(pmd_base, addr, next, direct, altmap);
+		free_pmd_table(pmd_base, pud);
+	}
+
+	if (direct)
+		update_page_count(PG_LEVEL_1G, -pages);
+}
+
+static void __meminit
+remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
+		 struct vmem_altmap *altmap, bool direct)
+{
+	unsigned long next, pages = 0;
+	pud_t *pud_base;
+	p4d_t *p4d;
+
+	p4d = p4d_start + p4d_index(addr);
+	for (; addr < end; addr = next, p4d++) {
+		next = p4d_addr_end(addr, end);
+
+		if (!p4d_present(*p4d))
+			continue;
+
+		BUILD_BUG_ON(p4d_leaf(*p4d));
+
+		pud_base = pud_offset(p4d, 0);
+		remove_pud_table(pud_base, addr, next, altmap, direct);
+		/*
+		 * For 4-level page tables we do not want to free PUDs, but in the
+		 * 5-level case we should free them. This code will have to change
+		 * to adapt for boot-time switching between 4 and 5 level page tables.
+		 */
+		if (pgtable_l5_enabled())
+			free_pud_table(pud_base, p4d);
+	}
+
+	if (direct)
+		update_page_count(PG_LEVEL_512G, -pages);
+}
+
+/* start and end are both virtual address. */
+static void __meminit
+remove_pagetable(unsigned long start, unsigned long end, bool direct,
+		struct vmem_altmap *altmap)
+{
+	unsigned long next;
+	unsigned long addr;
+	pgd_t *pgd;
+	p4d_t *p4d;
+
+	for (addr = start; addr < end; addr = next) {
+		next = pgd_addr_end(addr, end);
+
+		pgd = pgd_offset_k(addr);
+		if (!pgd_present(*pgd))
+			continue;
+
+		p4d = p4d_offset(pgd, 0);
+		remove_p4d_table(p4d, addr, next, altmap, direct);
+	}
+
+	flush_tlb_all();
+}
+
+void __ref vmemmap_free(unsigned long start, unsigned long end,
+		struct vmem_altmap *altmap)
+{
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
+
+	remove_pagetable(start, end, false, altmap);
+}
+
+static void __meminit
+kernel_physical_mapping_remove(unsigned long start, unsigned long end)
+{
+	start = (unsigned long)__va(start);
+	end = (unsigned long)__va(end);
+
+	remove_pagetable(start, end, true, NULL);
+}
+
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      struct dev_pagemap *pgmap)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
+	kernel_physical_mapping_remove(start, start + size);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+static struct kcore_list kcore_vsyscall;
+
+/*
+ * Pre-allocates page-table pages for the vmalloc area in the kernel page-table.
+ * Only the level which needs to be synchronized between all page-tables is
+ * allocated because the synchronization can be expensive.
+ */
+static void __init preallocate_vmalloc_pages(void)
+{
+	unsigned long addr;
+	const char *lvl;
+
+	for (addr = VMALLOC_START; addr <= VMEMORY_END; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		pgd_t *pgd = pgd_offset_k(addr);
+		p4d_t *p4d;
+		pud_t *pud;
+
+		lvl = "p4d";
+		p4d = p4d_alloc(&init_mm, pgd, addr);
+		if (!p4d)
+			goto failed;
+
+		if (pgtable_l5_enabled())
+			continue;
+
+		/*
+		 * The goal here is to allocate all possibly required
+		 * hardware page tables pointed to by the top hardware
+		 * level.
+		 *
+		 * On 4-level systems, the P4D layer is folded away and
+		 * the above code does no preallocation.  Below, go down
+		 * to the pud _software_ level to ensure the second
+		 * hardware level is allocated on 4-level systems too.
+		 */
+		lvl = "pud";
+		pud = pud_alloc(&init_mm, p4d, addr);
+		if (!pud)
+			goto failed;
+	}
+
+	return;
+
+failed:
+
+	/*
+	 * The pages have to be there now or they will be missing in
+	 * process page-tables later.
+	 */
+	panic("Failed to pre-allocate %s pages for vmalloc area\n", lvl);
+}
+
+void __init arch_mm_preinit(void)
+{
+	pci_iommu_alloc();
+}
+
+void __init mem_init(void)
+{
+	/* clear_bss() already clear the empty_zero_page */
+
+	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
+
+	/* Register memory areas for /proc/kcore */
+	if (get_gate_vma(&init_mm))
+		kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, PAGE_SIZE, KCORE_USER);
+
+	preallocate_vmalloc_pages();
+}
+
+int kernel_set_to_readonly;
+
+void mark_rodata_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
+	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long text_end = PFN_ALIGN(_etext);
+	unsigned long rodata_end = PFN_ALIGN(__end_rodata);
+	unsigned long all_end;
+
+	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
+	       (end - start) >> 10);
+	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+
+	kernel_set_to_readonly = 1;
+
+	/*
+	 * The rodata/data/bss/brk section (but not the kernel text!)
+	 * should also be not-executable.
+	 *
+	 * We align all_end to PMD_SIZE because the existing mapping
+	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+	 * split the PMD and the reminder between _brk_end and the end
+	 * of the PMD will remain mapped executable.
+	 *
+	 * Any PMD which was setup after the one which covers _brk_end
+	 * has been zapped already via cleanup_highmem().
+	 */
+	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
+	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
+
+	set_ftrace_ops_ro();
+
+#ifdef CONFIG_CPA_DEBUG
+	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
+	set_memory_rw(start, (end-start) >> PAGE_SHIFT);
+
+	printk(KERN_INFO "Testing CPA: again\n");
+	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
+#endif
+
+	free_kernel_image_pages("unused kernel image (text/rodata gap)",
+				(void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages("unused kernel image (rodata/data gap)",
+				(void *)rodata_end, (void *)_sdata);
+}
+
+/*
+ * Block size is the minimum amount of memory which can be hotplugged or
+ * hotremoved. It must be power of two and must be equal or larger than
+ * MIN_MEMORY_BLOCK_SIZE.
+ */
+#define MAX_BLOCK_SIZE (2UL << 30)
+
+/* Amount of ram needed to start using large blocks */
+#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+
+/* Adjustable memory block size */
+static unsigned long set_memory_block_size;
+int __init set_memory_block_size_order(unsigned int order)
+{
+	unsigned long size = 1UL << order;
+
+	if (size > MEM_SIZE_FOR_LARGE_BLOCK || size < MIN_MEMORY_BLOCK_SIZE)
+		return -EINVAL;
+
+	set_memory_block_size = size;
+	return 0;
+}
+
+static unsigned long probe_memory_block_size(void)
+{
+	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
+	unsigned long bz;
+
+	/* If memory block size has been set, then use it */
+	bz = set_memory_block_size;
+	if (bz)
+		goto done;
+
+	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
+	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
+		bz = MIN_MEMORY_BLOCK_SIZE;
+		goto done;
+	}
+
+	/*
+	 * When hotplug alignment is not a concern, maximize blocksize
+	 * to minimize overhead. Otherwise, align to the lesser of advice
+	 * alignment and end of memory alignment.
+	 */
+	bz = memory_block_advised_max_size();
+	if (!bz) {
+		bz = MAX_BLOCK_SIZE;
+		if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+			goto done;
+	} else {
+		bz = max(min(bz, MAX_BLOCK_SIZE), MIN_MEMORY_BLOCK_SIZE);
+	}
+
+	/* Find the largest allowed block size that aligns to memory end */
+	for (; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+		if (IS_ALIGNED(boot_mem_end, bz))
+			break;
+	}
+done:
+	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
+
+	return bz;
+}
+
+static unsigned long memory_block_size_probed;
+unsigned long memory_block_size_bytes(void)
+{
+	if (!memory_block_size_probed)
+		memory_block_size_probed = probe_memory_block_size();
+
+	return memory_block_size_probed;
+}
+
+/*
+ * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
+ */
+static long __meminitdata addr_start, addr_end;
+static void __meminitdata *p_start, *p_end;
+static int __meminitdata node_start;
+
+void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+			       unsigned long addr, unsigned long next)
+{
+	pte_t entry;
+
+	entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
+			PAGE_KERNEL_LARGE);
+	set_pmd(pmd, __pmd(pte_val(entry)));
+
+	/* check to see if we have contiguous blocks */
+	if (p_end != p || node_start != node) {
+		if (p_start)
+			pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+				addr_start, addr_end-1, p_start, p_end-1, node_start);
+		addr_start = addr;
+		node_start = node;
+		p_start = p;
+	}
+
+	addr_end = addr + PMD_SIZE;
+	p_end = p + PMD_SIZE;
+
+	if (!IS_ALIGNED(addr, PMD_SIZE) ||
+		!IS_ALIGNED(next, PMD_SIZE))
+		vmemmap_use_new_sub_pmd(addr, next);
+}
+
+int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+				unsigned long addr, unsigned long next)
+{
+	int large = pmd_leaf(*pmd);
+
+	if (pmd_leaf(*pmd)) {
+		vmemmap_verify((pte_t *)pmd, node, addr, next);
+		vmemmap_use_sub_pmd(addr, next);
+	}
+
+	return large;
+}
+
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
+		struct vmem_altmap *altmap)
+{
+	int err;
+
+	VM_BUG_ON(!PAGE_ALIGNED(start));
+	VM_BUG_ON(!PAGE_ALIGNED(end));
+
+	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+		err = vmemmap_populate_basepages(start, end, node, NULL);
+	else if (boot_cpu_has(X86_FEATURE_PSE))
+		err = vmemmap_populate_hugepages(start, end, node, altmap);
+	else if (altmap) {
+		pr_err_once("%s: no cpu support for altmap allocations\n",
+				__func__);
+		err = -ENOMEM;
+	} else
+		err = vmemmap_populate_basepages(start, end, node, NULL);
+	if (!err)
+		sync_global_pgds(start, end - 1);
+	return err;
+}
+
+void __meminit vmemmap_populate_print_last(void)
+{
+	if (p_start) {
+		pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+			addr_start, addr_end-1, p_start, p_end-1, node_start);
+		p_start = NULL;
+		p_end = NULL;
+		node_start = 0;
+	}
+}
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 000000000..9aaa756dd
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright © 2008 Ingo Molnar
+ */
+
+#include <asm/iomap.h>
+#include <asm/memtype.h>
+#include <linux/export.h>
+#include <linux/highmem.h>
+
+static int is_io_mapping_possible(resource_size_t base, unsigned long size)
+{
+#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT)
+	/* There is no way to map greater than 1 << 32 address without PAE */
+	if (base + size > 0x100000000ULL)
+		return 0;
+#endif
+	return 1;
+}
+
+int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
+{
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WC;
+	int ret;
+
+	if (!is_io_mapping_possible(base, size))
+		return -EINVAL;
+
+	ret = memtype_reserve_io(base, base + size, &pcm);
+	if (ret)
+		return ret;
+
+	*prot = __pgprot(__PAGE_KERNEL | cachemode2protval(pcm));
+	/* Filter out unsupported __PAGE_KERNEL* bits: */
+	pgprot_val(*prot) &= __default_kernel_pte_mask;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_create_wc);
+
+void iomap_free(resource_size_t base, unsigned long size)
+{
+	memtype_free_io(base, base + size);
+}
+EXPORT_SYMBOL_GPL(iomap_free);
+
+void __iomem *__iomap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
+{
+	/*
+	 * For non-PAT systems, translate non-WB request to UC- just in
+	 * case the caller set the PWT bit to prot directly without using
+	 * pgprot_writecombine(). UC- translates to uncached if the MTRR
+	 * is UC or WC. UC- gets the real intention, of the user, which is
+	 * "WC if the MTRR is WC, UC if you can't do that."
+	 */
+	if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB)
+		prot = __pgprot(__PAGE_KERNEL |
+				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
+
+	/* Filter out unsupported __PAGE_KERNEL* bits: */
+	pgprot_val(prot) &= __default_kernel_pte_mask;
+
+	return (void __force __iomem *)__kmap_local_pfn_prot(pfn, prot);
+}
+EXPORT_SYMBOL_GPL(__iomap_local_pfn_prot);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
new file mode 100644
index 000000000..12c8180ca
--- /dev/null
+++ b/arch/x86/mm/ioremap.c
@@ -0,0 +1,907 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Re-map IO memory to kernel address space so that we can access it.
+ * This is needed for high PCI addresses that aren't mapped in the
+ * 640k-1MB IO memory area on PC's
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ */
+
+#include <linux/memblock.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/ioremap.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmiotrace.h>
+#include <linux/cc_platform.h>
+#include <linux/efi.h>
+#include <linux/pgtable.h>
+#include <linux/kmsan.h>
+
+#include <asm/set_memory.h>
+#include <asm/e820/api.h>
+#include <asm/efi.h>
+#include <asm/fixmap.h>
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/memtype.h>
+#include <asm/setup.h>
+
+#include "physaddr.h"
+
+/*
+ * Descriptor controlling ioremap() behavior.
+ */
+struct ioremap_desc {
+	unsigned int flags;
+};
+
+/*
+ * Fix up the linear direct mapping of the kernel to avoid cache attribute
+ * conflicts.
+ */
+int ioremap_change_attr(unsigned long vaddr, unsigned long size,
+			enum page_cache_mode pcm)
+{
+	unsigned long nrpages = size >> PAGE_SHIFT;
+	int err;
+
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:
+	default:
+		err = _set_memory_uc(vaddr, nrpages);
+		break;
+	case _PAGE_CACHE_MODE_WC:
+		err = _set_memory_wc(vaddr, nrpages);
+		break;
+	case _PAGE_CACHE_MODE_WT:
+		err = _set_memory_wt(vaddr, nrpages);
+		break;
+	case _PAGE_CACHE_MODE_WB:
+		err = _set_memory_wb(vaddr, nrpages);
+		break;
+	}
+
+	return err;
+}
+
+/* Does the range (or a subset of) contain normal RAM? */
+static unsigned int __ioremap_check_ram(struct resource *res)
+{
+	unsigned long start_pfn, stop_pfn;
+	unsigned long pfn;
+
+	if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
+		return 0;
+
+	start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	stop_pfn = (res->end + 1) >> PAGE_SHIFT;
+	if (stop_pfn > start_pfn) {
+		for_each_valid_pfn(pfn, start_pfn, stop_pfn)
+			if (!PageReserved(pfn_to_page(pfn)))
+				return IORES_MAP_SYSTEM_RAM;
+	}
+
+	return 0;
+}
+
+/*
+ * In a SEV guest, NONE and RESERVED should not be mapped encrypted because
+ * there the whole memory is already encrypted.
+ */
+static unsigned int __ioremap_check_encrypted(struct resource *res)
+{
+	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return 0;
+
+	switch (res->desc) {
+	case IORES_DESC_NONE:
+	case IORES_DESC_RESERVED:
+		break;
+	default:
+		return IORES_MAP_ENCRYPTED;
+	}
+
+	return 0;
+}
+
+/*
+ * The EFI runtime services data area is not covered by walk_mem_res(), but must
+ * be mapped encrypted when SEV is active.
+ */
+static void __ioremap_check_other(resource_size_t addr, struct ioremap_desc *desc)
+{
+	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return;
+
+	if (x86_platform.hyper.is_private_mmio(addr)) {
+		desc->flags |= IORES_MAP_ENCRYPTED;
+		return;
+	}
+
+	if (!IS_ENABLED(CONFIG_EFI))
+		return;
+
+	if (efi_mem_type(addr) == EFI_RUNTIME_SERVICES_DATA ||
+	    (efi_mem_type(addr) == EFI_BOOT_SERVICES_DATA &&
+	     efi_mem_attributes(addr) & EFI_MEMORY_RUNTIME))
+		desc->flags |= IORES_MAP_ENCRYPTED;
+}
+
+static int __ioremap_collect_map_flags(struct resource *res, void *arg)
+{
+	struct ioremap_desc *desc = arg;
+
+	if (!(desc->flags & IORES_MAP_SYSTEM_RAM))
+		desc->flags |= __ioremap_check_ram(res);
+
+	if (!(desc->flags & IORES_MAP_ENCRYPTED))
+		desc->flags |= __ioremap_check_encrypted(res);
+
+	return ((desc->flags & (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED)) ==
+			       (IORES_MAP_SYSTEM_RAM | IORES_MAP_ENCRYPTED));
+}
+
+/*
+ * To avoid multiple resource walks, this function walks resources marked as
+ * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a
+ * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
+ *
+ * After that, deal with misc other ranges in __ioremap_check_other() which do
+ * not fall into the above category.
+ */
+static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
+				struct ioremap_desc *desc)
+{
+	u64 start, end;
+
+	start = (u64)addr;
+	end = start + size - 1;
+	memset(desc, 0, sizeof(struct ioremap_desc));
+
+	walk_mem_res(start, end, desc, __ioremap_collect_map_flags);
+
+	__ioremap_check_other(addr, desc);
+}
+
+/*
+ * Remap an arbitrary physical address space into the kernel virtual
+ * address space. It transparently creates kernel huge I/O mapping when
+ * the physical address is aligned by a huge page size (1GB or 2MB) and
+ * the requested size is at least the huge page size.
+ *
+ * NOTE: MTRRs can override PAT memory types with a 4KB granularity.
+ * Therefore, the mapping code falls back to use a smaller page toward 4KB
+ * when a mapping range is covered by non-WB type of MTRRs.
+ *
+ * NOTE! We need to allow non-page-aligned mappings too: we will obviously
+ * have to convert them into an offset in a page-aligned mapping, but the
+ * caller shouldn't need to know that small detail.
+ */
+static void __iomem *
+__ioremap_caller(resource_size_t phys_addr, unsigned long size,
+		 enum page_cache_mode pcm, void *caller, bool encrypted)
+{
+	unsigned long offset, vaddr;
+	resource_size_t last_addr;
+	const resource_size_t unaligned_phys_addr = phys_addr;
+	const unsigned long unaligned_size = size;
+	struct ioremap_desc io_desc;
+	struct vm_struct *area;
+	enum page_cache_mode new_pcm;
+	pgprot_t prot;
+	int retval;
+	void __iomem *ret_addr;
+
+	/* Don't allow wraparound or zero size */
+	last_addr = phys_addr + size - 1;
+	if (!size || last_addr < phys_addr)
+		return NULL;
+
+	if (!phys_addr_valid(phys_addr)) {
+		printk(KERN_WARNING "ioremap: invalid physical address %llx\n",
+		       (unsigned long long)phys_addr);
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	__ioremap_check_mem(phys_addr, size, &io_desc);
+
+	/*
+	 * Don't allow anybody to remap normal RAM that we're using..
+	 */
+	if (io_desc.flags & IORES_MAP_SYSTEM_RAM) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
+		return NULL;
+	}
+
+	/*
+	 * Mappings have to be page-aligned
+	 */
+	offset = phys_addr & ~PAGE_MASK;
+	phys_addr &= PAGE_MASK;
+	size = PAGE_ALIGN(last_addr+1) - phys_addr;
+
+	/*
+	 * Mask out any bits not part of the actual physical
+	 * address, like memory encryption bits.
+	 */
+	phys_addr &= PHYSICAL_PAGE_MASK;
+
+	retval = memtype_reserve(phys_addr, (u64)phys_addr + size,
+						pcm, &new_pcm);
+	if (retval) {
+		printk(KERN_ERR "ioremap memtype_reserve failed %d\n", retval);
+		return NULL;
+	}
+
+	if (pcm != new_pcm) {
+		if (!is_new_memtype_allowed(phys_addr, size, pcm, new_pcm)) {
+			printk(KERN_ERR
+		"ioremap error for 0x%llx-0x%llx, requested 0x%x, got 0x%x\n",
+				(unsigned long long)phys_addr,
+				(unsigned long long)(phys_addr + size),
+				pcm, new_pcm);
+			goto err_free_memtype;
+		}
+		pcm = new_pcm;
+	}
+
+	/*
+	 * If the page being mapped is in memory and SEV is active then
+	 * make sure the memory encryption attribute is enabled in the
+	 * resulting mapping.
+	 * In TDX guests, memory is marked private by default. If encryption
+	 * is not requested (using encrypted), explicitly set decrypt
+	 * attribute in all IOREMAPPED memory.
+	 */
+	prot = PAGE_KERNEL_IO;
+	if ((io_desc.flags & IORES_MAP_ENCRYPTED) || encrypted)
+		prot = pgprot_encrypted(prot);
+	else
+		prot = pgprot_decrypted(prot);
+
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:
+	default:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_UC));
+		break;
+	case _PAGE_CACHE_MODE_UC_MINUS:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
+		break;
+	case _PAGE_CACHE_MODE_WC:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WC));
+		break;
+	case _PAGE_CACHE_MODE_WT:
+		prot = __pgprot(pgprot_val(prot) |
+				cachemode2protval(_PAGE_CACHE_MODE_WT));
+		break;
+	case _PAGE_CACHE_MODE_WB:
+		break;
+	}
+
+	/*
+	 * Ok, go for it..
+	 */
+	area = get_vm_area_caller(size, VM_IOREMAP, caller);
+	if (!area)
+		goto err_free_memtype;
+	area->phys_addr = phys_addr;
+	vaddr = (unsigned long) area->addr;
+
+	if (memtype_kernel_map_sync(phys_addr, size, pcm))
+		goto err_free_area;
+
+	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
+		goto err_free_area;
+
+	ret_addr = (void __iomem *) (vaddr + offset);
+	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
+
+	/*
+	 * Check if the request spans more than any BAR in the iomem resource
+	 * tree.
+	 */
+	if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size))
+		pr_warn("caller %pS mapping multiple BARs\n", caller);
+
+	return ret_addr;
+err_free_area:
+	free_vm_area(area);
+err_free_memtype:
+	memtype_free(phys_addr, phys_addr + size);
+	return NULL;
+}
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @phys_addr:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * on the CPU as well as honouring existing caching rules from things like
+ * the PCI bus. Note that there are other caches and buffers on many
+ * busses. In particular driver authors should read up on PCI writes
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap(resource_size_t phys_addr, unsigned long size)
+{
+	/*
+	 * Ideally, this should be:
+	 *	pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
+	 *
+	 * Till we fix all X drivers to use ioremap_wc(), we will use
+	 * UC MINUS. Drivers that are certain they need or can already
+	 * be converted over to strong UC can use ioremap_uc().
+	 */
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
+
+	return __ioremap_caller(phys_addr, size, pcm,
+				__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL(ioremap);
+
+/**
+ * ioremap_uc     -   map bus memory into CPU space as strongly uncachable
+ * @phys_addr:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_uc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked with a strong
+ * preference as completely uncachable on the CPU when possible. For non-PAT
+ * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
+ * systems this will set the PAT entry for the pages as strong UC.  This call
+ * will honor existing caching rules from things like the PCI bus. Note that
+ * there are other caches and buffers on many busses. In particular driver
+ * authors should read up on PCI writes.
+ *
+ * It's useful if some control registers are in such an area and
+ * write combining or read caching is not desirable:
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
+{
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;
+
+	return __ioremap_caller(phys_addr, size, pcm,
+				__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL_GPL(ioremap_uc);
+
+/**
+ * ioremap_wc	-	map memory into CPU space write combined
+ * @phys_addr:	bus address of the memory
+ * @size:	size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write combining.
+ * Write combining allows faster writes to some hardware devices.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
+					__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+/**
+ * ioremap_wt	-	map memory into CPU space write through
+ * @phys_addr:	bus address of the memory
+ * @size:	size of the resource to map
+ *
+ * This version of ioremap ensures that the memory is marked write through.
+ * Write through stores data into memory while keeping the cache up-to-date.
+ *
+ * Must be freed with iounmap.
+ */
+void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
+					__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL(ioremap_wt);
+
+void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
+				__builtin_return_address(0), true);
+}
+EXPORT_SYMBOL(ioremap_encrypted);
+
+void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
+{
+	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
+				__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
+			   pgprot_t prot)
+{
+	return __ioremap_caller(phys_addr, size,
+				pgprot2cachemode(prot),
+				__builtin_return_address(0), false);
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
+void iounmap(volatile void __iomem *addr)
+{
+	struct vm_struct *p, *o;
+
+	if (WARN_ON_ONCE(!is_ioremap_addr((void __force *)addr)))
+		return;
+
+	/*
+	 * The PCI/ISA range special-casing was removed from __ioremap()
+	 * so this check, in theory, can be removed. However, there are
+	 * cases where iounmap() is called for addresses not obtained via
+	 * ioremap() (vga16fb for example). Add a warning so that these
+	 * cases can be caught and fixed.
+	 */
+	if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) &&
+	    (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) {
+		WARN(1, "iounmap() called for ISA range not obtained using ioremap()\n");
+		return;
+	}
+
+	mmiotrace_iounmap(addr);
+
+	addr = (volatile void __iomem *)
+		(PAGE_MASK & (unsigned long __force)addr);
+
+	/* Use the vm area unlocked, assuming the caller
+	   ensures there isn't another iounmap for the same address
+	   in parallel. Reuse of the virtual address is prevented by
+	   leaving it in the global lists until we're done with it.
+	   cpa takes care of the direct mappings. */
+	p = find_vm_area((void __force *)addr);
+
+	if (!p) {
+		printk(KERN_ERR "iounmap: bad address %p\n", addr);
+		dump_stack();
+		return;
+	}
+
+	kmsan_iounmap_page_range((unsigned long)addr,
+		(unsigned long)addr + get_vm_area_size(p));
+	memtype_free(p->phys_addr, p->phys_addr + get_vm_area_size(p));
+
+	/* Finally remove it */
+	o = remove_vm_area((void __force *)addr);
+	BUG_ON(p != o || o == NULL);
+	kfree(p);
+}
+EXPORT_SYMBOL(iounmap);
+
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
+{
+	if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (void __force *)ioremap_cache(phys_addr, size);
+
+	return (void __force *)ioremap_encrypted(phys_addr, size);
+}
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+void *xlate_dev_mem_ptr(phys_addr_t phys)
+{
+	unsigned long start  = phys &  PAGE_MASK;
+	unsigned long offset = phys & ~PAGE_MASK;
+	void *vaddr;
+
+	/* memremap() maps if RAM, otherwise falls back to ioremap() */
+	vaddr = memremap(start, PAGE_SIZE, MEMREMAP_WB);
+
+	/* Only add the offset on success and return NULL if memremap() failed */
+	if (vaddr)
+		vaddr += offset;
+
+	return vaddr;
+}
+
+void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
+{
+	memunmap((void *)((unsigned long)addr & PAGE_MASK));
+}
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+/*
+ * Examine the physical address to determine if it is an area of memory
+ * that should be mapped decrypted.  If the memory is not part of the
+ * kernel usable area it was accessed and created decrypted, so these
+ * areas should be mapped decrypted. And since the encryption key can
+ * change across reboots, persistent memory should also be mapped
+ * decrypted.
+ *
+ * If SEV is active, that implies that BIOS/UEFI also ran encrypted so
+ * only persistent memory should be mapped decrypted.
+ */
+static bool memremap_should_map_decrypted(resource_size_t phys_addr,
+					  unsigned long size)
+{
+	int is_pmem;
+
+	/*
+	 * Check if the address is part of a persistent memory region.
+	 * This check covers areas added by E820, EFI and ACPI.
+	 */
+	is_pmem = region_intersects(phys_addr, size, IORESOURCE_MEM,
+				    IORES_DESC_PERSISTENT_MEMORY);
+	if (is_pmem != REGION_DISJOINT)
+		return true;
+
+	/*
+	 * Check if the non-volatile attribute is set for an EFI
+	 * reserved area.
+	 */
+	if (efi_enabled(EFI_BOOT)) {
+		switch (efi_mem_type(phys_addr)) {
+		case EFI_RESERVED_TYPE:
+			if (efi_mem_attributes(phys_addr) & EFI_MEMORY_NV)
+				return true;
+			break;
+		default:
+			break;
+		}
+	}
+
+	/* Check if the address is outside kernel usable area */
+	switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) {
+	case E820_TYPE_RESERVED:
+	case E820_TYPE_ACPI:
+	case E820_TYPE_NVS:
+	case E820_TYPE_UNUSABLE:
+		/* For SEV, these areas are encrypted */
+		if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+			break;
+		fallthrough;
+
+	case E820_TYPE_PRAM:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+/*
+ * Examine the physical address to determine if it is EFI data. Check
+ * it against the boot params structure and EFI tables and memory types.
+ */
+static bool memremap_is_efi_data(resource_size_t phys_addr)
+{
+	u64 paddr;
+
+	/* Check if the address is part of EFI boot/runtime data */
+	if (!efi_enabled(EFI_BOOT))
+		return false;
+
+	paddr = boot_params.efi_info.efi_memmap_hi;
+	paddr <<= 32;
+	paddr |= boot_params.efi_info.efi_memmap;
+	if (phys_addr == paddr)
+		return true;
+
+	paddr = boot_params.efi_info.efi_systab_hi;
+	paddr <<= 32;
+	paddr |= boot_params.efi_info.efi_systab;
+	if (phys_addr == paddr)
+		return true;
+
+	if (efi_is_table_address(phys_addr))
+		return true;
+
+	switch (efi_mem_type(phys_addr)) {
+	case EFI_BOOT_SERVICES_DATA:
+	case EFI_RUNTIME_SERVICES_DATA:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
+/*
+ * Examine the physical address to determine if it is boot data by checking
+ * it against the boot params setup_data chain.
+ */
+static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early)
+{
+	unsigned int setup_data_sz = sizeof(struct setup_data);
+	struct setup_indirect *indirect;
+	struct setup_data *data;
+	u64 paddr, paddr_next;
+
+	paddr = boot_params.hdr.setup_data;
+	while (paddr) {
+		unsigned int len, size;
+
+		if (phys_addr == paddr)
+			return true;
+
+		if (early)
+			data = early_memremap_decrypted(paddr, setup_data_sz);
+		else
+			data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC);
+		if (!data) {
+			pr_warn("failed to remap setup_data entry\n");
+			return false;
+		}
+
+		size = setup_data_sz;
+
+		paddr_next = data->next;
+		len = data->len;
+
+		if ((phys_addr > paddr) &&
+		    (phys_addr < (paddr + setup_data_sz + len))) {
+			if (early)
+				early_memunmap(data, setup_data_sz);
+			else
+				memunmap(data);
+			return true;
+		}
+
+		if (data->type == SETUP_INDIRECT) {
+			size += len;
+			if (early) {
+				early_memunmap(data, setup_data_sz);
+				data = early_memremap_decrypted(paddr, size);
+			} else {
+				memunmap(data);
+				data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC);
+			}
+			if (!data) {
+				pr_warn("failed to remap indirect setup_data\n");
+				return false;
+			}
+
+			indirect = (struct setup_indirect *)data->data;
+
+			if (indirect->type != SETUP_INDIRECT) {
+				paddr = indirect->addr;
+				len = indirect->len;
+			}
+		}
+
+		if (early)
+			early_memunmap(data, size);
+		else
+			memunmap(data);
+
+		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
+			return true;
+
+		paddr = paddr_next;
+	}
+
+	return false;
+}
+
+static bool memremap_is_setup_data(resource_size_t phys_addr)
+{
+	return __memremap_is_setup_data(phys_addr, false);
+}
+
+static bool __init early_memremap_is_setup_data(resource_size_t phys_addr)
+{
+	return __memremap_is_setup_data(phys_addr, true);
+}
+
+/*
+ * Architecture function to determine if RAM remap is allowed. By default, a
+ * RAM remap will map the data as encrypted. Determine if a RAM remap should
+ * not be done so that the data will be mapped decrypted.
+ */
+bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
+				 unsigned long flags)
+{
+	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return true;
+
+	if (flags & MEMREMAP_ENC)
+		return true;
+
+	if (flags & MEMREMAP_DEC)
+		return false;
+
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		if (memremap_is_setup_data(phys_addr) ||
+		    memremap_is_efi_data(phys_addr))
+			return false;
+	}
+
+	return !memremap_should_map_decrypted(phys_addr, size);
+}
+
+/*
+ * Architecture override of __weak function to adjust the protection attributes
+ * used when remapping memory. By default, early_memremap() will map the data
+ * as encrypted. Determine if an encrypted mapping should not be done and set
+ * the appropriate protection attributes.
+ */
+pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
+					     unsigned long size,
+					     pgprot_t prot)
+{
+	bool encrypted_prot;
+
+	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return prot;
+
+	encrypted_prot = true;
+
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		if (early_memremap_is_setup_data(phys_addr) ||
+		    memremap_is_efi_data(phys_addr))
+			encrypted_prot = false;
+	}
+
+	if (encrypted_prot && memremap_should_map_decrypted(phys_addr, size))
+		encrypted_prot = false;
+
+	return encrypted_prot ? pgprot_encrypted(prot)
+			      : pgprot_decrypted(prot);
+}
+
+bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size)
+{
+	return arch_memremap_can_ram_remap(phys_addr, size, 0);
+}
+
+/* Remap memory with encryption */
+void __init *early_memremap_encrypted(resource_size_t phys_addr,
+				      unsigned long size)
+{
+	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC);
+}
+
+/*
+ * Remap memory with encryption and write-protected - cannot be called
+ * before pat_init() is called
+ */
+void __init *early_memremap_encrypted_wp(resource_size_t phys_addr,
+					 unsigned long size)
+{
+	if (!x86_has_pat_wp())
+		return NULL;
+	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC_WP);
+}
+
+/* Remap memory without encryption */
+void __init *early_memremap_decrypted(resource_size_t phys_addr,
+				      unsigned long size)
+{
+	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC);
+}
+
+/*
+ * Remap memory without encryption and write-protected - cannot be called
+ * before pat_init() is called
+ */
+void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
+					 unsigned long size)
+{
+	if (!x86_has_pat_wp())
+		return NULL;
+	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP);
+}
+#endif	/* CONFIG_AMD_MEM_ENCRYPT */
+
+static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;
+
+static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
+{
+	/* Don't assume we're using swapper_pg_dir at this point */
+	pgd_t *base = __va(read_cr3_pa());
+	pgd_t *pgd = &base[pgd_index(addr)];
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
+
+	return pmd;
+}
+
+static inline pte_t * __init early_ioremap_pte(unsigned long addr)
+{
+	return &bm_pte[pte_index(addr)];
+}
+
+bool __init is_early_ioremap_ptep(pte_t *ptep)
+{
+	return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)];
+}
+
+void __init early_ioremap_init(void)
+{
+	pmd_t *pmd;
+
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
+#else
+	WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
+#endif
+
+	early_ioremap_setup();
+
+	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
+	memset(bm_pte, 0, sizeof(bm_pte));
+	pmd_populate_kernel(&init_mm, pmd, bm_pte);
+
+	/*
+	 * The boot-ioremap range spans multiple pmds, for which
+	 * we are not prepared:
+	 */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
+		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
+#undef __FIXADDR_TOP
+	if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
+		WARN_ON(1);
+		printk(KERN_WARNING "pmd %p != %p\n",
+		       pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
+		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
+			fix_to_virt(FIX_BTMAP_BEGIN));
+		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_END):   %08lx\n",
+			fix_to_virt(FIX_BTMAP_END));
+
+		printk(KERN_WARNING "FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
+		printk(KERN_WARNING "FIX_BTMAP_BEGIN:     %d\n",
+		       FIX_BTMAP_BEGIN);
+	}
+}
+
+void __init __early_set_fixmap(enum fixed_addresses idx,
+			       phys_addr_t phys, pgprot_t flags)
+{
+	unsigned long addr = __fix_to_virt(idx);
+	pte_t *pte;
+
+	if (idx >= __end_of_fixed_addresses) {
+		BUG();
+		return;
+	}
+	pte = early_ioremap_pte(addr);
+
+	/* Sanitize 'prot' against any unsupported bits: */
+	pgprot_val(flags) &= __supported_pte_mask;
+
+	if (pgprot_val(flags))
+		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
+	else
+		pte_clear(&init_mm, addr, pte);
+	flush_tlb_one_kernel(addr);
+}
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
new file mode 100644
index 000000000..998b6010d
--- /dev/null
+++ b/arch/x86/mm/kasan_init_64.c
@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0
+#define pr_fmt(fmt) "kasan: " fmt
+
+/* cpu_feature_enabled() cannot be used this early */
+#define USE_EARLY_PGTABLE_L5
+
+#include <linux/memblock.h>
+#include <linux/kasan.h>
+#include <linux/kdebug.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/vmalloc.h>
+
+#include <asm/e820/types.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/cpu_entry_area.h>
+
+extern struct range pfn_mapped[E820_MAX_ENTRIES];
+
+static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
+
+static __init void *early_alloc(size_t size, int nid, bool should_panic)
+{
+	void *ptr = memblock_alloc_try_nid(size, size,
+			__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+
+	if (!ptr && should_panic)
+		panic("%pS: Failed to allocate page, nid=%d from=%lx\n",
+		      (void *)_RET_IP_, nid, __pa(MAX_DMA_ADDRESS));
+
+	return ptr;
+}
+
+static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
+				      unsigned long end, int nid)
+{
+	pte_t *pte;
+
+	if (pmd_none(*pmd)) {
+		void *p;
+
+		if (boot_cpu_has(X86_FEATURE_PSE) &&
+		    ((end - addr) == PMD_SIZE) &&
+		    IS_ALIGNED(addr, PMD_SIZE)) {
+			p = early_alloc(PMD_SIZE, nid, false);
+			if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
+				return;
+			memblock_free(p, PMD_SIZE);
+		}
+
+		p = early_alloc(PAGE_SIZE, nid, true);
+		pmd_populate_kernel(&init_mm, pmd, p);
+	}
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		pte_t entry;
+		void *p;
+
+		if (!pte_none(*pte))
+			continue;
+
+		p = early_alloc(PAGE_SIZE, nid, true);
+		entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
+		set_pte_at(&init_mm, addr, pte, entry);
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
+				      unsigned long end, int nid)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	if (pud_none(*pud)) {
+		void *p;
+
+		if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
+		    ((end - addr) == PUD_SIZE) &&
+		    IS_ALIGNED(addr, PUD_SIZE)) {
+			p = early_alloc(PUD_SIZE, nid, false);
+			if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
+				return;
+			memblock_free(p, PUD_SIZE);
+		}
+
+		p = early_alloc(PAGE_SIZE, nid, true);
+		pud_populate(&init_mm, pud, p);
+	}
+
+	pmd = pmd_offset(pud, addr);
+	do {
+		next = pmd_addr_end(addr, end);
+		if (!pmd_leaf(*pmd))
+			kasan_populate_pmd(pmd, addr, next, nid);
+	} while (pmd++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
+				      unsigned long end, int nid)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	if (p4d_none(*p4d)) {
+		void *p = early_alloc(PAGE_SIZE, nid, true);
+
+		p4d_populate(&init_mm, p4d, p);
+	}
+
+	pud = pud_offset(p4d, addr);
+	do {
+		next = pud_addr_end(addr, end);
+		if (!pud_leaf(*pud))
+			kasan_populate_pud(pud, addr, next, nid);
+	} while (pud++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
+				      unsigned long end, int nid)
+{
+	void *p;
+	p4d_t *p4d;
+	unsigned long next;
+
+	if (pgd_none(*pgd)) {
+		p = early_alloc(PAGE_SIZE, nid, true);
+		pgd_populate(&init_mm, pgd, p);
+	}
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		kasan_populate_p4d(p4d, addr, next, nid);
+	} while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_populate_shadow(unsigned long addr, unsigned long end,
+					 int nid)
+{
+	pgd_t *pgd;
+	unsigned long next;
+
+	addr = addr & PAGE_MASK;
+	end = round_up(end, PAGE_SIZE);
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		kasan_populate_pgd(pgd, addr, next, nid);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static void __init map_range(struct range *range)
+{
+	unsigned long start;
+	unsigned long end;
+
+	start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start));
+	end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end));
+
+	kasan_populate_shadow(start, end, early_pfn_to_nid(range->start));
+}
+
+static void __init clear_pgds(unsigned long start,
+			unsigned long end)
+{
+	pgd_t *pgd;
+	/* See comment in kasan_init() */
+	unsigned long pgd_end = end & PGDIR_MASK;
+
+	for (; start < pgd_end; start += PGDIR_SIZE) {
+		pgd = pgd_offset_k(start);
+		/*
+		 * With folded p4d, pgd_clear() is nop, use p4d_clear()
+		 * instead.
+		 */
+		if (pgtable_l5_enabled())
+			pgd_clear(pgd);
+		else
+			p4d_clear(p4d_offset(pgd, start));
+	}
+
+	pgd = pgd_offset_k(start);
+	for (; start < end; start += P4D_SIZE)
+		p4d_clear(p4d_offset(pgd, start));
+}
+
+static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
+{
+	unsigned long p4d;
+
+	if (!pgtable_l5_enabled())
+		return (p4d_t *)pgd;
+
+	p4d = pgd_val(*pgd) & PTE_PFN_MASK;
+	p4d += __START_KERNEL_map - phys_base;
+	return (p4d_t *)p4d + p4d_index(addr);
+}
+
+static void __init kasan_early_p4d_populate(pgd_t *pgd,
+		unsigned long addr,
+		unsigned long end)
+{
+	pgd_t pgd_entry;
+	p4d_t *p4d, p4d_entry;
+	unsigned long next;
+
+	if (pgd_none(*pgd)) {
+		pgd_entry = __pgd(_KERNPG_TABLE |
+					__pa_nodebug(kasan_early_shadow_p4d));
+		set_pgd(pgd, pgd_entry);
+	}
+
+	p4d = early_p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (!p4d_none(*p4d))
+			continue;
+
+		p4d_entry = __p4d(_KERNPG_TABLE |
+					__pa_nodebug(kasan_early_shadow_pud));
+		set_p4d(p4d, p4d_entry);
+	} while (p4d++, addr = next, addr != end && p4d_none(*p4d));
+}
+
+static void __init kasan_map_early_shadow(pgd_t *pgd)
+{
+	/* See comment in kasan_init() */
+	unsigned long addr = KASAN_SHADOW_START & PGDIR_MASK;
+	unsigned long end = KASAN_SHADOW_END;
+	unsigned long next;
+
+	pgd += pgd_index(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		kasan_early_p4d_populate(pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+static void __init kasan_shallow_populate_p4ds(pgd_t *pgd,
+					       unsigned long addr,
+					       unsigned long end)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	void *p;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (p4d_none(*p4d)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			p4d_populate(&init_mm, p4d, p);
+		}
+	} while (p4d++, addr = next, addr != end);
+}
+
+static void __init kasan_shallow_populate_pgds(void *start, void *end)
+{
+	unsigned long addr, next;
+	pgd_t *pgd;
+	void *p;
+
+	addr = (unsigned long)start;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, (unsigned long)end);
+
+		if (pgd_none(*pgd)) {
+			p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
+			pgd_populate(&init_mm, pgd, p);
+		}
+
+		/*
+		 * we need to populate p4ds to be synced when running in
+		 * four level mode - see sync_global_pgds_l4()
+		 */
+		kasan_shallow_populate_p4ds(pgd, addr, next);
+	} while (pgd++, addr = next, addr != (unsigned long)end);
+}
+
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_early_shadow_page) |
+				__PAGE_KERNEL | _PAGE_ENC;
+	pmdval_t pmd_val = __pa_nodebug(kasan_early_shadow_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_early_shadow_pmd) | _KERNPG_TABLE;
+	p4dval_t p4d_val = __pa_nodebug(kasan_early_shadow_pud) | _KERNPG_TABLE;
+
+	/* Mask out unsupported __PAGE_KERNEL bits: */
+	pte_val &= __default_kernel_pte_mask;
+	pmd_val &= __default_kernel_pte_mask;
+	pud_val &= __default_kernel_pte_mask;
+	p4d_val &= __default_kernel_pte_mask;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_early_shadow_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_early_shadow_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_early_shadow_pud[i] = __pud(pud_val);
+
+	for (i = 0; pgtable_l5_enabled() && i < PTRS_PER_P4D; i++)
+		kasan_early_shadow_p4d[i] = __p4d(p4d_val);
+
+	kasan_map_early_shadow(early_top_pgt);
+	kasan_map_early_shadow(init_top_pgt);
+}
+
+static unsigned long kasan_mem_to_shadow_align_down(unsigned long va)
+{
+	unsigned long shadow = (unsigned long)kasan_mem_to_shadow((void *)va);
+
+	return round_down(shadow, PAGE_SIZE);
+}
+
+static unsigned long kasan_mem_to_shadow_align_up(unsigned long va)
+{
+	unsigned long shadow = (unsigned long)kasan_mem_to_shadow((void *)va);
+
+	return round_up(shadow, PAGE_SIZE);
+}
+
+void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid)
+{
+	unsigned long shadow_start, shadow_end;
+
+	shadow_start = kasan_mem_to_shadow_align_down((unsigned long)va);
+	shadow_end = kasan_mem_to_shadow_align_up((unsigned long)va + size);
+	kasan_populate_shadow(shadow_start, shadow_end, nid);
+}
+
+void __init kasan_init(void)
+{
+	unsigned long shadow_cea_begin, shadow_cea_per_cpu_begin, shadow_cea_end;
+	int i;
+
+	memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt));
+
+	/*
+	 * We use the same shadow offset for 4- and 5-level paging to
+	 * facilitate boot-time switching between paging modes.
+	 * As result in 5-level paging mode KASAN_SHADOW_START and
+	 * KASAN_SHADOW_END are not aligned to PGD boundary.
+	 *
+	 * KASAN_SHADOW_START doesn't share PGD with anything else.
+	 * We claim whole PGD entry to make things easier.
+	 *
+	 * KASAN_SHADOW_END lands in the last PGD entry and it collides with
+	 * bunch of things like kernel code, modules, EFI mapping, etc.
+	 * We need to take extra steps to not overwrite them.
