Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 page table isolation updates from Thomas Gleixner: "This is the final set of enabling page table isolation on x86: - Infrastructure patches for handling the extra page tables. - Patches which map the various bits and pieces which are required to get in and out of user space into the user space visible page tables. - The required changes to have CR3 switching in the entry/exit code. - Optimizations for the CR3 switching along with documentation how the ASID/PCID mechanism works. - Updates to dump pagetables to cover the user space page tables for W+X scans and extra debugfs files to analyze both the kernel and the user space visible page tables The whole functionality is compile time controlled via a config switch and can be turned on/off on the command line as well" * 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits) x86/ldt: Make the LDT mapping RO x86/mm/dump_pagetables: Allow dumping current pagetables x86/mm/dump_pagetables: Check user space page table for WX pages x86/mm/dump_pagetables: Add page table directory to the debugfs VFS hierarchy x86/mm/pti: Add Kconfig x86/dumpstack: Indicate in Oops whether PTI is configured and enabled x86/mm: Clarify the whole ASID/kernel PCID/user PCID naming x86/mm: Use INVPCID for __native_flush_tlb_single() x86/mm: Optimize RESTORE_CR3 x86/mm: Use/Fix PCID to optimize user/kernel switches x86/mm: Abstract switching CR3 x86/mm: Allow flushing for future ASID switches x86/pti: Map the vsyscall page if needed x86/pti: Put the LDT in its own PGD if PTI is on x86/mm/64: Make a full PGD-entry size hole in the memory map x86/events/intel/ds: Map debug buffers in cpu_entry_area x86/cpu_entry_area: Add debugstore entries to cpu_entry_area x86/mm/pti: Map ESPFIX into user space x86/mm/pti: Share entry text PMD x86/entry: Align entry text section to PMD boundary ...
2017-12-29 17:02:49 -08:00
commit 5aa90a8458
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -41,9 +41,10 @@ obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o

-obj-$(CONFIG_X86_INTEL_MPX)	+= mpx.o
-obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_X86_INTEL_MPX)			+= mpx.o
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION)		+= pti.o

 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt.o
 obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= mem_encrypt_boot.o
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -38,6 +38,32 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
 		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
 }

+static void percpu_setup_debug_store(int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+	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
+}
+
 /* Setup the fixmap mappings only once per-processor */
 static void __init setup_cpu_entry_area(int cpu)
 {
@@ -109,6 +135,7 @@ static void __init setup_cpu_entry_area(int cpu)
 	cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
 #endif
+	percpu_setup_debug_store(cpu);
 }

 static __init void setup_cpu_entry_area_ptes(void)
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -5,7 +5,7 @@

 static int ptdump_show(struct seq_file *m, void *v)
 {
-	ptdump_walk_pgd_level(m, NULL);
+	ptdump_walk_pgd_level_debugfs(m, NULL, false);
 	return 0;
 }

@@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = {
 	.release	= single_release,
 };

-static struct dentry *pe;
+static int ptdump_show_curknl(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd) {
+		down_read(&current->mm->mmap_sem);
+		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
+		up_read(&current->mm->mmap_sem);
+	}
+	return 0;
+}
+
+static int ptdump_open_curknl(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show_curknl, NULL);
+}
+
+static const struct file_operations ptdump_curknl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open_curknl,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static struct dentry *pe_curusr;
+
+static int ptdump_show_curusr(struct seq_file *m, void *v)
+{
+	if (current->mm->pgd) {
+		down_read(&current->mm->mmap_sem);
+		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
+		up_read(&current->mm->mmap_sem);
+	}
+	return 0;
+}
+
+static int ptdump_open_curusr(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show_curusr, NULL);
+}
+
+static const struct file_operations ptdump_curusr_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open_curusr,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+#endif
+
+static struct dentry *dir, *pe_knl, *pe_curknl;

 static int __init pt_dump_debug_init(void)
 {
-	pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
-				 &ptdump_fops);
-	if (!pe)
+	dir = debugfs_create_dir("page_tables", NULL);
+	if (!dir)
 		return -ENOMEM;

+	pe_knl = debugfs_create_file("kernel", 0400, dir, NULL,
+				     &ptdump_fops);
+	if (!pe_knl)
+		goto err;
+
+	pe_curknl = debugfs_create_file("current_kernel", 0400,
+					dir, NULL, &ptdump_curknl_fops);
+	if (!pe_curknl)
+		goto err;
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pe_curusr = debugfs_create_file("current_user", 0400,
+					dir, NULL, &ptdump_curusr_fops);
+	if (!pe_curusr)
+		goto err;
+#endif
 	return 0;
+err:
+	debugfs_remove_recursive(dir);
+	return -ENOMEM;
 }

 static void __exit pt_dump_debug_exit(void)
 {
-	debugfs_remove_recursive(pe);
+	debugfs_remove_recursive(dir);
 }