+	 */
+	if (pgtable_l5_enabled()) {
+		void *ptr;
+
+		ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
+		memcpy(tmp_p4d_table, (void *)ptr, sizeof(tmp_p4d_table));
+		set_pgd(&early_top_pgt[pgd_index(KASAN_SHADOW_END)],
+				__pgd(__pa(tmp_p4d_table) | _KERNPG_TABLE));
+	}
+
+	load_cr3(early_top_pgt);
+	__flush_tlb_all();
+
+	clear_pgds(KASAN_SHADOW_START & PGDIR_MASK, KASAN_SHADOW_END);
+
+	kasan_populate_early_shadow((void *)(KASAN_SHADOW_START & PGDIR_MASK),
+			kasan_mem_to_shadow((void *)PAGE_OFFSET));
+
+	for (i = 0; i < E820_MAX_ENTRIES; i++) {
+		if (pfn_mapped[i].end == 0)
+			break;
+
+		map_range(&pfn_mapped[i]);
+	}
+
+	shadow_cea_begin = kasan_mem_to_shadow_align_down(CPU_ENTRY_AREA_BASE);
+	shadow_cea_per_cpu_begin = kasan_mem_to_shadow_align_up(CPU_ENTRY_AREA_PER_CPU);
+	shadow_cea_end = kasan_mem_to_shadow_align_up(CPU_ENTRY_AREA_BASE +
+						      CPU_ENTRY_AREA_MAP_SIZE);
+
+	kasan_populate_early_shadow(
+		kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
+		kasan_mem_to_shadow((void *)VMALLOC_START));
+
+	/*
+	 * If we're in full vmalloc mode, don't back vmalloc space with early
+	 * shadow pages. Instead, prepopulate pgds/p4ds so they are synced to
+	 * the global table and we can populate the lower levels on demand.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_shallow_populate_pgds(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+	else
+		kasan_populate_early_shadow(
+			kasan_mem_to_shadow((void *)VMALLOC_START),
+			kasan_mem_to_shadow((void *)VMALLOC_END));
+
+	kasan_populate_early_shadow(
+		kasan_mem_to_shadow((void *)VMALLOC_END + 1),
+		(void *)shadow_cea_begin);
+
+	/*
+	 * Populate the shadow for the shared portion of the CPU entry area.
+	 * Shadows for the per-CPU areas are mapped on-demand, as each CPU's
+	 * area is randomly placed somewhere in the 512GiB range and mapping
+	 * the entire 512GiB range is prohibitively expensive.
+	 */
+	kasan_populate_shadow(shadow_cea_begin,
+			      shadow_cea_per_cpu_begin, 0);
+
+	kasan_populate_early_shadow((void *)shadow_cea_end,
+			kasan_mem_to_shadow((void *)__START_KERNEL_map));
+
+	kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
+			      (unsigned long)kasan_mem_to_shadow(_end),
+			      early_pfn_to_nid(__pa(_stext)));
+
+	kasan_populate_early_shadow(kasan_mem_to_shadow((void *)MODULES_END),
+					(void *)KASAN_SHADOW_END);
+
+	load_cr3(init_top_pgt);
+	__flush_tlb_all();
+
+	/*
+	 * kasan_early_shadow_page has been used as early shadow memory, thus
+	 * it may contain some garbage. Now we can clear and write protect it,
+	 * since after the TLB flush no one should write to it.
+	 */
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte_t pte;
+		pgprot_t prot;
+
+		prot = __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC);
+		pgprot_val(prot) &= __default_kernel_pte_mask;
+
+		pte = __pte(__pa(kasan_early_shadow_page) | pgprot_val(prot));
+		set_pte(&kasan_early_shadow_pte[i], pte);
+	}
+	/* Flush TLBs again to be sure that write protection applied. */
+	__flush_tlb_all();
+
+	init_task.kasan_depth = 0;
+	kasan_init_generic();
+}
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
new file mode 100644
index 000000000..834641c60
--- /dev/null
+++ b/arch/x86/mm/kaslr.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This file implements KASLR memory randomization for x86_64. It randomizes
+ * the virtual address space of kernel memory regions (physical memory
+ * mapping, vmalloc & vmemmap) for x86_64. This security feature mitigates
+ * exploits relying on predictable kernel addresses.
+ *
+ * Entropy is generated using the KASLR early boot functions now shared in
+ * the lib directory (originally written by Kees Cook). Randomization is
+ * done on PGD & P4D/PUD page table levels to increase possible addresses.
+ * The physical memory mapping code was adapted to support P4D/PUD level
+ * virtual addresses. This implementation on the best configuration provides
+ * 30,000 possible virtual addresses in average for each memory region.
+ * An additional low memory page is used to ensure each CPU can start with
+ * a PGD aligned virtual address (for realmode).
+ *
+ * The order of each memory region is not changed. The feature looks at
+ * the available space for the regions based on different configuration
+ * options and randomizes the base and space between each. The size of the
+ * physical memory mapping is the available physical memory.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/prandom.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+
+#include <asm/setup.h>
+#include <asm/kaslr.h>
+
+#include "mm_internal.h"
+
+#define TB_SHIFT 40
+
+/*
+ * The end address could depend on more configuration options to make the
+ * highest amount of space for randomization available, but that's too hard
+ * to keep straight and caused issues already.
+ */
+static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
+
+/*
+ * Memory regions randomized by KASLR (except modules that use a separate logic
+ * earlier during boot). The list is ordered based on virtual addresses. This
+ * order is kept after randomization.
+ */
+static __initdata struct kaslr_memory_region {
+	unsigned long *base;
+	unsigned long *end;
+	unsigned long size_tb;
+} kaslr_regions[] = {
+	{
+		.base	= &page_offset_base,
+		.end	= &direct_map_physmem_end,
+	},
+	{
+		.base	= &vmalloc_base,
+	},
+	{
+		.base	= &vmemmap_base,
+	},
+};
+
+/*
+ * The end of the physical address space that can be mapped directly by the
+ * kernel. This starts out at (1<<MAX_PHYSMEM_BITS) - 1), but KASLR may reduce
+ * that in order to increase the available entropy for mapping other regions.
+ */
+unsigned long direct_map_physmem_end __ro_after_init;
+
+/* Get size in bytes used by the memory region */
+static inline unsigned long get_padding(struct kaslr_memory_region *region)
+{
+	return (region->size_tb << TB_SHIFT);
+}
+
+/* Initialize base and padding for each memory region randomized with KASLR */
+void __init kernel_randomize_memory(void)
+{
+	size_t i;
+	unsigned long vaddr_start, vaddr;
+	unsigned long rand, memory_tb;
+	struct rnd_state rand_state;
+	unsigned long remain_entropy;
+	unsigned long vmemmap_size;
+
+	vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4;
+	vaddr = vaddr_start;
+
+	/*
+	 * These BUILD_BUG_ON checks ensure the memory layout is consistent
+	 * with the vaddr_start/vaddr_end variables. These checks are very
+	 * limited....
+	 */
+	BUILD_BUG_ON(vaddr_start >= vaddr_end);
+	BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
+	BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
+	/* Preset the end of the possible address space for physical memory */
+	direct_map_physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
+	if (!kaslr_memory_enabled())
+		return;
+
+	kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
+	kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
+
+	/*
+	 * Update Physical memory mapping to available and
+	 * add padding if needed (especially for memory hotplug support).
+	 */
+	BUG_ON(kaslr_regions[0].base != &page_offset_base);
+	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
+		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
+
+	/*
+	 * Adapt physical memory region size based on available memory,
+	 * except when CONFIG_ZONE_DEVICE is enabled. ZONE_DEVICE wants to map
+	 * any physical address into the direct-map. KASLR wants to reliably
+	 * steal some physical address bits. Those design choices are in direct
+	 * conflict.
+	 */
+	if (!IS_ENABLED(CONFIG_ZONE_DEVICE) && (memory_tb < kaslr_regions[0].size_tb))
+		kaslr_regions[0].size_tb = memory_tb;
+
+	/*
+	 * Calculate the vmemmap region size in TBs, aligned to a TB
+	 * boundary.
+	 */
+	vmemmap_size = (kaslr_regions[0].size_tb << (TB_SHIFT - PAGE_SHIFT)) *
+			sizeof(struct page);
+	kaslr_regions[2].size_tb = DIV_ROUND_UP(vmemmap_size, 1UL << TB_SHIFT);
+
+	/* Calculate entropy available between regions */
+	remain_entropy = vaddr_end - vaddr_start;
+	for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++)
+		remain_entropy -= get_padding(&kaslr_regions[i]);
+
+	prandom_seed_state(&rand_state, kaslr_get_random_long("Memory"));
+
+	for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) {
+		unsigned long entropy;
+
+		/*
+		 * Select a random virtual address using the extra entropy
+		 * available.
+		 */
+		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
+		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
+		entropy = (rand % (entropy + 1)) & PUD_MASK;
+		vaddr += entropy;
+		*kaslr_regions[i].base = vaddr;
+
+		/* Calculate the end of the region */
+		vaddr += get_padding(&kaslr_regions[i]);
+		/*
+		 * KASLR trims the maximum possible size of the
+		 * direct-map. Update the direct_map_physmem_end boundary.
+		 * No rounding required as the region starts
+		 * PUD aligned and size is in units of TB.
+		 */
+		if (kaslr_regions[i].end)
+			*kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
+
+		/* Add a minimum padding based on randomization alignment. */
+		vaddr = round_up(vaddr + 1, PUD_SIZE);
+		remain_entropy -= entropy;
+	}
+}
+
+void __meminit init_trampoline_kaslr(void)
+{
+	pud_t *pud_page_tramp, *pud, *pud_tramp;
+	p4d_t *p4d_page_tramp, *p4d, *p4d_tramp;
+	unsigned long paddr, vaddr;
+	pgd_t *pgd;
+
+	pud_page_tramp = alloc_low_page();
+
+	/*
+	 * There are two mappings for the low 1MB area, the direct mapping
+	 * and the 1:1 mapping for the real mode trampoline:
+	 *
+	 * Direct mapping: virt_addr = phys_addr + PAGE_OFFSET
+	 * 1:1 mapping:    virt_addr = phys_addr
+	 */
+	paddr = 0;
+	vaddr = (unsigned long)__va(paddr);
+	pgd = pgd_offset_k(vaddr);
+
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
+
+	pud_tramp = pud_page_tramp + pud_index(paddr);
+	*pud_tramp = *pud;
+
+	if (pgtable_l5_enabled()) {
+		p4d_page_tramp = alloc_low_page();
+
+		p4d_tramp = p4d_page_tramp + p4d_index(paddr);
+
+		set_p4d(p4d_tramp,
+			__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
+
+		trampoline_pgd_entry =
+			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp));
+	} else {
+		trampoline_pgd_entry =
+			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp));
+	}
+}
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
new file mode 100644
index 000000000..6ac981cec
--- /dev/null
+++ b/arch/x86/mm/kmmio.c
@@ -0,0 +1,632 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Support for MMIO probes.
+ * Benefit many code from kprobes
+ * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>.
+ *     2007 Alexander Eichner
+ *     2008 Pekka Paalanen <pq@iki.fi>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
+#include <linux/hash.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/percpu.h>
+#include <linux/kdebug.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <linux/errno.h>
+#include <asm/debugreg.h>
+#include <linux/mmiotrace.h>
+
+#define KMMIO_PAGE_HASH_BITS 4
+#define KMMIO_PAGE_TABLE_SIZE (1 << KMMIO_PAGE_HASH_BITS)
+
+struct kmmio_fault_page {
+	struct list_head list;
+	struct kmmio_fault_page *release_next;
+	unsigned long addr; /* the requested address */
+	pteval_t old_presence; /* page presence prior to arming */
+	bool armed;
+
+	/*
+	 * Number of times this page has been registered as a part
+	 * of a probe. If zero, page is disarmed and this may be freed.
+	 * Used only by writers (RCU) and post_kmmio_handler().
+	 * Protected by kmmio_lock, when linked into kmmio_page_table.
+	 */
+	int count;
+
+	bool scheduled_for_release;
+};
+
+struct kmmio_delayed_release {
+	struct rcu_head rcu;
+	struct kmmio_fault_page *release_list;
+};
+
+struct kmmio_context {
+	struct kmmio_fault_page *fpage;
+	struct kmmio_probe *probe;
+	unsigned long saved_flags;
+	unsigned long addr;
+	int active;
+};
+
+/*
+ * The kmmio_lock is taken in int3 context, which is treated as NMI context.
+ * This causes lockdep to complain about it bein in both NMI and normal
+ * context. Hide it from lockdep, as it should not have any other locks
+ * taken under it, and this is only enabled for debugging mmio anyway.
+ */
+static arch_spinlock_t kmmio_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+/* Protected by kmmio_lock */
+unsigned int kmmio_count;
+
+/* Read-protected by RCU, write-protected by kmmio_lock. */
+static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE];
+static LIST_HEAD(kmmio_probes);
+
+static struct list_head *kmmio_page_list(unsigned long addr)
+{
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+
+	return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)];
+}
+
+/* Accessed per-cpu */
+static DEFINE_PER_CPU(struct kmmio_context, kmmio_ctx);
+
+/*
+ * this is basically a dynamic stabbing problem:
+ * Could use the existing prio tree code or
+ * Possible better implementations:
+ * The Interval Skip List: A Data Structure for Finding All Intervals That
+ * Overlap a Point (might be simple)
+ * Space Efficient Dynamic Stabbing with Fast Queries - Mikkel Thorup
+ */
+/* Get the kmmio at this addr (if any). You must be holding RCU read lock. */
+static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
+{
+	struct kmmio_probe *p;
+	list_for_each_entry_rcu(p, &kmmio_probes, list) {
+		if (addr >= p->addr && addr < (p->addr + p->len))
+			return p;
+	}
+	return NULL;
+}
+
+/* You must be holding RCU read lock. */
+static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
+{
+	struct list_head *head;
+	struct kmmio_fault_page *f;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+
+	if (!pte)
+		return NULL;
+	addr &= page_level_mask(l);
+	head = kmmio_page_list(addr);
+	list_for_each_entry_rcu(f, head, list) {
+		if (f->addr == addr)
+			return f;
+	}
+	return NULL;
+}
+
+static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
+{
+	pmd_t new_pmd;
+	pmdval_t v = pmd_val(*pmd);
+	if (clear) {
+		*old = v;
+		new_pmd = pmd_mkinvalid(*pmd);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		new_pmd = __pmd(*old);
+	}
+	set_pmd(pmd, new_pmd);
+}
+
+static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
+{
+	pteval_t v = pte_val(*pte);
+	if (clear) {
+		*old = v;
+		/* Nothing should care about address */
+		pte_clear(&init_mm, 0, pte);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		set_pte_atomic(pte, __pte(*old));
+	}
+}
+
+static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
+{
+	unsigned int level;
+	pte_t *pte = lookup_address(f->addr, &level);
+
+	if (!pte) {
+		pr_err("no pte for addr 0x%08lx\n", f->addr);
+		return -1;
+	}
+
+	switch (level) {
+	case PG_LEVEL_2M:
+		clear_pmd_presence((pmd_t *)pte, clear, &f->old_presence);
+		break;
+	case PG_LEVEL_4K:
+		clear_pte_presence(pte, clear, &f->old_presence);
+		break;
+	default:
+		pr_err("unexpected page level 0x%x.\n", level);
+		return -1;
+	}
+
+	flush_tlb_one_kernel(f->addr);
+	return 0;
+}
+
+/*
+ * Mark the given page as not present. Access to it will trigger a fault.
+ *
+ * Struct kmmio_fault_page is protected by RCU and kmmio_lock, but the
+ * protection is ignored here. RCU read lock is assumed held, so the struct
+ * will not disappear unexpectedly. Furthermore, the caller must guarantee,
+ * that double arming the same virtual address (page) cannot occur.
+ *
+ * Double disarming on the other hand is allowed, and may occur when a fault
+ * and mmiotrace shutdown happen simultaneously.
+ */
+static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
+{
+	int ret;
+	WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n"));
+	if (f->armed) {
+		pr_warn("double-arm: addr 0x%08lx, ref %d, old %d\n",
+			f->addr, f->count, !!f->old_presence);
+	}
+	ret = clear_page_presence(f, true);
+	WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"),
+		  f->addr);
+	f->armed = true;
+	return ret;
+}
+
+/** Restore the given page to saved presence state. */
+static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
+{
+	int ret = clear_page_presence(f, false);
+	WARN_ONCE(ret < 0,
+			KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr);
+	f->armed = false;
+}
+
+/*
+ * This is being called from do_page_fault().
+ *
+ * We may be in an interrupt or a critical section. Also prefecthing may
+ * trigger a page fault. We may be in the middle of process switch.
+ * We cannot take any locks, because we could be executing especially
+ * within a kmmio critical section.
+ *
+ * Local interrupts are disabled, so preemption cannot happen.
+ * Do not enable interrupts, do not sleep, and watch out for other CPUs.
+ */
+/*
+ * Interrupts are disabled on entry as trap3 is an interrupt gate
+ * and they remain disabled throughout this function.
+ */
+int kmmio_handler(struct pt_regs *regs, unsigned long addr)
+{
+	struct kmmio_context *ctx;
+	struct kmmio_fault_page *faultpage;
+	int ret = 0; /* default to fault not handled */
+	unsigned long page_base = addr;
+	unsigned int l;
+	pte_t *pte = lookup_address(addr, &l);
+	if (!pte)
+		return -EINVAL;
+	page_base &= page_level_mask(l);
+
+	/*
+	 * Hold the RCU read lock over single stepping to avoid looking
+	 * up the probe and kmmio_fault_page again. The rcu_read_lock_sched()
+	 * also disables preemption and prevents process switch during
+	 * the single stepping. We can only handle one active kmmio trace
+	 * per cpu, so ensure that we finish it before something else
+	 * gets to run.
+	 */
+	rcu_read_lock_sched_notrace();
+
+	faultpage = get_kmmio_fault_page(page_base);
+	if (!faultpage) {
+		/*
+		 * Either this page fault is not caused by kmmio, or
+		 * another CPU just pulled the kmmio probe from under
+		 * our feet. The latter case should not be possible.
+		 */
+		goto no_kmmio;
+	}
+
+	ctx = this_cpu_ptr(&kmmio_ctx);
+	if (ctx->active) {
+		if (page_base == ctx->addr) {
+			/*
+			 * A second fault on the same page means some other
+			 * condition needs handling by do_page_fault(), the
+			 * page really not being present is the most common.
+			 */
+			pr_debug("secondary hit for 0x%08lx CPU %d.\n",
+				 addr, smp_processor_id());
+
+			if (!faultpage->old_presence)
+				pr_info("unexpected secondary hit for address 0x%08lx on CPU %d.\n",
+					addr, smp_processor_id());
+		} else {
+			/*
+			 * Prevent overwriting already in-flight context.
+			 * This should not happen, let's hope disarming at
+			 * least prevents a panic.
+			 */
+			pr_emerg("recursive probe hit on CPU %d, for address 0x%08lx. Ignoring.\n",
+				 smp_processor_id(), addr);
+			pr_emerg("previous hit was at 0x%08lx.\n", ctx->addr);
+			disarm_kmmio_fault_page(faultpage);
+		}
+		goto no_kmmio;
+	}
+	ctx->active++;
+
+	ctx->fpage = faultpage;
+	ctx->probe = get_kmmio_probe(page_base);
+	ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
+	ctx->addr = page_base;
+
+	if (ctx->probe && ctx->probe->pre_handler)
+		ctx->probe->pre_handler(ctx->probe, regs, addr);
+
+	/*
+	 * Enable single-stepping and disable interrupts for the faulting
+	 * context. Local interrupts must not get enabled during stepping.
+	 */
+	regs->flags |= X86_EFLAGS_TF;
+	regs->flags &= ~X86_EFLAGS_IF;
+
+	/* Now we set present bit in PTE and single step. */
+	disarm_kmmio_fault_page(ctx->fpage);
+
+	/*
+	 * If another cpu accesses the same page while we are stepping,
+	 * the access will not be caught. It will simply succeed and the
+	 * only downside is we lose the event. If this becomes a problem,
+	 * the user should drop to single cpu before tracing.
+	 */
+
+	return 1; /* fault handled */
+
+no_kmmio:
+	rcu_read_unlock_sched_notrace();
+	return ret;
+}
+
+/*
+ * Interrupts are disabled on entry as trap1 is an interrupt gate
+ * and they remain disabled throughout this function.
+ * This must always get called as the pair to kmmio_handler().
+ */
+static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
+{
+	int ret = 0;
+	struct kmmio_context *ctx = this_cpu_ptr(&kmmio_ctx);
+
+	if (!ctx->active) {
+		/*
+		 * debug traps without an active context are due to either
+		 * something external causing them (f.e. using a debugger while
+		 * mmio tracing enabled), or erroneous behaviour
+		 */
+		pr_warn("unexpected debug trap on CPU %d.\n", smp_processor_id());
+		goto out;
+	}
+
+	if (ctx->probe && ctx->probe->post_handler)
+		ctx->probe->post_handler(ctx->probe, condition, regs);
+
+	/* Prevent racing against release_kmmio_fault_page(). */
+	arch_spin_lock(&kmmio_lock);
+	if (ctx->fpage->count)
+		arm_kmmio_fault_page(ctx->fpage);
+	arch_spin_unlock(&kmmio_lock);
+
+	regs->flags &= ~X86_EFLAGS_TF;
+	regs->flags |= ctx->saved_flags;
+
+	/* These were acquired in kmmio_handler(). */
+	ctx->active--;
+	BUG_ON(ctx->active);
+	rcu_read_unlock_sched_notrace();
+
+	/*
+	 * if somebody else is singlestepping across a probe point, flags
+	 * will have TF set, in which case, continue the remaining processing
+	 * of do_debug, as if this is not a probe hit.
+	 */
+	if (!(regs->flags & X86_EFLAGS_TF))
+		ret = 1;
+out:
+	return ret;
+}
+
+/* You must be holding kmmio_lock. */
+static int add_kmmio_fault_page(unsigned long addr)
+{
+	struct kmmio_fault_page *f;
+
+	f = get_kmmio_fault_page(addr);
+	if (f) {
+		if (!f->count)
+			arm_kmmio_fault_page(f);
+		f->count++;
+		return 0;
+	}
+
+	f = kzalloc_obj(*f, GFP_ATOMIC);
+	if (!f)
+		return -1;
+
+	f->count = 1;
+	f->addr = addr;
+
+	if (arm_kmmio_fault_page(f)) {
+		kfree(f);
+		return -1;
+	}
+
+	list_add_rcu(&f->list, kmmio_page_list(f->addr));
+
+	return 0;
+}
+
+/* You must be holding kmmio_lock. */
+static void release_kmmio_fault_page(unsigned long addr,
+				struct kmmio_fault_page **release_list)
+{
+	struct kmmio_fault_page *f;
+
+	f = get_kmmio_fault_page(addr);
+	if (!f)
+		return;
+
+	f->count--;
+	BUG_ON(f->count < 0);
+	if (!f->count) {
+		disarm_kmmio_fault_page(f);
+		if (!f->scheduled_for_release) {
+			f->release_next = *release_list;
+			*release_list = f;
+			f->scheduled_for_release = true;
+		}
+	}
+}
+
+/*
+ * With page-unaligned ioremaps, one or two armed pages may contain
+ * addresses from outside the intended mapping. Events for these addresses
+ * are currently silently dropped. The events may result only from programming
+ * mistakes by accessing addresses before the beginning or past the end of a
+ * mapping.
+ */
+int register_kmmio_probe(struct kmmio_probe *p)
+{
+	unsigned long flags;
+	int ret = 0;
+	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
+	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+	unsigned int l;
+	pte_t *pte;
+
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
+	if (get_kmmio_probe(addr)) {
+		ret = -EEXIST;
+		goto out;
+	}
+
+	pte = lookup_address(addr, &l);
+	if (!pte) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	kmmio_count++;
+	list_add_rcu(&p->list, &kmmio_probes);
+	while (size < size_lim) {
+		if (add_kmmio_fault_page(addr + size))
+			pr_err("Unable to set page fault.\n");
+		size += page_level_size(l);
+	}
+out:
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
+
+	/*
+	 * XXX: What should I do here?
+	 * Here was a call to global_flush_tlb(), but it does not exist
+	 * anymore. It seems it's not needed after all.
+	 */
+	return ret;
+}
+EXPORT_SYMBOL(register_kmmio_probe);
+
+static void rcu_free_kmmio_fault_pages(struct rcu_head *head)
+{
+	struct kmmio_delayed_release *dr = container_of(
+						head,
+						struct kmmio_delayed_release,
+						rcu);
+	struct kmmio_fault_page *f = dr->release_list;
+	while (f) {
+		struct kmmio_fault_page *next = f->release_next;
+		BUG_ON(f->count);
+		kfree(f);
+		f = next;
+	}
+	kfree(dr);
+}
+
+static void remove_kmmio_fault_pages(struct rcu_head *head)
+{
+	struct kmmio_delayed_release *dr =
+		container_of(head, struct kmmio_delayed_release, rcu);
+	struct kmmio_fault_page *f = dr->release_list;
+	struct kmmio_fault_page **prevp = &dr->release_list;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
+	while (f) {
+		if (!f->count) {
+			list_del_rcu(&f->list);
+			prevp = &f->release_next;
+		} else {
+			*prevp = f->release_next;
+			f->release_next = NULL;
+			f->scheduled_for_release = false;
+		}
+		f = *prevp;
+	}
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
+
+	/* This is the real RCU destroy call. */
+	call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages);
+}
+
+/*
+ * Remove a kmmio probe. You have to synchronize_rcu() before you can be
+ * sure that the callbacks will not be called anymore. Only after that
+ * you may actually release your struct kmmio_probe.
+ *
+ * Unregistering a kmmio fault page has three steps:
+ * 1. release_kmmio_fault_page()
+ *    Disarm the page, wait a grace period to let all faults finish.
+ * 2. remove_kmmio_fault_pages()
+ *    Remove the pages from kmmio_page_table.
+ * 3. rcu_free_kmmio_fault_pages()
+ *    Actually free the kmmio_fault_page structs as with RCU.
+ */
+void unregister_kmmio_probe(struct kmmio_probe *p)
+{
+	unsigned long flags;
+	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
+	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
+	struct kmmio_fault_page *release_list = NULL;
+	struct kmmio_delayed_release *drelease;
+	unsigned int l;
+	pte_t *pte;
+
+	pte = lookup_address(addr, &l);
+	if (!pte)
+		return;
+
+	local_irq_save(flags);
+	arch_spin_lock(&kmmio_lock);
+	while (size < size_lim) {
+		release_kmmio_fault_page(addr + size, &release_list);
+		size += page_level_size(l);
+	}
+	list_del_rcu(&p->list);
+	kmmio_count--;
+	arch_spin_unlock(&kmmio_lock);
+	local_irq_restore(flags);
+
+	if (!release_list)
+		return;
+
+	drelease = kmalloc_obj(*drelease, GFP_ATOMIC);
+	if (!drelease) {
+		pr_crit("leaking kmmio_fault_page objects.\n");
+		return;
+	}
+	drelease->release_list = release_list;
+
+	/*
+	 * This is not really RCU here. We have just disarmed a set of
+	 * pages so that they cannot trigger page faults anymore. However,
+	 * we cannot remove the pages from kmmio_page_table,
+	 * because a probe hit might be in flight on another CPU. The
+	 * pages are collected into a list, and they will be removed from
+	 * kmmio_page_table when it is certain that no probe hit related to
+	 * these pages can be in flight. RCU grace period sounds like a
+	 * good choice.
+	 *
+	 * If we removed the pages too early, kmmio page fault handler might
+	 * not find the respective kmmio_fault_page and determine it's not
+	 * a kmmio fault, when it actually is. This would lead to madness.
+	 */
+	call_rcu(&drelease->rcu, remove_kmmio_fault_pages);
+}
+EXPORT_SYMBOL(unregister_kmmio_probe);
+
+static int
+kmmio_die_notifier(struct notifier_block *nb, unsigned long val, void *args)
+{
+	struct die_args *arg = args;
+	unsigned long* dr6_p = (unsigned long *)ERR_PTR(arg->err);
+
+	if (val == DIE_DEBUG && (*dr6_p & DR_STEP))
+		if (post_kmmio_handler(*dr6_p, arg->regs) == 1) {
+			/*
+			 * Reset the BS bit in dr6 (pointed by args->err) to
+			 * denote completion of processing
+			 */
+			*dr6_p &= ~DR_STEP;
+			return NOTIFY_STOP;
+		}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nb_die = {
+	.notifier_call = kmmio_die_notifier
+};
+
+int kmmio_init(void)
+{
+	int i;
+
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++)
+		INIT_LIST_HEAD(&kmmio_page_table[i]);
+
+	return register_die_notifier(&nb_die);
+}
+
+void kmmio_cleanup(void)
+{
+	int i;
+
+	unregister_die_notifier(&nb_die);
+	for (i = 0; i < KMMIO_PAGE_TABLE_SIZE; i++) {
+		WARN_ONCE(!list_empty(&kmmio_page_table[i]),
+			KERN_ERR "kmmio_page_table not empty at cleanup, any further tracing will leak memory.\n");
+	}
+}
diff --git a/arch/x86/mm/kmsan_shadow.c b/arch/x86/mm/kmsan_shadow.c
new file mode 100644
index 000000000..bee2ec4a3
--- /dev/null
+++ b/arch/x86/mm/kmsan_shadow.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * x86-specific bits of KMSAN shadow implementation.
+ *
+ * Copyright (C) 2022 Google LLC
+ * Author: Alexander Potapenko <glider@google.com>
+ */
+
+#include <asm/cpu_entry_area.h>
+#include <linux/percpu-defs.h>
+
+/*
+ * Addresses within the CPU entry area (including e.g. exception stacks) do not
+ * have struct page entries corresponding to them, so they need separate
+ * handling.
+ * arch_kmsan_get_meta_or_null() (declared in the header) maps the addresses in
+ * CPU entry area to addresses in cpu_entry_area_shadow/cpu_entry_area_origin.
+ */
+DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow);
+DEFINE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin);
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
new file mode 100644
index 000000000..42115ac07
--- /dev/null
+++ b/arch/x86/mm/maccess.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+
+#include <asm/vsyscall.h>
+
+#ifdef CONFIG_X86_64
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
+{
+	unsigned long vaddr = (unsigned long)unsafe_src;
+
+	/*
+	 * Do not allow userspace addresses.  This disallows
+	 * normal userspace and the userspace guard page:
+	 */
+	if (vaddr < TASK_SIZE_MAX + PAGE_SIZE)
+		return false;
+
+	/*
+	 * Reading from the vsyscall page may cause an unhandled fault in
+	 * certain cases.  Though it is at an address above TASK_SIZE_MAX, it is
+	 * usually considered as a user space address.
+	 */
+	if (is_vsyscall_vaddr(vaddr))
+		return false;
+
+	/*
+	 * Allow everything during early boot before 'x86_virt_bits'
+	 * is initialized.  Needed for instruction decoding in early
+	 * exception handlers.
+	 */
+	if (!boot_cpu_data.x86_virt_bits)
+		return true;
+
+	return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
+}
+#else
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
+{
+	return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
+}
+#endif
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
new file mode 100644
index 000000000..95bae74fd
--- /dev/null
+++ b/arch/x86/mm/mem_encrypt.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Memory Encryption Support Common Code
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/dma-mapping.h>
+#include <linux/swiotlb.h>
+#include <linux/cc_platform.h>
+#include <linux/mem_encrypt.h>
+#include <linux/virtio_anchor.h>
+
+#include <asm/sev.h>
+
+/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
+bool force_dma_unencrypted(struct device *dev)
+{
+	/*
+	 * For SEV, all DMA must be to unencrypted addresses.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return true;
+
+	/*
+	 * For SME, all DMA must be to unencrypted addresses if the
+	 * device does not support DMA to addresses that include the
+	 * encryption mask.
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
+		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
+						dev->bus_dma_limit);
+
+		if (dma_dev_mask <= dma_enc_mask)
+			return true;
+	}
+
+	return false;
+}
+
+static void print_mem_encrypt_feature_info(void)
+{
+	pr_info("Memory Encryption Features active: ");
+
+	switch (cc_vendor) {
+	case CC_VENDOR_INTEL:
+		pr_cont("Intel TDX\n");
+		break;
+	case CC_VENDOR_AMD:
+		pr_cont("AMD");
+
+		/* Secure Memory Encryption */
+		if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		/*
+		 * SME is mutually exclusive with any of the SEV
+		 * features below.
+		*/
+			pr_cont(" SME\n");
+			return;
+		}
+
+		/* Secure Encrypted Virtualization */
+		if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+			pr_cont(" SEV");
+
+		/* Encrypted Register State */
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+			pr_cont(" SEV-ES");
+
+		/* Secure Nested Paging */
+		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+			pr_cont(" SEV-SNP");
+
+		pr_cont("\n");
+
+		sev_show_status();
+
+		break;
+	default:
+		pr_cont("Unknown\n");
+	}
+}
+
+/* Architecture __weak replacement functions */
+void __init mem_encrypt_init(void)
+{
+	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return;
+
+	/* Call into SWIOTLB to update the SWIOTLB DMA buffers */
+	swiotlb_update_mem_attributes();
+
+	snp_secure_tsc_prepare();
+
+	print_mem_encrypt_feature_info();
+}
+
+void __init mem_encrypt_setup_arch(void)
+{
+	phys_addr_t total_mem = memblock_phys_mem_size();
+	unsigned long size;
+
+	/*
+	 * Do RMP table fixups after the e820 tables have been setup by
+	 * e820__memory_setup().
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+		snp_fixup_e820_tables();
+
+	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+		return;
+
+	/*
+	 * For SEV and TDX, all DMA has to occur via shared/unencrypted pages.
+	 * Kernel uses SWIOTLB to make this happen without changing device
+	 * drivers. However, depending on the workload being run, the
+	 * default 64MB of SWIOTLB may not be enough and SWIOTLB may
+	 * run out of buffers for DMA, resulting in I/O errors and/or
+	 * performance degradation especially with high I/O workloads.
+	 *
+	 * Adjust the default size of SWIOTLB using a percentage of guest
+	 * memory for SWIOTLB buffers. Also, as the SWIOTLB bounce buffer
+	 * memory is allocated from low memory, ensure that the adjusted size
+	 * is within the limits of low available memory.
+	 *
+	 * The percentage of guest memory used here for SWIOTLB buffers
+	 * is more of an approximation of the static adjustment which
+	 * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
+	 */
+	size = total_mem * 6 / 100;
+	size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
+	swiotlb_adjust_size(size);
+
+	/* Set restricted memory access for virtio. */
+	virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
new file mode 100644
index 000000000..2f8c32173
--- /dev/null
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -0,0 +1,569 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2016-2024 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/swiotlb.h>
+#include <linux/mem_encrypt.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/dma-mapping.h>
+#include <linux/cc_platform.h>
+
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+#include <asm/setup.h>
+#include <asm/mem_encrypt.h>
+#include <asm/bootparam.h>
+#include <asm/set_memory.h>
+#include <asm/cacheflush.h>
+#include <asm/processor-flags.h>
+#include <asm/msr.h>
+#include <asm/cmdline.h>
+#include <asm/sev.h>
+#include <asm/ia32.h>
+
+#include "mm_internal.h"
+
+/*
+ * Since SME related variables are set early in the boot process they must
+ * reside in the .data section so as not to be zeroed out when the .bss
+ * section is later cleared.
+ */
+u64 sme_me_mask __section(".data") = 0;
+SYM_PIC_ALIAS(sme_me_mask);
+u64 sev_status __section(".data") = 0;
+SYM_PIC_ALIAS(sev_status);
+u64 sev_check_data __section(".data") = 0;
+EXPORT_SYMBOL(sme_me_mask);
+
+/* Buffer used for early in-place encryption by BSP, no locking needed */
+static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE);
+
+/*
+ * SNP-specific routine which needs to additionally change the page state from
+ * private to shared before copying the data from the source to destination and
+ * restore after the copy.
+ */
+static inline void __init snp_memcpy(void *dst, void *src, size_t sz,
+				     unsigned long paddr, bool decrypt)
+{
+	unsigned long npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+
+	if (decrypt) {
+		/*
+		 * @paddr needs to be accessed decrypted, mark the page shared in
+		 * the RMP table before copying it.
+		 */
+		early_snp_set_memory_shared((unsigned long)__va(paddr), paddr, npages);
+
+		memcpy(dst, src, sz);
+
+		/* Restore the page state after the memcpy. */
+		early_snp_set_memory_private((unsigned long)__va(paddr), paddr, npages);
+	} else {
+		/*
+		 * @paddr need to be accessed encrypted, no need for the page state
+		 * change.
+		 */
+		memcpy(dst, src, sz);
+	}
+}
+
+/*
+ * This routine does not change the underlying encryption setting of the
+ * page(s) that map this memory. It assumes that eventually the memory is
+ * meant to be accessed as either encrypted or decrypted but the contents
+ * are currently not in the desired state.
+ *
+ * This routine follows the steps outlined in the AMD64 Architecture
+ * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place.
+ */
+static void __init __sme_early_enc_dec(resource_size_t paddr,
+				       unsigned long size, bool enc)
+{
+	void *src, *dst;
+	size_t len;
+
+	if (!sme_me_mask)
+		return;
+
+	wbinvd();
+
+	/*
+	 * There are limited number of early mapping slots, so map (at most)
+	 * one page at time.
+	 */
+	while (size) {
+		len = min_t(size_t, sizeof(sme_early_buffer), size);
+
+		/*
+		 * Create mappings for the current and desired format of
+		 * the memory. Use a write-protected mapping for the source.
+		 */
+		src = enc ? early_memremap_decrypted_wp(paddr, len) :
+			    early_memremap_encrypted_wp(paddr, len);
+
+		dst = enc ? early_memremap_encrypted(paddr, len) :
+			    early_memremap_decrypted(paddr, len);
+
+		/*
+		 * If a mapping can't be obtained to perform the operation,
+		 * then eventual access of that area in the desired mode
+		 * will cause a crash.
+		 */
+		BUG_ON(!src || !dst);
+
+		/*
+		 * Use a temporary buffer, of cache-line multiple size, to
+		 * avoid data corruption as documented in the APM.
+		 */
+		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) {
+			snp_memcpy(sme_early_buffer, src, len, paddr, enc);
+			snp_memcpy(dst, sme_early_buffer, len, paddr, !enc);
+		} else {
+			memcpy(sme_early_buffer, src, len);
+			memcpy(dst, sme_early_buffer, len);
+		}
+
+		early_memunmap(dst, len);
+		early_memunmap(src, len);
+
+		paddr += len;
+		size -= len;
+	}
+}
+
+void __init sme_early_encrypt(resource_size_t paddr, unsigned long size)
+{
+	__sme_early_enc_dec(paddr, size, true);
+}
+
+void __init sme_early_decrypt(resource_size_t paddr, unsigned long size)
+{
+	__sme_early_enc_dec(paddr, size, false);
+}
+
+static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size,
+					     bool map)
+{
+	unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET;
+	pmdval_t pmd_flags, pmd;
+
+	/* Use early_pmd_flags but remove the encryption mask */
+	pmd_flags = __sme_clr(early_pmd_flags);
+
+	do {
+		pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0;
+		__early_make_pgtable((unsigned long)vaddr, pmd);
+
+		vaddr += PMD_SIZE;
+		paddr += PMD_SIZE;
+		size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE;
+	} while (size);
+
+	flush_tlb_local();
+}
+
+void __init sme_unmap_bootdata(char *real_mode_data)
+{
+	struct boot_params *boot_data;
+	unsigned long cmdline_paddr;
+
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return;
+
+	/* Get the command line address before unmapping the real_mode_data */
+	boot_data = (struct boot_params *)real_mode_data;
+	cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
+
+	__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false);
+
+	if (!cmdline_paddr)
+		return;
+
+	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false);
+}
+
+void __init sme_map_bootdata(char *real_mode_data)
+{
+	struct boot_params *boot_data;
+	unsigned long cmdline_paddr;
+
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return;
+
+	__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true);
+
+	/* Get the command line address after mapping the real_mode_data */
+	boot_data = (struct boot_params *)real_mode_data;
+	cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);
+
+	if (!cmdline_paddr)
+		return;
+
+	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
+}
+
+static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
+{
+	unsigned long pfn = 0;
+	pgprot_t prot;
+
+	switch (level) {
+	case PG_LEVEL_4K:
+		pfn = pte_pfn(*kpte);
+		prot = pte_pgprot(*kpte);
+		break;
+	case PG_LEVEL_2M:
+		pfn = pmd_pfn(*(pmd_t *)kpte);
+		prot = pmd_pgprot(*(pmd_t *)kpte);
+		break;
+	case PG_LEVEL_1G:
+		pfn = pud_pfn(*(pud_t *)kpte);
+		prot = pud_pgprot(*(pud_t *)kpte);
+		break;
+	default:
+		WARN_ONCE(1, "Invalid level for kpte\n");
+		return 0;
+	}
+
+	if (ret_prot)
+		*ret_prot = prot;
+
+	return pfn;
+}
+
+static bool amd_enc_tlb_flush_required(bool enc)
+{
+	return true;
+}
+
+static bool amd_enc_cache_flush_required(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_SME_COHERENT);
+}
+
+static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
+{
+#ifdef CONFIG_PARAVIRT
+	unsigned long vaddr_end = vaddr + size;
+
+	while (vaddr < vaddr_end) {
+		int psize, pmask, level;
+		unsigned long pfn;
+		pte_t *kpte;
+
+		kpte = lookup_address(vaddr, &level);
+		if (!kpte || pte_none(*kpte)) {
+			WARN_ONCE(1, "kpte lookup for vaddr\n");
+			return;
+		}
+
+		pfn = pg_level_to_pfn(level, kpte, NULL);
+		if (!pfn)
+			continue;
+
+		psize = page_level_size(level);
+		pmask = page_level_mask(level);
+
+		notify_page_enc_status_changed(pfn, psize >> PAGE_SHIFT, enc);
+
+		vaddr = (vaddr & pmask) + psize;
+	}
+#endif
+}
+
+static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+{
+	/*
+	 * To maintain the security guarantees of SEV-SNP guests, make sure
+	 * to invalidate the memory before encryption attribute is cleared.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
+		snp_set_memory_shared(vaddr, npages);
+
+	return 0;
+}
+
+/* Return true unconditionally: return value doesn't matter for the SEV side */
+static int amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+{
+	/*
+	 * After memory is mapped encrypted in the page table, validate it
+	 * so that it is consistent with the page table updates.
+	 */
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && enc)
+		snp_set_memory_private(vaddr, npages);
+
+	if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc);
+
+	return 0;
+}
+
+int prepare_pte_enc(struct pte_enc_desc *d)
+{
+	pgprot_t old_prot;
+
+	d->pfn = pg_level_to_pfn(d->pte_level, d->kpte, &old_prot);
+	if (!d->pfn)
+		return 1;
+
+	d->new_pgprot = old_prot;
+	if (d->encrypt)
+		pgprot_val(d->new_pgprot) |= _PAGE_ENC;
+	else
+		pgprot_val(d->new_pgprot) &= ~_PAGE_ENC;
+
+	/* If prot is same then do nothing. */
+	if (pgprot_val(old_prot) == pgprot_val(d->new_pgprot))
+		return 1;
+
+	d->pa = d->pfn << PAGE_SHIFT;
+	d->size = page_level_size(d->pte_level);
+
+	/*
+	 * In-place en-/decryption and physical page attribute change
+	 * from C=1 to C=0 or vice versa will be performed. Flush the
+	 * caches to ensure that data gets accessed with the correct
+	 * C-bit.
+	 */
+	if (d->va)
+		clflush_cache_range(d->va, d->size);
+	else
+		clflush_cache_range(__va(d->pa), d->size);
+
+	return 0;
+}
+
+void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot)
+{
+	pte_t new_pte;
+
+	/* Change the page encryption mask. */
+	new_pte = pfn_pte(pfn, new_prot);
+	set_pte_atomic(kpte, new_pte);
+}
+
+static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+{
+	struct pte_enc_desc d = {
+		.kpte	     = kpte,
+		.pte_level   = level,
+		.encrypt     = enc
+	};
+
+	if (prepare_pte_enc(&d))
+		return;
+
+	/* Encrypt/decrypt the contents in-place */
+	if (enc) {
+		sme_early_encrypt(d.pa, d.size);
+	} else {
+		sme_early_decrypt(d.pa, d.size);
+
+		/*
+		 * ON SNP, the page state in the RMP table must happen
+		 * before the page table updates.
+		 */
+		early_snp_set_memory_shared((unsigned long)__va(d.pa), d.pa, 1);
+	}
+
+	set_pte_enc_mask(kpte, d.pfn, d.new_pgprot);
+
+	/*
+	 * If page is set encrypted in the page table, then update the RMP table to
+	 * add this page as private.
+	 */
+	if (enc)
+		early_snp_set_memory_private((unsigned long)__va(d.pa), d.pa, 1);
+}
+
+static int __init early_set_memory_enc_dec(unsigned long vaddr,
+					   unsigned long size, bool enc)
+{
+	unsigned long vaddr_end, vaddr_next, start;
+	unsigned long psize, pmask;
+	int split_page_size_mask;
+	int level, ret;
+	pte_t *kpte;
+
+	start = vaddr;
+	vaddr_next = vaddr;
+	vaddr_end = vaddr + size;
+
+	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+		kpte = lookup_address(vaddr, &level);
+		if (!kpte || pte_none(*kpte)) {
+			ret = 1;
+			goto out;
+		}
+
+		if (level == PG_LEVEL_4K) {
+			__set_clr_pte_enc(kpte, level, enc);
+			vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE;
+			continue;
+		}
+
+		psize = page_level_size(level);
+		pmask = page_level_mask(level);
+
+		/*
+		 * Check whether we can change the large page in one go.
+		 * We request a split when the address is not aligned and
+		 * the number of pages to set/clear encryption bit is smaller
+		 * than the number of pages in the large page.
+		 */
+		if (vaddr == (vaddr & pmask) &&
+		    ((vaddr_end - vaddr) >= psize)) {
+			__set_clr_pte_enc(kpte, level, enc);
+			vaddr_next = (vaddr & pmask) + psize;
+			continue;
+		}
+
+		/*
+		 * The virtual address is part of a larger page, create the next
+		 * level page table mapping (4K or 2M). If it is part of a 2M
+		 * page then we request a split of the large page into 4K
+		 * chunks. A 1GB large page is split into 2M pages, resp.
+		 */
+		if (level == PG_LEVEL_2M)
+			split_page_size_mask = 0;
+		else
+			split_page_size_mask = 1 << PG_LEVEL_2M;
+
+		/*
+		 * kernel_physical_mapping_change() does not flush the TLBs, so
+		 * a TLB flush is required after we exit from the for loop.
+		 */
+		kernel_physical_mapping_change(__pa(vaddr & pmask),
+					       __pa((vaddr_end & pmask) + psize),
+					       split_page_size_mask);
+	}
+
+	ret = 0;
+
+	early_set_mem_enc_dec_hypercall(start, size, enc);
+out:
+	__flush_tlb_all();
+	return ret;
+}
+
+int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size)
+{
+	return early_set_memory_enc_dec(vaddr, size, false);
+}
+
+int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
+{
+	return early_set_memory_enc_dec(vaddr, size, true);
+}
+
+void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
+{
+	enc_dec_hypercall(vaddr, size, enc);
+}
+
+void __init sme_early_init(void)
+{
+	if (!sme_me_mask)
+		return;
+
+	early_pmd_flags = __sme_set(early_pmd_flags);
+
+	__supported_pte_mask = __sme_set(__supported_pte_mask);
+
+	/* Update the protection map with memory encryption mask */
+	add_encrypt_protection_map();
+
+	x86_platform.guest.enc_status_change_prepare = amd_enc_status_change_prepare;
+	x86_platform.guest.enc_status_change_finish  = amd_enc_status_change_finish;
+	x86_platform.guest.enc_tlb_flush_required    = amd_enc_tlb_flush_required;
+	x86_platform.guest.enc_cache_flush_required  = amd_enc_cache_flush_required;
+	x86_platform.guest.enc_kexec_begin	     = snp_kexec_begin;
+	x86_platform.guest.enc_kexec_finish	     = snp_kexec_finish;
+
+	/*
+	 * AMD-SEV-ES intercepts the RDMSR to read the X2APIC ID in the
+	 * parallel bringup low level code. That raises #VC which cannot be
+	 * handled there.
+	 * It does not provide a RDMSR GHCB protocol so the early startup
+	 * code cannot directly communicate with the secure firmware. The
+	 * alternative solution to retrieve the APIC ID via CPUID(0xb),
+	 * which is covered by the GHCB protocol, is not viable either
+	 * because there is no enforcement of the CPUID(0xb) provided
+	 * "initial" APIC ID to be the same as the real APIC ID.
+	 * Disable parallel bootup.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ES_ENABLED)
+		x86_cpuinit.parallel_bringup = false;
+
+	/*
+	 * The VMM is capable of injecting interrupt 0x80 and triggering the
+	 * compatibility syscall path.
+	 *
+	 * By default, the 32-bit emulation is disabled in order to ensure
+	 * the safety of the VM.
+	 */
+	if (sev_status & MSR_AMD64_SEV_ENABLED)
+		ia32_disable();
+
+	/*
+	 * Override init functions that scan the ROM region in SEV-SNP guests,
+	 * as this memory is not pre-validated and would thus cause a crash.
+	 */
+	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+		x86_init.mpparse.find_mptable = x86_init_noop;
+		x86_init.pci.init_irq = x86_init_noop;
+		x86_init.resources.probe_roms = x86_init_noop;
+
+		/*
+		 * DMI setup behavior for SEV-SNP guests depends on
+		 * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+		 * parsed yet. snp_dmi_setup() will run after that
+		 * parsing has happened.
+		 */
+		x86_init.resources.dmi_setup = snp_dmi_setup;
+	}
+
+	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+}
+
+void __init mem_encrypt_free_decrypted_mem(void)
+{
+	unsigned long vaddr, vaddr_end, npages;
+	int r;
+
+	vaddr = (unsigned long)__start_bss_decrypted_unused;
+	vaddr_end = (unsigned long)__end_bss_decrypted;
+	npages = (vaddr_end - vaddr) >> PAGE_SHIFT;
+
+	/*
+	 * If the unused memory range was mapped decrypted, change the encryption
+	 * attribute from decrypted to encrypted before freeing it. Base the
+	 * re-encryption on the same condition used for the decryption in
+	 * sme_postprocess_startup(). Higher level abstractions, such as
+	 * CC_ATTR_MEM_ENCRYPT, aren't necessarily equivalent in a Hyper-V VM
+	 * using vTOM, where sme_me_mask is always zero.
+	 */
+	if (sme_me_mask) {
+		r = set_memory_encrypted(vaddr, npages);
+		if (r) {
+			pr_warn("failed to free unused decrypted pages\n");
+			return;
+		}
+	}
+
+	free_init_pages("unused decrypted", vaddr, vaddr_end);
+}
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
new file mode 100644
index 000000000..edbf9c998
--- /dev/null
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2016 Advanced Micro Devices, Inc.
+ *
+ * Author: Tom Lendacky <thomas.lendacky@amd.com>
+ */
+
+#include <linux/linkage.h>
+#include <linux/pgtable.h>
+#include <asm/page.h>
+#include <asm/processor-flags.h>
+#include <asm/msr-index.h>
+#include <asm/nospec-branch.h>
+
+	.text
+	.code64
+SYM_FUNC_START(__pi_sme_encrypt_execute)
+
+	/*
+	 * Entry parameters:
+	 *   RDI - virtual address for the encrypted mapping
+	 *   RSI - virtual address for the decrypted mapping
+	 *   RDX - length to encrypt
+	 *   RCX - virtual address of the encryption workarea, including:
+	 *     - stack page (PAGE_SIZE)
+	 *     - encryption routine page (PAGE_SIZE)
+	 *     - intermediate copy buffer (PMD_SIZE)
+	 *    R8 - physical address of the pagetables to use for encryption
+	 */
+
+	push	%rbp
+	movq	%rsp, %rbp		/* RBP now has original stack pointer */
+
+	/* Set up a one page stack in the non-encrypted memory area */
+	movq	%rcx, %rax		/* Workarea stack page */
+	leaq	PAGE_SIZE(%rax), %rsp	/* Set new stack pointer */
+	addq	$PAGE_SIZE, %rax	/* Workarea encryption routine */
+
+	push	%r12
+	movq	%rdi, %r10		/* Encrypted area */
+	movq	%rsi, %r11		/* Decrypted area */
+	movq	%rdx, %r12		/* Area length */
+
+	/* Copy encryption routine into the workarea */
+	movq	%rax, %rdi				/* Workarea encryption routine */
+	leaq	__enc_copy(%rip), %rsi			/* Encryption routine */
+	movq	$(.L__enc_copy_end - __enc_copy), %rcx	/* Encryption routine length */
+	rep	movsb
+
+	/* Setup registers for call */
+	movq	%r10, %rdi		/* Encrypted area */
+	movq	%r11, %rsi		/* Decrypted area */
+	movq	%r8, %rdx		/* Pagetables used for encryption */
+	movq	%r12, %rcx		/* Area length */
+	movq	%rax, %r8		/* Workarea encryption routine */
+	addq	$PAGE_SIZE, %r8		/* Workarea intermediate copy buffer */
+
+	ANNOTATE_RETPOLINE_SAFE
+	call	*%rax			/* Call the encryption routine */
+
+	pop	%r12
+
+	movq	%rbp, %rsp		/* Restore original stack pointer */
+	pop	%rbp
+
+	/* Offset to __x86_return_thunk would be wrong here */
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_FUNC_END(__pi_sme_encrypt_execute)
+
+SYM_FUNC_START_LOCAL(__enc_copy)
+	ANNOTATE_NOENDBR
+/*
+ * Routine used to encrypt memory in place.
+ *   This routine must be run outside of the kernel proper since
+ *   the kernel will be encrypted during the process. So this
+ *   routine is defined here and then copied to an area outside
+ *   of the kernel where it will remain and run decrypted
+ *   during execution.
+ *
+ *   On entry the registers must be:
+ *     RDI - virtual address for the encrypted mapping
+ *     RSI - virtual address for the decrypted mapping
+ *     RDX - address of the pagetables to use for encryption
+ *     RCX - length of area
+ *      R8 - intermediate copy buffer
+ *
+ *     RAX - points to this routine
+ *
+ * The area will be encrypted by copying from the non-encrypted
+ * memory space to an intermediate buffer and then copying from the
+ * intermediate buffer back to the encrypted memory space. The physical
+ * addresses of the two mappings are the same which results in the area
+ * being encrypted "in place".
+ */
+	/* Enable the new page tables */
+	mov	%rdx, %cr3
+
+	/* Flush any global TLBs */
+	mov	%cr4, %rdx
+	andq	$~X86_CR4_PGE, %rdx
+	mov	%rdx, %cr4
+	orq	$X86_CR4_PGE, %rdx
+	mov	%rdx, %cr4
+
+	push	%r15
+	push	%r12
+
+	movq	%rcx, %r9		/* Save area length */
+	movq	%rdi, %r10		/* Save encrypted area address */
+	movq	%rsi, %r11		/* Save decrypted area address */
+
+	/* Set the PAT register PA5 entry to write-protect */
+	movl	$MSR_IA32_CR_PAT, %ecx
+	rdmsr
+	mov	%rdx, %r15		/* Save original PAT value */
+	andl	$0xffff00ff, %edx	/* Clear PA5 */
+	orl	$0x00000500, %edx	/* Set PA5 to WP */
+	wrmsr
+
+	wbinvd				/* Invalidate any cache entries */
+
+	/* Copy/encrypt up to 2MB at a time */
+	movq	$PMD_SIZE, %r12
+1:
+	cmpq	%r12, %r9
+	jnb	2f
+	movq	%r9, %r12
+
+2:
+	movq	%r11, %rsi		/* Source - decrypted area */
+	movq	%r8, %rdi		/* Dest   - intermediate copy buffer */
+	movq	%r12, %rcx
+	rep	movsb
+
+	movq	%r8, %rsi		/* Source - intermediate copy buffer */
+	movq	%r10, %rdi		/* Dest   - encrypted area */
+	movq	%r12, %rcx
+	rep	movsb
+
+	addq	%r12, %r11
+	addq	%r12, %r10
+	subq	%r12, %r9		/* Kernel length decrement */
+	jnz	1b			/* Kernel length not zero? */
+
+	/* Restore PAT register */
+	movl	$MSR_IA32_CR_PAT, %ecx
+	rdmsr
+	mov	%r15, %rdx		/* Restore original PAT value */
+	wrmsr
+
+	pop	%r12
+	pop	%r15
+
+	/* Offset to __x86_return_thunk would be wrong here */
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+.L__enc_copy_end:
+SYM_FUNC_END(__enc_copy)
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
new file mode 100644
index 000000000..7c4a41235
--- /dev/null
+++ b/arch/x86/mm/mm_internal.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __X86_MM_INTERNAL_H
+#define __X86_MM_INTERNAL_H
+
+void *alloc_low_pages(unsigned int num);
+static inline void *alloc_low_page(void)
+{
+	return alloc_low_pages(1);
+}
+
+void early_ioremap_page_table_range_init(void);
+
+unsigned long kernel_physical_mapping_init(unsigned long start,
+					     unsigned long end,
+					     unsigned long page_size_mask,
+					     pgprot_t prot);
+unsigned long kernel_physical_mapping_change(unsigned long start,
+					     unsigned long end,
+					     unsigned long page_size_mask);
+
+extern int after_bootmem;
+
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
+
+extern unsigned long tlb_single_page_flush_ceiling;
+
+#ifdef CONFIG_NUMA
+void __init x86_numa_init(void);
+#endif
+
+#endif	/* __X86_MM_INTERNAL_H */
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
new file mode 100644
index 000000000..82f3a987f
--- /dev/null
+++ b/arch/x86/mm/mmap.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Flexible mmap layout support
+ *
+ * Based on code by Ingo Molnar and Andi Kleen, copyrighted
+ * as follows:
+ *
+ * Copyright 2003-2009 Red Hat Inc.
+ * All Rights Reserved.
+ * Copyright 2005 Andi Kleen, SUSE Labs.
+ * Copyright 2007 Jiri Kosina, SUSE Labs.
+ */
+
+#include <linux/personality.h>
+#include <linux/mm.h>
+#include <linux/random.h>
+#include <linux/limits.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
+#include <linux/compat.h>
+#include <linux/elf-randomize.h>
+#include <asm/elf.h>
+#include <asm/io.h>
+
+#include "physaddr.h"
+
+struct va_alignment __read_mostly va_align = {
+	.flags = -1,
+};
+
+unsigned long task_size_32bit(void)
+{
+	return IA32_PAGE_OFFSET;
+}
+
+unsigned long task_size_64bit(int full_addr_space)
+{
+	return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW;
+}
+
+static unsigned long stack_maxrandom_size(unsigned long task_size)
+{
+	unsigned long max = 0;
+	if (current->flags & PF_RANDOMIZE) {
+		max = (-1UL) & __STACK_RND_MASK(task_size == task_size_32bit());
+		max <<= PAGE_SHIFT;
+	}
+
+	return max;
+}
+
+#ifdef CONFIG_COMPAT
+# define mmap32_rnd_bits  mmap_rnd_compat_bits
+# define mmap64_rnd_bits  mmap_rnd_bits
+#else
+# define mmap32_rnd_bits  mmap_rnd_bits
+# define mmap64_rnd_bits  mmap_rnd_bits
+#endif
+
+#define SIZE_128M    (128 * 1024 * 1024UL)
+
+static int mmap_is_legacy(void)
+{
+	if (current->personality & ADDR_COMPAT_LAYOUT)
+		return 1;
+
+	return sysctl_legacy_va_layout;
+}
+
+static unsigned long arch_rnd(unsigned int rndbits)
+{
+	if (!(current->flags & PF_RANDOMIZE))
+		return 0;
+	return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT;
+}
+
+unsigned long arch_mmap_rnd(void)
+{
+	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
+}
+
+static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
+			       const struct rlimit *rlim_stack)
+{
+	unsigned long gap = rlim_stack->rlim_cur;
+	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
+
+	/* Values close to RLIM_INFINITY can overflow. */
+	if (gap + pad > gap)
+		gap += pad;
+
+	/*
+	 * Top of mmap area (just below the process stack).
+	 * Leave an at least ~128 MB hole with possible stack randomization.
+	 */
+	gap = clamp(gap, SIZE_128M, (task_size / 6) * 5);
+
+	return PAGE_ALIGN(task_size - gap - rnd);
+}
+
+static unsigned long mmap_legacy_base(unsigned long rnd,
+				      unsigned long task_size)
+{
+	return __TASK_UNMAPPED_BASE(task_size) + rnd;
+}
+
+/*
+ * This function, called very early during the creation of a new
+ * process VM image, sets up which VM layout function to use:
+ */
+static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
+		unsigned long random_factor, unsigned long task_size,
+		const struct rlimit *rlim_stack)
+{
+	*legacy_base = mmap_legacy_base(random_factor, task_size);
+	if (mmap_is_legacy())
+		*base = *legacy_base;
+	else
+		*base = mmap_base(random_factor, task_size, rlim_stack);
+}
+
+void arch_pick_mmap_layout(struct mm_struct *mm, const struct rlimit *rlim_stack)
+{
+	if (mmap_is_legacy())
+		mm_flags_clear(MMF_TOPDOWN, mm);
+	else
+		mm_flags_set(MMF_TOPDOWN, mm);
+
+	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
+			arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
+			rlim_stack);
+
+#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
+	/*
+	 * The mmap syscall mapping base decision depends solely on the
+	 * syscall type (64-bit or compat). This applies for 64bit
+	 * applications and 32bit applications. The 64bit syscall uses
+	 * mmap_base, the compat syscall uses mmap_compat_base.
+	 */
+	arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base,
+			arch_rnd(mmap32_rnd_bits), task_size_32bit(),
+			rlim_stack);
+#endif
+}
+
+unsigned long get_mmap_base(int is_legacy)
+{
+	struct mm_struct *mm = current->mm;
+
+#ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
+	if (in_32bit_syscall()) {
+		return is_legacy ? mm->mmap_compat_legacy_base
+				 : mm->mmap_compat_base;
+	}
+#endif
+	return is_legacy ? mm->mmap_legacy_base : mm->mmap_base;
+}
+
+/**
+ * mmap_address_hint_valid - Validate the address hint of mmap
+ * @addr:	Address hint
+ * @len:	Mapping length
+ *
+ * Check whether @addr and @addr + @len result in a valid mapping.
+ *
+ * On 32bit this only checks whether @addr + @len is <= TASK_SIZE.
+ *
+ * On 64bit with 5-level page tables another sanity check is required
+ * because mappings requested by mmap(@addr, 0) which cross the 47-bit
+ * virtual address boundary can cause the following theoretical issue:
+ *
+ *  An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr
+ *  is below the border of the 47-bit address space and @addr + @len is
+ *  above the border.
+ *
+ *  With 4-level paging this request succeeds, but the resulting mapping
+ *  address will always be within the 47-bit virtual address space, because
+ *  the hint address does not result in a valid mapping and is
+ *  ignored. Hence applications which are not prepared to handle virtual
+ *  addresses above 47-bit work correctly.
+ *
+ *  With 5-level paging this request would be granted and result in a
+ *  mapping which crosses the border of the 47-bit virtual address
+ *  space. If the application cannot handle addresses above 47-bit this
+ *  will lead to misbehaviour and hard to diagnose failures.
+ *
+ * Therefore ignore address hints which would result in a mapping crossing
+ * the 47-bit virtual address boundary.
+ *
+ * Note, that in the same scenario with MAP_FIXED the behaviour is
+ * different. The request with @addr < 47-bit and @addr + @len > 47-bit
+ * fails on a 4-level paging machine but succeeds on a 5-level paging
+ * machine. It is reasonable to expect that an application does not rely on
+ * the failure of such a fixed mapping request, so the restriction is not
+ * applied.
+ */
+bool mmap_address_hint_valid(unsigned long addr, unsigned long len)
+{
+	if (TASK_SIZE - len < addr)
+		return false;
+
+	return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW);
+}
+
+/* Can we access it for direct reading/writing? Must be RAM: */
+int valid_phys_addr_range(phys_addr_t addr, size_t count)
+{
+	return addr + count - 1 <= __pa(high_memory - 1);
+}
+
+/* Can we access it through mmap? Must be a valid physical address: */
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
+{
+	phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT;
+
+	return phys_addr_valid(addr + count - 1);
+}
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return true;
+	if (!__pte_needs_invert(pgprot_val(prot)))
+		return true;
+	/* If it's real memory always allow */
+	if (pfn_valid(pfn))
+		return true;
+	if (pfn >= l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+		return false;
+	return true;
+}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
new file mode 100644
index 000000000..265ad1a0a
--- /dev/null
+++ b/arch/x86/mm/mmio-mod.c
@@ -0,0 +1,463 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *
+ * Copyright (C) IBM Corporation, 2005
+ *               Jeff Muizelaar, 2006, 2007
+ *               Pekka Paalanen, 2008 <pq@iki.fi>
+ *
+ * Derived from the read-mod example from relay-examples by Tom Zanussi.
+ */
+
+#define pr_fmt(fmt) "mmiotrace: " fmt
+
+#include <linux/moduleparam.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/mmiotrace.h>
+#include <linux/pgtable.h>
+#include <asm/e820/api.h> /* for ISA_START_ADDRESS */
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+
+#include "pf_in.h"
+
+struct trap_reason {
+	unsigned long addr;
+	unsigned long ip;
+	enum reason_type type;
+	int active_traces;
+};
+
+struct remap_trace {
+	struct list_head list;
+	struct kmmio_probe probe;
+	resource_size_t phys;
+	unsigned long id;
+};
+
+/* Accessed per-cpu. */
+static DEFINE_PER_CPU(struct trap_reason, pf_reason);
+static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
+
+static DEFINE_MUTEX(mmiotrace_mutex);
+static DEFINE_SPINLOCK(trace_lock);
+static atomic_t mmiotrace_enabled;
+static LIST_HEAD(trace_list);		/* struct remap_trace */
+
+/*
+ * Locking in this file:
+ * - mmiotrace_mutex enforces enable/disable_mmiotrace() critical sections.
+ * - mmiotrace_enabled may be modified only when holding mmiotrace_mutex
+ *   and trace_lock.
+ * - Routines depending on is_enabled() must take trace_lock.
+ * - trace_list users must hold trace_lock.
+ * - is_enabled() guarantees that mmio_trace_{rw,mapping} are allowed.
+ * - pre/post callbacks assume the effect of is_enabled() being true.
+ */
+
+/* module parameters */
+static unsigned long	filter_offset;
+static bool		nommiotrace;
+static bool		trace_pc;
+
+module_param(filter_offset, ulong, 0);
+module_param(nommiotrace, bool, 0);
+module_param(trace_pc, bool, 0);
+
+MODULE_PARM_DESC(filter_offset, "Start address of traced mappings.");
+MODULE_PARM_DESC(nommiotrace, "Disable actual MMIO tracing.");
+MODULE_PARM_DESC(trace_pc, "Record address of faulting instructions.");
+
+static bool is_enabled(void)
+{
+	return atomic_read(&mmiotrace_enabled);
+}
+
+static void print_pte(unsigned long address)
+{
+	unsigned int level;
+	pte_t *pte = lookup_address(address, &level);
+
+	if (!pte) {
+		pr_err("Error in %s: no pte for page 0x%08lx\n",
+		       __func__, address);
+		return;
+	}
+
+	if (level == PG_LEVEL_2M) {
+		pr_emerg("4MB pages are not currently supported: 0x%08lx\n",
+			 address);
+		BUG();
+	}
+	pr_info("pte for 0x%lx: 0x%llx 0x%llx\n",
+		address,
+		(unsigned long long)pte_val(*pte),
+		(unsigned long long)pte_val(*pte) & _PAGE_PRESENT);
+}
+
+/*
+ * For some reason the pre/post pairs have been called in an
+ * unmatched order. Report and die.
+ */
+static void die_kmmio_nesting_error(struct pt_regs *regs, unsigned long addr)
+{
+	const struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	pr_emerg("unexpected fault for address: 0x%08lx, last fault for address: 0x%08lx\n",
+		 addr, my_reason->addr);
+	print_pte(addr);
+	pr_emerg("faulting IP is at %pS\n", (void *)regs->ip);
+	pr_emerg("last faulting IP was at %pS\n", (void *)my_reason->ip);
+#ifdef __i386__
+	pr_emerg("eax: %08lx   ebx: %08lx   ecx: %08lx   edx: %08lx\n",
+		 regs->ax, regs->bx, regs->cx, regs->dx);
+	pr_emerg("esi: %08lx   edi: %08lx   ebp: %08lx   esp: %08lx\n",
+		 regs->si, regs->di, regs->bp, regs->sp);
+#else
+	pr_emerg("rax: %016lx   rcx: %016lx   rdx: %016lx\n",
+		 regs->ax, regs->cx, regs->dx);
+	pr_emerg("rsi: %016lx   rdi: %016lx   rbp: %016lx   rsp: %016lx\n",
+		 regs->si, regs->di, regs->bp, regs->sp);
+#endif
+	put_cpu_var(pf_reason);
+	BUG();
+}
+
+static void pre(struct kmmio_probe *p, struct pt_regs *regs,
+						unsigned long addr)
+{
+	struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace);
+	const unsigned long instptr = instruction_pointer(regs);
+	const enum reason_type type = get_ins_type(instptr);
+	struct remap_trace *trace = p->private;
+
+	/* it doesn't make sense to have more than one active trace per cpu */
+	if (my_reason->active_traces)
+		die_kmmio_nesting_error(regs, addr);
+	else
+		my_reason->active_traces++;
+
+	my_reason->type = type;
+	my_reason->addr = addr;
+	my_reason->ip = instptr;
+
+	my_trace->phys = addr - trace->probe.addr + trace->phys;
+	my_trace->map_id = trace->id;
+
+	/*
+	 * Only record the program counter when requested.
+	 * It may taint clean-room reverse engineering.
+	 */
+	if (trace_pc)
+		my_trace->pc = instptr;
+	else
+		my_trace->pc = 0;
+
+	/*
+	 * XXX: the timestamp recorded will be *after* the tracing has been
+	 * done, not at the time we hit the instruction. SMP implications
+	 * on event ordering?
+	 */
+
+	switch (type) {
+	case REG_READ:
+		my_trace->opcode = MMIO_READ;
+		my_trace->width = get_ins_mem_width(instptr);
+		break;
+	case REG_WRITE:
+		my_trace->opcode = MMIO_WRITE;
+		my_trace->width = get_ins_mem_width(instptr);
+		my_trace->value = get_ins_reg_val(instptr, regs);
+		break;
+	case IMM_WRITE:
+		my_trace->opcode = MMIO_WRITE;
+		my_trace->width = get_ins_mem_width(instptr);
+		my_trace->value = get_ins_imm_val(instptr);
+		break;
+	default:
+		{
+			unsigned char *ip = (unsigned char *)instptr;
+			my_trace->opcode = MMIO_UNKNOWN_OP;
+			my_trace->width = 0;
+			my_trace->value = (*ip) << 16 | *(ip + 1) << 8 |
+								*(ip + 2);
+		}
+	}
+	put_cpu_var(cpu_trace);
+	put_cpu_var(pf_reason);
+}
+
+static void post(struct kmmio_probe *p, unsigned long condition,
+							struct pt_regs *regs)
+{
+	struct trap_reason *my_reason = &get_cpu_var(pf_reason);
+	struct mmiotrace_rw *my_trace = &get_cpu_var(cpu_trace);
+
+	/* this should always return the active_trace count to 0 */
+	my_reason->active_traces--;
+	if (my_reason->active_traces) {
+		pr_emerg("unexpected post handler");
+		BUG();
+	}
+
+	switch (my_reason->type) {
+	case REG_READ:
+		my_trace->value = get_ins_reg_val(my_reason->ip, regs);
+		break;
+	default:
+		break;
+	}
+
+	mmio_trace_rw(my_trace);
+	put_cpu_var(cpu_trace);
+	put_cpu_var(pf_reason);
+}
+
+static void ioremap_trace_core(resource_size_t offset, unsigned long size,
+							void __iomem *addr)
+{
+	static atomic_t next_id;
+	struct remap_trace *trace = kmalloc_obj(*trace);
+	/* These are page-unaligned. */
+	struct mmiotrace_map map = {
+		.phys = offset,
+		.virt = (unsigned long)addr,
+		.len = size,
+		.opcode = MMIO_PROBE
+	};
+
+	if (!trace) {
+		pr_err("kmalloc failed in ioremap\n");
+		return;
+	}
+
+	*trace = (struct remap_trace) {
+		.probe = {
+			.addr = (unsigned long)addr,
+			.len = size,
+			.pre_handler = pre,
+			.post_handler = post,
+			.private = trace
+		},
+		.phys = offset,
+		.id = atomic_inc_return(&next_id)
+	};
+	map.map_id = trace->id;
+
+	spin_lock_irq(&trace_lock);
+	if (!is_enabled()) {
+		kfree(trace);
+		goto not_enabled;
+	}
+
+	mmio_trace_mapping(&map);
+	list_add_tail(&trace->list, &trace_list);
+	if (!nommiotrace)
+		register_kmmio_probe(&trace->probe);
+
+not_enabled:
+	spin_unlock_irq(&trace_lock);
+}
+
+void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
+						void __iomem *addr)
+{
+	if (!is_enabled()) /* recheck and proper locking in *_core() */
+		return;
+
+	pr_debug("ioremap_*(0x%llx, 0x%lx) = %p\n",
+		 (unsigned long long)offset, size, addr);
+	if ((filter_offset) && (offset != filter_offset))
+		return;
+	ioremap_trace_core(offset, size, addr);
+}
+
+static void iounmap_trace_core(volatile void __iomem *addr)
+{
+	struct mmiotrace_map map = {
+		.phys = 0,
+		.virt = (unsigned long)addr,
+		.len = 0,
+		.opcode = MMIO_UNPROBE
+	};
+	struct remap_trace *trace;
+	struct remap_trace *tmp;
+	struct remap_trace *found_trace = NULL;
+
+	pr_debug("Unmapping %p.\n", addr);
+
+	spin_lock_irq(&trace_lock);
+	if (!is_enabled())
+		goto not_enabled;
+
+	list_for_each_entry_safe(trace, tmp, &trace_list, list) {
+		if ((unsigned long)addr == trace->probe.addr) {
+			if (!nommiotrace)
+				unregister_kmmio_probe(&trace->probe);
+			list_del(&trace->list);
+			found_trace = trace;
+			break;
+		}
+	}
+	map.map_id = (found_trace) ? found_trace->id : -1;
+	mmio_trace_mapping(&map);
+
+not_enabled:
+	spin_unlock_irq(&trace_lock);
+	if (found_trace) {
+		synchronize_rcu(); /* unregister_kmmio_probe() requirement */
+		kfree(found_trace);
+	}
+}
+
+void mmiotrace_iounmap(volatile void __iomem *addr)
+{
+	might_sleep();
+	if (is_enabled()) /* recheck and proper locking in *_core() */
+		iounmap_trace_core(addr);
+}
+
+int mmiotrace_printk(const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+	unsigned long flags;
+	va_start(args, fmt);
+
+	spin_lock_irqsave(&trace_lock, flags);
+	if (is_enabled())
+		ret = mmio_trace_printk(fmt, args);
+	spin_unlock_irqrestore(&trace_lock, flags);
+
+	va_end(args);
+	return ret;
+}
+EXPORT_SYMBOL(mmiotrace_printk);
+
+static void clear_trace_list(void)
+{
+	struct remap_trace *trace;
+	struct remap_trace *tmp;
+
+	/*
+	 * No locking required, because the caller ensures we are in a
+	 * critical section via mutex, and is_enabled() is false,
+	 * i.e. nothing can traverse or modify this list.
+	 * Caller also ensures is_enabled() cannot change.
+	 */
+	list_for_each_entry(trace, &trace_list, list) {
+		pr_notice("purging non-iounmapped trace @0x%08lx, size 0x%lx.\n",
+			  trace->probe.addr, trace->probe.len);
+		if (!nommiotrace)
+			unregister_kmmio_probe(&trace->probe);
+	}
+	synchronize_rcu(); /* unregister_kmmio_probe() requirement */
+
+	list_for_each_entry_safe(trace, tmp, &trace_list, list) {
+		list_del(&trace->list);
+		kfree(trace);
+	}
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static cpumask_var_t downed_cpus;
+
+static void enter_uniprocessor(void)
+{
+	int cpu;
+	int err;
+
+	if (!cpumask_available(downed_cpus) &&
+	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
+		pr_notice("Failed to allocate mask\n");
+		goto out;
+	}
+
+	cpus_read_lock();
+	cpumask_copy(downed_cpus, cpu_online_mask);
+	cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
+	if (num_online_cpus() > 1)
+		pr_notice("Disabling non-boot CPUs...\n");
+	cpus_read_unlock();
+
+	for_each_cpu(cpu, downed_cpus) {
+		err = remove_cpu(cpu);
+		if (!err)
+			pr_info("CPU%d is down.\n", cpu);
+		else
+			pr_err("Error taking CPU%d down: %d\n", cpu, err);
+	}
+out:
+	if (num_online_cpus() > 1)
+		pr_warn("multiple CPUs still online, may miss events.\n");
+}
+
+static void leave_uniprocessor(void)
+{
+	int cpu;
+	int err;
+
+	if (!cpumask_available(downed_cpus) || cpumask_empty(downed_cpus))
+		return;
+	pr_notice("Re-enabling CPUs...\n");
+	for_each_cpu(cpu, downed_cpus) {
+		err = add_cpu(cpu);
+		if (!err)
+			pr_info("enabled CPU%d.\n", cpu);
+		else
+			pr_err("cannot re-enable CPU%d: %d\n", cpu, err);
+	}
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+static void enter_uniprocessor(void)
+{
+	if (num_online_cpus() > 1)
+		pr_warn("multiple CPUs are online, may miss events. "
+			"Suggest booting with maxcpus=1 kernel argument.\n");
+}
+
+static void leave_uniprocessor(void)
+{
+}
+#endif
+
+void enable_mmiotrace(void)
+{
+	mutex_lock(&mmiotrace_mutex);
+	if (is_enabled())
+		goto out;
+
+	if (nommiotrace)
+		pr_info("MMIO tracing disabled.\n");
+	kmmio_init();
+	enter_uniprocessor();
+	spin_lock_irq(&trace_lock);
+	atomic_inc(&mmiotrace_enabled);
+	spin_unlock_irq(&trace_lock);
+	pr_info("enabled.\n");
+out:
+	mutex_unlock(&mmiotrace_mutex);
+}
+
+void disable_mmiotrace(void)
+{
+	mutex_lock(&mmiotrace_mutex);
+	if (!is_enabled())
+		goto out;
+
+	spin_lock_irq(&trace_lock);
+	atomic_dec(&mmiotrace_enabled);
+	BUG_ON(is_enabled());
+	spin_unlock_irq(&trace_lock);
+
+	clear_trace_list(); /* guarantees: no more kmmio callbacks */
+	leave_uniprocessor();
+	kmmio_cleanup();
+	pr_info("disabled.\n");
+out:
+	mutex_unlock(&mmiotrace_mutex);
+}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
new file mode 100644
index 000000000..ced66e68a
--- /dev/null
+++ b/arch/x86/mm/numa.c
@@ -0,0 +1,463 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Common code for 32 and 64-bit NUMA */
+#include <linux/acpi.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/ctype.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+#include <linux/topology.h>
+#include <linux/sort.h>
+#include <linux/numa_memblks.h>
+
+#include <asm/e820/api.h>
+#include <asm/proto.h>
+#include <asm/dma.h>
+#include <asm/numa.h>
+#include <asm/amd/nb.h>
+
+#include "mm_internal.h"
+
+int numa_off;
+
+static __init int numa_setup(char *opt)
+{
+	if (!opt)
+		return -EINVAL;
+	if (!strncmp(opt, "off", 3))
+		numa_off = 1;
+	if (!strncmp(opt, "fake=", 5))
+		return numa_emu_cmdline(opt + 5);
+	if (!strncmp(opt, "noacpi", 6))
+		disable_srat();
+	if (!strncmp(opt, "nohmat", 6))
+		disable_hmat();
+	return 0;
+}
+early_param("numa", numa_setup);
+
+/*
+ * apicid, cpu, node mappings
+ */
+s16 __apicid_to_node[MAX_LOCAL_APIC] = {
+	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
+nodemask_t numa_phys_nodes_parsed __initdata;
+
+int numa_cpu_node(int cpu)
+{
+	u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
+}
+
+int __init num_phys_nodes(void)
+{
+	return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES);
+}
+
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+/*
+ * Map cpu index to node index
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+
+void numa_set_node(int cpu, int node)
+{
+	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+	/* early setting, no percpu area yet */
+	if (cpu_to_node_map) {
+		cpu_to_node_map[cpu] = node;
+		return;
+	}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
+		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+		dump_stack();
+		return;
+	}
+#endif
+	per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+	set_cpu_numa_node(cpu, node);
+}
+
+void numa_clear_node(int cpu)
+{
+	numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: cpumask_of_node() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int node;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES)
+		setup_nr_node_ids();
+
+	/* allocate the map */
+	for (node = 0; node < nr_node_ids; node++)
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
+}
+
+static int __init numa_register_nodes(void)
+{
+	int nid;
+
+	if (!memblock_validate_numa_coverage(SZ_1M))
+		return -EINVAL;
+
+	/* Finally register nodes. */
+	for_each_node_mask(nid, node_possible_map) {
+		unsigned long start_pfn, end_pfn;
+
+		/*
+		 * Note, get_pfn_range_for_nid() depends on
+		 * memblock_set_node() having already happened
+		 */
+		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+		if (start_pfn >= end_pfn)
+			continue;
+
+		alloc_node_data(nid);
+		node_set_online(nid);
+	}
+
+	/* Dump memblock with node info and return. */
+	memblock_dump_all();
+	return 0;
+}
+
+/*
+ * There are unfortunately some poorly designed mainboards around that
+ * only connect memory to a single CPU. This breaks the 1:1 cpu->node
+ * mapping. To avoid this fill in the mapping for all possible CPUs,
+ * as the number of CPUs is not known yet. We round robin the existing
+ * nodes.
+ */
+static void __init numa_init_array(void)
+{
+	int rr, i;
+
+	rr = first_node(node_online_map);
+	for (i = 0; i < nr_cpu_ids; i++) {
+		if (early_cpu_to_node(i) != NUMA_NO_NODE)
+			continue;
+		numa_set_node(i, rr);
+		rr = next_node_in(rr, node_online_map);
+	}
+}
+
+static int __init numa_init(int (*init_func)(void))
+{
+	int i;
+	int ret;
+
+	for (i = 0; i < MAX_LOCAL_APIC; i++)
+		set_apicid_to_node(i, NUMA_NO_NODE);
+
+	ret = numa_memblks_init(init_func, /* memblock_force_top_down */ true);
+	if (ret < 0)
+		return ret;
+
+	ret = numa_register_nodes();
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < nr_cpu_ids; i++) {
+		int nid = early_cpu_to_node(i);
+
+		if (nid == NUMA_NO_NODE)
+			continue;
+		if (!node_online(nid))
+			numa_clear_node(i);
+	}
+	numa_init_array();
+
+	return 0;
+}
+
+/**
+ * dummy_numa_init - Fallback dummy NUMA init
+ *
+ * Used if there's no underlying NUMA architecture, NUMA initialization
+ * fails, or NUMA is disabled on the command line.
+ *
+ * Must online at least one node and add memory blocks that cover all
+ * allowed memory.  This function must not fail.
+ */
+static int __init dummy_numa_init(void)
+{
+	printk(KERN_INFO "%s\n",
+	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
+	printk(KERN_INFO "Faking a node at [mem %#018Lx-%#018Lx]\n",
+	       0LLU, PFN_PHYS(max_pfn) - 1);
+
+	node_set(0, numa_phys_nodes_parsed);
+	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
+
+	return 0;
+}
+
+/**
+ * x86_numa_init - Initialize NUMA
+ *
+ * Try each configured NUMA initialization method until one succeeds.  The
+ * last fallback is dummy single node config encompassing whole memory and
+ * never fails.
+ */
+void __init x86_numa_init(void)
+{
+	if (!numa_off) {
+#ifdef CONFIG_ACPI_NUMA
+		if (!numa_init(x86_acpi_numa_init))
+			return;
+#endif
+#ifdef CONFIG_AMD_NUMA
+		if (!numa_init(amd_numa_init))
+			return;
+#endif
+		if (acpi_disabled && !numa_init(of_numa_init))
+			return;
+	}
+
+	numa_init(dummy_numa_init);
+}
+
+
+/*
+ * A node may exist which has one or more Generic Initiators but no CPUs and no
+ * memory.
+ *
+ * This function must be called after init_cpu_to_node(), to ensure that any
+ * memoryless CPU nodes have already been brought online, and before the
+ * node_data[nid] is needed for zone list setup in build_all_zonelists().
+ *
+ * When this function is called, any nodes containing either memory and/or CPUs
+ * will already be online and there is no need to do anything extra, even if
+ * they also contain one or more Generic Initiators.
+ */
+void __init init_gi_nodes(void)
+{
+	int nid;
+
+	/*
+	 * Exclude this node from
+	 * bringup_nonboot_cpus
+	 *  cpu_up
+	 *   __try_online_node
+	 *    register_node
+	 * because node_subsys is not initialized yet.
+	 * TODO remove dependency on node_online
+	 */
+	for_each_node_state(nid, N_GENERIC_INITIATOR)
+		if (!node_online(nid))
+			node_set_online(nid);
+}
+
+/*
+ * Setup early cpu_to_node.
+ *
+ * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
+ * and apicid_to_node[] tables have valid entries for a CPU.
+ * This means we skip cpu_to_node[] initialisation for NUMA
+ * emulation and faking node case (when running a kernel compiled
+ * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
+ * is already initialized in a round robin manner at numa_init_array,
+ * prior to this call, and this initialization is good enough
+ * for the fake NUMA cases.
+ *
+ * Called before the per_cpu areas are setup.
+ */
+void __init init_cpu_to_node(void)
+{
+	int cpu;
+	u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+
+	BUG_ON(cpu_to_apicid == NULL);
+
+	for_each_possible_cpu(cpu) {
+		int node = numa_cpu_node(cpu);
+
+		if (node == NUMA_NO_NODE)
+			continue;
+
+		/*
+		 * Exclude this node from
+		 * bringup_nonboot_cpus
+		 *  cpu_up
+		 *   __try_online_node
+		 *    register_node
+		 * because node_subsys is not initialized yet.
+		 * TODO remove dependency on node_online
+		 */
+		if (!node_online(node))
+			node_set_online(node);
+
+		numa_set_node(cpu, node);
+	}
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+# ifndef CONFIG_NUMA_EMU
+void numa_add_cpu(unsigned int cpu)
+{
+	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void numa_remove_cpu(unsigned int cpu)
+{
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+int __cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+		printk(KERN_WARNING
+			"cpu_to_node(%d): usage too early!\n", cpu);
+		dump_stack();
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(__cpu_to_node);
+
+/*
+ * Same function as cpu_to_node() but used if called before the
+ * per_cpu areas are setup.
+ */
+int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	if (!cpu_possible(cpu)) {
+		printk(KERN_WARNING
+			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+		dump_stack();
+		return NUMA_NO_NODE;
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable)
+{
+	struct cpumask *mask;
+
+	if (node == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return;
+	}
+	mask = node_to_cpumask_map[node];
+	if (!cpumask_available(mask)) {
+		pr_err("node_to_cpumask_map[%i] NULL\n", node);
+		dump_stack();
+		return;
+	}
+
+	if (enable)
+		cpumask_set_cpu(cpu, mask);
+	else
+		cpumask_clear_cpu(cpu, mask);
+
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %*pbl\n",
+		enable ? "numa_add_cpu" : "numa_remove_cpu",
+		cpu, node, cpumask_pr_args(mask));
+	return;
+}
+
+# ifndef CONFIG_NUMA_EMU
+static void numa_set_cpumask(int cpu, bool enable)
+{
+	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
+}
+
+void numa_add_cpu(unsigned int cpu)
+{
+	numa_set_cpumask(cpu, true);
+}
+
+void numa_remove_cpu(unsigned int cpu)
+{
+	numa_set_cpumask(cpu, false);
+}
+# endif	/* !CONFIG_NUMA_EMU */
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	if ((unsigned)node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): (unsigned)node >= nr_node_ids(%u)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return cpu_none_mask;
+	}
+	if (!cpumask_available(node_to_cpumask_map[node])) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return cpu_online_mask;
+	}
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#ifdef CONFIG_NUMA_EMU
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+					unsigned int nr_emu_nids)
+{
+	int i, j;
+
+	/*
+	 * Transform __apicid_to_node table to use emulated nids by
+	 * reverse-mapping phys_nid.  The maps should always exist but fall
+	 * back to zero just in case.
+	 */
+	for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) {
+		if (__apicid_to_node[i] == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < nr_emu_nids; j++)
+			if (__apicid_to_node[i] == emu_nid_to_phys[j])
+				break;
+		__apicid_to_node[i] = j < nr_emu_nids ? j : 0;
+	}
+}
+
+u64 __init numa_emu_dma_end(void)
+{
+	return PFN_PHYS(MAX_DMA32_PFN);
+}
+#endif /* CONFIG_NUMA_EMU */
diff --git a/arch/x86/mm/pat/Makefile b/arch/x86/mm/pat/Makefile
new file mode 100644
index 000000000..ea464c995
--- /dev/null
+++ b/arch/x86/mm/pat/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y				:= set_memory.o memtype.o
+
+obj-$(CONFIG_X86_PAT)		+= memtype_interval.o
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
new file mode 100644
index 000000000..ad3c1feec
--- /dev/null
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * self test for change_page_attr.
+ *
+ * Clears the a test pte bit on random pages in the direct mapping,
+ * then reverts and compares page tables forwards and afterwards.