 module_init(pt_dump_debug_init);
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -52,11 +52,17 @@ enum address_markers_idx {
 	USER_SPACE_NR = 0,
 	KERNEL_SPACE_NR,
 	LOW_KERNEL_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL)
+	LDT_NR,
+#endif
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
 #ifdef CONFIG_KASAN
 	KASAN_SHADOW_START_NR,
 	KASAN_SHADOW_END_NR,
+#endif
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
+	LDT_NR,
 #endif
 	CPU_ENTRY_AREA_NR,
 #ifdef CONFIG_X86_ESPFIX64
@@ -81,6 +87,9 @@ static struct addr_marker address_markers[] = {
 #ifdef CONFIG_KASAN
 	[KASAN_SHADOW_START_NR]	= { KASAN_SHADOW_START,	"KASAN shadow" },
 	[KASAN_SHADOW_END_NR]	= { KASAN_SHADOW_END,	"KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { LDT_BASE_ADDR,	"LDT remap" },
 #endif
 	[CPU_ENTRY_AREA_NR]	= { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
 #ifdef CONFIG_X86_ESPFIX64
@@ -467,7 +476,7 @@ static inline bool is_hypervisor_range(int idx)
 }

 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
-				       bool checkwx)
+				       bool checkwx, bool dmesg)
 {
 #ifdef CONFIG_X86_64
 	pgd_t *start = (pgd_t *) &init_top_pgt;
@@ -480,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,

 	if (pgd) {
 		start = pgd;
-		st.to_dmesg = true;
+		st.to_dmesg = dmesg;
 	}

 	st.check_wx = checkwx;
@@ -518,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,

 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 {
-	ptdump_walk_pgd_level_core(m, pgd, false);
+	ptdump_walk_pgd_level_core(m, pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (user && static_cpu_has(X86_FEATURE_PTI))
+		pgd = kernel_to_user_pgdp(pgd);
+#endif
+	ptdump_walk_pgd_level_core(m, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+static void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pgd_t *pgd = (pgd_t *) &init_top_pgt;
+
+	if (!static_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, pgd, true, false);
+#endif
 }
-EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);

 void ptdump_walk_pgd_level_checkwx(void)
 {
-	ptdump_walk_pgd_level_core(NULL, NULL, true);
+	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+	ptdump_walk_user_pgd_level_checkwx();
 }

 static int __init pt_dump_init(void)
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -20,6 +20,7 @@
 #include <asm/kaslr.h>
 #include <asm/hypervisor.h>
 #include <asm/cpufeature.h>
+#include <asm/pti.h>

 /*
 * We need to define the tracepoints somewhere, and tlb.c
@@ -160,6 +161,12 @@ struct map_range {

 static int page_size_mask;

+static void enable_global_pages(void)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		__supported_pte_mask |= _PAGE_GLOBAL;
+}
+
 static void __init probe_page_size_mask(void)
 {
 	/*
@@ -177,11 +184,11 @@ static void __init probe_page_size_mask(void)
 		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;
-	} else
-		__supported_pte_mask &= ~_PAGE_GLOBAL;
+		enable_global_pages();
+	}

 	/* Enable 1 GB linear kernel mappings if available: */
 	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
@@ -194,34 +201,44 @@ static void __init probe_page_size_mask(void)

 static void setup_pcid(void)
 {
-#ifdef CONFIG_X86_64
-	if (boot_cpu_has(X86_FEATURE_PCID)) {
-		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);
-		}
+	if (!IS_ENABLED(CONFIG_X86_64))
+		return;
+
+	if (!boot_cpu_has(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);
+
+		/*
+		 * INVPCID's single-context modes (2/3) only work if we set
+		 * X86_CR4_PCIDE, *and* we INVPCID support.  It's unusable
+		 * on systems that have X86_CR4_PCIDE clear, or that have
+		 * no INVPCID support at all.
+		 */
+		if (boot_cpu_has(X86_FEATURE_INVPCID))
+			setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+	} 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);
 	}
-#endif
 }

 #ifdef CONFIG_X86_32
@@ -622,6 +639,7 @@ void __init init_mem_mapping(void)
 {
 	unsigned long end;

+	pti_check_boottime_disable();
 	probe_page_size_mask();
 	setup_pcid();

@@ -845,7 +863,7 @@ void __init zone_sizes_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }

-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
 	.loaded_mm = &init_mm,
 	.next_asid = 1,
 	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd)
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
+
 static inline pgd_t *_pgd_alloc(void)
 {
-	return (pgd_t *)__get_free_page(PGALLOC_GFP);
+	return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
 }

 static inline void _pgd_free(pgd_t *pgd)
 {
-	free_page((unsigned long)pgd);
+	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 }
 #endif /* CONFIG_X86_PAE */