+ */
+#include <linux/memblock.h>
+#include <linux/kthread.h>
+#include <linux/random.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+
+#include <asm/cacheflush.h>
+#include <asm/kdebug.h>
+
+/*
+ * Only print the results of the first pass:
+ */
+static __read_mostly int print = 1;
+
+enum {
+	NTEST			= 3 * 100,
+	NPAGES			= 100,
+#ifdef CONFIG_X86_64
+	LPS			= (1 << PMD_SHIFT),
+#elif defined(CONFIG_X86_PAE)
+	LPS			= (1 << PMD_SHIFT),
+#else
+	LPS			= (1 << 22),
+#endif
+	GPS			= (1<<30)
+};
+
+#define PAGE_CPA_TEST	__pgprot(_PAGE_CPA_TEST)
+
+static int pte_testbit(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SOFTW1;
+}
+
+struct split_state {
+	long lpg, gpg, spg, exec;
+	long min_exec, max_exec;
+};
+
+static int print_split(struct split_state *s)
+{
+	long i, expected, missed = 0;
+	int err = 0;
+
+	s->lpg = s->gpg = s->spg = s->exec = 0;
+	s->min_exec = ~0UL;
+	s->max_exec = 0;
+	for (i = 0; i < max_pfn_mapped; ) {
+		unsigned long addr = (unsigned long)__va(i << PAGE_SHIFT);
+		unsigned int level;
+		pte_t *pte;
+
+		pte = lookup_address(addr, &level);
+		if (!pte) {
+			missed++;
+			i++;
+			continue;
+		}
+
+		if (level == PG_LEVEL_1G && sizeof(long) == 8) {
+			s->gpg++;
+			i += GPS/PAGE_SIZE;
+		} else if (level == PG_LEVEL_2M) {
+			if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) {
+				printk(KERN_ERR
+					"%lx level %d but not PSE %Lx\n",
+					addr, level, (u64)pte_val(*pte));
+				err = 1;
+			}
+			s->lpg++;
+			i += LPS/PAGE_SIZE;
+		} else {
+			s->spg++;
+			i++;
+		}
+		if (!(pte_val(*pte) & _PAGE_NX)) {
+			s->exec++;
+			if (addr < s->min_exec)
+				s->min_exec = addr;
+			if (addr > s->max_exec)
+				s->max_exec = addr;
+		}
+	}
+	if (print) {
+		printk(KERN_INFO
+			" 4k %lu large %lu gb %lu x %lu[%lx-%lx] miss %lu\n",
+			s->spg, s->lpg, s->gpg, s->exec,
+			s->min_exec != ~0UL ? s->min_exec : 0,
+			s->max_exec, missed);
+	}
+
+	expected = (s->gpg*GPS + s->lpg*LPS)/PAGE_SIZE + s->spg + missed;
+	if (expected != i) {
+		printk(KERN_ERR "CPA max_pfn_mapped %lu but expected %lu\n",
+			max_pfn_mapped, expected);
+		return 1;
+	}
+	return err;
+}
+
+static unsigned long addr[NTEST];
+static unsigned int len[NTEST];
+
+static struct page *pages[NPAGES];
+static unsigned long addrs[NPAGES];
+
+/* Change the global bit on random pages in the direct mapping */
+static int pageattr_test(void)
+{
+	struct split_state sa, sb, sc;
+	unsigned long *bm;
+	pte_t *pte, pte0;
+	int failed = 0;
+	unsigned int level;
+	int i, k;
+	int err;
+
+	if (print)
+		printk(KERN_INFO "CPA self-test:\n");
+
+	bm = vzalloc((max_pfn_mapped + 7) / 8);
+	if (!bm) {
+		printk(KERN_ERR "CPA Cannot vmalloc bitmap\n");
+		return -ENOMEM;
+	}
+
+	failed += print_split(&sa);
+
+	for (i = 0; i < NTEST; i++) {
+		unsigned long pfn = get_random_u32_below(max_pfn_mapped);
+
+		addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT);
+		len[i] = get_random_u32_below(NPAGES);
+		len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1);
+
+		if (len[i] == 0)
+			len[i] = 1;
+
+		pte = NULL;
+		pte0 = pfn_pte(0, __pgprot(0)); /* shut gcc up */
+
+		for (k = 0; k < len[i]; k++) {
+			pte = lookup_address(addr[i] + k*PAGE_SIZE, &level);
+			if (!pte || pgprot_val(pte_pgprot(*pte)) == 0 ||
+			    !(pte_val(*pte) & _PAGE_PRESENT)) {
+				addr[i] = 0;
+				break;
+			}
+			if (k == 0) {
+				pte0 = *pte;
+			} else {
+				if (pgprot_val(pte_pgprot(*pte)) !=
+					pgprot_val(pte_pgprot(pte0))) {
+					len[i] = k;
+					break;
+				}
+			}
+			if (test_bit(pfn + k, bm)) {
+				len[i] = k;
+				break;
+			}
+			__set_bit(pfn + k, bm);
+			addrs[k] = addr[i] + k*PAGE_SIZE;
+			pages[k] = pfn_to_page(pfn + k);
+		}
+		if (!addr[i] || !pte || !k) {
+			addr[i] = 0;
+			continue;
+		}
+
+		switch (i % 3) {
+		case 0:
+			err = change_page_attr_set(&addr[i], len[i], PAGE_CPA_TEST, 0);
+			break;
+
+		case 1:
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
+			break;
+
+		case 2:
+			err = cpa_set_pages_array(pages, len[i], PAGE_CPA_TEST);
+			break;
+		}
+
+
+		if (err < 0) {
+			printk(KERN_ERR "CPA %d failed %d\n", i, err);
+			failed++;
+		}
+
+		pte = lookup_address(addr[i], &level);
+		if (!pte || !pte_testbit(*pte) || pte_huge(*pte)) {
+			printk(KERN_ERR "CPA %lx: bad pte %Lx\n", addr[i],
+				pte ? (u64)pte_val(*pte) : 0ULL);
+			failed++;
+		}
+		if (level != PG_LEVEL_4K) {
+			printk(KERN_ERR "CPA %lx: unexpected level %d\n",
+				addr[i], level);
+			failed++;
+		}
+
+	}
+	vfree(bm);
+
+	failed += print_split(&sb);
+
+	for (i = 0; i < NTEST; i++) {
+		if (!addr[i])
+			continue;
+		pte = lookup_address(addr[i], &level);
+		if (!pte) {
+			printk(KERN_ERR "CPA lookup of %lx failed\n", addr[i]);
+			failed++;
+			continue;
+		}
+		err = change_page_attr_clear(&addr[i], len[i], PAGE_CPA_TEST, 0);
+		if (err < 0) {
+			printk(KERN_ERR "CPA reverting failed: %d\n", err);
+			failed++;
+		}
+		pte = lookup_address(addr[i], &level);
+		if (!pte || pte_testbit(*pte)) {
+			printk(KERN_ERR "CPA %lx: bad pte after revert %Lx\n",
+				addr[i], pte ? (u64)pte_val(*pte) : 0ULL);
+			failed++;
+		}
+
+	}
+
+	failed += print_split(&sc);
+
+	if (failed) {
+		WARN(1, KERN_ERR "NOT PASSED. Please report.\n");
+		return -EINVAL;
+	} else {
+		if (print)
+			printk(KERN_INFO "ok.\n");
+	}
+
+	return 0;
+}
+
+static int do_pageattr_test(void *__unused)
+{
+	while (!kthread_should_stop()) {
+		schedule_timeout_interruptible(HZ*30);
+		if (pageattr_test() < 0)
+			break;
+		if (print)
+			print--;
+	}
+	return 0;
+}
+
+static int start_pageattr_test(void)
+{
+	struct task_struct *p;
+
+	p = kthread_create(do_pageattr_test, NULL, "pageattr-test");
+	if (!IS_ERR(p))
+		wake_up_process(p);
+	else
+		WARN_ON(1);
+
+	return 0;
+}
+device_initcall(start_pageattr_test);
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
new file mode 100644
index 000000000..cf94fb561
--- /dev/null
+++ b/arch/x86/mm/pat/memtype.c
@@ -0,0 +1,1049 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Page Attribute Table (PAT) support: handle memory caching attributes in page tables.
+ *
+ * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *          Suresh B Siddha <suresh.b.siddha@intel.com>
+ *
+ * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen.
+ *
+ * Basic principles:
+ *
+ * PAT is a CPU feature supported by all modern x86 CPUs, to allow the firmware and
+ * the kernel to set one of a handful of 'caching type' attributes for physical
+ * memory ranges: uncached, write-combining, write-through, write-protected,
+ * and the most commonly used and default attribute: write-back caching.
+ *
+ * PAT support supersedes and augments MTRR support in a compatible fashion: MTRR is
+ * a hardware interface to enumerate a limited number of physical memory ranges
+ * and set their caching attributes explicitly, programmed into the CPU via MSRs.
+ * Even modern CPUs have MTRRs enabled - but these are typically not touched
+ * by the kernel or by user-space (such as the X server), we rely on PAT for any
+ * additional cache attribute logic.
+ *
+ * PAT doesn't work via explicit memory ranges, but uses page table entries to add
+ * cache attribute information to the mapped memory range: there's 3 bits used,
+ * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT), with the 8 possible values mapped by the
+ * CPU to actual cache attributes via an MSR loaded into the CPU (MSR_IA32_CR_PAT).
+ *
+ * ( There's a metric ton of finer details, such as compatibility with CPU quirks
+ *   that only support 4 types of PAT entries, and interaction with MTRRs, see
+ *   below for details. )
+ */
+
+#include <linux/seq_file.h>
+#include <linux/memblock.h>
+#include <linux/debugfs.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/fs.h>
+#include <linux/rbtree.h>
+#include <linux/kvm_types.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/cacheflush.h>
+#include <asm/cacheinfo.h>
+#include <asm/processor.h>
+#include <asm/tlbflush.h>
+#include <asm/x86_init.h>
+#include <asm/fcntl.h>
+#include <asm/e820/api.h>
+#include <asm/mtrr.h>
+#include <asm/page.h>
+#include <asm/msr.h>
+#include <asm/memtype.h>
+#include <asm/io.h>
+
+#include "memtype.h"
+#include "../mm_internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "" fmt
+
+static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);
+static u64 __ro_after_init pat_msr_val;
+
+/*
+ * PAT support is enabled by default, but can be disabled for
+ * various user-requested or hardware-forced reasons:
+ */
+static void __init pat_disable(const char *msg_reason)
+{
+	if (pat_disabled)
+		return;
+
+	pat_disabled = true;
+	pr_info("x86/PAT: %s\n", msg_reason);
+
+	memory_caching_control &= ~CACHE_PAT;
+}
+
+static int __init nopat(char *str)
+{
+	pat_disable("PAT support disabled via boot option.");
+	return 0;
+}
+early_param("nopat", nopat);
+
+bool pat_enabled(void)
+{
+	return !pat_disabled;
+}
+EXPORT_SYMBOL_GPL(pat_enabled);
+
+int pat_debug_enable;
+
+static int __init pat_debug_setup(char *str)
+{
+	pat_debug_enable = 1;
+	return 1;
+}
+__setup("debugpat", pat_debug_setup);
+
+#ifdef CONFIG_X86_PAT
+/*
+ * X86 PAT uses page flags arch_1 and arch_2 together to keep track of
+ * memory type of pages that have backing page struct.
+ *
+ * X86 PAT supports 4 different memory types:
+ *  - _PAGE_CACHE_MODE_WB
+ *  - _PAGE_CACHE_MODE_WC
+ *  - _PAGE_CACHE_MODE_UC_MINUS
+ *  - _PAGE_CACHE_MODE_WT
+ *
+ * _PAGE_CACHE_MODE_WB is the default type.
+ */
+
+#define _PGMT_WB		0
+#define _PGMT_WC		(1UL << PG_arch_1)
+#define _PGMT_UC_MINUS		(1UL << PG_arch_2)
+#define _PGMT_WT		(1UL << PG_arch_2 | 1UL << PG_arch_1)
+#define _PGMT_MASK		(1UL << PG_arch_2 | 1UL << PG_arch_1)
+#define _PGMT_CLEAR_MASK	(~_PGMT_MASK)
+
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+	unsigned long pg_flags = pg->flags.f & _PGMT_MASK;
+
+	if (pg_flags == _PGMT_WB)
+		return _PAGE_CACHE_MODE_WB;
+	else if (pg_flags == _PGMT_WC)
+		return _PAGE_CACHE_MODE_WC;
+	else if (pg_flags == _PGMT_UC_MINUS)
+		return _PAGE_CACHE_MODE_UC_MINUS;
+	else
+		return _PAGE_CACHE_MODE_WT;
+}
+
+static inline void set_page_memtype(struct page *pg,
+				    enum page_cache_mode memtype)
+{
+	unsigned long memtype_flags;
+	unsigned long old_flags;
+	unsigned long new_flags;
+
+	switch (memtype) {
+	case _PAGE_CACHE_MODE_WC:
+		memtype_flags = _PGMT_WC;
+		break;
+	case _PAGE_CACHE_MODE_UC_MINUS:
+		memtype_flags = _PGMT_UC_MINUS;
+		break;
+	case _PAGE_CACHE_MODE_WT:
+		memtype_flags = _PGMT_WT;
+		break;
+	case _PAGE_CACHE_MODE_WB:
+	default:
+		memtype_flags = _PGMT_WB;
+		break;
+	}
+
+	old_flags = READ_ONCE(pg->flags.f);
+	do {
+		new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
+	} while (!try_cmpxchg(&pg->flags.f, &old_flags, new_flags));
+}
+#else
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+	return -1;
+}
+static inline void set_page_memtype(struct page *pg,
+				    enum page_cache_mode memtype)
+{
+}
+#endif
+
+#define CM(c) (_PAGE_CACHE_MODE_ ## c)
+
+static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val,
+						      char *msg)
+{
+	enum page_cache_mode cache;
+	char *cache_mode;
+
+	switch (pat_val) {
+	case X86_MEMTYPE_UC:       cache = CM(UC);       cache_mode = "UC  "; break;
+	case X86_MEMTYPE_WC:       cache = CM(WC);       cache_mode = "WC  "; break;
+	case X86_MEMTYPE_WT:       cache = CM(WT);       cache_mode = "WT  "; break;
+	case X86_MEMTYPE_WP:       cache = CM(WP);       cache_mode = "WP  "; break;
+	case X86_MEMTYPE_WB:       cache = CM(WB);       cache_mode = "WB  "; break;
+	case X86_MEMTYPE_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break;
+	default:                   cache = CM(WB);       cache_mode = "WB  "; break;
+	}
+
+	memcpy(msg, cache_mode, 4);
+
+	return cache;
+}
+
+#undef CM
+
+/*
+ * Update the cache mode to pgprot translation tables according to PAT
+ * configuration.
+ * Using lower indices is preferred, so we start with highest index.
+ */
+static void __init init_cache_modes(u64 pat)
+{
+	enum page_cache_mode cache;
+	char pat_msg[33];
+	int i;
+
+	pat_msg[32] = 0;
+	for (i = 7; i >= 0; i--) {
+		cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
+					   pat_msg + 4 * i);
+		update_cache_mode_entry(i, cache);
+	}
+	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);
+}
+
+void pat_cpu_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
+		/*
+		 * If this happens we are on a secondary CPU, but switched to
+		 * PAT on the boot CPU. We have no way to undo PAT.
+		 */
+		panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
+	}
+
+	wrmsrq(MSR_IA32_CR_PAT, pat_msr_val);
+
+	__flush_tlb_all();
+}
+
+/**
+ * pat_bp_init - Initialize the PAT MSR value and PAT table
+ *
+ * This function initializes PAT MSR value and PAT table with an OS-defined
+ * value to enable additional cache attributes, WC, WT and WP.
+ *
+ * This function prepares the calls of pat_cpu_init() via cache_cpu_init()
+ * on all CPUs.
+ */
+void __init pat_bp_init(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	if (!IS_ENABLED(CONFIG_X86_PAT))
+		pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n");
+
+	if (!cpu_feature_enabled(X86_FEATURE_PAT))
+		pat_disable("PAT not supported by the CPU.");
+	else
+		rdmsrq(MSR_IA32_CR_PAT, pat_msr_val);
+
+	if (!pat_msr_val) {
+		pat_disable("PAT support disabled by the firmware.");
+
+		/*
+		 * No PAT. Emulate the PAT table that corresponds to the two
+		 * cache bits, PWT (Write Through) and PCD (Cache Disable).
+		 * This setup is also the same as the BIOS default setup.
+		 *
+		 * PTE encoding:
+		 *
+		 *       PCD
+		 *       |PWT  PAT
+		 *       ||    slot
+		 *       00    0    WB : _PAGE_CACHE_MODE_WB
+		 *       01    1    WT : _PAGE_CACHE_MODE_WT
+		 *       10    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *       11    3    UC : _PAGE_CACHE_MODE_UC
+		 *
+		 * NOTE: When WC or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat_msr_val = PAT_VALUE(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC);
+	}
+
+	/*
+	 * Xen PV doesn't allow to set PAT MSR, but all cache modes are
+	 * supported.
+	 */
+	if (pat_disabled || cpu_feature_enabled(X86_FEATURE_XENPV)) {
+		init_cache_modes(pat_msr_val);
+		return;
+	}
+
+	if ((c->x86_vfm >= INTEL_PENTIUM_PRO   && c->x86_vfm <= INTEL_PENTIUM_M_DOTHAN) ||
+	    (c->x86_vfm >= INTEL_P4_WILLAMETTE && c->x86_vfm <= INTEL_P4_CEDARMILL)) {
+		/*
+		 * PAT support with the lower four entries. Intel Pentium 2,
+		 * 3, M, and 4 are affected by PAT errata, which makes the
+		 * upper four entries unusable. To be on the safe side, we don't
+		 * use those.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 * PAT bit unused
+		 *
+		 * NOTE: When WT or WP is used, it is redirected to UC- per
+		 * the default setup in __cachemode2pte_tbl[].
+		 */
+		pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC);
+	} else {
+		/*
+		 * Full PAT support.  We put WT in slot 7 to improve
+		 * robustness in the presence of errata that might cause
+		 * the high PAT bit to be ignored.  This way, a buggy slot 7
+		 * access will hit slot 3, and slot 3 is UC, so at worst
+		 * we lose performance without causing a correctness issue.
+		 * Pentium 4 erratum N46 is an example for such an erratum,
+		 * although we try not to use PAT at all on affected CPUs.
+		 *
+		 *  PTE encoding:
+		 *      PAT
+		 *      |PCD
+		 *      ||PWT  PAT
+		 *      |||    slot
+		 *      000    0    WB : _PAGE_CACHE_MODE_WB
+		 *      001    1    WC : _PAGE_CACHE_MODE_WC
+		 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
+		 *      011    3    UC : _PAGE_CACHE_MODE_UC
+		 *      100    4    WB : Reserved
+		 *      101    5    WP : _PAGE_CACHE_MODE_WP
+		 *      110    6    UC-: Reserved
+		 *      111    7    WT : _PAGE_CACHE_MODE_WT
+		 *
+		 * The reserved slots are unused, but mapped to their
+		 * corresponding types in the presence of PAT errata.
+		 */
+		pat_msr_val = PAT_VALUE(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT);
+	}
+
+	memory_caching_control |= CACHE_PAT;
+
+	init_cache_modes(pat_msr_val);
+}
+
+static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype accesses */
+
+/*
+ * Does intersection of PAT memory type and MTRR memory type and returns
+ * the resulting memory type as PAT understands it.
+ * (Type in pat and mtrr will not have same value)
+ * The intersection is based on "Effective Memory Type" tables in IA-32
+ * SDM vol 3a
+ */
+static unsigned long pat_x_mtrr_type(u64 start, u64 end,
+				     enum page_cache_mode req_type)
+{
+	/*
+	 * Look for MTRR hint to get the effective type in case where PAT
+	 * request is for WB.
+	 */
+	if (req_type == _PAGE_CACHE_MODE_WB) {
+		u8 mtrr_type, uniform;
+
+		mtrr_type = mtrr_type_lookup(start, end, &uniform);
+		if (mtrr_type != MTRR_TYPE_WRBACK)
+			return _PAGE_CACHE_MODE_UC_MINUS;
+
+		return _PAGE_CACHE_MODE_WB;
+	}
+
+	return req_type;
+}
+
+struct pagerange_state {
+	unsigned long		cur_pfn;
+	int			ram;
+	int			not_ram;
+};
+
+static int
+pagerange_is_ram_callback(unsigned long initial_pfn, unsigned long total_nr_pages, void *arg)
+{
+	struct pagerange_state *state = arg;
+
+	state->not_ram	|= initial_pfn > state->cur_pfn;
+	state->ram	|= total_nr_pages > 0;
+	state->cur_pfn	 = initial_pfn + total_nr_pages;
+
+	return state->ram && state->not_ram;
+}
+
+static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
+{
+	int ret = 0;
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long end_pfn = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	struct pagerange_state state = {start_pfn, 0, 0};
+
+	/*
+	 * For legacy reasons, physical address range in the legacy ISA
+	 * region is tracked as non-RAM. This will allow users of
+	 * /dev/mem to map portions of legacy ISA region, even when
+	 * some of those portions are listed(or not even listed) with
+	 * different e820 types(RAM/reserved/..)
+	 */
+	if (start_pfn < ISA_END_ADDRESS >> PAGE_SHIFT)
+		start_pfn = ISA_END_ADDRESS >> PAGE_SHIFT;
+
+	if (start_pfn < end_pfn) {
+		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
+				&state, pagerange_is_ram_callback);
+	}
+
+	return (ret > 0) ? -1 : (state.ram ? 1 : 0);
+}
+
+/*
+ * For RAM pages, we use page flags to mark the pages with appropriate type.
+ * The page flags are limited to four types, WB (default), WC, WT and UC-.
+ * WP request fails with -EINVAL, and UC gets redirected to UC-.  Setting
+ * a new memory type is only allowed for a page mapped with the default WB
+ * type.
+ *
+ * Here we do two passes:
+ * - Find the memtype of all the pages in the range, look for any conflicts.
+ * - In case of no conflicts, set the new memtype for pages in the range.
+ */
+static int reserve_ram_pages_type(u64 start, u64 end,
+				  enum page_cache_mode req_type,
+				  enum page_cache_mode *new_type)
+{
+	struct page *page;
+	u64 pfn;
+
+	if (req_type == _PAGE_CACHE_MODE_WP) {
+		if (new_type)
+			*new_type = _PAGE_CACHE_MODE_UC_MINUS;
+		return -EINVAL;
+	}
+
+	if (req_type == _PAGE_CACHE_MODE_UC) {
+		/* We do not support strong UC */
+		WARN_ON_ONCE(1);
+		req_type = _PAGE_CACHE_MODE_UC_MINUS;
+	}
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		enum page_cache_mode type;
+
+		page = pfn_to_page(pfn);
+		type = get_page_memtype(page);
+		if (type != _PAGE_CACHE_MODE_WB) {
+			pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
+				start, end - 1, type, req_type);
+			if (new_type)
+				*new_type = type;
+
+			return -EBUSY;
+		}
+	}
+
+	if (new_type)
+		*new_type = req_type;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		page = pfn_to_page(pfn);
+		set_page_memtype(page, req_type);
+	}
+	return 0;
+}
+
+static int free_ram_pages_type(u64 start, u64 end)
+{
+	struct page *page;
+	u64 pfn;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		page = pfn_to_page(pfn);
+		set_page_memtype(page, _PAGE_CACHE_MODE_WB);
+	}
+	return 0;
+}
+
+static u64 sanitize_phys(u64 address)
+{
+	/*
+	 * When changing the memtype for pages containing poison allow
+	 * for a "decoy" virtual address (bit 63 clear) passed to
+	 * set_memory_X(). __pa() on a "decoy" address results in a
+	 * physical address with bit 63 set.
+	 *
+	 * Decoy addresses are not present for 32-bit builds, see
+	 * set_mce_nospec().
+	 */
+	if (IS_ENABLED(CONFIG_X86_64))
+		return address & __PHYSICAL_MASK;
+	return address;
+}
+
+/*
+ * req_type typically has one of the:
+ * - _PAGE_CACHE_MODE_WB
+ * - _PAGE_CACHE_MODE_WC
+ * - _PAGE_CACHE_MODE_UC_MINUS
+ * - _PAGE_CACHE_MODE_UC
+ * - _PAGE_CACHE_MODE_WT
+ *
+ * If new_type is NULL, function will return an error if it cannot reserve the
+ * region with req_type. If new_type is non-NULL, function will return
+ * available type in new_type in case of no error. In case of any error
+ * it will return a negative return value.
+ */
+int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_type,
+		    enum page_cache_mode *new_type)
+{
+	struct memtype *entry_new;
+	enum page_cache_mode actual_type;
+	int is_range_ram;
+	int err = 0;
+
+	start = sanitize_phys(start);
+
+	/*
+	 * The end address passed into this function is exclusive, but
+	 * sanitize_phys() expects an inclusive address.
+	 */
+	end = sanitize_phys(end - 1) + 1;
+	if (start >= end) {
+		WARN(1, "%s failed: [mem %#010Lx-%#010Lx], req %s\n", __func__,
+				start, end - 1, cattr_name(req_type));
+		return -EINVAL;
+	}
+
+	if (!pat_enabled()) {
+		/* This is identical to page table setting without PAT */
+		if (new_type)
+			*new_type = req_type;
+		return 0;
+	}
+
+	/* Low ISA region is always mapped WB in page table. No need to track */
+	if (x86_platform.is_untracked_pat_range(start, end)) {
+		if (new_type)
+			*new_type = _PAGE_CACHE_MODE_WB;
+		return 0;
+	}
+
+	/*
+	 * Call mtrr_lookup to get the type hint. This is an
+	 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+	 * tools and ACPI tools). Use WB request for WB memory and use
+	 * UC_MINUS otherwise.
+	 */
+	actual_type = pat_x_mtrr_type(start, end, req_type);
+
+	if (new_type)
+		*new_type = actual_type;
+
+	is_range_ram = pat_pagerange_is_ram(start, end);
+	if (is_range_ram == 1) {
+
+		err = reserve_ram_pages_type(start, end, req_type, new_type);
+
+		return err;
+	} else if (is_range_ram < 0) {
+		return -EINVAL;
+	}
+
+	entry_new = kzalloc_obj(struct memtype);
+	if (!entry_new)
+		return -ENOMEM;
+
+	entry_new->start = start;
+	entry_new->end	 = end;
+	entry_new->type	 = actual_type;
+
+	spin_lock(&memtype_lock);
+
+	err = memtype_check_insert(entry_new, new_type);
+	if (err) {
+		pr_info("x86/PAT: memtype_reserve failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+			start, end - 1,
+			cattr_name(entry_new->type), cattr_name(req_type));
+		kfree(entry_new);
+		spin_unlock(&memtype_lock);
+
+		return err;
+	}
+
+	spin_unlock(&memtype_lock);
+
+	dprintk("memtype_reserve added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
+		start, end - 1, cattr_name(entry_new->type), cattr_name(req_type),
+		new_type ? cattr_name(*new_type) : "-");
+
+	return err;
+}
+
+int memtype_free(u64 start, u64 end)
+{
+	int is_range_ram;
+	struct memtype *entry_old;
+
+	if (!pat_enabled())
+		return 0;
+
+	start = sanitize_phys(start);
+	end = sanitize_phys(end);
+
+	/* Low ISA region is always mapped WB. No need to track */
+	if (x86_platform.is_untracked_pat_range(start, end))
+		return 0;
+
+	is_range_ram = pat_pagerange_is_ram(start, end);
+	if (is_range_ram == 1)
+		return free_ram_pages_type(start, end);
+	if (is_range_ram < 0)
+		return -EINVAL;
+
+	spin_lock(&memtype_lock);
+	entry_old = memtype_erase(start, end);
+	spin_unlock(&memtype_lock);
+
+	if (IS_ERR(entry_old)) {
+		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+			current->comm, current->pid, start, end - 1);
+		return -EINVAL;
+	}
+
+	kfree(entry_old);
+
+	dprintk("memtype_free request [mem %#010Lx-%#010Lx]\n", start, end - 1);
+
+	return 0;
+}
+
+
+/**
+ * lookup_memtype - Looks up the memory type for a physical address
+ * @paddr: physical address of which memory type needs to be looked up
+ *
+ * Only to be called when PAT is enabled
+ *
+ * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
+ * or _PAGE_CACHE_MODE_WT.
+ */
+static enum page_cache_mode lookup_memtype(u64 paddr)
+{
+	enum page_cache_mode rettype = _PAGE_CACHE_MODE_WB;
+	struct memtype *entry;
+
+	if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
+		return rettype;
+
+	if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
+		struct page *page;
+
+		page = pfn_to_page(paddr >> PAGE_SHIFT);
+		return get_page_memtype(page);
+	}
+
+	spin_lock(&memtype_lock);
+
+	entry = memtype_lookup(paddr);
+	if (entry != NULL)
+		rettype = entry->type;
+	else
+		rettype = _PAGE_CACHE_MODE_UC_MINUS;
+
+	spin_unlock(&memtype_lock);
+
+	return rettype;
+}
+
+/**
+ * pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type
+ * of @pfn cannot be overridden by UC MTRR memory type.
+ * @pfn: The page frame number to check.
+ *
+ * Only to be called when PAT is enabled.
+ *
+ * Returns true, if the PAT memory type of @pfn is UC, UC-, or WC.
+ * Returns false in other cases.
+ */
+bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn)
+{
+	enum page_cache_mode cm = lookup_memtype(PFN_PHYS(pfn));
+
+	return cm == _PAGE_CACHE_MODE_UC ||
+	       cm == _PAGE_CACHE_MODE_UC_MINUS ||
+	       cm == _PAGE_CACHE_MODE_WC;
+}
+EXPORT_SYMBOL_FOR_KVM(pat_pfn_immune_to_uc_mtrr);
+
+/**
+ * memtype_reserve_io - Request a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ * @type: A pointer to memtype, with requested type. On success, requested
+ * or any other compatible type that was available for the region is returned
+ *
+ * On success, returns 0
+ * On failure, returns non-zero
+ */
+int memtype_reserve_io(resource_size_t start, resource_size_t end,
+			enum page_cache_mode *type)
+{
+	resource_size_t size = end - start;
+	enum page_cache_mode req_type = *type;
+	enum page_cache_mode new_type;
+	int ret;
+
+	WARN_ON_ONCE(iomem_map_sanity_check(start, size));
+
+	ret = memtype_reserve(start, end, req_type, &new_type);
+	if (ret)
+		goto out_err;
+
+	if (!is_new_memtype_allowed(start, size, req_type, new_type))
+		goto out_free;
+
+	if (memtype_kernel_map_sync(start, size, new_type) < 0)
+		goto out_free;
+
+	*type = new_type;
+	return 0;
+
+out_free:
+	memtype_free(start, end);
+	ret = -EBUSY;
+out_err:
+	return ret;
+}
+
+/**
+ * memtype_free_io - Release a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ */
+void memtype_free_io(resource_size_t start, resource_size_t end)
+{
+	memtype_free(start, end);
+}
+
+#ifdef CONFIG_X86_PAT
+int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	enum page_cache_mode type = _PAGE_CACHE_MODE_WC;
+
+	return memtype_reserve_io(start, start + size, &type);
+}
+EXPORT_SYMBOL(arch_io_reserve_memtype_wc);
+
+void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size)
+{
+	memtype_free_io(start, start + size);
+}
+EXPORT_SYMBOL(arch_io_free_memtype_wc);
+#endif
+
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				unsigned long size, pgprot_t vma_prot)
+{
+	if (!phys_mem_access_encrypted(pfn << PAGE_SHIFT, size))
+		vma_prot = pgprot_decrypted(vma_prot);
+
+	return vma_prot;
+}
+
+static inline void pgprot_set_cachemode(pgprot_t *prot, enum page_cache_mode pcm)
+{
+	*prot = __pgprot((pgprot_val(*prot) & ~_PAGE_CACHE_MASK) |
+			 cachemode2protval(pcm));
+}
+
+int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
+				unsigned long size, pgprot_t *vma_prot)
+{
+	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
+
+	if (!pat_enabled())
+		return 1;
+
+	if (!range_is_allowed(pfn, size))
+		return 0;
+
+	if (file->f_flags & O_DSYNC)
+		pcm = _PAGE_CACHE_MODE_UC_MINUS;
+
+	pgprot_set_cachemode(vma_prot, pcm);
+	return 1;
+}
+
+/*
+ * Change the memory type for the physical address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+int memtype_kernel_map_sync(u64 base, unsigned long size,
+			    enum page_cache_mode pcm)
+{
+	unsigned long id_sz;
+
+	if (base > __pa(high_memory-1))
+		return 0;
+
+	/*
+	 * Some areas in the middle of the kernel identity range
+	 * are not mapped, for example the PCI space.
+	 */
+	if (!page_is_ram(base >> PAGE_SHIFT))
+		return 0;
+
+	id_sz = (__pa(high_memory-1) <= base + size) ?
+				__pa(high_memory) - base : size;
+
+	if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
+		pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
+			current->comm, current->pid,
+			cattr_name(pcm),
+			base, (unsigned long long)(base + size-1));
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Internal interface to reserve a range of physical memory with prot.
+ * Reserved non RAM regions only and after successful memtype_reserve,
+ * this func also keeps identity mapping (if any) in sync with this new prot.
+ */
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot)
+{
+	int is_ram = 0;
+	int ret;
+	enum page_cache_mode want_pcm = pgprot2cachemode(*vma_prot);
+	enum page_cache_mode pcm = want_pcm;
+
+	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
+
+	/*
+	 * reserve_pfn_range() for RAM pages. We do not refcount to keep
+	 * track of number of mappings of RAM pages. We can assert that
+	 * the type requested matches the type of first page in the range.
+	 */
+	if (is_ram) {
+		if (!pat_enabled())
+			return 0;
+
+		pcm = lookup_memtype(paddr);
+		if (want_pcm != pcm) {
+			pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+				current->comm, current->pid,
+				cattr_name(want_pcm),
+				(unsigned long long)paddr,
+				(unsigned long long)(paddr + size - 1),
+				cattr_name(pcm));
+			pgprot_set_cachemode(vma_prot, pcm);
+		}
+		return 0;
+	}
+
+	ret = memtype_reserve(paddr, paddr + size, want_pcm, &pcm);
+	if (ret)
+		return ret;
+
+	if (pcm != want_pcm) {
+		if (!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
+			memtype_free(paddr, paddr + size);
+			pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
+			       current->comm, current->pid,
+			       cattr_name(want_pcm),
+			       (unsigned long long)paddr,
+			       (unsigned long long)(paddr + size - 1),
+			       cattr_name(pcm));
+			return -EINVAL;
+		}
+		pgprot_set_cachemode(vma_prot, pcm);
+	}
+
+	if (memtype_kernel_map_sync(paddr, size, pcm) < 0) {
+		memtype_free(paddr, paddr + size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Internal interface to free a range of physical memory.
+ * Frees non RAM regions only.
+ */
+static void free_pfn_range(u64 paddr, unsigned long size)
+{
+	int is_ram;
+
+	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
+	if (is_ram == 0)
+		memtype_free(paddr, paddr + size);
+}
+
+int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot)
+{
+	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
+	enum page_cache_mode pcm;
+
+	if (!pat_enabled())
+		return 0;
+
+	pcm = lookup_memtype(paddr);
+
+	/* Check memtype for the remaining pages */
+	while (size > PAGE_SIZE) {
+		size -= PAGE_SIZE;
+		paddr += PAGE_SIZE;
+		if (pcm != lookup_memtype(paddr))
+			return -EINVAL;
+	}
+
+	pgprot_set_cachemode(prot, pcm);
+	return 0;
+}
+
+int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot)
+{
+	const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
+
+	return reserve_pfn_range(paddr, size, prot);
+}
+
+void pfnmap_untrack(unsigned long pfn, unsigned long size)
+{
+	const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
+
+	free_pfn_range(paddr, size);
+}
+
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WC);
+	return prot;
+}
+EXPORT_SYMBOL_GPL(pgprot_writecombine);
+
+pgprot_t pgprot_writethrough(pgprot_t prot)
+{
+	pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WT);
+	return prot;
+}
+EXPORT_SYMBOL_GPL(pgprot_writethrough);
+
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
+
+/*
+ * We are allocating a temporary printout-entry to be passed
+ * between seq_start()/next() and seq_show():
+ */
+static struct memtype *memtype_get_idx(loff_t pos)
+{
+	struct memtype *entry_print;
+	int ret;
+
+	entry_print  = kzalloc_obj(struct memtype);
+	if (!entry_print)
+		return NULL;
+
+	spin_lock(&memtype_lock);
+	ret = memtype_copy_nth_element(entry_print, pos);
+	spin_unlock(&memtype_lock);
+
+	/* Free it on error: */
+	if (ret) {
+		kfree(entry_print);
+		return NULL;
+	}
+
+	return entry_print;
+}
+
+static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	if (*pos == 0) {
+		++*pos;
+		seq_puts(seq, "PAT memtype list:\n");
+	}
+
+	return memtype_get_idx(*pos);
+}
+
+static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	kfree(v);
+	++*pos;
+	return memtype_get_idx(*pos);
+}
+
+static void memtype_seq_stop(struct seq_file *seq, void *v)
+{
+	kfree(v);
+}
+
+static int memtype_seq_show(struct seq_file *seq, void *v)
+{
+	struct memtype *entry_print = (struct memtype *)v;
+
+	seq_printf(seq, "PAT: [mem 0x%016Lx-0x%016Lx] %s\n",
+			entry_print->start,
+			entry_print->end,
+			cattr_name(entry_print->type));
+
+	return 0;
+}
+
+static const struct seq_operations memtype_seq_ops = {
+	.start = memtype_seq_start,
+	.next  = memtype_seq_next,
+	.stop  = memtype_seq_stop,
+	.show  = memtype_seq_show,
+};
+
+static int memtype_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &memtype_seq_ops);
+}
+
+static const struct file_operations memtype_fops = {
+	.open    = memtype_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init pat_memtype_list_init(void)
+{
+	if (pat_enabled()) {
+		debugfs_create_file("pat_memtype_list", S_IRUSR,
+				    arch_debugfs_dir, NULL, &memtype_fops);
+	}
+	return 0;
+}
+late_initcall(pat_memtype_list_init);
+
+#endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */
diff --git a/arch/x86/mm/pat/memtype.h b/arch/x86/mm/pat/memtype.h
new file mode 100644
index 000000000..cacecdbce
--- /dev/null
+++ b/arch/x86/mm/pat/memtype.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __MEMTYPE_H_
+#define __MEMTYPE_H_
+
+extern int pat_debug_enable;
+
+#define dprintk(fmt, arg...) \
+	do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0)
+
+struct memtype {
+	u64			start;
+	u64			end;
+	u64			subtree_max_end;
+	enum page_cache_mode	type;
+	struct rb_node		rb;
+};
+
+static inline char *cattr_name(enum page_cache_mode pcm)
+{
+	switch (pcm) {
+	case _PAGE_CACHE_MODE_UC:		return "uncached";
+	case _PAGE_CACHE_MODE_UC_MINUS:		return "uncached-minus";
+	case _PAGE_CACHE_MODE_WB:		return "write-back";
+	case _PAGE_CACHE_MODE_WC:		return "write-combining";
+	case _PAGE_CACHE_MODE_WT:		return "write-through";
+	case _PAGE_CACHE_MODE_WP:		return "write-protected";
+	default:				return "broken";
+	}
+}
+
+#ifdef CONFIG_X86_PAT
+extern int memtype_check_insert(struct memtype *entry_new,
+				enum page_cache_mode *new_type);
+extern struct memtype *memtype_erase(u64 start, u64 end);
+extern struct memtype *memtype_lookup(u64 addr);
+extern int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos);
+#else
+static inline int memtype_check_insert(struct memtype *entry_new,
+				       enum page_cache_mode *new_type)
+{ return 0; }
+static inline struct memtype *memtype_erase(u64 start, u64 end)
+{ return NULL; }
+static inline struct memtype *memtype_lookup(u64 addr)
+{ return NULL; }
+static inline int memtype_copy_nth_element(struct memtype *out, loff_t pos)
+{ return 0; }
+#endif
+
+#endif /* __MEMTYPE_H_ */
diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c
new file mode 100644
index 000000000..e5844ed13
--- /dev/null
+++ b/arch/x86/mm/pat/memtype_interval.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Handle caching attributes in page tables (PAT)
+ *
+ * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ *          Suresh B Siddha <suresh.b.siddha@intel.com>
+ *
+ * Interval tree used to store the PAT memory type reservations.
+ */
+
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/interval_tree_generic.h>
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <linux/pgtable.h>
+
+#include <asm/memtype.h>
+
+#include "memtype.h"
+
+/*
+ * The memtype tree keeps track of memory type for specific
+ * physical memory areas. Without proper tracking, conflicting memory
+ * types in different mappings can cause CPU cache corruption.
+ *
+ * The tree is an interval tree (augmented rbtree) which tree is ordered
+ * by the starting address. The tree can contain multiple entries for
+ * different regions which overlap. All the aliases have the same
+ * cache attributes of course, as enforced by the PAT logic.
+ *
+ * memtype_lock protects the rbtree.
+ */
+
+static inline u64 interval_start(struct memtype *entry)
+{
+	return entry->start;
+}
+
+static inline u64 interval_end(struct memtype *entry)
+{
+	return entry->end - 1;
+}
+
+INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
+		     interval_start, interval_end,
+		     static, interval)
+
+static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED;
+
+static int memtype_check_conflict(u64 start, u64 end,
+				  enum page_cache_mode reqtype,
+				  enum page_cache_mode *newtype)
+{
+	struct memtype *entry_match;
+	enum page_cache_mode found_type = reqtype;
+
+	entry_match = interval_iter_first(&memtype_rbroot, start, end-1);
+	if (entry_match == NULL)
+		goto success;
+
+	if (entry_match->type != found_type && newtype == NULL)
+		goto failure;
+
+	dprintk("Overlap at 0x%Lx-0x%Lx\n", entry_match->start, entry_match->end);
+	found_type = entry_match->type;
+
+	entry_match = interval_iter_next(entry_match, start, end-1);
+	while (entry_match) {
+		if (entry_match->type != found_type)
+			goto failure;
+
+		entry_match = interval_iter_next(entry_match, start, end-1);
+	}
+success:
+	if (newtype)
+		*newtype = found_type;
+
+	return 0;
+
+failure:
+	pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n",
+		current->comm, current->pid, start, end,
+		cattr_name(found_type), cattr_name(entry_match->type));
+
+	return -EBUSY;
+}
+
+int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_type)
+{
+	int err = 0;
+
+	err = memtype_check_conflict(entry_new->start, entry_new->end, entry_new->type, ret_type);
+	if (err)
+		return err;
+
+	if (ret_type)
+		entry_new->type = *ret_type;
+
+	interval_insert(entry_new, &memtype_rbroot);
+	return 0;
+}
+
+struct memtype *memtype_erase(u64 start, u64 end)
+{
+	struct memtype *entry = interval_iter_first(&memtype_rbroot, start, end - 1);
+
+	while (entry && entry->start < end) {
+		if (entry->start == start && entry->end == end) {
+			interval_remove(entry, &memtype_rbroot);
+			return entry;
+		}
+		entry = interval_iter_next(entry, start, end - 1);
+	}
+	return ERR_PTR(-EINVAL);
+}
+
+struct memtype *memtype_lookup(u64 addr)
+{
+	return interval_iter_first(&memtype_rbroot, addr, addr + PAGE_SIZE-1);
+}
+
+/*
+ * Debugging helper, copy the Nth entry of the tree into a
+ * a copy for printout. This allows us to print out the tree
+ * via debugfs, without holding the memtype_lock too long:
+ */
+#ifdef CONFIG_DEBUG_FS
+int memtype_copy_nth_element(struct memtype *entry_out, loff_t pos)
+{
+	struct memtype *entry_match;
+	int i = 1;
+
+	entry_match = interval_iter_first(&memtype_rbroot, 0, ULONG_MAX);
+
+	while (entry_match && pos != i) {
+		entry_match = interval_iter_next(entry_match, 0, ULONG_MAX);
+		i++;
+	}
+
+	if (entry_match) { /* pos == i */
+		*entry_out = *entry_match;
+		return 0;
+	} else {
+		return 1;
+	}
+}
+#endif
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
new file mode 100644
index 000000000..c38faf39c
--- /dev/null
+++ b/arch/x86/mm/pat/set_memory.c
@@ -0,0 +1,2803 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Thanks to Ben LaHaise for precious feedback.
+ */
+#include <linux/highmem.h>
+#include <linux/memblock.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/debugfs.h>
+#include <linux/pfn.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/pci.h>
+#include <linux/vmalloc.h>
+#include <linux/libnvdimm.h>
+#include <linux/vmstat.h>
+#include <linux/kernel.h>
+#include <linux/cc_platform.h>
+#include <linux/set_memory.h>
+#include <linux/memregion.h>
+
+#include <asm/e820/api.h>
+#include <asm/processor.h>
+#include <asm/tlbflush.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <linux/uaccess.h>
+#include <asm/pgalloc.h>
+#include <asm/proto.h>
+#include <asm/memtype.h>
+
+#include "../mm_internal.h"
+
+/*
+ * The current flushing context - we pass it instead of 5 arguments:
+ */
+struct cpa_data {
+	unsigned long	*vaddr;
+	pgd_t		*pgd;
+	pgprot_t	mask_set;
+	pgprot_t	mask_clr;
+	unsigned long	numpages;
+	unsigned long	curpage;
+	unsigned long	pfn;
+	unsigned int	flags;
+	unsigned int	force_split		: 1,
+			force_static_prot	: 1,
+			force_flush_all		: 1;
+	struct page	**pages;
+};
+
+enum cpa_warn {
+	CPA_CONFLICT,
+	CPA_PROTECT,
+	CPA_DETECT,
+};
+
+static const int cpa_warn_level = CPA_PROTECT;
+
+/*
+ * Serialize cpa() using cpa_lock so that we don't allow any other cpu, with
+ * stale large tlb entries, to change the page attribute in parallel to some
+ * other cpu splitting a large page entry along with changing the attribute.
+ */
+static DEFINE_SPINLOCK(cpa_lock);
+
+#define CPA_FLUSHTLB		0x01
+#define CPA_ARRAY		0x02
+#define CPA_PAGES_ARRAY		0x04
+#define CPA_NO_CHECK_ALIAS	0x08 /* Do not search for aliases */
+#define CPA_COLLAPSE		0x10 /* try to collapse large pages */
+#define CPA_DEBUG_PAGEALLOC	0x20
+
+static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
+{
+	return __pgprot(cachemode2protval(pcm));
+}
+
+#ifdef CONFIG_PROC_FS
+static unsigned long direct_pages_count[PG_LEVEL_NUM];
+
+void update_page_count(int level, unsigned long pages)
+{
+	/* Protect against CPA */
+	guard(spinlock)(&pgd_lock);
+	direct_pages_count[level] += pages;
+}
+
+static void split_page_count(int level)
+{
+	if (direct_pages_count[level] == 0)
+		return;
+
+	direct_pages_count[level]--;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_SPLIT);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_SPLIT);
+	}
+	direct_pages_count[level - 1] += PTRS_PER_PTE;
+}
+
+static void collapse_page_count(int level)
+{
+	direct_pages_count[level]++;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+	}
+	direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
+void arch_report_meminfo(struct seq_file *m)
+{
+	seq_printf(m, "DirectMap4k:    %8lu kB\n",
+			direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+	seq_printf(m, "DirectMap2M:    %8lu kB\n",
+			direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+	seq_printf(m, "DirectMap4M:    %8lu kB\n",
+			direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
+	if (direct_gbpages)
+		seq_printf(m, "DirectMap1G:    %8lu kB\n",
+			direct_pages_count[PG_LEVEL_1G] << 20);
+}
+#else
+static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
+#endif
+
+#ifdef CONFIG_X86_CPA_STATISTICS
+
+static unsigned long cpa_1g_checked;
+static unsigned long cpa_1g_sameprot;
+static unsigned long cpa_1g_preserved;
+static unsigned long cpa_2m_checked;
+static unsigned long cpa_2m_sameprot;
+static unsigned long cpa_2m_preserved;
+static unsigned long cpa_4k_install;
+
+static inline void cpa_inc_1g_checked(void)
+{
+	cpa_1g_checked++;
+}
+
+static inline void cpa_inc_2m_checked(void)
+{
+	cpa_2m_checked++;
+}
+
+static inline void cpa_inc_4k_install(void)
+{
+	data_race(cpa_4k_install++);
+}
+
+static inline void cpa_inc_lp_sameprot(int level)
+{
+	if (level == PG_LEVEL_1G)
+		cpa_1g_sameprot++;
+	else
+		cpa_2m_sameprot++;
+}
+
+static inline void cpa_inc_lp_preserved(int level)
+{
+	if (level == PG_LEVEL_1G)
+		cpa_1g_preserved++;
+	else
+		cpa_2m_preserved++;
+}
+
+static int cpastats_show(struct seq_file *m, void *p)
+{
+	seq_printf(m, "1G pages checked:     %16lu\n", cpa_1g_checked);
+	seq_printf(m, "1G pages sameprot:    %16lu\n", cpa_1g_sameprot);
+	seq_printf(m, "1G pages preserved:   %16lu\n", cpa_1g_preserved);
+	seq_printf(m, "2M pages checked:     %16lu\n", cpa_2m_checked);
+	seq_printf(m, "2M pages sameprot:    %16lu\n", cpa_2m_sameprot);
+	seq_printf(m, "2M pages preserved:   %16lu\n", cpa_2m_preserved);
+	seq_printf(m, "4K pages set-checked: %16lu\n", cpa_4k_install);
+	return 0;
+}
+
+static int cpastats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, cpastats_show, NULL);
+}
+
+static const struct file_operations cpastats_fops = {
+	.open		= cpastats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init cpa_stats_init(void)
+{
+	debugfs_create_file("cpa_stats", S_IRUSR, arch_debugfs_dir, NULL,
+			    &cpastats_fops);
+	return 0;
+}
+late_initcall(cpa_stats_init);
+#else
+static inline void cpa_inc_1g_checked(void) { }
+static inline void cpa_inc_2m_checked(void) { }
+static inline void cpa_inc_4k_install(void) { }
+static inline void cpa_inc_lp_sameprot(int level) { }
+static inline void cpa_inc_lp_preserved(int level) { }
+#endif
+
+
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr < end;
+}
+
+#ifdef CONFIG_X86_64
+
+static inline int
+within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
+{
+	return addr >= start && addr <= end;
+}
+
+/*
+ * The kernel image is mapped into two places in the virtual address space
+ * (addresses without KASLR, of course):
+ *
+ * 1. The kernel direct map (0xffff880000000000)
+ * 2. The "high kernel map" (0xffffffff81000000)
+ *
+ * We actually execute out of #2. If we get the address of a kernel symbol, it
+ * points to #2, but almost all physical-to-virtual translations point to #1.
+ *
+ * This is so that we can have both a directmap of all physical memory *and*
+ * take full advantage of the limited (s32) immediate addressing range (2G)
+ * of x86_64.
+ *
+ * See Documentation/arch/x86/x86_64/mm.rst for more detail.
+ */
+
+static inline unsigned long highmap_start_pfn(void)
+{
+	return __pa_symbol(_text) >> PAGE_SHIFT;
+}
+
+static inline unsigned long highmap_end_pfn(void)
+{
+	/* Do not reference physical address outside the kernel. */
+	return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT;
+}
+
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
+{
+	/*
+	 * Kernel text has an alias mapping at a high address, known
+	 * here as "highmap".
+	 */
+	return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn());
+}
+
+#else
+
+static bool __cpa_pfn_in_highmap(unsigned long pfn)
+{
+	/* There is no highmap on 32-bit */
+	return false;
+}
+
+#endif
+
+/*
+ * See set_mce_nospec().
+ *
+ * Machine check recovery code needs to change cache mode of poisoned pages to
+ * UC to avoid speculative access logging another error. But passing the
+ * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a
+ * speculative access. So we cheat and flip the top bit of the address. This
+ * works fine for the code that updates the page tables. But at the end of the
+ * process we need to flush the TLB and cache and the non-canonical address
+ * causes a #GP fault when used by the INVLPG and CLFLUSH instructions.
+ *
+ * But in the common case we already have a canonical address. This code
+ * will fix the top bit if needed and is a no-op otherwise.
+ */
+static inline unsigned long fix_addr(unsigned long addr)
+{
+#ifdef CONFIG_X86_64
+	return (long)(addr << 1) >> 1;
+#else
+	return addr;
+#endif
+}
+
+static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx)
+{
+	if (cpa->flags & CPA_PAGES_ARRAY) {
+		struct page *page = cpa->pages[idx];
+
+		if (unlikely(PageHighMem(page)))
+			return 0;
+
+		return (unsigned long)page_address(page);
+	}
+
+	if (cpa->flags & CPA_ARRAY)
+		return cpa->vaddr[idx];
+
+	return *cpa->vaddr + idx * PAGE_SIZE;
+}
+
+/*
+ * Flushing functions
+ */
+
+static void clflush_cache_range_opt(void *vaddr, unsigned int size)
+{
+	const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
+	void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
+	void *vend = vaddr + size;
+
+	if (p >= vend)
+		return;
+
+	for (; p < vend; p += clflush_size)
+		clflushopt(p);
+}
+
+/**
+ * clflush_cache_range - flush a cache range with clflush
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to flush
+ *
+ * CLFLUSHOPT is an unordered instruction which needs fencing with MFENCE or
+ * SFENCE to avoid ordering issues.
+ */
+void clflush_cache_range(void *vaddr, unsigned int size)
+{
+	mb();
+	clflush_cache_range_opt(vaddr, size);
+	mb();
+}
+EXPORT_SYMBOL_GPL(clflush_cache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	clflush_cache_range(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
+
+#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
+bool cpu_cache_has_invalidate_memregion(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR);
+}
+EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, "DEVMEM");
+
+int cpu_cache_invalidate_memregion(phys_addr_t start, size_t len)
+{
+	if (WARN_ON_ONCE(!cpu_cache_has_invalidate_memregion()))
+		return -ENXIO;
+	wbinvd_on_all_cpus();
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, "DEVMEM");
+#endif
+
+static void __cpa_flush_all(void *arg)
+{
+	unsigned long cache = (unsigned long)arg;
+
+	/*
+	 * Flush all to work around Errata in early athlons regarding
+	 * large page flushing.
+	 */
+	__flush_tlb_all();
+
+	if (cache && boot_cpu_data.x86 >= 4)
+		wbinvd();
+}
+
+static void cpa_flush_all(unsigned long cache)
+{
+	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
+
+	on_each_cpu(__cpa_flush_all, (void *) cache, 1);
+}
+
+static void __cpa_flush_tlb(void *data)
+{
+	struct cpa_data *cpa = data;
+	unsigned int i;
+
+	for (i = 0; i < cpa->numpages; i++)
+		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
+}
+
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+	unsigned long start, addr, end;
+	struct ptdesc *ptdesc, *tmp;
+	LIST_HEAD(pgtables);
+	int collapsed = 0;
+	int i;
+
+	guard(spinlock)(&cpa_lock);
+
+	if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+		for (i = 0; i < cpa->numpages; i++)
+			collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+							  &pgtables);
+	} else {
+		addr = __cpa_addr(cpa, 0);
+		start = addr & PMD_MASK;
+		end = addr + PAGE_SIZE * cpa->numpages;
+
+		for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+			collapsed += collapse_large_pages(addr, &pgtables);
+	}
+
+	if (!collapsed)
+		return;
+
+	flush_tlb_all();
+
+	list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+		list_del(&ptdesc->pt_list);
+		pagetable_free(ptdesc);
+	}
+}
+
+static void cpa_flush(struct cpa_data *cpa, int cache)
+{
+	unsigned int i;
+
+	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
+
+	if (cache && !cpu_feature_enabled(X86_FEATURE_CLFLUSH)) {
+		cpa_flush_all(cache);
+		goto collapse_large_pages;
+	}
+
+	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
+		flush_tlb_all();
+	else
+		on_each_cpu(__cpa_flush_tlb, cpa, 1);
+
+	if (!cache)
+		goto collapse_large_pages;
+
+	mb();
+	for (i = 0; i < cpa->numpages; i++) {
+		unsigned long addr = __cpa_addr(cpa, i);
+		unsigned int level;
+
+		pte_t *pte = lookup_address(addr, &level);
+
+		/*
+		 * Only flush present addresses:
+		 */
+		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
+			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
+	}
+	mb();
+
+collapse_large_pages:
+	if (cpa->flags & CPA_COLLAPSE)
+		cpa_collapse_large_pages(cpa);
+}
+
+static bool overlaps(unsigned long r1_start, unsigned long r1_end,
+		     unsigned long r2_start, unsigned long r2_end)
+{
+	return (r1_start <= r2_end && r1_end >= r2_start) ||
+		(r2_start <= r1_end && r2_end >= r1_start);
+}
+
+#ifdef CONFIG_PCI_BIOS
+/*
+ * The BIOS area between 640k and 1Mb needs to be executable for PCI BIOS
+ * based config access (CONFIG_PCI_GOBIOS) support.
+ */
+#define BIOS_PFN	PFN_DOWN(BIOS_BEGIN)
+#define BIOS_PFN_END	PFN_DOWN(BIOS_END - 1)
+
+static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
+{
+	if (pcibios_enabled && overlaps(spfn, epfn, BIOS_PFN, BIOS_PFN_END))
+		return _PAGE_NX;
+	return 0;
+}
+#else
+static pgprotval_t protect_pci_bios(unsigned long spfn, unsigned long epfn)
+{
+	return 0;
+}
+#endif
+
+/*
+ * The .rodata section needs to be read-only. Using the pfn catches all
+ * aliases.  This also includes __ro_after_init, so do not enforce until
+ * kernel_set_to_readonly is true.
+ */
+static pgprotval_t protect_rodata(unsigned long spfn, unsigned long epfn)
+{
+	unsigned long epfn_ro, spfn_ro = PFN_DOWN(__pa_symbol(__start_rodata));
+
+	/*
+	 * Note: __end_rodata is at page aligned and not inclusive, so
+	 * subtract 1 to get the last enforced PFN in the rodata area.
+	 */
+	epfn_ro = PFN_DOWN(__pa_symbol(__end_rodata)) - 1;
+
+	if (kernel_set_to_readonly && overlaps(spfn, epfn, spfn_ro, epfn_ro))
+		return _PAGE_RW;
+	return 0;
+}
+
+/*
+ * Protect kernel text against becoming non executable by forbidding
+ * _PAGE_NX.  This protects only the high kernel mapping (_text -> _etext)
+ * out of which the kernel actually executes.  Do not protect the low
+ * mapping.
+ *
+ * This does not cover __inittext since that is gone after boot.
+ */
+static pgprotval_t protect_kernel_text(unsigned long start, unsigned long end)
+{
+	unsigned long t_end = (unsigned long)_etext - 1;
+	unsigned long t_start = (unsigned long)_text;
+
+	if (overlaps(start, end, t_start, t_end))
+		return _PAGE_NX;
+	return 0;
+}
+
+#if defined(CONFIG_X86_64)
+/*
+ * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
+ * kernel text mappings for the large page aligned text, rodata sections
+ * will be always read-only. For the kernel identity mappings covering the
+ * holes caused by this alignment can be anything that user asks.
+ *
+ * This will preserve the large page mappings for kernel text/data at no
+ * extra cost.
+ */
+static pgprotval_t protect_kernel_text_ro(unsigned long start,
+					  unsigned long end)
+{
+	unsigned long t_end = (unsigned long)__end_rodata_hpage_align - 1;
+	unsigned long t_start = (unsigned long)_text;
+	unsigned int level;
+
+	if (!kernel_set_to_readonly || !overlaps(start, end, t_start, t_end))
+		return 0;
+	/*
+	 * Don't enforce the !RW mapping for the kernel text mapping, if
+	 * the current mapping is already using small page mapping.  No
+	 * need to work hard to preserve large page mappings in this case.
+	 *
+	 * This also fixes the Linux Xen paravirt guest boot failure caused
+	 * by unexpected read-only mappings for kernel identity
+	 * mappings. In this paravirt guest case, the kernel text mapping
+	 * and the kernel identity mapping share the same page-table pages,
+	 * so the protections for kernel text and identity mappings have to
+	 * be the same.
+	 */
+	if (lookup_address(start, &level) && (level != PG_LEVEL_4K))
+		return _PAGE_RW;
+	return 0;
+}
+#else
+static pgprotval_t protect_kernel_text_ro(unsigned long start,
+					  unsigned long end)
+{
+	return 0;
+}
+#endif
+
+static inline bool conflicts(pgprot_t prot, pgprotval_t val)
+{
+	return (pgprot_val(prot) & ~val) != pgprot_val(prot);
+}
+
+static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val,
+				  unsigned long start, unsigned long end,
+				  unsigned long pfn, const char *txt)
+{
+	static const char *lvltxt[] = {
+		[CPA_CONFLICT]	= "conflict",
+		[CPA_PROTECT]	= "protect",
+		[CPA_DETECT]	= "detect",
+	};
+
+	if (warnlvl > cpa_warn_level || !conflicts(prot, val))
+		return;
+
+	pr_warn("CPA %8s %10s: 0x%016lx - 0x%016lx PFN %lx req %016llx prevent %016llx\n",
+		lvltxt[warnlvl], txt, start, end, pfn, (unsigned long long)pgprot_val(prot),
+		(unsigned long long)val);
+}
+
+/*
+ * Certain areas of memory on x86 require very specific protection flags,
+ * for example the BIOS area or kernel text. Callers don't always get this
+ * right (again, ioremap() on BIOS memory is not uncommon) so this function
+ * checks and fixes these known static required protection bits.
+ */
+static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
+					  unsigned long pfn, unsigned long npg,
+					  unsigned long lpsize, int warnlvl)
+{
+	pgprotval_t forbidden, res;
+	unsigned long end;
+
+	/*
+	 * There is no point in checking RW/NX conflicts when the requested
+	 * mapping is setting the page !PRESENT.
+	 */
+	if (!(pgprot_val(prot) & _PAGE_PRESENT))
+		return prot;
+
+	/* Operate on the virtual address */
+	end = start + npg * PAGE_SIZE - 1;
+
+	res = protect_kernel_text(start, end);
+	check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX");
+	forbidden = res;
+
+	/*
+	 * Special case to preserve a large page. If the change spawns the
+	 * full large page mapping then there is no point to split it
+	 * up. Happens with ftrace and is going to be removed once ftrace
+	 * switched to text_poke().
+	 */
+	if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) {
+		res = protect_kernel_text_ro(start, end);
+		check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
+		forbidden |= res;
+	}
+
+	/* Check the PFN directly */
+	res = protect_pci_bios(pfn, pfn + npg - 1);
+	check_conflict(warnlvl, prot, res, start, end, pfn, "PCIBIOS NX");
+	forbidden |= res;
+
+	res = protect_rodata(pfn, pfn + npg - 1);
+	check_conflict(warnlvl, prot, res, start, end, pfn, "Rodata RO");
+	forbidden |= res;
+
+	return __pgprot(pgprot_val(prot) & ~forbidden);
+}
+
+/*
+ * Validate strict W^X semantics.
+ */
+static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long start,
+				  unsigned long pfn, unsigned long npg,
+				  bool nx, bool rw)
+{
+	unsigned long end;
+
+	/*
+	 * 32-bit has some unfixable W+X issues, like EFI code
+	 * and writeable data being in the same page.  Disable
+	 * detection and enforcement there.
+	 */
+	if (IS_ENABLED(CONFIG_X86_32))
+		return new;
+
+	/* Only verify when NX is supported: */
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return new;
+
+	if (!((pgprot_val(old) ^ pgprot_val(new)) & (_PAGE_RW | _PAGE_NX)))
+		return new;
+
+	if ((pgprot_val(new) & (_PAGE_RW | _PAGE_NX)) != _PAGE_RW)
+		return new;
+
+	/* Non-leaf translation entries can disable writing or execution. */
+	if (!rw || nx)
+		return new;
+
+	end = start + npg * PAGE_SIZE - 1;
+	WARN_ONCE(1, "CPA detected W^X violation: %016llx -> %016llx range: 0x%016lx - 0x%016lx PFN %lx\n",
+		  (unsigned long long)pgprot_val(old),
+		  (unsigned long long)pgprot_val(new),
+		  start, end, pfn);
+
+	/*
+	 * For now, allow all permission change attempts by returning the
+	 * attempted permissions.  This can 'return old' to actively
+	 * refuse the permission change at a later time.
+	 */
+	return new;
+}
+
+/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry (or NULL if the entry does not exist),
+ * the level of the entry, and the effective NX and RW bits of all
+ * page table levels.
+ */
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw)
+{
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	*level = PG_LEVEL_256T;
+	*nx = false;
+	*rw = true;
+
+	if (pgd_none(*pgd))
+		return NULL;
+
+	*level = PG_LEVEL_512G;
+	*nx |= pgd_flags(*pgd) & _PAGE_NX;
+	*rw &= pgd_flags(*pgd) & _PAGE_RW;
+
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d))
+		return NULL;
+
+	if (p4d_leaf(*p4d) || !p4d_present(*p4d))
+		return (pte_t *)p4d;
+
+	*level = PG_LEVEL_1G;
+	*nx |= p4d_flags(*p4d) & _PAGE_NX;
+	*rw &= p4d_flags(*p4d) & _PAGE_RW;
+
+	pud = pud_offset(p4d, address);
+	if (pud_none(*pud))
+		return NULL;
+
+	if (pud_leaf(*pud) || !pud_present(*pud))
+		return (pte_t *)pud;
+
+	*level = PG_LEVEL_2M;
+	*nx |= pud_flags(*pud) & _PAGE_NX;
+	*rw &= pud_flags(*pud) & _PAGE_RW;
+
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd))
+		return NULL;
+
+	if (pmd_leaf(*pmd) || !pmd_present(*pmd))
+		return (pte_t *)pmd;
+
+	*level = PG_LEVEL_4K;
+	*nx |= pmd_flags(*pmd) & _PAGE_NX;
+	*rw &= pmd_flags(*pmd) & _PAGE_RW;
+
+	return pte_offset_kernel(pmd, address);
+}
+
+/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+			     unsigned int *level)
+{
+	bool nx, rw;
+
+	return lookup_address_in_pgd_attr(pgd, address, level, &nx, &rw);
+}
+
+/*
+ * Lookup the page table entry for a virtual address. Return a pointer
+ * to the entry and the level of the mapping.
+ *
+ * Note: the function returns p4d, pud or pmd either when the entry is marked
+ * large or when the present bit is not set. Otherwise it returns NULL.
+ */
+pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+	return lookup_address_in_pgd(pgd_offset_k(address), address, level);
+}
+EXPORT_SYMBOL_GPL(lookup_address);
+
+static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw)
+{
+	pgd_t *pgd;
+
+	if (!cpa->pgd)
+		pgd = pgd_offset_k(address);
+	else
+		pgd = cpa->pgd + pgd_index(address);
+
+	return lookup_address_in_pgd_attr(pgd, address, level, nx, rw);
+}
+
+/*
+ * Lookup the PMD entry for a virtual address. Return a pointer to the entry
+ * or NULL if not present.
+ */
+pmd_t *lookup_pmd_address(unsigned long address)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(address);
+	if (pgd_none(*pgd))
+		return NULL;
+
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d) || p4d_leaf(*p4d) || !p4d_present(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, address);
+	if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud))
+		return NULL;
+
+	return pmd_offset(pud, address);
+}
+
+/*
+ * This is necessary because __pa() does not work on some
+ * kinds of memory, like vmalloc() or the alloc_remap()
+ * areas on 32-bit NUMA systems.  The percpu areas can
+ * end up in this kind of memory, for instance.
+ *
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
+ */
+phys_addr_t slow_virt_to_phys(void *__virt_addr)
+{
+	unsigned long virt_addr = (unsigned long)__virt_addr;
+	phys_addr_t phys_addr;
+	unsigned long offset;
+	enum pg_level level;
+	pte_t *pte;
+
+	pte = lookup_address(virt_addr, &level);
+	BUG_ON(!pte);
+
+	/*
+	 * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t
+	 * before being left-shifted PAGE_SHIFT bits -- this trick is to
+	 * make 32-PAE kernel work correctly.
+	 */
+	switch (level) {
+	case PG_LEVEL_1G:
+		phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PUD_MASK;
+		break;
+	case PG_LEVEL_2M:
+		phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PMD_MASK;
+		break;
+	default:
+		phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
+		offset = virt_addr & ~PAGE_MASK;
+	}
+
+	return (phys_addr_t)(phys_addr | offset);
+}
+EXPORT_SYMBOL_GPL(slow_virt_to_phys);
+
+/*
+ * Set the new pmd in all the pgds we know about:
+ */
+static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
+{
+	/* change init_mm */
+	set_pte_atomic(kpte, pte);
+
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		struct ptdesc *ptdesc;
+
+		list_for_each_entry(ptdesc, &pgd_list, pt_list) {
+			pgd_t *pgd;
+			p4d_t *p4d;
+			pud_t *pud;
+			pmd_t *pmd;
+
+			pgd = (pgd_t *)ptdesc_address(ptdesc) + pgd_index(address);
+			p4d = p4d_offset(pgd, address);
+			pud = pud_offset(p4d, address);
+			pmd = pmd_offset(pud, address);
+			set_pte_atomic((pte_t *)pmd, pte);
+		}
+	}
+}
+
+static pgprot_t pgprot_clear_protnone_bits(pgprot_t prot)
+{
+	/*
+	 * _PAGE_GLOBAL means "global page" for present PTEs.
+	 * But, it is also used to indicate _PAGE_PROTNONE
+	 * for non-present PTEs.
+	 *
+	 * This ensures that a _PAGE_GLOBAL PTE going from
+	 * present to non-present is not confused as
+	 * _PAGE_PROTNONE.
+	 */
+	if (!(pgprot_val(prot) & _PAGE_PRESENT))
+		pgprot_val(prot) &= ~_PAGE_GLOBAL;
+
+	return prot;
+}
+
+static int __should_split_large_page(pte_t *kpte, unsigned long address,
+				     struct cpa_data *cpa)
+{
+	unsigned long numpages, pmask, psize, lpaddr, pfn, old_pfn;
+	pgprot_t old_prot, new_prot, req_prot, chk_prot;
+	pte_t new_pte, *tmp;
+	enum pg_level level;
+	bool nx, rw;
+
+	/*
+	 * Check for races, another CPU might have split this page
+	 * up already:
+	 */
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
+	if (tmp != kpte)
+		return 1;
+
+	switch (level) {
+	case PG_LEVEL_2M:
+		old_prot = pmd_pgprot(*(pmd_t *)kpte);
+		old_pfn = pmd_pfn(*(pmd_t *)kpte);
+		cpa_inc_2m_checked();
+		break;
+	case PG_LEVEL_1G:
+		old_prot = pud_pgprot(*(pud_t *)kpte);
+		old_pfn = pud_pfn(*(pud_t *)kpte);
+		cpa_inc_1g_checked();
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	psize = page_level_size(level);
+	pmask = page_level_mask(level);
+
+	/*
+	 * Calculate the number of pages, which fit into this large
+	 * page starting at address:
+	 */
+	lpaddr = (address + psize) & pmask;
+	numpages = (lpaddr - address) >> PAGE_SHIFT;
+	if (numpages < cpa->numpages)
+		cpa->numpages = numpages;
+
+	/*
+	 * We are safe now. Check whether the new pgprot is the same:
+	 * Convert protection attributes to 4k-format, as cpa->mask* are set
+	 * up accordingly.
+	 */
+
+	/* Clear PSE (aka _PAGE_PAT) and move PAT bit to correct position */
+	req_prot = pgprot_large_2_4k(old_prot);
+
+	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
+
+	/*
+	 * req_prot is in format of 4k pages. It must be converted to large
+	 * page format: the caching mode includes the PAT bit located at
+	 * different bit positions in the two formats.
+	 */
+	req_prot = pgprot_4k_2_large(req_prot);
+	req_prot = pgprot_clear_protnone_bits(req_prot);
+	if (pgprot_val(req_prot) & _PAGE_PRESENT)
+		pgprot_val(req_prot) |= _PAGE_PSE;
+
+	/*
+	 * old_pfn points to the large page base pfn. So we need to add the
+	 * offset of the virtual address:
+	 */
+	pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT);
+	cpa->pfn = pfn;
+
+	/*
+	 * Calculate the large page base address and the number of 4K pages
+	 * in the large page
+	 */
+	lpaddr = address & pmask;
+	numpages = psize >> PAGE_SHIFT;
+
+	/*
+	 * Sanity check that the existing mapping is correct versus the static
+	 * protections. static_protections() guards against !PRESENT, so no
+	 * extra conditional required here.
+	 */
+	chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages,
+				      psize, CPA_CONFLICT);
+
+	if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) {
+		/*
+		 * Split the large page and tell the split code to
+		 * enforce static protections.
+		 */
+		cpa->force_static_prot = 1;
+		return 1;
+	}
+
+	/*
+	 * Optimization: If the requested pgprot is the same as the current
+	 * pgprot, then the large page can be preserved and no updates are
+	 * required independent of alignment and length of the requested
+	 * range. The above already established that the current pgprot is
+	 * correct, which in consequence makes the requested pgprot correct
+	 * as well if it is the same. The static protection scan below will
+	 * not come to a different conclusion.
+	 */
+	if (pgprot_val(req_prot) == pgprot_val(old_prot)) {
+		cpa_inc_lp_sameprot(level);
+		return 0;
+	}
+
+	/*
+	 * If the requested range does not cover the full page, split it up
+	 */
+	if (address != lpaddr || cpa->numpages != numpages)
+		return 1;
+
+	/*
+	 * Check whether the requested pgprot is conflicting with a static
+	 * protection requirement in the large page.
+	 */
+	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
+				      psize, CPA_DETECT);
+
+	new_prot = verify_rwx(old_prot, new_prot, lpaddr, old_pfn, numpages,
+			      nx, rw);
+
+	/*
+	 * If there is a conflict, split the large page.
+	 *
+	 * There used to be a 4k wise evaluation trying really hard to
+	 * preserve the large pages, but experimentation has shown, that this
+	 * does not help at all. There might be corner cases which would
+	 * preserve one large page occasionally, but it's really not worth the
+	 * extra code and cycles for the common case.
+	 */
+	if (pgprot_val(req_prot) != pgprot_val(new_prot))
+		return 1;
+
+	/* All checks passed. Update the large page mapping. */
+	new_pte = pfn_pte(old_pfn, new_prot);
+	__set_pmd_pte(kpte, address, new_pte);
+	cpa->flags |= CPA_FLUSHTLB;
+	cpa_inc_lp_preserved(level);
+	return 0;
+}
+
+static int should_split_large_page(pte_t *kpte, unsigned long address,
+				   struct cpa_data *cpa)
+{
+	if (cpa->force_split)
+		return 1;
+
+	guard(spinlock)(&pgd_lock);
+	return __should_split_large_page(kpte, address, cpa);
+}
+
+static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn,
+			  pgprot_t ref_prot, unsigned long address,
+			  unsigned long size)
+{
+	unsigned int npg = PFN_DOWN(size);
+	pgprot_t prot;
+
+	/*
+	 * If should_split_large_page() discovered an inconsistent mapping,
+	 * remove the invalid protection in the split mapping.
+	 */
+	if (!cpa->force_static_prot)
+		goto set;
+
+	/* Hand in lpsize = 0 to enforce the protection mechanism */
+	prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT);
+
+	if (pgprot_val(prot) == pgprot_val(ref_prot))
+		goto set;
+
+	/*
+	 * If this is splitting a PMD, fix it up. PUD splits cannot be
+	 * fixed trivially as that would require to rescan the newly
+	 * installed PMD mappings after returning from split_large_page()
+	 * so an eventual further split can allocate the necessary PTE
+	 * pages. Warn for now and revisit it in case this actually
+	 * happens.
+	 */
+	if (size == PAGE_SIZE)
+		ref_prot = prot;
+	else
+		pr_warn_once("CPA: Cannot fixup static protections for PUD split\n");
+set:
+	set_pte(pte, pfn_pte(pfn, ref_prot));
+}
+
+static int
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+		   struct ptdesc *ptdesc)
+{
+	unsigned long lpaddr, lpinc, ref_pfn, pfn, pfninc = 1;
+	struct page *base = ptdesc_page(ptdesc);
+	pte_t *pbase = (pte_t *)page_address(base);
+	unsigned int i, level;
+	pgprot_t ref_prot;
+	bool nx, rw;
+	pte_t *tmp;
+
+	guard(spinlock)(&pgd_lock);
+	/*
+	 * Check for races, another CPU might have split this page
+	 * up for us already:
+	 */
+	tmp = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
+	if (tmp != kpte)
+		return 1;
+
+	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
+
+	switch (level) {
+	case PG_LEVEL_2M:
+		ref_prot = pmd_pgprot(*(pmd_t *)kpte);
+		/*
+		 * Clear PSE (aka _PAGE_PAT) and move
+		 * PAT bit to correct position.
+		 */
+		ref_prot = pgprot_large_2_4k(ref_prot);
+		ref_pfn = pmd_pfn(*(pmd_t *)kpte);
+		lpaddr = address & PMD_MASK;
+		lpinc = PAGE_SIZE;
+		break;
+
+	case PG_LEVEL_1G:
+		ref_prot = pud_pgprot(*(pud_t *)kpte);
+		ref_pfn = pud_pfn(*(pud_t *)kpte);
+		pfninc = PMD_SIZE >> PAGE_SHIFT;
+		lpaddr = address & PUD_MASK;
+		lpinc = PMD_SIZE;
+		/*
+		 * Clear the PSE flags if the PRESENT flag is not set
+		 * otherwise pmd_present() will return true even on a non
+		 * present pmd.
+		 */
+		if (!(pgprot_val(ref_prot) & _PAGE_PRESENT))
+			pgprot_val(ref_prot) &= ~_PAGE_PSE;
+		break;
+
+	default:
+		return 1;
+	}
+
+	ref_prot = pgprot_clear_protnone_bits(ref_prot);
+
+	/*
+	 * Get the target pfn from the original entry:
+	 */
+	pfn = ref_pfn;
+	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc, lpaddr += lpinc)
+		split_set_pte(cpa, pbase + i, pfn, ref_prot, lpaddr, lpinc);
+
+	if (virt_addr_valid(address)) {
+		unsigned long pfn = PFN_DOWN(__pa(address));
+
+		if (pfn_range_is_mapped(pfn, pfn + 1))
+			split_page_count(level);
+	}
+
+	/*
+	 * Install the new, split up pagetable.
+	 *
+	 * We use the standard kernel pagetable protections for the new
+	 * pagetable protections, the actual ptes set above control the
+	 * primary protection behavior:
+	 */
+	__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
+
+	/*
+	 * Do a global flush tlb after splitting the large page
+	 * and before we do the actual change page attribute in the PTE.
+	 *
+	 * Without this, we violate the TLB application note, that says:
+	 * "The TLBs may contain both ordinary and large-page
+	 *  translations for a 4-KByte range of linear addresses. This
+	 *  may occur if software modifies the paging structures so that
+	 *  the page size used for the address range changes. If the two
+	 *  translations differ with respect to page frame or attributes
+	 *  (e.g., permissions), processor behavior is undefined and may
+	 *  be implementation-specific."
+	 *
+	 * We do this global tlb flush inside the cpa_lock, so that we
+	 * don't allow any other cpu, with stale tlb entries change the
+	 * page attribute in parallel, that also falls into the
+	 * just split large page entry.
+	 */
+	flush_tlb_all();
+
+	return 0;
+}
+
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+			    unsigned long address)
+{
+	struct ptdesc *ptdesc;
+
+	spin_unlock(&cpa_lock);
+	ptdesc = pagetable_alloc(GFP_KERNEL, 0);
+	spin_lock(&cpa_lock);
+	if (!ptdesc)
+		return -ENOMEM;
+
+	if (__split_large_page(cpa, kpte, address, ptdesc))
+		pagetable_free(ptdesc);
+
+	return 0;
+}
+
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	pmd_t _pmd, old_pmd;
+	pte_t *pte, first;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	int i = 0;
+
+	if (!cpu_feature_enabled(X86_FEATURE_PSE))
+		return 0;
+
+	addr &= PMD_MASK;
+	pte = pte_offset_kernel(pmd, addr);
+	first = *pte;
+	pfn = pte_pfn(first);
+
+	/* Make sure alignment is suitable */
+	if (PFN_PHYS(pfn) & ~PMD_MASK)
+		return 0;
+
+	/* The page is 4k intentionally */
+	if (pte_flags(first) & _PAGE_KERNEL_4K)
+		return 0;
+
+	/* Check that the rest of PTEs are compatible with the first one */
+	for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+		pte_t entry = *pte;
+
+		if (!pte_present(entry))
+			return 0;
+		if (pte_flags(entry) != pte_flags(first))
+			return 0;
+		if (pte_pfn(entry) != pte_pfn(first) + i)
+			return 0;
+	}
+
+	old_pmd = *pmd;
+
+	/* Success: set up a large page */
+	pgprot = pgprot_4k_2_large(pte_pgprot(first));
+	pgprot_val(pgprot) |= _PAGE_PSE;
+	_pmd = pfn_pmd(pfn, pgprot);
+	set_pmd(pmd, _pmd);
+
+	/* Queue the page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		struct ptdesc *ptdesc;
+
+		/* Update all PGD tables to use the same large page */
+		list_for_each_entry(ptdesc, &pgd_list, pt_list) {
+			pgd_t *pgd = (pgd_t *)ptdesc_address(ptdesc) + pgd_index(addr);
+			p4d_t *p4d = p4d_offset(pgd, addr);
+			pud_t *pud = pud_offset(p4d, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
+			/* Something is wrong if entries doesn't match */
+			if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+				continue;
+			set_pmd(pmd, _pmd);
+		}
+	}
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_2M);
+
+	return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	unsigned long pfn;
+	pmd_t *pmd, first;
+	int i;
+
+	if (!direct_gbpages)
+		return 0;
+
+	addr &= PUD_MASK;
+	pmd = pmd_offset(pud, addr);
+	first = *pmd;
+
+	/*
+	 * To restore PUD page all PMD entries must be large and
+	 * have suitable alignment
+	 */
+	pfn = pmd_pfn(first);
+	if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+		return 0;
+
+	/*
+	 * To restore PUD page, all following PMDs must be compatible with the
+	 * first one.
+	 */
+	for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+		pmd_t entry = *pmd;
+
+		if (!pmd_present(entry) || !pmd_leaf(entry))
+			return 0;
+		if (pmd_flags(entry) != pmd_flags(first))
+			return 0;
+		if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+			return 0;
+	}
+
+	/* Restore PUD page and queue page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+	set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_1G);
+
+	return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+	int collapsed;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	addr &= PMD_MASK;
+
+	guard(spinlock)(&pgd_lock);
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return 0;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return 0;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		return 0;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		return 0;
+
+	collapsed = collapse_pmd_page(pmd, addr, pgtables);
+	if (collapsed)
+		collapsed += collapse_pud_page(pud, addr, pgtables);
+
+	return collapsed;
+}
+
+static bool try_to_free_pte_page(pte_t *pte)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		if (!pte_none(pte[i]))
+			return false;
+
+	pte_free_kernel(&init_mm, pte);
+	return true;
+}
+
+static bool try_to_free_pmd_page(pmd_t *pmd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_none(pmd[i]))
+			return false;
+
+	pmd_free(&init_mm, pmd);
+	return true;
+}
+
+static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, start);
+
+	while (start < end) {
+		set_pte(pte, __pte(0));
+
+		start += PAGE_SIZE;
+		pte++;
+	}
+
+	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+		pmd_clear(pmd);
+		return true;
+	}
+	return false;
+}
+
+static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+			      unsigned long start, unsigned long end)
+{
+	if (unmap_pte_range(pmd, start, end))
+		if (try_to_free_pmd_page(pud_pgtable(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, start);
+
+	/*
+	 * Not on a 2MB page boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+		unsigned long pre_end = min_t(unsigned long, end, next_page);
+
+		__unmap_pmd_range(pud, pmd, start, pre_end);
+
+		start = pre_end;
+		pmd++;
+	}
+
+	/*
+	 * Try to unmap in 2M chunks.
+	 */
+	while (end - start >= PMD_SIZE) {
+		if (pmd_leaf(*pmd))
+			pmd_clear(pmd);
+		else
+			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+
+		start += PMD_SIZE;
+		pmd++;
+	}
+
+	/*
+	 * 4K leftovers?
+	 */
+	if (start < end)
+		return __unmap_pmd_range(pud, pmd, start, end);
+
+	/*
+	 * Try again to free the PMD page if haven't succeeded above.
+	 */
+	if (!pud_none(*pud))
+		if (try_to_free_pmd_page(pud_pgtable(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end)
+{
+	pud_t *pud = pud_offset(p4d, start);
+
+	/*
+	 * Not on a GB page boundary?
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+		unsigned long pre_end	= min_t(unsigned long, end, next_page);
+
+		unmap_pmd_range(pud, start, pre_end);
+
+		start = pre_end;
+		pud++;
+	}
+
+	/*
+	 * Try to unmap in 1G chunks?
+	 */
+	while (end - start >= PUD_SIZE) {
+
+		if (pud_leaf(*pud))
+			pud_clear(pud);
+		else
+			unmap_pmd_range(pud, start, start + PUD_SIZE);
+
+		start += PUD_SIZE;
+		pud++;
+	}
+
+	/*
+	 * 2M leftovers?
+	 */
+	if (start < end)
+		unmap_pmd_range(pud, start, end);
+
+	/*
+	 * No need to try to free the PUD page because we'll free it in
+	 * populate_pgd's error path
+	 */
+}
+
+static int alloc_pte_page(pmd_t *pmd)
+{
+	pte_t *pte = pte_alloc_one_kernel(&init_mm);
+	if (!pte)
+		return -1;
+
+	set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+	return 0;
+}
+
+static int alloc_pmd_page(pud_t *pud)
+{
+	/*
+	 * Pass 0 as a placeholder for the second argument, since the
+	 * generic implementation of pmd_alloc_one() does not use it.
+	 */
+	pmd_t *pmd = pmd_alloc_one(&init_mm, 0);
+	if (!pmd)
+		return -1;
+
+	set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	return 0;
+}
+
+static void populate_pte(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, start);
+
+	pgprot = pgprot_clear_protnone_bits(pgprot);
+
+	while (num_pages-- && start < end) {
+		set_pte(pte, pfn_pte(cpa->pfn, pgprot));
+
+		start	 += PAGE_SIZE;
+		cpa->pfn++;
+		pte++;
+	}
+}
+
+static long populate_pmd(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+{
+	long cur_pages = 0;
+	pmd_t *pmd;
+	pgprot_t pmd_pgprot;
+
+	/*
+	 * Not on a 2M boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long pre_end = start + (num_pages << PAGE_SHIFT);
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+
+		pre_end   = min_t(unsigned long, pre_end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(unsigned int, num_pages, cur_pages);
+
+		/*
+		 * Need a PTE page?
+		 */
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot);
+
+		start = pre_end;
+	}
+
+	/*
+	 * We mapped them all?
+	 */
+	if (num_pages == cur_pages)
+		return cur_pages;
+
+	pmd_pgprot = pgprot_4k_2_large(pgprot);
+
+	while (end - start >= PMD_SIZE) {
+
+		/*
+		 * We cannot use a 1G page so allocate a PMD page if needed.
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		pmd = pmd_offset(pud, start);
+
+		set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn,
+					canon_pgprot(pmd_pgprot))));
+
+		start	  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
+		cur_pages += PMD_SIZE >> PAGE_SHIFT;
+	}
+
+	/*
+	 * Map trailing 4K pages.
+	 */
+	if (start < end) {
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, end, num_pages - cur_pages,
+			     pmd, pgprot);
+	}
+	return num_pages;
+}
+
+static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d,
+			pgprot_t pgprot)
+{
+	pud_t *pud;
+	unsigned long end;
+	long cur_pages = 0;
+	pgprot_t pud_pgprot;
+
+	end = start + (cpa->numpages << PAGE_SHIFT);
+
+	/*
+	 * Not on a Gb page boundary? => map everything up to it with
+	 * smaller pages.
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long pre_end;
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+
+		pre_end   = min_t(unsigned long, end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);
+
+		pud = pud_offset(p4d, start);
+
+		/*
+		 * Need a PMD page?
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		cur_pages = populate_pmd(cpa, start, pre_end, cur_pages,
+					 pud, pgprot);
+		if (cur_pages < 0)
+			return cur_pages;
+
+		start = pre_end;
+	}
+
+	/* We mapped them all? */
+	if (cpa->numpages == cur_pages)
+		return cur_pages;
+
+	pud = pud_offset(p4d, start);
+	pud_pgprot = pgprot_4k_2_large(pgprot);
+
+	/*
+	 * Map everything starting from the Gb boundary, possibly with 1G pages
+	 */
+	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
+		set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
+				   canon_pgprot(pud_pgprot))));
+
+		start	  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
+		cur_pages += PUD_SIZE >> PAGE_SHIFT;
+		pud++;
+	}
+
+	/* Map trailing leftover */
+	if (start < end) {
+		long tmp;
+
+		pud = pud_offset(p4d, start);
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages,
+				   pud, pgprot);
+		if (tmp < 0)
+			return cur_pages;
+
+		cur_pages += tmp;
+	}
+	return cur_pages;
+}
+
+/*
+ * Restrictions for kernel page table do not necessarily apply when mapping in
+ * an alternate PGD.
+ */
+static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
+{
+	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
+	pud_t *pud = NULL;	/* shut up gcc */
+	p4d_t *p4d;
+	pgd_t *pgd_entry;
+	long ret;
+
+	pgd_entry = cpa->pgd + pgd_index(addr);
+
+	if (pgd_none(*pgd_entry)) {
+		/*
+		 * Pass 0 as a placeholder for the second argument, since the
+		 * generic implementation of p4d_alloc_one() does not use it.
+		 */
+		p4d = p4d_alloc_one(&init_mm, 0);
+		if (!p4d)
+			return -1;
+
+		set_pgd(pgd_entry, __pgd(__pa(p4d) | _KERNPG_TABLE));
+	}
+
+	/*
+	 * Allocate a PUD page and hand it down for mapping.
+	 */
+	p4d = p4d_offset(pgd_entry, addr);
+	if (p4d_none(*p4d)) {
+		/*
+		 * Pass 0 as a placeholder for the second argument, since the
+		 * generic implementation of pud_alloc_one() does not use it.
+		 */
+		pud = pud_alloc_one(&init_mm, 0);
+		if (!pud)
+			return -1;
+
+		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+	}
+
+	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
+
+	ret = populate_pud(cpa, addr, p4d, pgprot);
+	if (ret < 0) {
+		/*
+		 * Leave the PUD page in place in case some other CPU or thread
+		 * already found it, but remove any useless entries we just
+		 * added to it.
+		 */
+		unmap_pud_range(p4d, addr,
+				addr + (cpa->numpages << PAGE_SHIFT));
+		return ret;
+	}
+
+	cpa->numpages = ret;
+	return 0;
+}
+
+static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
+			       int primary)
+{
+	if (cpa->pgd) {
+		/*
+		 * Right now, we only execute this code path when mapping
+		 * the EFI virtual memory map regions, no other users
+		 * provide a ->pgd value. This may change in the future.
+		 */
+		return populate_pgd(cpa, vaddr);
+	}
+
+	/*
+	 * Ignore all non primary paths.
+	 */
+	if (!primary) {
+		cpa->numpages = 1;
+		return 0;
+	}
+
+	/*
+	 * Ignore the NULL PTE for kernel identity mapping, as it is expected
+	 * to have holes.
+	 * Also set numpages to '1' indicating that we processed cpa req for
+	 * one virtual address page and its pfn. TBD: numpages can be set based
+	 * on the initial value and the level returned by lookup_address().
+	 */
+	if (within(vaddr, PAGE_OFFSET,
+		   PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+		cpa->numpages = 1;
+		cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
+		return 0;
+
+	} else if (__cpa_pfn_in_highmap(cpa->pfn)) {
+		/* Faults in the highmap are OK, so do not warn: */
+		return -EFAULT;
+	} else {
+		WARN(1, KERN_WARNING "CPA: called for zero pte. "
+			"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
+			*cpa->vaddr);
+
+		return -EFAULT;
+	}
+}
+
+static int __change_page_attr(struct cpa_data *cpa, int primary)
+{
+	unsigned long address;
+	int do_split, err;
+	unsigned int level;
+	pte_t *kpte, old_pte;
+	bool nx, rw;
+
+	address = __cpa_addr(cpa, cpa->curpage);
+repeat:
+	kpte = _lookup_address_cpa(cpa, address, &level, &nx, &rw);
+	if (!kpte)
+		return __cpa_process_fault(cpa, address, primary);
+
+	old_pte = *kpte;
+	if (pte_none(old_pte))
+		return __cpa_process_fault(cpa, address, primary);
+
+	if (level == PG_LEVEL_4K) {
+		pte_t new_pte;
+		pgprot_t old_prot = pte_pgprot(old_pte);
+		pgprot_t new_prot = pte_pgprot(old_pte);
+		unsigned long pfn = pte_pfn(old_pte);
+
+		pgprot_val(new_prot) &= ~pgprot_val(cpa->mask_clr);
+		pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
+
+		cpa_inc_4k_install();
+		/* Hand in lpsize = 0 to enforce the protection mechanism */
+		new_prot = static_protections(new_prot, address, pfn, 1, 0,
+					      CPA_PROTECT);
+
+		new_prot = verify_rwx(old_prot, new_prot, address, pfn, 1,
+				      nx, rw);
+
+		new_prot = pgprot_clear_protnone_bits(new_prot);
+
+		/*
+		 * We need to keep the pfn from the existing PTE,
+		 * after all we're only going to change its attributes
+		 * not the memory it points to
+		 */
+		new_pte = pfn_pte(pfn, new_prot);
+		cpa->pfn = pfn;
+		/*
+		 * Do we really change anything ?
+		 */
+		if (pte_val(old_pte) != pte_val(new_pte)) {
+			set_pte_atomic(kpte, new_pte);
+			cpa->flags |= CPA_FLUSHTLB;
+		}
+		cpa->numpages = 1;
+		return 0;
+	}
+
+	/*
+	 * Check, whether we can keep the large page intact
+	 * and just change the pte:
+	 */
+	do_split = should_split_large_page(kpte, address, cpa);
+	/*
+	 * When the range fits into the existing large page,
+	 * return. cp->numpages and cpa->tlbflush have been updated in
+	 * try_large_page:
+	 */
+	if (do_split <= 0)
+		return do_split;
+
+	/*
+	 * We have to split the large page:
+	 */
+	err = split_large_page(cpa, kpte, address);
+	if (!err)
+		goto repeat;
+
+	return err;
+}
+
+static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary);
+
+/*
+ * Check the directmap and "high kernel map" 'aliases'.
+ */
+static int cpa_process_alias(struct cpa_data *cpa)
+{
+	struct cpa_data alias_cpa;
+	unsigned long laddr = (unsigned long)__va(cpa->pfn << PAGE_SHIFT);
+	unsigned long vaddr;
+	int ret;
+
+	if (!pfn_range_is_mapped(cpa->pfn, cpa->pfn + 1))
+		return 0;
+
+	/*
+	 * No need to redo, when the primary call touched the direct
+	 * mapping already:
+	 */
+	vaddr = __cpa_addr(cpa, cpa->curpage);
+	if (!(within(vaddr, PAGE_OFFSET,
+		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
+
+		alias_cpa = *cpa;
+		alias_cpa.vaddr = &laddr;
+		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+		alias_cpa.curpage = 0;
+
+		/* Directmap always has NX set, do not modify. */
+		if (__supported_pte_mask & _PAGE_NX) {
+			alias_cpa.mask_clr.pgprot &= ~_PAGE_NX;
+			alias_cpa.mask_set.pgprot &= ~_PAGE_NX;
+		}
+
+		cpa->force_flush_all = 1;
+
+		ret = __change_page_attr_set_clr(&alias_cpa, 0);
+		if (ret)
+			return ret;
+	}
+
+#ifdef CONFIG_X86_64
+	/*
+	 * If the primary call didn't touch the high mapping already
+	 * and the physical address is inside the kernel map, we need
+	 * to touch the high mapped kernel as well:
+	 */
+	if (!within(vaddr, (unsigned long)_text, _brk_end) &&
+	    __cpa_pfn_in_highmap(cpa->pfn)) {
+		unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) +
+					       __START_KERNEL_map - phys_base;
+		alias_cpa = *cpa;
+		alias_cpa.vaddr = &temp_cpa_vaddr;
+		alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY);
+		alias_cpa.curpage = 0;
+
+		/*
+		 * [_text, _brk_end) also covers data, do not modify NX except
+		 * in cases where the highmap is the primary target.