--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,387 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * This code is based in part on work published here:
+ *
+ *	https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and 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@linutronix.de> 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 <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK	0
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+		pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+		pr_info("%s\n", reason);
+}
+
+void __init pti_check_boottime_disable(void)
+{
+	char arg[5];
+	int ret;
+
+	if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+		pti_print_if_insecure("disabled on XEN PV.");
+		return;
+	}
+
+	ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+	if (ret > 0)  {
+		if (ret == 3 && !strncmp(arg, "off", 3)) {
+			pti_print_if_insecure("disabled on command line.");
+			return;
+		}
+		if (ret == 2 && !strncmp(arg, "on", 2)) {
+			pti_print_if_secure("force enabled on command line.");
+			goto enable;
+		}
+		if (ret == 4 && !strncmp(arg, "auto", 4))
+			goto autosel;
+	}
+
+	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+		pti_print_if_insecure("disabled on command line.");
+		return;
+	}
+
+autosel:
+	if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+		return;
+enable:
+	setup_force_cpu_cap(X86_FEATURE_PTI);
+}
+
+pgd_t __pti_set_user_pgd(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))
+		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 (!new_p4d_page)
+			return NULL;
+
+		if (pgd_none(*pgd)) {
+			set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+			new_p4d_page = 0;
+		}
+		if (new_p4d_page)
+			free_page(new_p4d_page);
+	}
+	BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+	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 = pti_user_pagetable_walk_p4d(address);
+	pud_t *pud;
+
+	BUILD_BUG_ON(p4d_large(*p4d) != 0);
+	if (p4d_none(*p4d)) {
+		unsigned long new_pud_page = __get_free_page(gfp);
+		if (!new_pud_page)
+			return NULL;
+
+		if (p4d_none(*p4d)) {
+			set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+			new_pud_page = 0;
+		}
+		if (new_pud_page)
+			free_page(new_pud_page);
+	}
+
+	pud = pud_offset(p4d, address);
+	/* The user page tables do not use large mappings: */
+	if (pud_large(*pud)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	if (pud_none(*pud)) {
+		unsigned long new_pmd_page = __get_free_page(gfp);
+		if (!new_pmd_page)
+			return NULL;
+
+		if (pud_none(*pud)) {
+			set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+			new_pmd_page = 0;
+		}
+		if (new_pmd_page)
+			free_page(new_pmd_page);
+	}
+
+	return pmd_offset(pud, address);
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+/*
+ * 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 __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+{
+	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+	pte_t *pte;
+
+	/* We can't do anything sensible if we hit a large mapping. */
+	if (pmd_large(*pmd)) {
+		WARN_ON(1);
+		return NULL;
+	}
+
+	if (pmd_none(*pmd)) {
+		unsigned long new_pte_page = __get_free_page(gfp);
+		if (!new_pte_page)
+			return NULL;
+
+		if (pmd_none(*pmd)) {
+			set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+			new_pte_page = 0;
+		}
+		if (new_pte_page)
+			free_page(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;
+}
+
+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);
+	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
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+	unsigned long addr;
+
+	/*
+	 * Clone the populated PMDs which cover start to end. These PMD areas
+	 * can have holes.
+	 */
+	for (addr = start; addr < end; addr += PMD_SIZE) {
+		pmd_t *pmd, *target_pmd;
+		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
+
+		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))
+			continue;
+		pmd = pmd_offset(pud, addr);
+		if (pmd_none(*pmd))
+			continue;
+
+		target_pmd = pti_user_pagetable_walk_pmd(addr);
+		if (WARN_ON(!target_pmd))
+			return;
+
+		/*
+		 * Copy the PMD.  That is, the kernelmode and usermode
+		 * tables will share the last-level page tables of this
+		 * address range
+		 */
+		*target_pmd = pmd_clear_flags(*pmd, clear);
+	}
+}
+
+/*
+ * 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);
+	kernel_pgd = pgd_offset_k(addr);
+	kernel_p4d = p4d_offset(kernel_pgd, addr);
+	*user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+}
+
+/*
+ * Clone the ESPFIX P4D into the user space visinble 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 and irqentry text and force it RO.
+ */
+static void __init pti_clone_entry_text(void)
+{
+	pti_clone_pmds((unsigned long) __entry_text_start,
+			(unsigned long) __irqentry_text_end, _PAGE_RW);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	pr_info("enabled\n");
+
+	pti_clone_user_shared();
+	pti_clone_entry_text();
+	pti_setup_espfix64();
+	pti_setup_vsyscall();
+}
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,38 @@
 *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
 */

+/*
+ * 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.
+ */
+void clear_asid_other(void)
+{
+	u16 asid;
+
+	/*
+	 * This is only expected to be set if we have disabled
+	 * kernel _PAGE_GLOBAL pages.
+	 */
+	if (!static_cpu_has(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);


@@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		return;
 	}

+	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)
@@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 	*need_flush = true;
 }

+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+{
+	unsigned long new_mm_cr3;
+
+	if (need_flush) {
+		invalidate_user_asid(new_asid);
+		new_mm_cr3 = build_cr3(pgdir, new_asid);
+	} else {
+		new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+	}
+
+	/*
+	 * 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(int cpu)
 {
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -195,7 +249,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			write_cr3(build_cr3(next->pgd, new_asid));
+			load_new_mm_cr3(next->pgd, new_asid, true);

 			/*
 			 * NB: This gets called via leave_mm() in the idle path
@@ -208,7 +262,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 		} else {
 			/* The new ASID is already up to date. */
-			write_cr3(build_cr3_noflush(next->pgd, new_asid));
+			load_new_mm_cr3(next->pgd, new_asid, false);

 			/* See above wrt _rcuidle. */
 			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);