+		 */
+		if (__supported_pte_mask & _PAGE_NX) {
+			alias_cpa.mask_clr.pgprot &= ~_PAGE_NX;
+			alias_cpa.mask_set.pgprot &= ~_PAGE_NX;
+		}
+
+		cpa->force_flush_all = 1;
+		/*
+		 * The high mapping range is imprecise, so ignore the
+		 * return value.
+		 */
+		__change_page_attr_set_clr(&alias_cpa, 0);
+	}
+#endif
+
+	return 0;
+}
+
+static int __change_page_attr_set_clr(struct cpa_data *cpa, int primary)
+{
+	unsigned long numpages = cpa->numpages;
+	unsigned long rempages = numpages;
+	bool lock = true;
+	int ret = 0;
+
+	/*
+	 * No changes, easy!
+	 */
+	if (!(pgprot_val(cpa->mask_set) | pgprot_val(cpa->mask_clr)) &&
+	    !cpa->force_split)
+		return ret;
+
+	/*
+	 * DEBUG_PAGEALLOC is special; it is called from any context the
+	 * page-allocator is, which violates the normal cpa_lock locking
+	 * rules.
+	 *
+	 * However, since it is part of the page-allocator, things are still
+	 * properly serialized by the page-allocator locking and the fact that
+	 * when a page is owned by the page-allocator, it isn't owned by
+	 * anybody else. That is, you *SHOULD NOT* be calling cpa() on memory
+	 * that isn't allocated.
+	 *
+	 * Additionally, DEBUG_PAGEALLOC ensures (per probe_page_size_mask())
+	 * that the kernel mapping is 4k pages, therefore there are no large
+	 * pages to split/collapse.
+	 *
+	 * Furthermore, the page-allocator strictly manages pages that
+	 * *exist*, avoiding pgd_lock.
+	 *
+	 * Therefore, it is safe to not take cpa_lock.
+	 */
+	if (debug_pagealloc_enabled() && (cpa->flags & CPA_DEBUG_PAGEALLOC))
+		lock = false;
+
+	while (rempages) {
+		/*
+		 * Store the remaining nr of pages for the large page
+		 * preservation check.
+		 */
+		cpa->numpages = rempages;
+		/* for array changes, we can't use large page */
+		if (cpa->flags & (CPA_ARRAY | CPA_PAGES_ARRAY))
+			cpa->numpages = 1;
+
+		if (lock) {
+			guard(spinlock)(&cpa_lock);
+			ret = __change_page_attr(cpa, primary);
+		} else {
+			ret = __change_page_attr(cpa, primary);
+		}
+		if (ret)
+			goto out;
+
+		if (primary && !(cpa->flags & CPA_NO_CHECK_ALIAS)) {
+			ret = cpa_process_alias(cpa);
+			if (ret)
+				goto out;
+		}
+
+		/*
+		 * Adjust the number of pages with the result of the
+		 * CPA operation. Either a large page has been
+		 * preserved or a single page update happened.
+		 */
+		BUG_ON(cpa->numpages > rempages || !cpa->numpages);
+		rempages -= cpa->numpages;
+		cpa->curpage += cpa->numpages;
+	}
+
+out:
+	/* Restore the original numpages */
+	cpa->numpages = numpages;
+	return ret;
+}
+
+static int change_page_attr_set_clr(unsigned long *addr, int numpages,
+				    pgprot_t mask_set, pgprot_t mask_clr,
+				    int force_split, int in_flag,
+				    struct page **pages)
+{
+	struct cpa_data cpa;
+	int ret, cache;
+
+	memset(&cpa, 0, sizeof(cpa));
+
+	/*
+	 * Check, if we are requested to set a not supported
+	 * feature.  Clearing non-supported features is OK.
+	 */
+	mask_set = canon_pgprot(mask_set);
+
+	if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
+		return 0;
+
+	/* Ensure we are PAGE_SIZE aligned */
+	if (in_flag & CPA_ARRAY) {
+		int i;
+		for (i = 0; i < numpages; i++) {
+			if (addr[i] & ~PAGE_MASK) {
+				addr[i] &= PAGE_MASK;
+				WARN_ON_ONCE(1);
+			}
+		}
+	} else if (!(in_flag & CPA_PAGES_ARRAY)) {
+		/*
+		 * in_flag of CPA_PAGES_ARRAY implies it is aligned.
+		 * No need to check in that case
+		 */
+		if (*addr & ~PAGE_MASK) {
+			*addr &= PAGE_MASK;
+			/*
+			 * People should not be passing in unaligned addresses:
+			 */
+			WARN_ON_ONCE(1);
+		}
+	}
+
+	/* Must avoid aliasing mappings in the highmem code */
+	kmap_flush_unused();
+
+	vm_unmap_aliases();
+
+	cpa.vaddr = addr;
+	cpa.pages = pages;
+	cpa.numpages = numpages;
+	cpa.mask_set = mask_set;
+	cpa.mask_clr = mask_clr;
+	cpa.flags = in_flag;
+	cpa.curpage = 0;
+	cpa.force_split = force_split;
+
+	ret = __change_page_attr_set_clr(&cpa, 1);
+
+	/*
+	 * Check whether we really changed something:
+	 */
+	if (!(cpa.flags & CPA_FLUSHTLB))
+		goto out;
+
+	/*
+	 * No need to flush, when we did not set any of the caching
+	 * attributes:
+	 */
+	cache = !!pgprot2cachemode(mask_set);
+
+	/*
+	 * On error; flush everything to be sure.
+	 */
+	if (ret) {
+		cpa_flush_all(cache);
+		goto out;
+	}
+
+	cpa_flush(&cpa, cache);
+out:
+	return ret;
+}
+
+static inline int change_page_attr_set(unsigned long *addr, int numpages,
+				       pgprot_t mask, int array)
+{
+	return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0,
+		(array ? CPA_ARRAY : 0), NULL);
+}
+
+static inline int change_page_attr_clear(unsigned long *addr, int numpages,
+					 pgprot_t mask, int array)
+{
+	return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0,
+		(array ? CPA_ARRAY : 0), NULL);
+}
+
+static inline int cpa_set_pages_array(struct page **pages, int numpages,
+				       pgprot_t mask)
+{
+	return change_page_attr_set_clr(NULL, numpages, mask, __pgprot(0), 0,
+		CPA_PAGES_ARRAY, pages);
+}
+
+static inline int cpa_clear_pages_array(struct page **pages, int numpages,
+					 pgprot_t mask)
+{
+	return change_page_attr_set_clr(NULL, numpages, __pgprot(0), mask, 0,
+		CPA_PAGES_ARRAY, pages);
+}
+
+int _set_memory_uc(unsigned long addr, int numpages)
+{
+	/*
+	 * for now UC MINUS. see comments in ioremap()
+	 * If you really need strong UC use ioremap_uc(), but note
+	 * that you cannot override IO areas with set_memory_*() as
+	 * these helpers cannot work with IO memory.
+	 */
+	return change_page_attr_set(&addr, numpages,
+				    cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+				    0);
+}
+
+int set_memory_uc(unsigned long addr, int numpages)
+{
+	int ret;
+
+	/*
+	 * for now UC MINUS. see comments in ioremap()
+	 */
+	ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+			      _PAGE_CACHE_MODE_UC_MINUS, NULL);
+	if (ret)
+		goto out_err;
+
+	ret = _set_memory_uc(addr, numpages);
+	if (ret)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+	return ret;
+}
+EXPORT_SYMBOL(set_memory_uc);
+
+int _set_memory_wc(unsigned long addr, int numpages)
+{
+	int ret;
+
+	ret = change_page_attr_set(&addr, numpages,
+				   cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+				   0);
+	if (!ret) {
+		ret = change_page_attr_set_clr(&addr, numpages,
+					       cachemode2pgprot(_PAGE_CACHE_MODE_WC),
+					       __pgprot(_PAGE_CACHE_MASK),
+					       0, 0, NULL);
+	}
+	return ret;
+}
+
+int set_memory_wc(unsigned long addr, int numpages)
+{
+	int ret;
+
+	ret = memtype_reserve(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+		_PAGE_CACHE_MODE_WC, NULL);
+	if (ret)
+		return ret;
+
+	ret = _set_memory_wc(addr, numpages);
+	if (ret)
+		memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+
+	return ret;
+}
+EXPORT_SYMBOL(set_memory_wc);
+
+int _set_memory_wt(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0);
+}
+
+int _set_memory_wb(unsigned long addr, int numpages)
+{
+	/* WB cache mode is hard wired to all cache attribute bits being 0 */
+	return change_page_attr_clear(&addr, numpages,
+				      __pgprot(_PAGE_CACHE_MASK), 0);
+}
+
+int set_memory_wb(unsigned long addr, int numpages)
+{
+	int ret;
+
+	ret = _set_memory_wb(addr, numpages);
+	if (ret)
+		return ret;
+
+	memtype_free(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL(set_memory_wb);
+
+/* Prevent speculative access to a page by marking it not-present */
+#ifdef CONFIG_X86_64
+int set_mce_nospec(unsigned long pfn)
+{
+	unsigned long decoy_addr;
+	int rc;
+
+	/* SGX pages are not in the 1:1 map */
+	if (arch_is_platform_page(pfn << PAGE_SHIFT))
+		return 0;
+	/*
+	 * We would like to just call:
+	 *      set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1);
+	 * but doing that would radically increase the odds of a
+	 * speculative access to the poison page because we'd have
+	 * the virtual address of the kernel 1:1 mapping sitting
+	 * around in registers.
+	 * Instead we get tricky.  We create a non-canonical address
+	 * that looks just like the one we want, but has bit 63 flipped.
+	 * This relies on set_memory_XX() properly sanitizing any __pa()
+	 * results with __PHYSICAL_MASK or PTE_PFN_MASK.
+	 */
+	decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63));
+
+	rc = set_memory_np(decoy_addr, 1);
+	if (rc)
+		pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(set_mce_nospec);
+
+/* Restore full speculative operation to the pfn. */
+int clear_mce_nospec(unsigned long pfn)
+{
+	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
+
+	return set_memory_p(addr, 1);
+}
+EXPORT_SYMBOL_GPL(clear_mce_nospec);
+#endif /* CONFIG_X86_64 */
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return 0;
+
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0);
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	if (!(__supported_pte_mask & _PAGE_NX))
+		return 0;
+
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0);
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW | _PAGE_DIRTY), 0);
+}
+
+int set_memory_rox(unsigned long addr, int numpages)
+{
+	pgprot_t clr = __pgprot(_PAGE_RW | _PAGE_DIRTY);
+
+	if (__supported_pte_mask & _PAGE_NX)
+		clr.pgprot |= _PAGE_NX;
+
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+					CPA_COLLAPSE, NULL);
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0);
+}
+
+int set_memory_np(unsigned long addr, int numpages)
+{
+	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
+int set_memory_np_noalias(unsigned long addr, int numpages)
+{
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+					__pgprot(_PAGE_PRESENT), 0,
+					CPA_NO_CHECK_ALIAS, NULL);
+}
+
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
+int set_memory_4k(unsigned long addr, int numpages)
+{
+	return change_page_attr_set_clr(&addr, numpages,
+					__pgprot(_PAGE_KERNEL_4K),
+					__pgprot(0), 1, 0, NULL);
+}
+
+int set_memory_nonglobal(unsigned long addr, int numpages)
+{
+	return change_page_attr_clear(&addr, numpages,
+				      __pgprot(_PAGE_GLOBAL), 0);
+}
+
+int set_memory_global(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_GLOBAL), 0);
+}
+
+/*
+ * __set_memory_enc_pgtable() is used for the hypervisors that get
+ * informed about "encryption" status via page tables.
+ */
+static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
+{
+	pgprot_t empty = __pgprot(0);
+	struct cpa_data cpa;
+	int ret;
+
+	/* Should not be working on unaligned addresses */
+	if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
+		addr &= PAGE_MASK;
+
+	memset(&cpa, 0, sizeof(cpa));
+	cpa.vaddr = &addr;
+	cpa.numpages = numpages;
+	cpa.mask_set = enc ? pgprot_encrypted(empty) : pgprot_decrypted(empty);
+	cpa.mask_clr = enc ? pgprot_decrypted(empty) : pgprot_encrypted(empty);
+	cpa.pgd = init_mm.pgd;
+
+	/* Must avoid aliasing mappings in the highmem code */
+	kmap_flush_unused();
+	vm_unmap_aliases();
+
+	/* Flush the caches as needed before changing the encryption attribute. */
+	if (x86_platform.guest.enc_tlb_flush_required(enc))
+		cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
+
+	/* Notify hypervisor that we are about to set/clr encryption attribute. */
+	ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
+	if (ret)
+		goto vmm_fail;
+
+	ret = __change_page_attr_set_clr(&cpa, 1);
+
+	/*
+	 * After changing the encryption attribute, we need to flush TLBs again
+	 * in case any speculative TLB caching occurred (but no need to flush
+	 * caches again).  We could just use cpa_flush_all(), but in case TLB
+	 * flushing gets optimized in the cpa_flush() path use the same logic
+	 * as above.
+	 */
+	cpa_flush(&cpa, 0);
+
+	if (ret)
+		return ret;
+
+	/* Notify hypervisor that we have successfully set/clr encryption attribute. */
+	ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc);
+	if (ret)
+		goto vmm_fail;
+
+	return 0;
+
+vmm_fail:
+	WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n",
+		  (void *)addr, numpages, enc ? "private" : "shared", ret);
+
+	return ret;
+}
+
+/*
+ * The lock serializes conversions between private and shared memory.
+ *
+ * It is taken for read on conversion. A write lock guarantees that no
+ * concurrent conversions are in progress.
+ */
+static DECLARE_RWSEM(mem_enc_lock);
+
+/*
+ * Stop new private<->shared conversions.
+ *
+ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
+ * The lock is not released to prevent new conversions from being started.
+ */
+bool set_memory_enc_stop_conversion(void)
+{
+	/*
+	 * In a crash scenario, sleep is not allowed. Try to take the lock.
+	 * Failure indicates that there is a race with the conversion.
+	 */
+	if (oops_in_progress)
+		return down_write_trylock(&mem_enc_lock);
+
+	down_write(&mem_enc_lock);
+
+	return true;
+}
+
+static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+{
+	int ret = 0;
+
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
+		if (!down_read_trylock(&mem_enc_lock))
+			return -EBUSY;
+
+		ret = __set_memory_enc_pgtable(addr, numpages, enc);
+
+		up_read(&mem_enc_lock);
+	}
+
+	return ret;
+}
+
+int set_memory_encrypted(unsigned long addr, int numpages)
+{
+	return __set_memory_enc_dec(addr, numpages, true);
+}
+EXPORT_SYMBOL_GPL(set_memory_encrypted);
+
+int set_memory_decrypted(unsigned long addr, int numpages)
+{
+	return __set_memory_enc_dec(addr, numpages, false);
+}
+EXPORT_SYMBOL_GPL(set_memory_decrypted);
+
+int set_pages_uc(struct page *page, int numpages)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	return set_memory_uc(addr, numpages);
+}
+EXPORT_SYMBOL(set_pages_uc);
+
+static int _set_pages_array(struct page **pages, int numpages,
+		enum page_cache_mode new_type)
+{
+	unsigned long start;
+	unsigned long end;
+	enum page_cache_mode set_type;
+	int i;
+	int free_idx;
+	int ret;
+
+	for (i = 0; i < numpages; i++) {
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
+		end = start + PAGE_SIZE;
+		if (memtype_reserve(start, end, new_type, NULL))
+			goto err_out;
+	}
+
+	/* If WC, set to UC- first and then WC */
+	set_type = (new_type == _PAGE_CACHE_MODE_WC) ?
+				_PAGE_CACHE_MODE_UC_MINUS : new_type;
+
+	ret = cpa_set_pages_array(pages, numpages,
+				  cachemode2pgprot(set_type));
+	if (!ret && new_type == _PAGE_CACHE_MODE_WC)
+		ret = change_page_attr_set_clr(NULL, numpages,
+					       cachemode2pgprot(
+						_PAGE_CACHE_MODE_WC),
+					       __pgprot(_PAGE_CACHE_MASK),
+					       0, CPA_PAGES_ARRAY, pages);
+	if (ret)
+		goto err_out;
+	return 0; /* Success */
+err_out:
+	free_idx = i;
+	for (i = 0; i < free_idx; i++) {
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
+		end = start + PAGE_SIZE;
+		memtype_free(start, end);
+	}
+	return -EINVAL;
+}
+
+int set_pages_array_uc(struct page **pages, int numpages)
+{
+	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_UC_MINUS);
+}
+EXPORT_SYMBOL(set_pages_array_uc);
+
+int set_pages_array_wc(struct page **pages, int numpages)
+{
+	return _set_pages_array(pages, numpages, _PAGE_CACHE_MODE_WC);
+}
+EXPORT_SYMBOL(set_pages_array_wc);
+
+int set_pages_wb(struct page *page, int numpages)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	return set_memory_wb(addr, numpages);
+}
+EXPORT_SYMBOL(set_pages_wb);
+
+int set_pages_array_wb(struct page **pages, int numpages)
+{
+	int retval;
+	unsigned long start;
+	unsigned long end;
+	int i;
+
+	/* WB cache mode is hard wired to all cache attribute bits being 0 */
+	retval = cpa_clear_pages_array(pages, numpages,
+			__pgprot(_PAGE_CACHE_MASK));
+	if (retval)
+		return retval;
+
+	for (i = 0; i < numpages; i++) {
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
+		end = start + PAGE_SIZE;
+		memtype_free(start, end);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(set_pages_array_wb);
+
+int set_pages_ro(struct page *page, int numpages)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	return set_memory_ro(addr, numpages);
+}
+
+int set_pages_rw(struct page *page, int numpages)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	return set_memory_rw(addr, numpages);
+}
+
+static int __set_pages_p(struct page *page, int numpages, unsigned int cpa_flags)
+{
+	unsigned long tempaddr = (unsigned long) page_address(page);
+	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
+				.numpages = numpages,
+				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.mask_clr = __pgprot(0),
+				.flags = CPA_NO_CHECK_ALIAS | cpa_flags };
+
+	/*
+	 * No alias checking needed for setting present flag. otherwise,
+	 * we may need to break large pages for 64-bit kernel text
+	 * mappings (this adds to complexity if we want to do this from
+	 * atomic context especially). Let's keep it simple!
+	 */
+	return __change_page_attr_set_clr(&cpa, 1);
+}
+
+static int __set_pages_np(struct page *page, int numpages, unsigned int cpa_flags)
+{
+	unsigned long tempaddr = (unsigned long) page_address(page);
+	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
+				.numpages = numpages,
+				.mask_set = __pgprot(0),
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
+				.flags = CPA_NO_CHECK_ALIAS | cpa_flags };
+
+	/*
+	 * No alias checking needed for setting not present flag. otherwise,
+	 * we may need to break large pages for 64-bit kernel text
+	 * mappings (this adds to complexity if we want to do this from
+	 * atomic context especially). Let's keep it simple!
+	 */
+	return __change_page_attr_set_clr(&cpa, 1);
+}
+
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_pages_np(page, 1, 0);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_pages_p(page, 1, 0);
+}
+
+int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid)
+{
+	if (valid)
+		return __set_pages_p(page, nr, 0);
+
+	return __set_pages_np(page, nr, 0);
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (PageHighMem(page))
+		return;
+	if (!enable) {
+		debug_check_no_locks_freed(page_address(page),
+					   numpages * PAGE_SIZE);
+	}
+
+	/*
+	 * The return value is ignored as the calls cannot fail.
+	 * Large pages for identity mappings are not used at boot time
+	 * and hence no memory allocations during large page split.
+	 */
+	if (enable)
+		__set_pages_p(page, numpages, CPA_DEBUG_PAGEALLOC);
+	else
+		__set_pages_np(page, numpages, CPA_DEBUG_PAGEALLOC);
+
+	/*
+	 * We should perform an IPI and flush all tlbs, but that can
+	 * deadlock, settle for a local flush.
+	 *
+	 * Not doing a global TLB flush means that remote CPUs will retain
+	 * stale TLB entries. In case of P->NP (on free) this means the remote
+	 * CPUs will not take the faults, making the debug scheme less
+	 * reliable. On the NP->P (on alloc) this means the remote CPUs can
+	 * take a spurious fault. However spurious_kernel_fault() will observe
+	 * *_present() and fix it up.
+	 *
+	 * Preemption needs to be disabled around __flush_tlb_all() due to CR3
+	 * reload in __native_flush_tlb().
+	 */
+	preempt_disable();
+	__flush_tlb_all();
+	preempt_enable();
+
+	arch_flush_lazy_mmu_mode();
+}
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
+bool kernel_page_present(struct page *page)
+{
+	unsigned int level;
+	pte_t *pte;
+
+	if (PageHighMem(page))
+		return false;
+
+	pte = lookup_address((unsigned long)page_address(page), &level);
+	return (pte_val(*pte) & _PAGE_PRESENT);
+}
+
+int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+				   unsigned numpages, unsigned long page_flags)
+{
+	int retval = -EINVAL;
+
+	struct cpa_data cpa = {
+		.vaddr = &address,
+		.pfn = pfn,
+		.pgd = pgd,
+		.numpages = numpages,
+		.mask_set = __pgprot(0),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)),
+		.flags = CPA_NO_CHECK_ALIAS,
+	};
+
+	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		goto out;
+
+	if (!(page_flags & _PAGE_ENC))
+		cpa.mask_clr = pgprot_encrypted(cpa.mask_clr);
+
+	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
+
+	retval = __change_page_attr_set_clr(&cpa, 1);
+	__flush_tlb_all();
+
+out:
+	return retval;
+}
+
+/*
+ * __flush_tlb_all() flushes mappings only on current CPU and hence this
+ * function shouldn't be used in an SMP environment. Presently, it's used only
+ * during boot (way before smp_init()) by EFI subsystem and hence is ok.
+ */
+int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
+				     unsigned long numpages)
+{
+	int retval;
+
+	/*
+	 * The typical sequence for unmapping is to find a pte through
+	 * lookup_address_in_pgd() (ideally, it should never return NULL because
+	 * the address is already mapped) and change its protections. As pfn is
+	 * the *target* of a mapping, it's not useful while unmapping.
+	 */
+	struct cpa_data cpa = {
+		.vaddr		= &address,
+		.pfn		= 0,
+		.pgd		= pgd,
+		.numpages	= numpages,
+		.mask_set	= __pgprot(0),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
+		.flags		= CPA_NO_CHECK_ALIAS,
+	};
+
+	WARN_ONCE(num_online_cpus() > 1, "Don't call after initializing SMP");
+
+	retval = __change_page_attr_set_clr(&cpa, 1);
+	__flush_tlb_all();
+
+	return retval;
+}
+
+/*
+ * The testcases use internal knowledge of the implementation that shouldn't
+ * be exposed to the rest of the kernel. Include these directly here.
+ */
+#ifdef CONFIG_CPA_DEBUG
+#include "cpa-test.c"
+#endif
diff --git a/arch/x86/mm/pf_in.c b/arch/x86/mm/pf_in.c
new file mode 100644
index 000000000..3f83e31b3
--- /dev/null
+++ b/arch/x86/mm/pf_in.c
@@ -0,0 +1,516 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Fault Injection Test harness (FI)
+ *  Copyright (C) Intel Crop.
+ */
+
+/*  Id: pf_in.c,v 1.1.1.1 2002/11/12 05:56:32 brlock Exp
+ *  Copyright by Intel Crop., 2002
+ *  Louis Zhuang (louis.zhuang@intel.com)
+ *
+ *  Bjorn Steinbrink (B.Steinbrink@gmx.de), 2007
+ */
+
+#include <linux/ptrace.h> /* struct pt_regs */
+#include "pf_in.h"
+
+#ifdef __i386__
+/* IA32 Manual 3, 2-1 */
+static unsigned char prefix_codes[] = {
+	0xF0, 0xF2, 0xF3, 0x2E, 0x36, 0x3E, 0x26, 0x64,
+	0x65, 0x66, 0x67
+};
+/* IA32 Manual 3, 3-432*/
+static unsigned int reg_rop[] = {
+	0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB };
+static unsigned int imm_wop[] = { 0xC6, 0xC7 };
+/* IA32 Manual 3, 3-432*/
+static unsigned int rw8[] = { 0x88, 0x8A, 0xC6, 0xAA };
+static unsigned int rw32[] = {
+	0x89, 0x8B, 0xC7, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB
+};
+static unsigned int mw8[] = { 0x88, 0x8A, 0xC6, 0xB60F, 0xBE0F, 0xAA };
+static unsigned int mw16[] = { 0xB70F, 0xBF0F };
+static unsigned int mw32[] = { 0x89, 0x8B, 0xC7, 0xAB };
+static unsigned int mw64[] = {};
+#else /* not __i386__ */
+static unsigned char prefix_codes[] = {
+	0x66, 0x67, 0x2E, 0x3E, 0x26, 0x64, 0x65, 0x36,
+	0xF0, 0xF3, 0xF2,
+	/* REX Prefixes */
+	0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
+	0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f
+};
+/* AMD64 Manual 3, Appendix A*/
+static unsigned int reg_rop[] = {
+	0x8A, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F
+};
+static unsigned int reg_wop[] = { 0x88, 0x89, 0xAA, 0xAB };
+static unsigned int imm_wop[] = { 0xC6, 0xC7 };
+static unsigned int rw8[] = { 0xC6, 0x88, 0x8A, 0xAA };
+static unsigned int rw32[] = {
+	0xC7, 0x89, 0x8B, 0xB60F, 0xB70F, 0xBE0F, 0xBF0F, 0xAB
+};
+/* 8 bit only */
+static unsigned int mw8[] = { 0xC6, 0x88, 0x8A, 0xB60F, 0xBE0F, 0xAA };
+/* 16 bit only */
+static unsigned int mw16[] = { 0xB70F, 0xBF0F };
+/* 16 or 32 bit */
+static unsigned int mw32[] = { 0xC7 };
+/* 16, 32 or 64 bit */
+static unsigned int mw64[] = { 0x89, 0x8B, 0xAB };
+#endif /* not __i386__ */
+
+struct prefix_bits {
+	unsigned shorted:1;
+	unsigned enlarged:1;
+	unsigned rexr:1;
+	unsigned rex:1;
+};
+
+static int skip_prefix(unsigned char *addr, struct prefix_bits *prf)
+{
+	int i;
+	unsigned char *p = addr;
+	prf->shorted = 0;
+	prf->enlarged = 0;
+	prf->rexr = 0;
+	prf->rex = 0;
+
+restart:
+	for (i = 0; i < ARRAY_SIZE(prefix_codes); i++) {
+		if (*p == prefix_codes[i]) {
+			if (*p == 0x66)
+				prf->shorted = 1;
+#ifdef __amd64__
+			if ((*p & 0xf8) == 0x48)
+				prf->enlarged = 1;
+			if ((*p & 0xf4) == 0x44)
+				prf->rexr = 1;
+			if ((*p & 0xf0) == 0x40)
+				prf->rex = 1;
+#endif
+			p++;
+			goto restart;
+		}
+	}
+
+	return (p - addr);
+}
+
+static int get_opcode(unsigned char *addr, unsigned int *opcode)
+{
+	int len;
+
+	if (*addr == 0x0F) {
+		/* 0x0F is extension instruction */
+		*opcode = *(unsigned short *)addr;
+		len = 2;
+	} else {
+		*opcode = *addr;
+		len = 1;
+	}
+
+	return len;
+}
+
+#define CHECK_OP_TYPE(opcode, array, type) \
+	for (i = 0; i < ARRAY_SIZE(array); i++) { \
+		if (array[i] == opcode) { \
+			rv = type; \
+			goto exit; \
+		} \
+	}
+
+enum reason_type get_ins_type(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	struct prefix_bits prf;
+	int i;
+	enum reason_type rv = OTHERS;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &prf);
+	p += get_opcode(p, &opcode);
+
+	CHECK_OP_TYPE(opcode, reg_rop, REG_READ);
+	CHECK_OP_TYPE(opcode, reg_wop, REG_WRITE);
+	CHECK_OP_TYPE(opcode, imm_wop, IMM_WRITE);
+
+exit:
+	return rv;
+}
+#undef CHECK_OP_TYPE
+
+static unsigned int get_ins_reg_width(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	struct prefix_bits prf;
+	int i;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &prf);
+	p += get_opcode(p, &opcode);
+
+	for (i = 0; i < ARRAY_SIZE(rw8); i++)
+		if (rw8[i] == opcode)
+			return 1;
+
+	for (i = 0; i < ARRAY_SIZE(rw32); i++)
+		if (rw32[i] == opcode)
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
+
+	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
+	return 0;
+}
+
+unsigned int get_ins_mem_width(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char *p;
+	struct prefix_bits prf;
+	int i;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &prf);
+	p += get_opcode(p, &opcode);
+
+	for (i = 0; i < ARRAY_SIZE(mw8); i++)
+		if (mw8[i] == opcode)
+			return 1;
+
+	for (i = 0; i < ARRAY_SIZE(mw16); i++)
+		if (mw16[i] == opcode)
+			return 2;
+
+	for (i = 0; i < ARRAY_SIZE(mw32); i++)
+		if (mw32[i] == opcode)
+			return prf.shorted ? 2 : 4;
+
+	for (i = 0; i < ARRAY_SIZE(mw64); i++)
+		if (mw64[i] == opcode)
+			return prf.shorted ? 2 : (prf.enlarged ? 8 : 4);
+
+	printk(KERN_ERR "mmiotrace: Unknown opcode 0x%02x\n", opcode);
+	return 0;
+}
+
+/*
+ * Define register ident in mod/rm byte.
+ * Note: these are NOT the same as in ptrace-abi.h.
+ */
+enum {
+	arg_AL = 0,
+	arg_CL = 1,
+	arg_DL = 2,
+	arg_BL = 3,
+	arg_AH = 4,
+	arg_CH = 5,
+	arg_DH = 6,
+	arg_BH = 7,
+
+	arg_AX = 0,
+	arg_CX = 1,
+	arg_DX = 2,
+	arg_BX = 3,
+	arg_SP = 4,
+	arg_BP = 5,
+	arg_SI = 6,
+	arg_DI = 7,
+#ifdef __amd64__
+	arg_R8  = 8,
+	arg_R9  = 9,
+	arg_R10 = 10,
+	arg_R11 = 11,
+	arg_R12 = 12,
+	arg_R13 = 13,
+	arg_R14 = 14,
+	arg_R15 = 15
+#endif
+};
+
+static unsigned char *get_reg_w8(int no, int rex, struct pt_regs *regs)
+{
+	unsigned char *rv = NULL;
+
+	switch (no) {
+	case arg_AL:
+		rv = (unsigned char *)&regs->ax;
+		break;
+	case arg_BL:
+		rv = (unsigned char *)&regs->bx;
+		break;
+	case arg_CL:
+		rv = (unsigned char *)&regs->cx;
+		break;
+	case arg_DL:
+		rv = (unsigned char *)&regs->dx;
+		break;
+#ifdef __amd64__
+	case arg_R8:
+		rv = (unsigned char *)&regs->r8;
+		break;
+	case arg_R9:
+		rv = (unsigned char *)&regs->r9;
+		break;
+	case arg_R10:
+		rv = (unsigned char *)&regs->r10;
+		break;
+	case arg_R11:
+		rv = (unsigned char *)&regs->r11;
+		break;
+	case arg_R12:
+		rv = (unsigned char *)&regs->r12;
+		break;
+	case arg_R13:
+		rv = (unsigned char *)&regs->r13;
+		break;
+	case arg_R14:
+		rv = (unsigned char *)&regs->r14;
+		break;
+	case arg_R15:
+		rv = (unsigned char *)&regs->r15;
+		break;
+#endif
+	default:
+		break;
+	}
+
+	if (rv)
+		return rv;
+
+	if (rex) {
+		/*
+		 * If REX prefix exists, access low bytes of SI etc.
+		 * instead of AH etc.
+		 */
+		switch (no) {
+		case arg_SI:
+			rv = (unsigned char *)&regs->si;
+			break;
+		case arg_DI:
+			rv = (unsigned char *)&regs->di;
+			break;
+		case arg_BP:
+			rv = (unsigned char *)&regs->bp;
+			break;
+		case arg_SP:
+			rv = (unsigned char *)&regs->sp;
+			break;
+		default:
+			break;
+		}
+	} else {
+		switch (no) {
+		case arg_AH:
+			rv = 1 + (unsigned char *)&regs->ax;
+			break;
+		case arg_BH:
+			rv = 1 + (unsigned char *)&regs->bx;
+			break;
+		case arg_CH:
+			rv = 1 + (unsigned char *)&regs->cx;
+			break;
+		case arg_DH:
+			rv = 1 + (unsigned char *)&regs->dx;
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (!rv)
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+
+	return rv;
+}
+
+static unsigned long *get_reg_w32(int no, struct pt_regs *regs)
+{
+	unsigned long *rv = NULL;
+
+	switch (no) {
+	case arg_AX:
+		rv = &regs->ax;
+		break;
+	case arg_BX:
+		rv = &regs->bx;
+		break;
+	case arg_CX:
+		rv = &regs->cx;
+		break;
+	case arg_DX:
+		rv = &regs->dx;
+		break;
+	case arg_SP:
+		rv = &regs->sp;
+		break;
+	case arg_BP:
+		rv = &regs->bp;
+		break;
+	case arg_SI:
+		rv = &regs->si;
+		break;
+	case arg_DI:
+		rv = &regs->di;
+		break;
+#ifdef __amd64__
+	case arg_R8:
+		rv = &regs->r8;
+		break;
+	case arg_R9:
+		rv = &regs->r9;
+		break;
+	case arg_R10:
+		rv = &regs->r10;
+		break;
+	case arg_R11:
+		rv = &regs->r11;
+		break;
+	case arg_R12:
+		rv = &regs->r12;
+		break;
+	case arg_R13:
+		rv = &regs->r13;
+		break;
+	case arg_R14:
+		rv = &regs->r14;
+		break;
+	case arg_R15:
+		rv = &regs->r15;
+		break;
+#endif
+	default:
+		printk(KERN_ERR "mmiotrace: Error reg no# %d\n", no);
+	}
+
+	return rv;
+}
+
+unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs)
+{
+	unsigned int opcode;
+	int reg;
+	unsigned char *p;
+	struct prefix_bits prf;
+	int i;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &prf);
+	p += get_opcode(p, &opcode);
+	for (i = 0; i < ARRAY_SIZE(reg_rop); i++)
+		if (reg_rop[i] == opcode)
+			goto do_work;
+
+	for (i = 0; i < ARRAY_SIZE(reg_wop); i++)
+		if (reg_wop[i] == opcode)
+			goto do_work;
+
+	printk(KERN_ERR "mmiotrace: Not a register instruction, opcode "
+							"0x%02x\n", opcode);
+	goto err;
+
+do_work:
+	/* for STOS, source register is fixed */
+	if (opcode == 0xAA || opcode == 0xAB) {
+		reg = arg_AX;
+	} else {
+		unsigned char mod_rm = *p;
+		reg = ((mod_rm >> 3) & 0x7) | (prf.rexr << 3);
+	}
+	switch (get_ins_reg_width(ins_addr)) {
+	case 1:
+		return *get_reg_w8(reg, prf.rex, regs);
+
+	case 2:
+		return *(unsigned short *)get_reg_w32(reg, regs);
+
+	case 4:
+		return *(unsigned int *)get_reg_w32(reg, regs);
+
+#ifdef __amd64__
+	case 8:
+		return *(unsigned long *)get_reg_w32(reg, regs);
+#endif
+
+	default:
+		printk(KERN_ERR "mmiotrace: Error width# %d\n", reg);
+	}
+
+err:
+	return 0;
+}
+
+unsigned long get_ins_imm_val(unsigned long ins_addr)
+{
+	unsigned int opcode;
+	unsigned char mod_rm;
+	unsigned char mod;
+	unsigned char *p;
+	struct prefix_bits prf;
+	int i;
+
+	p = (unsigned char *)ins_addr;
+	p += skip_prefix(p, &prf);
+	p += get_opcode(p, &opcode);
+	for (i = 0; i < ARRAY_SIZE(imm_wop); i++)
+		if (imm_wop[i] == opcode)
+			goto do_work;
+
+	printk(KERN_ERR "mmiotrace: Not an immediate instruction, opcode "
+							"0x%02x\n", opcode);
+	goto err;
+
+do_work:
+	mod_rm = *p;
+	mod = mod_rm >> 6;
+	p++;
+	switch (mod) {
+	case 0:
+		/* if r/m is 5 we have a 32 disp (IA32 Manual 3, Table 2-2)  */
+		/* AMD64: XXX Check for address size prefix? */
+		if ((mod_rm & 0x7) == 0x5)
+			p += 4;
+		break;
+
+	case 1:
+		p += 1;
+		break;
+
+	case 2:
+		p += 4;
+		break;
+
+	case 3:
+	default:
+		printk(KERN_ERR "mmiotrace: not a memory access instruction "
+						"at 0x%lx, rm_mod=0x%02x\n",
+						ins_addr, mod_rm);
+	}
+
+	switch (get_ins_reg_width(ins_addr)) {
+	case 1:
+		return *(unsigned char *)p;
+
+	case 2:
+		return *(unsigned short *)p;
+
+	case 4:
+		return *(unsigned int *)p;
+
+#ifdef __amd64__
+	case 8:
+		return *(unsigned long *)p;
+#endif
+
+	default:
+		printk(KERN_ERR "mmiotrace: Error: width.\n");
+	}
+
+err:
+	return 0;
+}
diff --git a/arch/x86/mm/pf_in.h b/arch/x86/mm/pf_in.h
new file mode 100644
index 000000000..e2a13dce0
--- /dev/null
+++ b/arch/x86/mm/pf_in.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  Fault Injection Test harness (FI)
+ *  Copyright (C) Intel Crop.
+ */
+
+#ifndef __PF_H_
+#define __PF_H_
+
+enum reason_type {
+	NOT_ME,	/* page fault is not in regions */
+	NOTHING,	/* access others point in regions */
+	REG_READ,	/* read from addr to reg */
+	REG_WRITE,	/* write from reg to addr */
+	IMM_WRITE,	/* write from imm to addr */
+	OTHERS	/* Other instructions can not intercept */
+};
+
+enum reason_type get_ins_type(unsigned long ins_addr);
+unsigned int get_ins_mem_width(unsigned long ins_addr);
+unsigned long get_ins_reg_val(unsigned long ins_addr, struct pt_regs *regs);
+unsigned long get_ins_imm_val(unsigned long ins_addr);
+
+#endif /* __PF_H_ */
diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c
new file mode 100644
index 000000000..dc1afd5c8
--- /dev/null
+++ b/arch/x86/mm/pgprot.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <asm/pgtable.h>
+#include <asm/mem_encrypt.h>
+
+static pgprot_t protection_map[16] __ro_after_init = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READONLY,
+	[VM_WRITE]					= PAGE_COPY,
+	[VM_WRITE | VM_READ]				= PAGE_COPY,
+	[VM_EXEC]					= PAGE_READONLY_EXEC,
+	[VM_EXEC | VM_READ]				= PAGE_READONLY_EXEC,
+	[VM_EXEC | VM_WRITE]				= PAGE_COPY_EXEC,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY_EXEC,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READONLY,
+	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC]				= PAGE_READONLY_EXEC,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READONLY_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED_EXEC,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
+};
+
+void add_encrypt_protection_map(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
+		protection_map[i] = pgprot_encrypted(protection_map[i]);
+}
+
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
+{
+	unsigned long val = pgprot_val(protection_map[vm_flags &
+				      (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	/*
+	 * Take the 4 protection key bits out of the vma->vm_flags value and
+	 * turn them in to the bits that we can put in to a pte.
+	 *
+	 * Only override these if Protection Keys are available (which is only
+	 * on 64-bit).
+	 */
+	if (vm_flags & VM_PKEY_BIT0)
+		val |= _PAGE_PKEY_BIT0;
+	if (vm_flags & VM_PKEY_BIT1)
+		val |= _PAGE_PKEY_BIT1;
+	if (vm_flags & VM_PKEY_BIT2)
+		val |= _PAGE_PKEY_BIT2;
+	if (vm_flags & VM_PKEY_BIT3)
+		val |= _PAGE_PKEY_BIT3;
+#endif
+
+	val = __sme_set(val);
+	if (val & _PAGE_PRESENT)
+		val &= __supported_pte_mask;
+	return __pgprot(val);
+}
+EXPORT_SYMBOL(vm_get_page_prot);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
new file mode 100644
index 000000000..cb03f5a2b
--- /dev/null
+++ b/arch/x86/mm/pgtable.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/gfp.h>
+#include <linux/hugetlb.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+#include <asm/fixmap.h>
+#include <asm/mtrr.h>
+
+#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
+phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
+EXPORT_SYMBOL(physical_mask);
+SYM_PIC_ALIAS(physical_mask);
+#endif
+
+pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
+}
+
+void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
+{
+	paravirt_release_pte(page_to_pfn(pte));
+	tlb_remove_ptdesc(tlb, page_ptdesc(pte));
+}
+
+#if CONFIG_PGTABLE_LEVELS > 2
+void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
+{
+	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+	/*
+	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
+	 * entries need a full cr3 reload to flush.
+	 */
+#ifdef CONFIG_X86_PAE
+	tlb->need_flush_all = 1;
+#endif
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd));
+}
+
+#if CONFIG_PGTABLE_LEVELS > 3
+void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
+{
+	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud));
+}
+
+#if CONFIG_PGTABLE_LEVELS > 4
+void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
+{
+	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
+	tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
+}
+#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
+#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
+
+static inline void pgd_list_add(pgd_t *pgd)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
+
+	list_add(&ptdesc->pt_list, &pgd_list);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
+
+	list_del(&ptdesc->pt_list);
+}
+
+static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+	virt_to_ptdesc(pgd)->pt_mm = mm;
+}
+
+struct mm_struct *pgd_page_get_mm(struct ptdesc *pt)
+{
+	return pt->pt_mm;
+}
+
+static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
+{
+	/* PAE preallocates all its PMDs.  No cloning needed. */
+	if (!IS_ENABLED(CONFIG_X86_PAE))
+		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
+				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+				KERNEL_PGD_PTRS);
+
+	/* List used to sync kernel mapping updates */
+	pgd_set_mm(pgd, mm);
+	pgd_list_add(pgd);
+}
+
+static void pgd_dtor(pgd_t *pgd)
+{
+	spin_lock(&pgd_lock);
+	pgd_list_del(pgd);
+	spin_unlock(&pgd_lock);
+}
+
+#ifdef CONFIG_X86_PAE
+/*
+ * In PAE mode, we need to do a cr3 reload (=tlb flush) when
+ * updating the top-level pagetable entries to guarantee the
+ * processor notices the update.  Since this is expensive, and
+ * all 4 top-level entries are used almost immediately in a
+ * new process's life, we just pre-populate them here.
+ */
+#define PREALLOCATED_PMDS	PTRS_PER_PGD
+
+/*
+ * "USER_PMDS" are the PMDs for the user copy of the page tables when
+ * PTI is enabled. They do not exist when PTI is disabled.  Note that
+ * this is distinct from the user _portion_ of the kernel page tables
+ * which always exists.
+ *
+ * We allocate separate PMDs for the kernel part of the user page-table
+ * when PTI is enabled. We need them to map the per-process LDT into the
+ * user-space page-table.
+ */
+#define PREALLOCATED_USER_PMDS	 (boot_cpu_has(X86_FEATURE_PTI) ? \
+					KERNEL_PGD_PTRS : 0)
+#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
+
+void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
+{
+	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
+
+	/* Note: almost everything apart from _PAGE_PRESENT is
+	   reserved at the pmd (PDPT) level. */
+	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
+
+	/*
+	 * According to Intel App note "TLBs, Paging-Structure Caches,
+	 * and Their Invalidation", April 2007, document 317080-001,
+	 * section 8.1: in PAE mode we explicitly have to flush the
+	 * TLB via cr3 if the top-level pgd is changed...
+	 */
+	flush_tlb_mm(mm);
+}
+#else  /* !CONFIG_X86_PAE */
+
+/* No need to prepopulate any pagetable entries in non-PAE modes. */
+#define PREALLOCATED_PMDS	0
+#define PREALLOCATED_USER_PMDS	 0
+#define MAX_PREALLOCATED_USER_PMDS 0
+#endif	/* CONFIG_X86_PAE */
+
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
+{
+	int i;
+	struct ptdesc *ptdesc;
+
+	for (i = 0; i < count; i++)
+		if (pmds[i]) {
+			ptdesc = virt_to_ptdesc(pmds[i]);
+
+			pagetable_dtor(ptdesc);
+			pagetable_free(ptdesc);
+			mm_dec_nr_pmds(mm);
+		}
+}
+
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
+{
+	int i;
+	bool failed = false;
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	gfp &= ~__GFP_HIGHMEM;
+
+	for (i = 0; i < count; i++) {
+		pmd_t *pmd = NULL;
+		struct ptdesc *ptdesc = pagetable_alloc(gfp, 0);
+
+		if (!ptdesc)
+			failed = true;
+		if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) {
+			pagetable_free(ptdesc);
+			ptdesc = NULL;
+			failed = true;
+		}
+		if (ptdesc) {
+			mm_inc_nr_pmds(mm);
+			pmd = ptdesc_address(ptdesc);
+		}
+
+		pmds[i] = pmd;
+	}
+
+	if (failed) {
+		free_pmds(mm, pmds, count);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/*
+ * Mop up any pmd pages which may still be attached to the pgd.
+ * Normally they will be freed by munmap/exit_mmap, but any pmd we
+ * preallocate which never got a corresponding vma will need to be
+ * freed manually.
+ */
+static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
+{
+	pgd_t pgd = *pgdp;
+
+	if (pgd_val(pgd) != 0) {
+		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+		pgd_clear(pgdp);
+
+		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+		pmd_free(mm, pmd);
+		mm_dec_nr_pmds(mm);
+	}
+}
+
+static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
+{
+	int i;
+
+	for (i = 0; i < PREALLOCATED_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i]);
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+
+	if (!boot_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pgdp = kernel_to_user_pgdp(pgdp);
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
+#endif
+}
+
+static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
+{
+	p4d_t *p4d;
+	pud_t *pud;
+	int i;
+
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
+
+	for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) {
+		pmd_t *pmd = pmds[i];
+
+		if (i >= KERNEL_PGD_BOUNDARY)
+			memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
+			       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, pud, pmd);
+	}
+}
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+	pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	p4d_t *u_p4d;
+	pud_t *u_pud;
+	int i;
+
+	u_p4d = p4d_offset(u_pgd, 0);
+	u_pud = pud_offset(u_p4d, 0);
+
+	s_pgd += KERNEL_PGD_BOUNDARY;
+	u_pud += KERNEL_PGD_BOUNDARY;
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
+		pmd_t *pmd = pmds[i];
+
+		memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
+		       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, u_pud, pmd);
+	}
+
+}
+#else
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+}
+#endif
+
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
+{
+	/*
+	 * PTI and Xen need a whole page for the PAE PGD
+	 * even though the hardware only needs 32 bytes.
+	 *
+	 * For simplicity, allocate a page for all users.
+	 */
+	return __pgd_alloc(mm, pgd_allocation_order());
+}
+
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	__pgd_free(mm, pgd);
+}
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd;
+	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
+	pmd_t *pmds[PREALLOCATED_PMDS];
+
+	pgd = _pgd_alloc(mm);
+
+	if (pgd == NULL)
+		goto out;
+
+	mm->pgd = pgd;
+
+	if (sizeof(pmds) != 0 &&
+			preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
+		goto out_free_pgd;
+
+	if (sizeof(u_pmds) != 0 &&
+			preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
+		goto out_free_pmds;
+
+	if (paravirt_pgd_alloc(mm) != 0)
+		goto out_free_user_pmds;
+
+	/*
+	 * Make sure that pre-populating the pmds is atomic with
+	 * respect to anything walking the pgd_list, so that they
+	 * never see a partially populated pgd.
+	 */
+	spin_lock(&pgd_lock);
+
+	pgd_ctor(mm, pgd);
+	if (sizeof(pmds) != 0)
+		pgd_prepopulate_pmd(mm, pgd, pmds);
+
+	if (sizeof(u_pmds) != 0)
+		pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
+
+	spin_unlock(&pgd_lock);
+
+	return pgd;
+
+out_free_user_pmds:
+	if (sizeof(u_pmds) != 0)
+		free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
+out_free_pmds:
+	if (sizeof(pmds) != 0)
+		free_pmds(mm, pmds, PREALLOCATED_PMDS);
+out_free_pgd:
+	_pgd_free(mm, pgd);
+out:
+	return NULL;
+}
+
+void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	pgd_mop_up_pmds(mm, pgd);
+	pgd_dtor(pgd);
+	paravirt_pgd_free(mm, pgd);
+	_pgd_free(mm, pgd);
+}
+
+/*
+ * Used to set accessed or dirty bits in the page table entries
+ * on other architectures. On x86, the accessed and dirty bits
+ * are tracked by hardware. However, do_wp_page calls this function
+ * to also make the pte writeable at the same time the dirty bit is
+ * set. In that case we do actually need to write the PTE.
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	int changed = !pte_same(*ptep, entry);
+
+	if (changed && dirty)
+		set_pte(ptep, entry);
+
+	return changed;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+int pmdp_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp,
+			  pmd_t entry, int dirty)
+{
+	int changed = !pmd_same(*pmdp, entry);
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	if (changed && dirty) {
+		set_pmd(pmdp, entry);
+		/*
+		 * We had a write-protection fault here and changed the pmd
+		 * to to more permissive. No need to flush the TLB for that,
+		 * #PF is architecturally guaranteed to do that and in the
+		 * worst-case we'll generate a spurious fault.
+		 */
+	}
+
+	return changed;
+}
+
+int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+			  pud_t *pudp, pud_t entry, int dirty)
+{
+	int changed = !pud_same(*pudp, entry);
+
+	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
+
+	if (changed && dirty) {
+		set_pud(pudp, entry);
+		/*
+		 * We had a write-protection fault here and changed the pud
+		 * to to more permissive. No need to flush the TLB for that,
+		 * #PF is architecturally guaranteed to do that and in the
+		 * worst-case we'll generate a spurious fault.
+		 */
+	}
+
+	return changed;
+}
+#endif
+
+bool ptep_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep)
+{
+	bool ret = false;
+
+	if (pte_young(*ptep))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *) &ptep->pte);
+
+	return ret;
+}
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
+bool pmdp_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t *pmdp)
+{
+	bool ret = false;
+
+	if (pmd_young(*pmdp))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *)pmdp);
+
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+bool pudp_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long addr, pud_t *pudp)
+{
+	bool ret = false;
+
+	if (pud_young(*pudp))
+		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
+					 (unsigned long *)pudp);
+
+	return ret;
+}
+#endif
+
+bool ptep_clear_flush_young(struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep)
+{
+	/*
+	 * On x86 CPUs, clearing the accessed bit without a TLB flush
+	 * doesn't cause data corruption. [ It could cause incorrect
+	 * page aging and the (mistaken) reclaim of hot pages, but the
+	 * chance of that should be relatively low. ]
+	 *
+	 * So as a performance optimization don't flush the TLB when
+	 * clearing the accessed bit, it will eventually be flushed by
+	 * a context switch or a VM operation anyway. [ In the rare
+	 * event of it not getting flushed for a long time the delay
+	 * shouldn't really matter because there's no real memory
+	 * pressure for swapout to react to. ]
+	 */
+	return ptep_test_and_clear_young(vma, address, ptep);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+bool pmdp_clear_flush_young(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp)
+{
+	bool young;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	young = pmdp_test_and_clear_young(vma, address, pmdp);
+	if (young)
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	return young;
+}
+
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+			 pmd_t *pmdp)
+{
+	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
+
+	/*
+	 * No flush is necessary. Once an invalid PTE is established, the PTE's
+	 * access and dirty bits cannot be updated.
+	 */
+	return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
+}
+#endif
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
+	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		     pud_t *pudp)
+{
+	VM_WARN_ON_ONCE(!pud_present(*pudp));
+	pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp));
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return old;
+}
+#endif
+
+/**
+ * reserve_top_address - Reserve a hole in the top of the kernel address space
+ * @reserve: Size of hole to reserve
+ *
+ * Can be used to relocate the fixmap area and poke a hole in the top
+ * of the kernel address space to make room for a hypervisor.
+ */
+void __init reserve_top_address(unsigned long reserve)
+{
+#ifdef CONFIG_X86_32
+	BUG_ON(fixmaps_set > 0);
+	__FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE;
+	printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n",
+	       -reserve, __FIXADDR_TOP + PAGE_SIZE);
+#endif
+}
+
+int fixmaps_set;
+
+void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
+{
+	unsigned long address = __fix_to_virt(idx);
+
+#ifdef CONFIG_X86_64
+       /*
+	* Ensure that the static initial page tables are covering the
+	* fixmap completely.
+	*/
+	BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
+		     (FIXMAP_PMD_NUM * PTRS_PER_PTE));
+#endif
+
+	if (idx >= __end_of_fixed_addresses) {
+		BUG();
+		return;
+	}
+	set_pte_vaddr(address, pte);
+	fixmaps_set++;
+}
+
+void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
+		       phys_addr_t phys, pgprot_t flags)
+{
+	/* Sanitize 'prot' against any unsupported bits: */
+	pgprot_val(flags) &= __default_kernel_pte_mask;
+
+	__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
+}
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+#if CONFIG_PGTABLE_LEVELS > 4
+/**
+ * p4d_set_huge - Set up kernel P4D mapping
+ * @p4d: Pointer to the P4D entry
+ * @addr: Virtual address associated with the P4D entry
+ * @prot: Protection bits to use
+ *
+ * No 512GB pages yet -- always return 0
+ */
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+
+/**
+ * p4d_clear_huge - Clear kernel P4D mapping when it is set
+ * @p4d: Pointer to the P4D entry to clear
+ *
+ * No 512GB pages yet -- do nothing
+ */
+void p4d_clear_huge(p4d_t *p4d)
+{
+}
+#endif
+
+/**
+ * pud_set_huge - Set up kernel PUD mapping
+ * @pud: Pointer to the PUD entry
+ * @addr: Virtual address associated with the PUD entry
+ * @prot: Protection bits to use
+ *
+ * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
+ * function sets up a huge page only if the complete range has the same MTRR
+ * caching mode.
+ *
+ * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
+ * page mapping attempt fails.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
+int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
+{
+	u8 uniform;
+
+	mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
+	if (!uniform)
+		return 0;
+
+	/* Bail out if we are we on a populated non-leaf entry: */
+	if (pud_present(*pud) && !pud_leaf(*pud))
+		return 0;
+
+	set_pte((pte_t *)pud, pfn_pte(
+		(u64)addr >> PAGE_SHIFT,
+		__pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE)));
+
+	return 1;
+}
+
+/**
+ * pmd_set_huge - Set up kernel PMD mapping
+ * @pmd: Pointer to the PMD entry
+ * @addr: Virtual address associated with the PMD entry
+ * @prot: Protection bits to use
+ *
+ * See text over pud_set_huge() above.
+ *
+ * Returns 1 on success and 0 on failure.
+ */
+int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
+{
+	u8 uniform;
+
+	mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
+	if (!uniform) {
+		pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
+			     __func__, addr, addr + PMD_SIZE);
+		return 0;
+	}
+
+	/* Bail out if we are we on a populated non-leaf entry: */
+	if (pmd_present(*pmd) && !pmd_leaf(*pmd))
+		return 0;
+
+	set_pte((pte_t *)pmd, pfn_pte(
+		(u64)addr >> PAGE_SHIFT,
+		__pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE)));
+
+	return 1;
+}
+
+/**
+ * pud_clear_huge - Clear kernel PUD mapping when it is set
+ * @pud: Pointer to the PUD entry to clear.
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
+int pud_clear_huge(pud_t *pud)
+{
+	if (pud_leaf(*pud)) {
+		pud_clear(pud);
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * pmd_clear_huge - Clear kernel PMD mapping when it is set
+ * @pmd: Pointer to the PMD entry to clear.
+ *
+ * Returns 1 on success and 0 on failure (no PMD map is found).
+ */
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (pmd_leaf(*pmd)) {
+		pmd_clear(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_X86_64
+/**
+ * pud_free_pmd_page - Clear PUD entry and free PMD page
+ * @pud: Pointer to a PUD
+ * @addr: Virtual address associated with PUD
+ *
+ * Context: The PUD range has been unmapped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ *
+ * NOTE: Callers must allow a single page allocation.
+ */
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	pmd_t *pmd, *pmd_sv;
+	struct ptdesc *pt;
+	int i;
+
+	pmd = pud_pgtable(*pud);
+	pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
+	if (!pmd_sv)
+		return 0;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd_sv[i] = pmd[i];
+		if (!pmd_none(pmd[i]))
+			pmd_clear(&pmd[i]);
+	}
+
+	pud_clear(pud);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd_sv[i])) {
+			pt = page_ptdesc(pmd_page(pmd_sv[i]));
+			pagetable_dtor_free(pt);
+		}
+	}
+
+	free_page((unsigned long)pmd_sv);
+
+	pmd_free(&init_mm, pmd);
+
+	return 1;
+}
+
+/**
+ * pmd_free_pte_page - Clear PMD entry and free PTE page.
+ * @pmd: Pointer to the PMD
+ * @addr: Virtual address associated with PMD
+ *
+ * Context: The PMD range has been unmapped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	struct ptdesc *pt;
+
+	pt = page_ptdesc(pmd_page(*pmd));
+	pmd_clear(pmd);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+	pagetable_dtor_free(pt);
+
+	return 1;
+}
+
+#else /* !CONFIG_X86_64 */
+
+/*
+ * Disable free page handling on x86-PAE. This assures that ioremap()
+ * does not update sync'd PMD entries. See vmalloc_sync_one().
+ */
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	return pmd_none(*pmd);
+}
+
+#endif /* CONFIG_X86_64 */
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
+
+pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pte_mkwrite_shstk(pte);
+
+	pte = pte_mkwrite_novma(pte);
+
+	return pte_clear_saveddirty(pte);
+}
+
+pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pmd_mkwrite_shstk(pmd);
+
+	pmd = pmd_mkwrite_novma(pmd);
+
+	return pmd_clear_saveddirty(pmd);
+}
+
+void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte)
+{
+	/*
+	 * Hardware before shadow stack can (rarely) set Dirty=1
+	 * on a Write=0 PTE. So the below condition
+	 * only indicates a software bug when shadow stack is
+	 * supported by the HW. This checking is covered in
+	 * pte_shstk().
+	 */
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) &&
+			pte_shstk(pte));
+}
+
+void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd)
+{
+	/* See note in arch_check_zapped_pte() */
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) &&
+			pmd_shstk(pmd));
+}
+
+void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud)
+{
+	/* See note in arch_check_zapped_pte() */
+	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) && pud_shstk(pud));
+}
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
new file mode 100644
index 000000000..c234634e2
--- /dev/null
+++ b/arch/x86/mm/pgtable_32.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/nmi.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/spinlock.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/fixmap.h>
+#include <asm/e820/api.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/io.h>
+#include <linux/vmalloc.h>
+
+unsigned int __VMALLOC_RESERVE = 128 << 20;
+
+/*
+ * Associate a virtual page frame with a given physical page frame 
+ * and protection flags for that frame.
+ */ 
+void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = swapper_pg_dir + pgd_index(vaddr);
+	if (pgd_none(*pgd)) {
+		BUG();
+		return;
+	}
+	p4d = p4d_offset(pgd, vaddr);
+	if (p4d_none(*p4d)) {
+		BUG();
+		return;
+	}
+	pud = pud_offset(p4d, vaddr);
+	if (pud_none(*pud)) {
+		BUG();
+		return;
+	}
+	pmd = pmd_offset(pud, vaddr);
+	if (pmd_none(*pmd)) {
+		BUG();
+		return;
+	}
+	pte = pte_offset_kernel(pmd, vaddr);
+	if (!pte_none(pteval))
+		set_pte_at(&init_mm, vaddr, pte, pteval);
+	else
+		pte_clear(&init_mm, vaddr, pte);
+
+	/*
+	 * It's enough to flush this one mapping.
+	 * (PGE mappings get flushed as well)
+	 */
+	flush_tlb_one_kernel(vaddr);
+}
+
+unsigned long __FIXADDR_TOP = 0xfffff000;
+EXPORT_SYMBOL(__FIXADDR_TOP);
+
+/*
+ * vmalloc=size forces the vmalloc area to be exactly 'size'
+ * bytes. This can be used to increase (or decrease) the
+ * vmalloc area - the default is 128m.
+ */
+static int __init parse_vmalloc(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	/* Add VMALLOC_OFFSET to the parsed value due to vm area guard hole*/
+	__VMALLOC_RESERVE = memparse(arg, &arg) + VMALLOC_OFFSET;
+	return 0;
+}
+early_param("vmalloc", parse_vmalloc);
+
+/*
+ * reservetop=size reserves a hole at the top of the kernel address space which
+ * a hypervisor can load into later.  Needed for dynamically loaded hypervisors,
+ * so relocating the fixmap can be done before paging initialization.
+ */
+static int __init parse_reservetop(char *arg)
+{
+	unsigned long address;
+
+	if (!arg)
+		return -EINVAL;
+
+	address = memparse(arg, &arg);
+	reserve_top_address(address);
+	early_ioremap_init();
+	return 0;
+}
+early_param("reservetop", parse_reservetop);
diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c
new file mode 100644
index 000000000..8d31c6b9e
--- /dev/null
+++ b/arch/x86/mm/physaddr.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/memblock.h>
+#include <linux/mmdebug.h>
+#include <linux/export.h>
+#include <linux/mm.h>
+
+#include <asm/page.h>
+#include <linux/vmalloc.h>
+
+#include "physaddr.h"
+
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+unsigned long __phys_addr(unsigned long x)
+{
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* use the carry flag to determine if x was < __START_KERNEL_map */
+	if (unlikely(x > y)) {
+		x = y + phys_base;
+
+		VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE);
+	} else {
+		x = y + (__START_KERNEL_map - PAGE_OFFSET);
+
+		/* carry flag will be set if starting x was >= PAGE_OFFSET */
+		VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x));
+	}
+
+	return x;
+}
+EXPORT_SYMBOL(__phys_addr);
+#endif
+
+bool __virt_addr_valid(unsigned long x)
+{
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* use the carry flag to determine if x was < __START_KERNEL_map */
+	if (unlikely(x > y)) {
+		x = y + phys_base;
+
+		if (y >= KERNEL_IMAGE_SIZE)
+			return false;
+	} else {
+		x = y + (__START_KERNEL_map - PAGE_OFFSET);
+
+		/* carry flag will be set if starting x was >= PAGE_OFFSET */
+		if ((x > y) || !phys_addr_valid(x))
+			return false;
+	}
+
+	return pfn_valid(x >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(__virt_addr_valid);
+
+#else
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+unsigned long __phys_addr(unsigned long x)
+{
+	unsigned long phys_addr = x - PAGE_OFFSET;
+	/* VMALLOC_* aren't constants  */
+	VIRTUAL_BUG_ON(x < PAGE_OFFSET);
+	VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x));
+	/* max_low_pfn is set early, but not _that_ early */
+	if (max_low_pfn) {
+		VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn);
+		BUG_ON(slow_virt_to_phys((void *)x) != phys_addr);
+	}
+	return phys_addr;
+}
+EXPORT_SYMBOL(__phys_addr);
+#endif
+
+bool __virt_addr_valid(unsigned long x)
+{
+	if (x < PAGE_OFFSET)
+		return false;
+	if (__vmalloc_start_set && is_vmalloc_addr((void *) x))
+		return false;
+	if (x >= FIXADDR_START)
+		return false;
+	return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT);
+}
+EXPORT_SYMBOL(__virt_addr_valid);
+
+#endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/mm/physaddr.h b/arch/x86/mm/physaddr.h
new file mode 100644
index 000000000..9f6419caf
--- /dev/null
+++ b/arch/x86/mm/physaddr.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/processor.h>
+
+static inline int phys_addr_valid(resource_size_t addr)
+{
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	return !(addr >> boot_cpu_data.x86_phys_bits);
+#else
+	return 1;
+#endif
+}
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
new file mode 100644
index 000000000..1dfcfaf77
--- /dev/null
+++ b/arch/x86/mm/pkeys.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel Memory Protection Keys management
+ * Copyright (c) 2015, Intel Corporation.
+ */
+#include <linux/debugfs.h>		/* debugfs_create_u32()		*/
+#include <linux/mm_types.h>             /* mm_struct, vma, etc...       */
+#include <linux/pkeys.h>                /* PKEY_*                       */
+#include <uapi/asm-generic/mman-common.h>
+
+#include <asm/cpufeature.h>             /* boot_cpu_has, ...            */
+#include <asm/mmu_context.h>            /* vma_pkey()                   */
+
+int __execute_only_pkey(struct mm_struct *mm)
+{
+	bool need_to_set_mm_pkey = false;
+	int execute_only_pkey = mm->context.execute_only_pkey;
+	int ret;
+
+	/* Do we need to assign a pkey for mm's execute-only maps? */
+	if (execute_only_pkey == -1) {
+		/* Go allocate one to use, which might fail */
+		execute_only_pkey = mm_pkey_alloc(mm);
+		if (execute_only_pkey < 0)
+			return -1;
+		need_to_set_mm_pkey = true;
+	}
+
+	/*
+	 * We do not want to go through the relatively costly
+	 * dance to set PKRU if we do not need to.  Check it
+	 * first and assume that if the execute-only pkey is
+	 * write-disabled that we do not have to set it
+	 * ourselves.
+	 */
+	if (!need_to_set_mm_pkey &&
+	    !__pkru_allows_read(read_pkru(), execute_only_pkey)) {
+		return execute_only_pkey;
+	}
+
+	/*
+	 * Set up PKRU so that it denies access for everything
+	 * other than execution.
+	 */
+	ret = arch_set_user_pkey_access(execute_only_pkey, PKEY_DISABLE_ACCESS);
+	/*
+	 * If the PKRU-set operation failed somehow, just return
+	 * 0 and effectively disable execute-only support.
+	 */
+	if (ret) {
+		mm_set_pkey_free(mm, execute_only_pkey);
+		return -1;
+	}
+
+	/* We got one, store it and use it from here on out */
+	if (need_to_set_mm_pkey)
+		mm->context.execute_only_pkey = execute_only_pkey;
+	return execute_only_pkey;
+}
+
+static inline bool vma_is_pkey_exec_only(struct vm_area_struct *vma)
+{
+	/* Do this check first since the vm_flags should be hot */
+	if ((vma->vm_flags & VM_ACCESS_FLAGS) != VM_EXEC)
+		return false;
+	if (vma_pkey(vma) != vma->vm_mm->context.execute_only_pkey)
+		return false;
+
+	return true;
+}
+
+/*
+ * This is only called for *plain* mprotect calls.
+ */
+int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey)
+{
+	/*
+	 * Is this an mprotect_pkey() call?  If so, never
+	 * override the value that came from the user.
+	 */
+	if (pkey != -1)
+		return pkey;
+
+	/*
+	 * The mapping is execute-only.  Go try to get the
+	 * execute-only protection key.  If we fail to do that,
+	 * fall through as if we do not have execute-only
+	 * support in this mm.
+	 */
+	if (prot == PROT_EXEC) {
+		pkey = execute_only_pkey(vma->vm_mm);
+		if (pkey > 0)
+			return pkey;
+	} else if (vma_is_pkey_exec_only(vma)) {
+		/*
+		 * Protections are *not* PROT_EXEC, but the mapping
+		 * is using the exec-only pkey.  This mapping was
+		 * PROT_EXEC and will no longer be.  Move back to
+		 * the default pkey.
+		 */
+		return ARCH_DEFAULT_PKEY;
+	}
+
+	/*
+	 * This is a vanilla, non-pkey mprotect (or we failed to
+	 * setup execute-only), inherit the pkey from the VMA we
+	 * are working on.
+	 */
+	return vma_pkey(vma);
+}
+
+#define PKRU_AD_MASK(pkey)	(PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY))
+
+/*
+ * Make the default PKRU value (at execve() time) as restrictive
+ * as possible.  This ensures that any threads clone()'d early
+ * in the process's lifetime will not accidentally get access
+ * to data which is pkey-protected later on.
+ */
+u32 init_pkru_value = PKRU_AD_MASK( 1) | PKRU_AD_MASK( 2) |
+		      PKRU_AD_MASK( 3) | PKRU_AD_MASK( 4) |
+		      PKRU_AD_MASK( 5) | PKRU_AD_MASK( 6) |
+		      PKRU_AD_MASK( 7) | PKRU_AD_MASK( 8) |
+		      PKRU_AD_MASK( 9) | PKRU_AD_MASK(10) |
+		      PKRU_AD_MASK(11) | PKRU_AD_MASK(12) |
+		      PKRU_AD_MASK(13) | PKRU_AD_MASK(14) |
+		      PKRU_AD_MASK(15);
+
+static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	char buf[32];
+	unsigned int len;
+
+	len = sprintf(buf, "0x%x\n", init_pkru_value);
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t init_pkru_write_file(struct file *file,
+		 const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[32];
+	ssize_t len;
+	u32 new_init_pkru;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	/* Make the buffer a valid string that we can not overrun */
+	buf[len] = '\0';
+	if (kstrtouint(buf, 0, &new_init_pkru))
+		return -EINVAL;
+
+	/*
+	 * Don't allow insane settings that will blow the system
+	 * up immediately if someone attempts to disable access
+	 * or writes to pkey 0.
+	 */
+	if (new_init_pkru & (PKRU_AD_BIT|PKRU_WD_BIT))
+		return -EINVAL;
+
+	WRITE_ONCE(init_pkru_value, new_init_pkru);
+	return count;
+}
+
+static const struct file_operations fops_init_pkru = {
+	.read = init_pkru_read_file,
+	.write = init_pkru_write_file,
+	.llseek = default_llseek,
+};
+
+static int __init create_init_pkru_value(void)
+{
+	/* Do not expose the file if pkeys are not supported. */
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return 0;
+
+	debugfs_create_file("init_pkru", S_IRUSR | S_IWUSR,
+			arch_debugfs_dir, NULL, &fops_init_pkru);
+	return 0;
+}
+late_initcall(create_init_pkru_value);
+
+static __init int setup_init_pkru(char *opt)
+{
+	u32 new_init_pkru;
+
+	if (kstrtouint(opt, 0, &new_init_pkru))
+		return 1;
+
+	WRITE_ONCE(init_pkru_value, new_init_pkru);
+
+	return 1;
+}
+__setup("init_pkru=", setup_init_pkru);
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
new file mode 100644
index 000000000..598f553cc
--- /dev/null
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This code is based in part on work published here:
+ *
+ *	https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and signed off by for the Linux
+ * kernel by:
+ *
+ *   Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
+ *   Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at>
+ *   Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
+ *   Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
+ *
+ * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com>
+ * Mostly rewritten by Thomas Gleixner <tglx@kernel.org> and
+ *		       Andy Lutomirsky <luto@amacapital.net>
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/cpu.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/cpuid/api.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+#include <asm/sections.h>
+#include <asm/set_memory.h>
+#include <asm/bugs.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK	0
+#endif
+
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		pr_info("%s\n", reason);
+}
+
+/* Assume mode is auto unless overridden via cmdline below. */
+static enum pti_mode {
+	PTI_AUTO = 0,
+	PTI_FORCE_OFF,
+	PTI_FORCE_ON
+} pti_mode;
+
+void __init pti_check_boottime_disable(void)
+{
+	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+		pti_mode = PTI_FORCE_OFF;
+		pti_print_if_insecure("disabled on XEN PV.");
+		return;
+	}
+
+	if (pti_mode == PTI_AUTO &&
+	    !cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL))
+		pti_mode = PTI_FORCE_OFF;
+	if (pti_mode == PTI_FORCE_OFF) {
+		pti_print_if_insecure("disabled on command line.");
+		return;
+	}
+
+	if (pti_mode == PTI_FORCE_ON)
+		pti_print_if_secure("force enabled on command line.");
+
+	if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		return;
+
+	setup_force_cpu_cap(X86_FEATURE_PTI);
+
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		pr_debug("PTI enabled, disabling INVLPGB\n");
+		setup_clear_cpu_cap(X86_FEATURE_INVLPGB);
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_FRED)) {
+		pr_debug("PTI enabled, disabling FRED\n");
+		setup_clear_cpu_cap(X86_FEATURE_FRED);
+	}
+}
+
+static int __init pti_parse_cmdline(char *arg)
+{
+	if (!strcmp(arg, "off"))
+		pti_mode = PTI_FORCE_OFF;
+	else if (!strcmp(arg, "on"))
+		pti_mode = PTI_FORCE_ON;
+	else if (!strcmp(arg, "auto"))
+		pti_mode = PTI_AUTO;
+	else
+		return -EINVAL;
+	return 0;
+}
+early_param("pti", pti_parse_cmdline);
+
+static int __init pti_parse_cmdline_nopti(char *arg)
+{
+	pti_mode = PTI_FORCE_OFF;
+	return 0;
+}
+early_param("nopti", pti_parse_cmdline_nopti);
+
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	/*
+	 * Changes to the high (kernel) portion of the kernelmode page
+	 * tables are not automatically propagated to the usermode tables.
+	 *
+	 * Users should keep in mind that, unlike the kernelmode tables,
+	 * there is no vmalloc_fault equivalent for the usermode tables.
+	 * Top-level entries added to init_mm's usermode pgd after boot
+	 * will not be automatically propagated to other mms.
+	 */
+	if (!pgdp_maps_userspace(pgdp) || (pgd.pgd & _PAGE_NOPTISHADOW))
+		return pgd;
+
+	/*
+	 * The user page tables get the full PGD, accessible from
+	 * userspace:
+	 */
+	kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+	/*
+	 * If this is normal user memory, make it NX in the kernel
+	 * pagetables so that, if we somehow screw up and return to
+	 * usermode with the kernel CR3 loaded, we'll get a page fault
+	 * instead of allowing user code to execute with the wrong CR3.
+	 *
+	 * As exceptions, we don't set NX if:
+	 *  - _PAGE_USER is not set.  This could be an executable
+	 *     EFI runtime mapping or something similar, and the kernel
+	 *     may execute from it
+	 *  - we don't have NX support
+	 *  - we're clearing the PGD (i.e. the new pgd is not present).
+	 */
+	if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+	    (__supported_pte_mask & _PAGE_NX))
+		pgd.pgd |= _PAGE_NX;
+
+	/* return the copy of the PGD we want the kernel to use: */
+	return pgd;
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+	pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+	if (address < PAGE_OFFSET) {
+		WARN_ONCE(1, "attempt to walk user address\n");
+		return NULL;
+	}
+
+	if (pgd_none(*pgd)) {
+		unsigned long new_p4d_page = __get_free_page(gfp);
+		if (WARN_ON_ONCE(!new_p4d_page))
+			return NULL;
+
+		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+	}
+	BUILD_BUG_ON(pgd_leaf(*pgd));
+
+	return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	p4d_t *p4d;
+	pud_t *pud;
+
+	p4d = pti_user_pagetable_walk_p4d(address);
+	if (!p4d)
+		return NULL;
+
+	BUILD_BUG_ON(p4d_leaf(*p4d));
+	if (p4d_none(*p4d)) {
+		unsigned long new_pud_page = __get_free_page(gfp);
+		if (WARN_ON_ONCE(!new_pud_page))
+			return NULL;
+
+		set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+	}
+
+	pud = pud_offset(p4d, address);
+	/* The user page tables do not use large mappings: */
+	if (pud_leaf(*pud)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pud_none(*pud)) {
+		unsigned long new_pmd_page = __get_free_page(gfp);
+		if (WARN_ON_ONCE(!new_pmd_page))
+			return NULL;
+
+		set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+	}
+
+	return pmd_offset(pud, address);
+}
+
+/*
+ * Walk the shadow copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.  Does not support large pages.
+ *
+ * Note: this is only used when mapping *new* kernel data into the
+ * user/shadow page tables.  It is never used for userspace data.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pmd = pti_user_pagetable_walk_pmd(address);
+	if (!pmd)
+		return NULL;
+
+	/* Large PMD mapping found */
+	if (pmd_leaf(*pmd)) {
+		/* Clear the PMD if we hit a large mapping from the first round */
+		if (late_text) {
+			set_pmd(pmd, __pmd(0));
+		} else {
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
+	}
+
+	if (pmd_none(*pmd)) {
+		unsigned long new_pte_page = __get_free_page(gfp);
+		if (!new_pte_page)
+			return NULL;
+
+		set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+	}
+
+	pte = pte_offset_kernel(pmd, address);
+	if (pte_flags(*pte) & _PAGE_USER) {
+		WARN_ONCE(1, "attempt to walk to user pte\n");
+		return NULL;
+	}
+	return pte;
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+static void __init pti_setup_vsyscall(void)
+{
+	pte_t *pte, *target_pte;
+	unsigned int level;
+
+	pte = lookup_address(VSYSCALL_ADDR, &level);
+	if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+		return;
+
+	target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false);
+	if (WARN_ON(!target_pte))
+		return;
+
+	*target_pte = *pte;
+	set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
+}
+#else
+static void __init pti_setup_vsyscall(void) { }
+#endif
+
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
+static void
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level, bool late_text)
+{
+	unsigned long addr;
+
+	/*
+	 * Clone the populated PMDs which cover start to end. These PMD areas
+	 * can have holes.
+	 */
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
+		pmd_t *pmd, *target_pmd;
+		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
+
+		/* Overflow check */
+		if (addr < start)
+			break;
+
+		pgd = pgd_offset_k(addr);
+		if (WARN_ON(pgd_none(*pgd)))
+			return;
+		p4d = p4d_offset(pgd, addr);
+		if (WARN_ON(p4d_none(*p4d)))
+			return;
+
+		pud = pud_offset(p4d, addr);
+		if (pud_none(*pud)) {
+			WARN_ON_ONCE(addr & ~PUD_MASK);
+			addr = round_up(addr + 1, PUD_SIZE);
+			continue;
+		}
+
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd)) {
+			WARN_ON_ONCE(addr & ~PMD_MASK);
+			addr = round_up(addr + 1, PMD_SIZE);
+			continue;
+		}
+
+		if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) {
+			target_pmd = pti_user_pagetable_walk_pmd(addr);
+			if (WARN_ON(!target_pmd))
+				return;
+
+			/*
+			 * Only clone present PMDs.  This ensures only setting
+			 * _PAGE_GLOBAL on present PMDs.  This should only be
+			 * called on well-known addresses anyway, so a non-
+			 * present PMD would be a surprise.
+			 */
+			if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+				return;
+
+			/*
+			 * Setting 'target_pmd' below creates a mapping in both
+			 * the user and kernel page tables.  It is effectively
+			 * global, so set it as global in both copies.  Note:
+			 * the X86_FEATURE_PGE check is not _required_ because
+			 * the CPU ignores _PAGE_GLOBAL when PGE is not
+			 * supported.  The check keeps consistency with
+			 * code that only set this bit when supported.
+			 */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+			/*
+			 * Copy the PMD.  That is, the kernelmode and usermode
+			 * tables will share the last-level page tables of this
+			 * address range
+			 */
+			*target_pmd = *pmd;
+
+			addr = round_up(addr + 1, PMD_SIZE);
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr = round_up(addr + 1, PAGE_SIZE);
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr, late_text);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr = round_up(addr + 1, PAGE_SIZE);
+
+		} else {
+			BUG();
+		}
+	}
+}
+
+#ifdef CONFIG_X86_64
+/*
+ * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
+ * next-level entry on 5-level systems.
+ */
+static void __init pti_clone_p4d(unsigned long addr)
+{
+	p4d_t *kernel_p4d, *user_p4d;
+	pgd_t *kernel_pgd;
+
+	user_p4d = pti_user_pagetable_walk_p4d(addr);
+	if (!user_p4d)
+		return;
+
+	kernel_pgd = pgd_offset_k(addr);
+	kernel_p4d = p4d_offset(kernel_pgd, addr);
+	*user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA and associated data into the user space visible
+ * page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	unsigned int cpu;
+
+	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * The SYSCALL64 entry code needs one word of scratch space
+		 * in which to spill a register.  It lives in the sp2 slot
+		 * of the CPU's TSS.
+		 *
+		 * This is done for all possible CPUs during boot to ensure
+		 * that it's propagated to all mms.
+		 */
+
+		unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu);
+		phys_addr_t pa = per_cpu_ptr_to_phys((void *)va);
+		pte_t *target_pte;
+
+		target_pte = pti_user_pagetable_walk_pte(va, false);
+		if (WARN_ON(!target_pte))
+			return;
+
+		*target_pte = pfn_pte(pa >> PAGE_SHIFT, PAGE_KERNEL);
+	}
+}
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * On 32 bit PAE systems with 1GB of Kernel address space there is only
+ * one pgd/p4d for the whole kernel. Cloning that would map the whole
+ * address space into the user page-tables, making PTI useless. So clone
+ * the page-table on the PMD level to prevent that.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	unsigned long start, end;
+
+	start = CPU_ENTRY_AREA_BASE;
+	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD, false);
+}
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Clone the ESPFIX P4D into the user space visible page table
+ */
+static void __init pti_setup_espfix64(void)
+{
+#ifdef CONFIG_X86_ESPFIX64
+	pti_clone_p4d(ESPFIX_BASE_ADDR);
+#endif
+}
+
+/*
+ * Clone the populated PMDs of the entry text and force it RO.
+ */
+static void pti_clone_entry_text(bool late)
+{
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __entry_text_end,
+			  PTI_LEVEL_KERNEL_IMAGE, late);
+}
+
+/*
+ * Global pages and PCIDs are both ways to make kernel TLB entries
+ * live longer, reduce TLB misses and improve kernel performance.
+ * But, leaving all kernel text Global makes it potentially accessible
+ * to Meltdown-style attacks which make it trivial to find gadgets or
+ * defeat KASLR.
+ *
+ * Only use global pages when it is really worth it.
+ */
+static inline bool pti_kernel_image_global_ok(void)
+{
+	/*
+	 * Systems with PCIDs get little benefit from global
+	 * kernel text and are not worth the downsides.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_PCID))
+		return false;
+
+	/*
+	 * Only do global kernel image for pti=auto.  Do the most
+	 * secure thing (not global) if pti=on specified.
+	 */
+	if (pti_mode != PTI_AUTO)
+		return false;
+
+	/*
+	 * K8 may not tolerate the cleared _PAGE_RW on the userspace
+	 * global kernel image pages.  Do the safe thing (disable
+	 * global kernel image).  This is unlikely to ever be
+	 * noticed because PTI is disabled by default on AMD CPUs.
+	 */
+	if (boot_cpu_has(X86_FEATURE_K8))
+		return false;
+
+	/*
+	 * RANDSTRUCT derives its hardening benefits from the
+	 * attacker's lack of knowledge about the layout of kernel
+	 * data structures.  Keep the kernel image non-global in
+	 * cases where RANDSTRUCT is in use to help keep the layout a
+	 * secret.
+	 */
+	if (IS_ENABLED(CONFIG_RANDSTRUCT))
+		return false;
+
+	return true;
+}
+
+/*
+ * For some configurations, map all of kernel text into the user page
+ * tables.  This reduces TLB misses, especially on non-PCID systems.
+ */
+static void pti_clone_kernel_text(void)
+{
+	/*
+	 * rodata is part of the kernel image and is normally
+	 * readable on the filesystem or on the web.  But, do not
+	 * clone the areas past rodata, they might contain secrets.
+	 */
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long end_clone  = (unsigned long)__end_rodata_aligned;
+	unsigned long end_global = PFN_ALIGN((unsigned long)_etext);
+
+	if (!pti_kernel_image_global_ok())
+		return;
+
+	pr_debug("mapping partial kernel image into user address space\n");
+
+	/*
+	 * Note that this will undo _some_ of the work that
+	 * pti_set_kernel_image_nonglobal() did to clear the
+	 * global bit.
+	 */
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false);
+
+	/*
+	 * pti_clone_pgtable() will set the global bit in any PMDs
+	 * that it clones, but we also need to get any PTEs in
+	 * the last level for areas that are not huge-page-aligned.
+	 */
+
+	/* Set the global bit for normal non-__init kernel text: */
+	set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
+}
+
+static void pti_set_kernel_image_nonglobal(void)
+{
+	/*
+	 * The identity map is created with PMDs, regardless of the
+	 * actual length of the kernel.  We need to clear
+	 * _PAGE_GLOBAL up to a PMD boundary, not just to the end
+	 * of the image.
+	 */
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long end = ALIGN((unsigned long)_end, PMD_SIZE);
+
+	/*
+	 * This clears _PAGE_GLOBAL from the entire kernel image.
+	 * pti_clone_kernel_text() map put _PAGE_GLOBAL back for
+	 * areas that are mapped to userspace.
+	 */
+	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pr_info("enabled\n");
+
+#ifdef CONFIG_X86_32
+	/*
+	 * We check for X86_FEATURE_PCID here. But the init-code will
+	 * clear the feature flag on 32 bit because the feature is not
+	 * supported on 32 bit anyway. To print the warning we need to
+	 * check with cpuid directly again.
+	 */
+	if (cpuid_ecx(0x1) & BIT(17)) {
+		/* Use printk to work around pr_fmt() */
+		printk(KERN_WARNING "\n");
+		printk(KERN_WARNING "************************************************************\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n");
+		printk(KERN_WARNING "** Your performance will increase dramatically if you     **\n");
+		printk(KERN_WARNING "** switch to a 64-bit kernel!                             **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "************************************************************\n");
+	}
+#endif
+
+	pti_clone_user_shared();
+
+	/* Undo all global bits from the init pagetables in head_64.S: */
+	pti_set_kernel_image_nonglobal();
+
+	/* Replace some of the global bits just for shared entry text: */
+	/*
+	 * This is very early in boot. Device and Late initcalls can do
+	 * modprobe before free_initmem() and mark_readonly(). This
+	 * pti_clone_entry_text() allows those user-mode-helpers to function,
+	 * but notably the text is still RW.
+	 */
+	pti_clone_entry_text(false);
+	pti_setup_espfix64();
+	pti_setup_vsyscall();
+}
+
+/*
+ * Finalize the kernel mappings in the userspace page-table. Some of the
+ * mappings for the kernel image might have changed since pti_init()
+ * cloned them. This is because parts of the kernel image have been
+ * mapped RO and/or NX.  These changes need to be cloned again to the
+ * userspace page-table.
+ */
+void pti_finalize(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_PTI))
+		return;
+	/*
+	 * This is after free_initmem() (all initcalls are done) and we've done
+	 * mark_readonly(). Text is now NX which might've split some PMDs
+	 * relative to the early clone.
+	 */
+	pti_clone_entry_text(true);
+	pti_clone_kernel_text();
+
+	debug_checkwx_user();
+}
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
new file mode 100644
index 000000000..44ca66651
--- /dev/null
+++ b/arch/x86/mm/srat.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACPI 3.0 based NUMA setup
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#include <linux/kernel.h>
+#include <linux/acpi.h>
+#include <linux/mmzone.h>
+#include <linux/bitmap.h>
+#include <linux/init.h>
+#include <linux/topology.h>
+#include <linux/mm.h>
+#include <asm/proto.h>
+#include <asm/numa.h>
+#include <asm/e820/api.h>
+#include <asm/apic.h>
+#include <asm/uv/uv.h>
+
+/* Callback for Proximity Domain -> x2APIC mapping */
+void __init
+acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
+{
+	int pxm, node;
+	int apic_id;
+
+	if (srat_disabled())
+		return;
+	if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) {
+		bad_srat();
+		return;
+	}
+	if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
+		return;
+	pxm = pa->proximity_domain;
+	apic_id = pa->apic_id;
+	if (!apic_id_valid(apic_id)) {
+		pr_info("SRAT: PXM %u -> X2APIC 0x%04x ignored\n", pxm, apic_id);
+		return;
+	}
+	node = acpi_map_pxm_to_node(pxm);
+	if (node < 0) {
+		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
+	set_apicid_to_node(apic_id, node);
+	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
+	pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node);
+}
+
+/* Callback for Proximity Domain -> LAPIC mapping */
+void __init
+acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
+{
+	int pxm, node;
+	int apic_id;
+
+	if (srat_disabled())
+		return;
+	if (pa->header.length != sizeof(struct acpi_srat_cpu_affinity)) {
+		bad_srat();
+		return;
+	}
+	if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
+		return;
+	pxm = pa->proximity_domain_lo;
+	if (acpi_srat_revision >= 2)
+		pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
+	node = acpi_map_pxm_to_node(pxm);
+	if (node < 0) {
+		printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
+		bad_srat();
+		return;
+	}
+
+	if (get_uv_system_type() >= UV_X2APIC)
+		apic_id = (pa->apic_id << 8) | pa->local_sapic_eid;
+	else
+		apic_id = pa->apic_id;
+
+	if (apic_id >= MAX_LOCAL_APIC) {
+		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
+		return;
+	}
+
+	set_apicid_to_node(apic_id, node);
+	node_set(node, numa_nodes_parsed);
+	node_set(node, numa_phys_nodes_parsed);
+	pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node);
+}
+
+int __init x86_acpi_numa_init(void)
+{
+	int ret;
+
+	ret = acpi_numa_init();
+	if (ret < 0)
+		return ret;
+	return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
new file mode 100644
index 000000000..ae295659c
--- /dev/null
+++ b/arch/x86/mm/testmmiotrace.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/mmiotrace.h>
+#include <linux/security.h>
+
+static unsigned long mmio_address;
+module_param_hw(mmio_address, ulong, iomem, 0);
+MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
+				"(or 8 MB if read_far is non-zero).");
+
+static unsigned long read_far = 0x400100;
+module_param(read_far, ulong, 0);
+MODULE_PARM_DESC(read_far, " Offset of a 32-bit read within 8 MB "
+				"(default: 0x400100).");
+
+static unsigned v16(unsigned i)
+{
+	return i * 12 + 7;
+}
+
+static unsigned v32(unsigned i)
+{
+	return i * 212371 + 13;
+}
+
+static void do_write_test(void __iomem *p)
+{
+	unsigned int i;
+	pr_info("write test.\n");
+	mmiotrace_printk("Write test.\n");
+
+	for (i = 0; i < 256; i++)
+		iowrite8(i, p + i);
+
+	for (i = 1024; i < (5 * 1024); i += 2)
+		iowrite16(v16(i), p + i);
+
+	for (i = (5 * 1024); i < (16 * 1024); i += 4)
+		iowrite32(v32(i), p + i);
+}
+
+static void do_read_test(void __iomem *p)
+{
+	unsigned int i;
+	unsigned errs[3] = { 0 };
+	pr_info("read test.\n");
+	mmiotrace_printk("Read test.\n");
+
+	for (i = 0; i < 256; i++)
+		if (ioread8(p + i) != i)
+			++errs[0];
+
+	for (i = 1024; i < (5 * 1024); i += 2)
+		if (ioread16(p + i) != v16(i))
+			++errs[1];
+
+	for (i = (5 * 1024); i < (16 * 1024); i += 4)
+		if (ioread32(p + i) != v32(i))
+			++errs[2];
+
+	mmiotrace_printk("Read errors: 8-bit %d, 16-bit %d, 32-bit %d.\n",
+						errs[0], errs[1], errs[2]);
+}
+
+static void do_read_far_test(void __iomem *p)
+{
+	pr_info("read far test.\n");
+	mmiotrace_printk("Read far test.\n");
+
+	ioread32(p + read_far);
+}
+
+static void do_test(unsigned long size)
+{
+	void __iomem *p = ioremap(mmio_address, size);
+	if (!p) {
+		pr_err("could not ioremap, aborting.\n");
+		return;
+	}
+	mmiotrace_printk("ioremap returned %p.\n", p);
+	do_write_test(p);
+	do_read_test(p);
+	if (read_far && read_far < size - 4)
+		do_read_far_test(p);
+	iounmap(p);
+}
+
+/*
+ * Tests how mmiotrace behaves in face of multiple ioremap / iounmaps in
+ * a short time. We had a bug in deferred freeing procedure which tried
+ * to free this region multiple times (ioremap can reuse the same address
+ * for many mappings).
+ */
+static void do_test_bulk_ioremapping(void)
+{
+	void __iomem *p;
+	int i;
+
+	for (i = 0; i < 10; ++i) {
+		p = ioremap(mmio_address, PAGE_SIZE);
+		if (p)
+			iounmap(p);
+	}
+
+	/* Force freeing. If it will crash we will know why. */
+	synchronize_rcu();
+}
+
+static int __init init(void)
+{
+	unsigned long size = (read_far) ? (8 << 20) : (16 << 10);
+	int ret = security_locked_down(LOCKDOWN_MMIOTRACE);
+
+	if (ret)
+		return ret;
+
+	if (mmio_address == 0) {
+		pr_err("you have to use the module argument mmio_address.\n");
+		pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n");
+		return -ENXIO;
+	}
+
+	pr_warn("WARNING: mapping %lu kB @ 0x%08lx in PCI address space, "
+		"and writing 16 kB of rubbish in there.\n",
+		size >> 10, mmio_address);
+	do_test(size);
+	do_test_bulk_ioremapping();
+	pr_info("All done.\n");
+	return 0;
+}
+
+static void __exit cleanup(void)
+{
+	pr_debug("unloaded.\n");
+}
+
+module_init(init);
+module_exit(cleanup);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Test module for mmiotrace");
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
new file mode 100644
index 000000000..0c4da3208
--- /dev/null
+++ b/arch/x86/mm/tlb.c
@@ -0,0 +1,1786 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/export.h>
+#include <linux/cpu.h>
+#include <linux/debugfs.h>
+#include <linux/sched/smt.h>
+#include <linux/task_work.h>
+#include <linux/mmu_notifier.h>
+#include <linux/mmu_context.h>
+#include <linux/kvm_types.h>
+
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/nospec-branch.h>
+#include <asm/cache.h>
+#include <asm/cacheflush.h>
+#include <asm/apic.h>
+#include <asm/msr.h>
+#include <asm/perf_event.h>
+#include <asm/tlb.h>
+
+#include "mm_internal.h"
+
+#ifdef CONFIG_PARAVIRT
+# define STATIC_NOPV
+#else
+# define STATIC_NOPV			static
+# define __flush_tlb_local		native_flush_tlb_local
+# define __flush_tlb_global		native_flush_tlb_global
+# define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
+# define __flush_tlb_multi(msk, info)	native_flush_tlb_multi(msk, info)
+#endif
+
+/*
+ *	TLB flushing, formerly SMP-only
+ *		c/o Linus Torvalds.
+ *
+ *	These mean you can really definitely utterly forget about
+ *	writing to user space from interrupts. (Its not allowed anyway).
+ *
+ *	Optimizations Manfred Spraul <manfred@colorfullife.com>
+ *
+ *	More scalable flush, from Andi Kleen
+ *
+ *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
+ */
+
+/*
+ * Bits to mangle the TIF_SPEC_* state into the mm pointer which is
+ * stored in cpu_tlb_state.last_user_mm_spec.
+ */
+#define LAST_USER_MM_IBPB	0x1UL
+#define LAST_USER_MM_L1D_FLUSH	0x2UL
+#define LAST_USER_MM_SPEC_MASK	(LAST_USER_MM_IBPB | LAST_USER_MM_L1D_FLUSH)
+
+/* Bits to set when tlbstate and flush is (re)initialized */
+#define LAST_USER_MM_INIT	LAST_USER_MM_IBPB
+
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID  - [0, TLB_NR_DYN_ASIDS-1]
+ *         the canonical identifier for an mm, dynamically allocated on each CPU
+ *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
+ *         the canonical, global identifier for an mm, identical across all CPUs
+ *
+ * kPCID - [1, MAX_ASID_AVAILABLE]
+ *         the value we write into the PCID part of CR3; corresponds to the
+ *         ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
+ *         for KPTI each mm has two address spaces and thus needs two
+ *         PCID values, but we can still do with a single ASID denomination
+ *         for each mm. Corresponds to kPCID + 2048.
+ *
+ */
+
+/*
+ * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS	1
+#else
+# define PTI_CONSUMED_PCID_BITS	0
+#endif
+
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
+
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
+{
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+	/*
+	 * Make sure that the dynamic ASID space does not conflict with the
+	 * bit we are using to switch between user and kernel ASIDs.
+	 */
+	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
+
+	/*
+	 * The ASID being passed in here should have respected the
+	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+	 */
+	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
+#endif
+	/*
+	 * The dynamically-assigned ASIDs that get passed in are small
+	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
+	 * so do not bother to clear it.
+	 *
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
+}
+
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
+{
+	u16 ret = kern_pcid(asid);
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
+#endif
+	return ret;
+}
+
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid, unsigned long lam)
+{
+	unsigned long cr3 = __sme_pa(pgd) | lam;
+
+	if (cpu_feature_enabled(X86_FEATURE_PCID)) {
+		cr3 |= kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+	}
+
+	return cr3;
+}
+
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid,
+					      unsigned long lam)
+{
+	/*
+	 * Use boot_cpu_has() instead of this_cpu_has() as this function
+	 * might be called during early boot. This should work even after
+	 * boot because all CPU's the have same capabilities:
+	 */
+	VM_WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_PCID));
+	return build_cr3(pgd, asid, lam) | CR3_NOFLUSH;
+}
+
+/*
+ * We get here when we do something requiring a TLB invalidation
+ * but could not go invalidate all of the contexts.  We do the
+ * necessary invalidation by clearing out the 'ctx_id' which
+ * forces a TLB flush when the context is loaded.
+ */
+static void clear_asid_other(void)
+{
+	u16 asid;
+
+	/*
+	 * This is only expected to be set if we have disabled
+	 * kernel _PAGE_GLOBAL pages.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_PTI)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+		/* Do not need to flush the current asid */
+		if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
+			continue;
+		/*
+		 * Make sure the next time we go to switch to
+		 * this asid, we do a flush:
+		 */
+		this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
+	}
+	this_cpu_write(cpu_tlbstate.invalidate_other, false);
+}
+
+atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+
+struct new_asid {
+	unsigned int asid	: 16;
+	unsigned int need_flush : 1;
+};
+
+static struct new_asid choose_new_asid(struct mm_struct *next, u64 next_tlb_gen)
+{
+	struct new_asid ns;
+	u16 asid;
+
+	if (!cpu_feature_enabled(X86_FEATURE_PCID)) {
+		ns.asid = 0;
+		ns.need_flush = 1;
+		return ns;
+	}
+
+	/*
+	 * TLB consistency for global ASIDs is maintained with hardware assisted
+	 * remote TLB flushing. Global ASIDs are always up to date.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		u16 global_asid = mm_global_asid(next);
+
+		if (global_asid) {
+			ns.asid = global_asid;
+			ns.need_flush = 0;
+			return ns;
+		}
+	}
+
+	if (this_cpu_read(cpu_tlbstate.invalidate_other))
+		clear_asid_other();
+
+	for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+		if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
+		    next->context.ctx_id)
+			continue;
+
+		ns.asid = asid;
+		ns.need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < next_tlb_gen);
+		return ns;
+	}
+
+	/*
+	 * We don't currently own an ASID slot on this CPU.
+	 * Allocate a slot.
+	 */
+	ns.asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
+	if (ns.asid >= TLB_NR_DYN_ASIDS) {
+		ns.asid = 0;
+		this_cpu_write(cpu_tlbstate.next_asid, 1);
+	}
+	ns.need_flush = true;
+
+	return ns;
+}
+
+/*
+ * Global ASIDs are allocated for multi-threaded processes that are
+ * active on multiple CPUs simultaneously, giving each of those
+ * processes the same PCID on every CPU, for use with hardware-assisted
+ * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
+ *
+ * These global ASIDs are held for the lifetime of the process.
+ */
+static DEFINE_RAW_SPINLOCK(global_asid_lock);
+static u16 last_global_asid = MAX_ASID_AVAILABLE;
+static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
+static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
+static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;
+
+/*
+ * When the search for a free ASID in the global ASID space reaches
+ * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
+ * freed global ASIDs are safe to re-use.
+ *
+ * This way the global flush only needs to happen at ASID rollover
+ * time, and not at ASID allocation time.
+ */
+static void reset_global_asid_space(void)
+{
+	lockdep_assert_held(&global_asid_lock);
+
+	invlpgb_flush_all_nonglobals();
+
+	/*
+	 * The TLB flush above makes it safe to re-use the previously
+	 * freed global ASIDs.
+	 */
+	bitmap_andnot(global_asid_used, global_asid_used,
+			global_asid_freed, MAX_ASID_AVAILABLE);
+	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);
+
+	/* Restart the search from the start of global ASID space. */
+	last_global_asid = TLB_NR_DYN_ASIDS;
+}
+
+static u16 allocate_global_asid(void)
+{
+	u16 asid;
+
+	lockdep_assert_held(&global_asid_lock);
+
+	/* The previous allocation hit the edge of available address space */
+	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
+		reset_global_asid_space();
+
+	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);
+
+	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
+		/* This should never happen. */
+		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
+				global_asid_available);
+		return 0;
+	}
+
+	/* Claim this global ASID. */
+	__set_bit(asid, global_asid_used);
+	last_global_asid = asid;
+	global_asid_available--;
+	return asid;
+}
+
+/*
+ * Check whether a process is currently active on more than @threshold CPUs.
+ * This is a cheap estimation on whether or not it may make sense to assign
+ * a global ASID to this process, and use broadcast TLB invalidation.
+ */
+static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
+{
+	int count = 0;
+	int cpu;
+
+	/* This quick check should eliminate most single threaded programs. */
+	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
+		return false;
+
+	/* Slower check to make sure. */
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/* Skip the CPUs that aren't really running this process. */
+		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
+			continue;
+
+		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+			continue;
+
+		if (++count > threshold)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Assign a global ASID to the current process, protecting against
+ * races between multiple threads in the process.
+ */
+static void use_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* This process is already using broadcast TLB invalidation. */
+	if (mm_global_asid(mm))
+		return;
+
+	/*
+	 * The last global ASID was consumed while waiting for the lock.
+	 *
+	 * If this fires, a more aggressive ASID reuse scheme might be
+	 * needed.
+	 */
+	if (!global_asid_available) {
+		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
+		return;
+	}
+
+	asid = allocate_global_asid();
+	if (!asid)
+		return;
+
+	mm_assign_global_asid(mm, asid);
+}
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+void mm_free_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	if (!mm_global_asid(mm))
+		return;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* The global ASID can be re-used only after flush at wrap-around. */
+	__set_bit(mm->context.global_asid, global_asid_freed);
+
+	mm->context.global_asid = 0;
+	global_asid_available++;
+}
+#endif
+
+/*
+ * Is the mm transitioning from a CPU-local ASID to a global ASID?
+ */
+static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
+{
+	u16 global_asid = mm_global_asid(mm);
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	/* Process is transitioning to a global ASID */
+	if (global_asid && asid != global_asid)
+		return true;
+
+	return false;
+}
+
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
+ * systems have over 8k CPUs. Because of this potential ASID shortage,
+ * global ASIDs are handed out to processes that have frequent TLB
+ * flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!mm_in_asid_transition(mm))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	mm_clear_asid_transition(mm);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = mm_global_asid(info->mm);
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
+}
+
+/*
+ * Given an ASID, flush the corresponding user ASID.  We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
+{
+	/* There is no user ASID if address space separation is off */
+	if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION))
+		return;
+
+	/*
+	 * We only have a single ASID if PCID is off and the CR3
+	 * write will have flushed it.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_PCID))
+		return;
+
+	if (!cpu_feature_enabled(X86_FEATURE_PTI))
+		return;
+
+	__set_bit(kern_pcid(asid),
+		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
+}
+
+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam,
+			    bool need_flush)
+{
+	unsigned long new_mm_cr3;
+
+	if (need_flush) {
+		invalidate_user_asid(new_asid);
+		new_mm_cr3 = build_cr3(pgdir, new_asid, lam);
+	} else {
+		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid, lam);
+	}
+
+	/*
+	 * Caution: many callers of this function expect
+	 * that load_cr3() is serializing and orders TLB
+	 * fills with respect to the mm_cpumask writes.
+	 */
+	write_cr3(new_mm_cr3);
+}
+
+void leave_mm(void)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+
+	/*
+	 * It's plausible that we're in lazy TLB mode while our mm is init_mm.
+	 * If so, our callers still expect us to flush the TLB, but there
+	 * aren't any user TLB entries in init_mm to worry about.
+	 *
+	 * This needs to happen before any other sanity checks due to
+	 * intel_idle's shenanigans.
+	 */
+	if (loaded_mm == &init_mm)
+		return;
+
+	/* Warn if we're not lazy. */
+	WARN_ON(!this_cpu_read(cpu_tlbstate_shared.is_lazy));
+
+	switch_mm(NULL, &init_mm, NULL);
+}
+EXPORT_SYMBOL_GPL(leave_mm);
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	       struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(NULL, next, tsk);
+	local_irq_restore(flags);
+}
+
+/*
+ * Invoked from return to user/guest by a task that opted-in to L1D
+ * flushing but ended up running on an SMT enabled core due to wrong
+ * affinity settings or CPU hotplug. This is part of the paranoid L1D flush
+ * contract which this task requested.
+ */
+static void l1d_flush_force_sigbus(struct callback_head *ch)
+{
+	force_sig(SIGBUS);
+}
+
+static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
+				struct task_struct *next)
+{
+	/* Flush L1D if the outgoing task requests it */
+	if (prev_mm & LAST_USER_MM_L1D_FLUSH)
+		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+
+	/* Check whether the incoming task opted in for L1D flush */
+	if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
+		return;
+
+	/*
+	 * Validate that it is not running on an SMT sibling as this would
+	 * make the exercise pointless because the siblings share L1D. If
+	 * it runs on a SMT sibling, notify it with SIGBUS on return to
+	 * user/guest
+	 */
+	if (this_cpu_read(cpu_info.smt_active)) {
+		clear_ti_thread_flag(&next->thread_info, TIF_SPEC_L1D_FLUSH);
+		next->l1d_flush_kill.func = l1d_flush_force_sigbus;
+		task_work_add(next, &next->l1d_flush_kill, TWA_RESUME);
+	}
+}
+
+static unsigned long mm_mangle_tif_spec_bits(struct task_struct *next)
+{
+	unsigned long next_tif = read_task_thread_flags(next);
+	unsigned long spec_bits = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_SPEC_MASK;
+
+	/*
+	 * Ensure that the bit shift above works as expected and the two flags
+	 * end up in bit 0 and 1.
+	 */
+	BUILD_BUG_ON(TIF_SPEC_L1D_FLUSH != TIF_SPEC_IB + 1);
+
+	return (unsigned long)next->mm | spec_bits;
+}
+
+static void cond_mitigation(struct task_struct *next)
+{
+	unsigned long prev_mm, next_mm;
+
+	if (!next || !next->mm)
+		return;
+
+	next_mm = mm_mangle_tif_spec_bits(next);
+	prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec);
+
+	/*
+	 * Avoid user->user BTB/RSB poisoning by flushing them when switching
+	 * between processes. This stops one process from doing Spectre-v2
+	 * attacks on another.
+	 *
+	 * Both, the conditional and the always IBPB mode use the mm
+	 * pointer to avoid the IBPB when switching between tasks of the
+	 * same process. Using the mm pointer instead of mm->context.ctx_id
+	 * opens a hypothetical hole vs. mm_struct reuse, which is more or
+	 * less impossible to control by an attacker. Aside of that it
+	 * would only affect the first schedule so the theoretically
+	 * exposed data is not really interesting.
+	 */
+	if (static_branch_likely(&switch_mm_cond_ibpb)) {
+		/*
+		 * This is a bit more complex than the always mode because
+		 * it has to handle two cases:
+		 *
+		 * 1) Switch from a user space task (potential attacker)
+		 *    which has TIF_SPEC_IB set to a user space task
+		 *    (potential victim) which has TIF_SPEC_IB not set.
+		 *
+		 * 2) Switch from a user space task (potential attacker)
+		 *    which has TIF_SPEC_IB not set to a user space task
+		 *    (potential victim) which has TIF_SPEC_IB set.
+		 *
+		 * This could be done by unconditionally issuing IBPB when
+		 * a task which has TIF_SPEC_IB set is either scheduled in
+		 * or out. Though that results in two flushes when:
+		 *
+		 * - the same user space task is scheduled out and later
+		 *   scheduled in again and only a kernel thread ran in
+		 *   between.
+		 *
+		 * - a user space task belonging to the same process is
+		 *   scheduled in after a kernel thread ran in between
+		 *
+		 * - a user space task belonging to the same process is
+		 *   scheduled in immediately.
+		 *
+		 * Optimize this with reasonably small overhead for the
+		 * above cases. Mangle the TIF_SPEC_IB bit into the mm
+		 * pointer of the incoming task which is stored in
+		 * cpu_tlbstate.last_user_mm_spec for comparison.
+		 *
+		 * Issue IBPB only if the mm's are different and one or
+		 * both have the IBPB bit set.
+		 */
+		if (next_mm != prev_mm &&
+		    (next_mm | prev_mm) & LAST_USER_MM_IBPB)
+			indirect_branch_prediction_barrier();
+	}
+
+	if (static_branch_unlikely(&switch_mm_always_ibpb)) {
+		/*
+		 * Only flush when switching to a user space task with a
+		 * different context than the user space task which ran
+		 * last on this CPU.
+		 */
+		if ((prev_mm & ~LAST_USER_MM_SPEC_MASK) != (unsigned long)next->mm)
+			indirect_branch_prediction_barrier();
+	}
+
+	if (static_branch_unlikely(&switch_mm_cond_l1d_flush)) {
+		/*
+		 * Flush L1D when the outgoing task requested it and/or
+		 * check whether the incoming task requested L1D flushing
+		 * and ended up on an SMT sibling.
+		 */
+		if (unlikely((prev_mm | next_mm) & LAST_USER_MM_L1D_FLUSH))
+			l1d_flush_evaluate(prev_mm, next_mm, next);
+	}
+
+	this_cpu_write(cpu_tlbstate.last_user_mm_spec, next_mm);
+}
+
+#ifdef CONFIG_PERF_EVENTS
+static inline void cr4_update_pce_mm(struct mm_struct *mm)
+{
+	if (static_branch_unlikely(&rdpmc_always_available_key) ||
+	    (!static_branch_unlikely(&rdpmc_never_available_key) &&
+	     atomic_read(&mm->context.perf_rdpmc_allowed))) {
+		/*
+		 * Clear the existing dirty counters to
+		 * prevent the leak for an RDPMC task.
+		 */
+		perf_clear_dirty_counters();
+		cr4_set_bits_irqsoff(X86_CR4_PCE);
+	} else
+		cr4_clear_bits_irqsoff(X86_CR4_PCE);
+}
+
+void cr4_update_pce(void *ignored)
+{
+	cr4_update_pce_mm(this_cpu_read(cpu_tlbstate.loaded_mm));
+}
+
+#else
+static inline void cr4_update_pce_mm(struct mm_struct *mm) { }
+#endif
+
+/*
+ * This optimizes when not actually switching mm's.  Some architectures use the
+ * 'unused' argument for this optimization, but x86 must use
+ * 'cpu_tlbstate.loaded_mm' instead because it does not always keep
+ * 'current->active_mm' up to date.
+ */
+void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
+			struct task_struct *tsk)
+{
+	struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm);
+	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
+	unsigned cpu = smp_processor_id();
+	unsigned long new_lam;
+	struct new_asid ns;
+	u64 next_tlb_gen;
+
+
+	/* We don't want flush_tlb_func() to run concurrently with us. */
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING))
+		WARN_ON_ONCE(!irqs_disabled());
+
+	/*
+	 * Verify that CR3 is what we think it is.  This will catch
+	 * hypothetical buggy code that directly switches to swapper_pg_dir
+	 * without going through leave_mm() / switch_mm_irqs_off() or that
+	 * does something like write_cr3(read_cr3_pa()).
+	 *
+	 * Only do this check if CONFIG_DEBUG_VM=y because __read_cr3()
+	 * isn't free.
+	 */
+#ifdef CONFIG_DEBUG_VM
+	if (WARN_ON_ONCE(__read_cr3() != build_cr3(prev->pgd, prev_asid,
+						   tlbstate_lam_cr3_mask()))) {
+		/*
+		 * If we were to BUG here, we'd be very likely to kill
+		 * the system so hard that we don't see the call trace.
+		 * Try to recover instead by ignoring the error and doing
+		 * a global flush to minimize the chance of corruption.
+		 *
+		 * (This is far from being a fully correct recovery.
+		 *  Architecturally, the CPU could prefetch something
+		 *  back into an incorrect ASID slot and leave it there
+		 *  to cause trouble down the road.  It's better than
+		 *  nothing, though.)
+		 */
+		__flush_tlb_all();
+	}
+#endif
+	if (was_lazy)
+		this_cpu_write(cpu_tlbstate_shared.is_lazy, false);
+
+	/*
+	 * The membarrier system call requires a full memory barrier and
+	 * core serialization before returning to user-space, after
+	 * storing to rq->curr, when changing mm.  This is because
+	 * membarrier() sends IPIs to all CPUs that are in the target mm
+	 * to make them issue memory barriers.  However, if another CPU
+	 * switches to/from the target mm concurrently with
+	 * membarrier(), it can cause that CPU not to receive an IPI
+	 * when it really should issue a memory barrier.  Writing to CR3
+	 * provides that full memory barrier and core serializing
+	 * instruction.
+	 */
+	if (prev == next) {
+		/* Not actually switching mm's */
+		VM_WARN_ON(is_dyn_asid(prev_asid) &&
+			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+			   next->context.ctx_id);
+
+		/*
+		 * If this races with another thread that enables lam, 'new_lam'
+		 * might not match tlbstate_lam_cr3_mask().
+		 */
+
+		/*
+		 * Even in lazy TLB mode, the CPU should stay set in the
+		 * mm_cpumask. The TLB shootdown code can figure out from
+		 * cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
+		 */
+		if (IS_ENABLED(CONFIG_DEBUG_VM) &&
+		    WARN_ON_ONCE(prev != &init_mm && !is_notrack_mm(prev) &&
+				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		/* Check if the current mm is transitioning to a global ASID */
+		if (mm_needs_global_asid(next, prev_asid)) {
+			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+			ns = choose_new_asid(next, next_tlb_gen);
+			goto reload_tlb;
+		}
+
+		/*
+		 * Broadcast TLB invalidation keeps this ASID up to date
+		 * all the time.
+		 */
+		if (is_global_asid(prev_asid))
+			return;
+
+		/*
+		 * If the CPU is not in lazy TLB mode, we are just switching
+		 * from one thread in a process to another thread in the same
+		 * process. No TLB flush required.
+		 */
+		if (!was_lazy)
+			return;
+
+		/*
+		 * Read the tlb_gen to check whether a flush is needed.
+		 * If the TLB is up to date, just use it.
+		 * The barrier synchronizes with the tlb_gen increment in
+		 * the TLB shootdown code.
+		 */
+		smp_mb();
+		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+				next_tlb_gen)
+			return;
+
+		/*
+		 * TLB contents went out of date while we were in lazy
+		 * mode. Fall through to the TLB switching code below.
+		 */
+		ns.asid = prev_asid;
+		ns.need_flush = true;
+	} else {
+		/*
+		 * Apply process to process speculation vulnerability
+		 * mitigations if applicable.
+		 */
+		cond_mitigation(tsk);
+
+		/*
+		 * Indicate that CR3 is about to change. nmi_uaccess_okay()
+		 * and others are sensitive to the window where mm_cpumask(),
+		 * CR3 and cpu_tlbstate.loaded_mm are not all in sync.
+		 */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+
+		/*
+		 * Make sure this CPU is set in mm_cpumask() such that we'll
+		 * receive invalidation IPIs.
+		 *
+		 * Rely on the smp_mb() implied by cpumask_set_cpu()'s atomic
+		 * operation, or explicitly provide one. Such that:
+		 *
+		 * switch_mm_irqs_off()				flush_tlb_mm_range()
+		 *   smp_store_release(loaded_mm, SWITCHING);     atomic64_inc_return(tlb_gen)
+		 *   smp_mb(); // here                            // smp_mb() implied
+		 *   atomic64_read(tlb_gen);                      this_cpu_read(loaded_mm);
+		 *
+		 * we properly order against flush_tlb_mm_range(), where the
+		 * loaded_mm load can happen in mative_flush_tlb_multi() ->
+		 * should_flush_tlb().
+		 *
+		 * This way switch_mm() must see the new tlb_gen or
+		 * flush_tlb_mm_range() must see the new loaded_mm, or both.
+		 */
+		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+		else
+			smp_mb();
+
+		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+
+		ns = choose_new_asid(next, next_tlb_gen);
+	}
+
+reload_tlb:
+	new_lam = mm_lam_cr3_mask(next);
+	if (ns.need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(ns.asid));
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[ns.asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, true);
+
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+	} else {
+		/* The new ASID is already up to date. */
+		load_new_mm_cr3(next->pgd, ns.asid, new_lam, false);
+
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
+	}
+
+	/* Make sure we write CR3 before loaded_mm. */
+	barrier();
+
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, ns.asid);
+	cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next));
+
+	if (next != prev) {
+		cr4_update_pce_mm(next);
+		switch_ldt(prev, next);
+	}
+}
+
+/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.  Temporary mms can also be used for EFI runtime service
+ * calls or similar functionality.
+ *
+ * It is illegal to schedule while using a temporary mm -- the context switch
+ * code is unaware of the temporary mm and does not know how to context switch.
+ * Use a real (non-temporary) mm in a kernel thread if you need to sleep.
+ *
+ * Note: For sensitive memory writes, the temporary mm needs to be used
+ *       exclusively by a single core, and IRQs should be disabled while the
+ *       temporary mm is loaded, thereby preventing interrupt handler bugs from
+ *       overriding the kernel memory protection.
+ */
+struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm)
+{
+	struct mm_struct *prev_mm;
+
+	lockdep_assert_preemption_disabled();
+	guard(irqsave)();
+
+	/*
+	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+	 * with a stale address space WITHOUT being in lazy mode after
+	 * restoring the previous mm.
+	 */
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
+		leave_mm();
+
+	prev_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, temp_mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return prev_mm;
+}
+
+void unuse_temporary_mm(struct mm_struct *prev_mm)
+{
+	lockdep_assert_preemption_disabled();
+	guard(irqsave)();
+
+	/* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
+	cpumask_clear_cpu(smp_processor_id(), mm_cpumask(this_cpu_read(cpu_tlbstate.loaded_mm)));
+
+	switch_mm_irqs_off(NULL, prev_mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
+/*
+ * Call this when reinitializing a CPU.  It fixes the following potential
+ * problems:
+ *
+ * - The ASID changed from what cpu_tlbstate thinks it is (most likely
+ *   because the CPU was taken down and came back up with CR3's PCID
+ *   bits clear.  CPU hotplug can do this.
+ *
+ * - The TLB contains junk in slots corresponding to inactive ASIDs.
+ *
+ * - The CPU went so far out to lunch that it may have missed a TLB
+ *   flush.
+ */
+void initialize_tlbstate_and_flush(void)
+{
+	int i;
+	struct mm_struct *mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	u64 tlb_gen = atomic64_read(&init_mm.context.tlb_gen);
+	unsigned long lam = mm_lam_cr3_mask(mm);
+	unsigned long cr3 = __read_cr3();
+
+	/* Assert that CR3 already references the right mm. */
+	WARN_ON((cr3 & CR3_ADDR_MASK) != __pa(mm->pgd));
+
+	/* LAM expected to be disabled */
+	WARN_ON(cr3 & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57));
+	WARN_ON(lam);
+
+	/*
+	 * Assert that CR4.PCIDE is set if needed.  (CR4.PCIDE initialization
+	 * doesn't work like other CR4 bits because it can only be set from
+	 * long mode.)
+	 */
+	WARN_ON(boot_cpu_has(X86_FEATURE_PCID) &&
+		!(cr4_read_shadow() & X86_CR4_PCIDE));
+
+	/* Disable LAM, force ASID 0 and force a TLB flush. */
+	write_cr3(build_cr3(mm->pgd, 0, 0));
+
+	/* Reinitialize tlbstate. */
+	this_cpu_write(cpu_tlbstate.last_user_mm_spec, LAST_USER_MM_INIT);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
+	this_cpu_write(cpu_tlbstate.next_asid, 1);
+	this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id);
+	this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, tlb_gen);
+	cpu_tlbstate_update_lam(lam, mm_untag_mask(mm));
+
+	for (i = 1; i < TLB_NR_DYN_ASIDS; i++)
+		this_cpu_write(cpu_tlbstate.ctxs[i].ctx_id, 0);
+}
+
+/*
+ * flush_tlb_func()'s memory ordering requirement is that any
+ * TLB fills that happen after we flush the TLB are ordered after we
+ * read active_mm's tlb_gen.  We don't need any explicit barriers
+ * because all x86 flush operations are serializing and the
+ * atomic64_read operation won't be reordered by the compiler.
+ */
+static void flush_tlb_func(void *info)
+{
+	/*
+	 * We have three different tlb_gen values in here.  They are:
+	 *
+	 * - mm_tlb_gen:     the latest generation.
+	 * - local_tlb_gen:  the generation that this CPU has already caught
+	 *                   up to.
+	 * - f->new_tlb_gen: the generation that the requester of the flush
+	 *                   wants us to catch up to.
+	 */
+	const struct flush_tlb_info *f = info;
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	u64 local_tlb_gen;
+	bool local = smp_processor_id() == f->initiating_cpu;
+	unsigned long nr_invalidate = 0;
+	u64 mm_tlb_gen;
+
+	/* This code cannot presently handle being reentered. */
+	VM_WARN_ON(!irqs_disabled());
+
+	if (!local) {
+		inc_irq_stat(TLB);
+		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	}
+
+	/* The CPU was left in the mm_cpumask of the target mm. Clear it. */
+	if (f->mm && f->mm != loaded_mm) {
+		cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
+		trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
+		return;
+	}
+
+	if (unlikely(loaded_mm == &init_mm))
+		return;
+
+	/* Reload the ASID if transitioning into or out of a global ASID */
+	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
+		switch_mm_irqs_off(NULL, loaded_mm, NULL);
+		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	}
+
+	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
+	if (is_global_asid(loaded_mm_asid))
+		return;
+
+	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
+		   loaded_mm->context.ctx_id);
+
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) {
+		/*
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
+		 *
+		 * This should be rare, with native_flush_tlb_multi() skipping
+		 * IPIs to lazy TLB mode CPUs.
+		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
+		return;
+	}
+
+	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+
+	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
+		     f->new_tlb_gen <= local_tlb_gen)) {
+		/*
+		 * The TLB is already up to date in respect to f->new_tlb_gen.
+		 * While the core might be still behind mm_tlb_gen, checking
+		 * mm_tlb_gen unnecessarily would have negative caching effects
+		 * so avoid it.
+		 */
+		return;
+	}
+
+	/*
+	 * Defer mm_tlb_gen reading as long as possible to avoid cache
+	 * contention.
+	 */
+	mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
+
+	if (unlikely(local_tlb_gen == mm_tlb_gen)) {
+		/*
+		 * There's nothing to do: we're already up to date.  This can
+		 * happen if two concurrent flushes happen -- the first flush to
+		 * be handled can catch us all the way up, leaving no work for
+		 * the second flush.
+		 */
+		goto done;
+	}
+
+	WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen);
+	WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen);
+
+	/*
+	 * If we get to this point, we know that our TLB is out of date.
+	 * This does not strictly imply that we need to flush (it's
+	 * possible that f->new_tlb_gen <= local_tlb_gen), but we're
+	 * going to need to flush in the very near future, so we might
+	 * as well get it over with.
+	 *
+	 * The only question is whether to do a full or partial flush.
+	 *
+	 * We do a partial flush if requested and two extra conditions
+	 * are met:
+	 *
+	 * 1. f->new_tlb_gen == local_tlb_gen + 1.  We have an invariant that
+	 *    we've always done all needed flushes to catch up to
+	 *    local_tlb_gen.  If, for example, local_tlb_gen == 2 and
+	 *    f->new_tlb_gen == 3, then we know that the flush needed to bring
+	 *    us up to date for tlb_gen 3 is the partial flush we're
+	 *    processing.
+	 *
+	 *    As an example of why this check is needed, suppose that there
+	 *    are two concurrent flushes.  The first is a full flush that
+	 *    changes context.tlb_gen from 1 to 2.  The second is a partial
+	 *    flush that changes context.tlb_gen from 2 to 3.  If they get
+	 *    processed on this CPU in reverse order, we'll see
+	 *     local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL.
+	 *    If we were to use __flush_tlb_one_user() and set local_tlb_gen to
+	 *    3, we'd be break the invariant: we'd update local_tlb_gen above
+	 *    1 without the full flush that's needed for tlb_gen 2.
+	 *
+	 * 2. f->new_tlb_gen == mm_tlb_gen.  This is purely an optimization.
+	 *    Partial TLB flushes are not all that much cheaper than full TLB
+	 *    flushes, so it seems unlikely that it would be a performance win
+	 *    to do a partial flush if that won't bring our TLB fully up to
+	 *    date.  By doing a full flush instead, we can increase
+	 *    local_tlb_gen all the way to mm_tlb_gen and we can probably
+	 *    avoid another flush in the very near future.
+	 */
+	if (f->end != TLB_FLUSH_ALL &&
+	    f->new_tlb_gen == local_tlb_gen + 1 &&
+	    f->new_tlb_gen == mm_tlb_gen) {
+		/* Partial flush */
+		unsigned long addr = f->start;
+
+		/* Partial flush cannot have invalid generations */
+		VM_WARN_ON(f->new_tlb_gen == TLB_GENERATION_INVALID);
+
+		/* Partial flush must have valid mm */
+		VM_WARN_ON(f->mm == NULL);
+
+		nr_invalidate = (f->end - f->start) >> f->stride_shift;
+
+		while (addr < f->end) {
+			flush_tlb_one_user(addr);
+			addr += 1UL << f->stride_shift;
+		}
+		if (local)
+			count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate);
+	} else {
+		/* Full flush. */
+		nr_invalidate = TLB_FLUSH_ALL;
+
+		flush_tlb_local();
+		if (local)
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+	}
+
+	/* Both paths above update our state to mm_tlb_gen. */
+	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
+
+	/* Tracing is done in a unified manner to reduce the code size */
+done:
+	trace_tlb_flush(!local ? TLB_REMOTE_SHOOTDOWN :
+				(f->mm == NULL) ? TLB_LOCAL_SHOOTDOWN :
+						  TLB_LOCAL_MM_SHOOTDOWN,
+			nr_invalidate);
+}
+
+static bool should_flush_tlb(int cpu, void *data)
+{
+	struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu);
+	struct flush_tlb_info *info = data;
+
+	/*
+	 * Order the 'loaded_mm' and 'is_lazy' against their
+	 * write ordering in switch_mm_irqs_off(). Ensure
+	 * 'is_lazy' is at least as new as 'loaded_mm'.
+	 */
+	smp_rmb();
+
+	/* Lazy TLB will get flushed at the next context switch. */
+	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+		return false;
+
+	/* No mm means kernel memory flush. */
+	if (!info->mm)
+		return true;
+
+	/*
+	 * While switching, the remote CPU could have state from
+	 * either the prev or next mm. Assume the worst and flush.
+	 */
+	if (loaded_mm == LOADED_MM_SWITCHING)
+		return true;
+
+	/* The target mm is loaded, and the CPU is not lazy. */
+	if (loaded_mm == info->mm)
+		return true;
+
+	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
+	if (info->trim_cpumask)
+		return true;
+
+	return false;
+}
+
+static bool should_trim_cpumask(struct mm_struct *mm)
+{
+	if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) {
+		WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ);
+		return true;
+	}
+	return false;
+}
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
+EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared);
+
+STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
+					 const struct flush_tlb_info *info)
+{
+	/*
+	 * Do accounting and tracing. Note that there are (and have always been)
+	 * cases in which a remote TLB flush will be traced, but eventually
+	 * would not happen.
+	 */
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
+	if (info->end == TLB_FLUSH_ALL)
+		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
+	else
+		trace_tlb_flush(TLB_REMOTE_SEND_IPI,
+				(info->end - info->start) >> PAGE_SHIFT);
+
+	/*
+	 * If no page tables were freed, we can skip sending IPIs to
+	 * CPUs in lazy TLB mode. They will flush the CPU themselves
+	 * at the next context switch.
+	 *
+	 * However, if page tables are getting freed, we need to send the
+	 * IPI everywhere, to prevent CPUs in lazy TLB mode from tripping
+	 * up on the new contents of what used to be page tables, while
+	 * doing a speculative memory access.
+	 */
+	if (info->freed_tables || mm_in_asid_transition(info->mm))
+		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
+	else
+		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
+				(void *)info, 1, cpumask);
+}
+
+void flush_tlb_multi(const struct cpumask *cpumask,
+		      const struct flush_tlb_info *info)
+{
+	__flush_tlb_multi(cpumask, info);
+}
+
+/*
+ * See Documentation/arch/x86/tlb.rst for details.  We choose 33
+ * because it is large enough to cover the vast majority (at
+ * least 95%) of allocations, and is small enough that we are
+ * confident it will not cause too much overhead.  Each single
+ * flush is about 100 ns, so this caps the maximum overhead at
+ * _about_ 3,000 ns.
+ *
+ * This is in units of pages.
+ */
+unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
+
+static void init_flush_tlb_info(struct flush_tlb_info *info,
+				struct mm_struct *mm,
+				unsigned long start, unsigned long end,
+				unsigned int stride_shift, bool freed_tables,
+				u64 new_tlb_gen)
+{
+	/*
+	 * If the number of flushes is so large that a full flush
+	 * would be faster, do a full flush.
+	 */
+	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
+		start	= 0;
+		end	= TLB_FLUSH_ALL;
+	}
+
+	info->start		= start;
+	info->end		= end;
+	info->mm		= mm;
+	info->stride_shift	= stride_shift;
+	info->freed_tables	= freed_tables;
+	info->new_tlb_gen	= new_tlb_gen;
+	info->initiating_cpu	= smp_processor_id();
+	info->trim_cpumask	= 0;
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned int stride_shift,
+				bool freed_tables)
+{
+	struct flush_tlb_info info;
+	bool remote_flush = false;
+	int cpu = get_cpu();
+	u64 new_tlb_gen;
+
+	/* This is also a barrier that synchronizes with switch_mm(). */
+	new_tlb_gen = inc_mm_tlb_gen(mm);
+
+	init_flush_tlb_info(&info, mm, start, end, stride_shift, freed_tables, new_tlb_gen);
+
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(&info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		remote_flush = true;
+	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
+		lockdep_assert_irqs_enabled();
+		local_irq_disable();
+		flush_tlb_func(&info);
+		local_irq_enable();
+	}
+
+	put_cpu();
+
+	if (remote_flush) {
+		info.trim_cpumask = should_trim_cpumask(mm);
+		flush_tlb_multi(mm_cpumask(mm), &info);
+		consider_global_asid(mm);
+	}
+
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
+}
+
+static void do_flush_tlb_all(void *info)
+{
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	__flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
+
+	/* First try (faster) hardware-assisted TLB invalidation. */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		/* Fall back to the IPI-based invalidation. */
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+/* Flush an arbitrarily large range of memory with INVLPGB. */
+static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
+{
+	unsigned long addr, nr;
+
+	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
+		nr = (info->end - addr) >> PAGE_SHIFT;
+
+		/*
+		 * INVLPGB has a limit on the size of ranges it can
+		 * flush. Break up large flushes.
+		 */
+		nr = clamp_val(nr, 1, invlpgb_count_max);
+
+		invlpgb_flush_addr_nosync(addr, nr);
+	}
+	__tlbsync();
+}
+
+static void do_kernel_range_flush(void *info)
+{
+	struct flush_tlb_info *f = info;
+	unsigned long addr;
+
+	/* flush range by one by one 'invlpg' */
+	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
+		flush_tlb_one_kernel(addr);
+}
+
+static void kernel_tlb_flush_all(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+static void kernel_tlb_flush_range(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_kernel_range_flush(info);
+	else
+		on_each_cpu(do_kernel_range_flush, info, 1);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct flush_tlb_info info;
+
+	guard(preempt)();
+	init_flush_tlb_info(&info, NULL, start, end, PAGE_SHIFT, false,
+			    TLB_GENERATION_INVALID);
+
+	if (info.end == TLB_FLUSH_ALL)
+		kernel_tlb_flush_all(&info);
+	else
+		kernel_tlb_flush_range(&info);
+}
+
+/*
+ * This can be used from process context to figure out what the value of
+ * CR3 is without needing to do a (slow) __read_cr3().
+ *
+ * It's intended to be used for code like KVM that sneakily changes CR3
+ * and needs to restore it.  It needs to be used very carefully.
+ */
+unsigned long __get_current_cr3_fast(void)
+{
+	unsigned long cr3 =
+		build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
+			  this_cpu_read(cpu_tlbstate.loaded_mm_asid),
+			  tlbstate_lam_cr3_mask());
+
+	/* For now, be very restrictive about when this can be called. */
+	VM_WARN_ON(in_nmi() || preemptible());
+
+	VM_BUG_ON(cr3 != __read_cr3());
+	return cr3;
+}
+EXPORT_SYMBOL_FOR_KVM(__get_current_cr3_fast);
+
+/*
+ * Flush one page in the kernel mapping
+ */
+void flush_tlb_one_kernel(unsigned long addr)
+{
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
+
+	/*
+	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
+	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
+	 * use PCID if we also use global PTEs for the kernel mapping, and
+	 * INVLPG flushes global translations across all address spaces.
+	 *
+	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
+	 * __flush_tlb_one_user() will flush the given address for the current
+	 * kernel address space and for its usermode counterpart, but it does
+	 * not flush it for other address spaces.
+	 */
+	flush_tlb_one_user(addr);
+
+	if (!cpu_feature_enabled(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * See above.  We need to propagate the flush to all other address
+	 * spaces.  In principle, we only need to propagate it to kernelmode
+	 * address spaces, but the extra bookkeeping we would need is not
+	 * worth it.
+	 */
+	this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
+/*
+ * Flush one page in the user mapping
+ */
+STATIC_NOPV void native_flush_tlb_one_user(unsigned long addr)
+{
+	u32 loaded_mm_asid;
+	bool cpu_pcide;
+
+	/* Flush 'addr' from the kernel PCID: */
+	invlpg(addr);
+
+	/* If PTI is off there is no user PCID and nothing to flush. */
+	if (!cpu_feature_enabled(X86_FEATURE_PTI))
+		return;
+
+	loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	cpu_pcide      = this_cpu_read(cpu_tlbstate.cr4) & X86_CR4_PCIDE;
+
+	/*
+	 * invpcid_flush_one(pcid>0) will #GP if CR4.PCIDE==0.  Check
+	 * 'cpu_pcide' to ensure that *this* CPU will not trigger those
+	 * #GP's even if called before CR4.PCIDE has been initialized.
+	 */
+	if (boot_cpu_has(X86_FEATURE_INVPCID) && cpu_pcide)
+		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
+	else
+		invalidate_user_asid(loaded_mm_asid);
+}
+
+void flush_tlb_one_user(unsigned long addr)
+{
+	__flush_tlb_one_user(addr);
+}
+
+/*
+ * Flush everything
+ */
+STATIC_NOPV void native_flush_tlb_global(void)
+{
+	unsigned long flags;
+
+	if (cpu_feature_enabled(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+		 * Note, this works with CR4.PCIDE=0 or 1.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
+	/*
+	 * Read-modify-write to CR4 - protect it from preemption and
+	 * from interrupts. (Use the raw variant because this code can
+	 * be called from deep inside debugging code.)
+	 */
+	raw_local_irq_save(flags);
+
+	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
+
+	raw_local_irq_restore(flags);
+}
+
+/*
+ * Flush the entire current user mapping
+ */
+STATIC_NOPV void native_flush_tlb_local(void)
+{
+	/*
+	 * Preemption or interrupts must be disabled to protect the access
+	 * to the per CPU variable and to prevent being preempted between
+	 * read_cr3() and write_cr3().
+	 */
+	WARN_ON_ONCE(preemptible());
+
+	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
+	native_write_cr3(__native_read_cr3());
+}
+
+void flush_tlb_local(void)
+{
+	__flush_tlb_local();
+}
+
+/*
+ * Flush everything
+ */
+void __flush_tlb_all(void)
+{
+	/*
+	 * This is to catch users with enabled preemption and the PGE feature
+	 * and don't trigger the warning in __native_flush_tlb().
+	 */
+	VM_WARN_ON_ONCE(preemptible());
+
+	if (cpu_feature_enabled(X86_FEATURE_PGE)) {
+		__flush_tlb_global();
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
+		flush_tlb_local();
+	}
+}
+EXPORT_SYMBOL_FOR_KVM(__flush_tlb_all);
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	struct flush_tlb_info info;
+	bool remote_flush = false;
+	int cpu = get_cpu();
+
+	init_flush_tlb_info(&info, NULL, 0, TLB_FLUSH_ALL, 0, false,
+			    TLB_GENERATION_INVALID);
+	/*
+	 * flush_tlb_multi() is not optimized for the common case in which only
+	 * a local TLB flush is needed. Optimize this use-case by calling
+	 * flush_tlb_func_local() directly in this case.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
+		invlpgb_flush_all_nonglobals();
+		batch->unmapped_pages = false;
+	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+		remote_flush = true;
+	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
+		lockdep_assert_irqs_enabled();
+		local_irq_disable();
+		flush_tlb_func(&info);
+		local_irq_enable();
+	}
+
+	put_cpu();
+
+	if (remote_flush)
+		flush_tlb_multi(&batch->cpumask, &info);
+
+	cpumask_clear(&batch->cpumask);
+}
+
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or
+ * switching the loaded mm.  It can also be dangerous if we
+ * interrupted some kernel code that was temporarily using a
+ * different mm.
+ */
+bool nmi_uaccess_okay(void)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	struct mm_struct *current_mm = current->mm;
+
+	VM_WARN_ON_ONCE(!loaded_mm);
+
+	/*
+	 * The condition we want to check is
+	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
+	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
+	 * is supposed to be reasonably fast.
+	 *
+	 * Instead, we check the almost equivalent but somewhat conservative
+	 * condition below, and we rely on the fact that switch_mm_irqs_off()
+	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
+	 */
+	if (loaded_mm != current_mm)
+		return false;
+
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
+
+	return true;
+}
+
+static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
+				  size_t count, loff_t *ppos)
+{
+	char buf[32];
+	unsigned int len;
+
+	len = sprintf(buf, "%ld\n", tlb_single_page_flush_ceiling);
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t tlbflush_write_file(struct file *file, const char __user *user_buf,
+				   size_t count, loff_t *ppos)
+{
+	int ceiling;
+	int err;
+
+	err = kstrtoint_from_user(user_buf, count, 0, &ceiling);
+	if (err)
+		return err;
+
+	if (ceiling < 0)
+		return -EINVAL;
+
+	tlb_single_page_flush_ceiling = ceiling;
+	return count;
+}
+
+static const struct file_operations fops_tlbflush = {
+	.read = tlbflush_read_file,
+	.write = tlbflush_write_file,
+	.llseek = default_llseek,
+};
+
+static int __init create_tlb_single_page_flush_ceiling(void)
+{
+	debugfs_create_file("tlb_single_page_flush_ceiling", S_IRUSR | S_IWUSR,
+			    arch_debugfs_dir, NULL, &fops_tlbflush);
+	return 0;
+}
+late_initcall(create_tlb_single_page_flush_ceiling);