1 files changed, 904 insertions, 600 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae3047..998bd807fc7b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1,48 +1,49 @@
+// 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/magic.h>		/* STACK_END_MAGIC		*/
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
+#include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
-#include <linux/module.h>		/* search_exception_table	*/
-#include <linux/bootmem.h>		/* max_low_pfn			*/
-#include <linux/kprobes.h>		/* __kprobes, ...		*/
+#include <linux/memblock.h>		/* max_low_pfn			*/
+#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/prefetch.h>		/* prefetchw			*/
 #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/pgalloc.h>		/* pgd_*(), ...			*/
-#include <asm/kmemcheck.h>		/* kmemcheck_*(), ...		*/
-#include <asm/fixmap.h>			/* VSYSCALL_START		*/
-
-/*
- * Page fault error code bits:
- *
- *   bit 0 ==	 0: no page found	1: protection fault
- *   bit 1 ==	 0: read access		1: write access
- *   bit 2 ==	 0: kernel-mode access	1: user-mode access
- *   bit 3 ==				1: use of reserved bit detected
- *   bit 4 ==				1: fault was an instruction fetch
- */
-enum x86_pf_error_code {
-
-	PF_PROT		=		1 << 0,
-	PF_WRITE	=		1 << 1,
-	PF_USER		=		1 << 2,
-	PF_RSVD		=		1 << 3,
-	PF_INSTR	=		1 << 4,
-};
+#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 inline int __kprobes
+static nokprobe_inline int
 kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
 	if (unlikely(is_kmmio_active()))
@@ -51,28 +52,13 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
 	return 0;
 }
 
-static inline int __kprobes notify_page_fault(struct pt_regs *regs)
-{
-	int ret = 0;
-
-	/* kprobe_running() needs smp_processor_id() */
-	if (kprobes_built_in() && !user_mode_vm(regs)) {
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, 14))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-
 /*
  * Prefetch quirks:
  *
  * 32-bit mode:
  *
  *   Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
- *   Check that here and ignore it.
+ *   Check that here and ignore it.  This is AMD erratum #91.
  *
  * 64-bit mode:
  *
@@ -101,11 +87,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 #ifdef CONFIG_X86_64
 	case 0x40:
 		/*
-		 * In AMD64 long mode 0x40..0x4F are valid REX prefixes
-		 * Need to figure out under what instruction mode the
-		 * instruction was issued. Could check the LDT for lm,
-		 * but for now it's good enough to assume that long
-		 * mode only uses well known segments or kernel.
+		 * In 64-bit mode 0x40..0x4F are valid REX prefixes
 		 */
 		return (!user_mode(regs) || user_64bit_mode(regs));
 #endif
@@ -117,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 		return !instr_lo || (instr_lo>>1) == 1;
 	case 0x00:
 		/* Prefetch instruction is 0x0F0D or 0x0F18 */
-		if (probe_kernel_address(instr, opcode))
+		if (get_kernel_nofault(opcode, instr))
 			return 0;
 
 		*prefetch = (instr_lo == 0xF) &&
@@ -128,6 +110,15 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
 	}
 }
 
+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)
 {
@@ -135,51 +126,46 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 	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 & PF_INSTR)
+	if (error_code & X86_PF_INSTR)
 		return 0;
 
 	instr = (void *)convert_ip_to_linear(current, regs);
 	max_instr = instr + 15;
 
-	if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
-		return 0;
+	/*
+	 * 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 (probe_kernel_address(instr, opcode))
-			break;
+		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;
 	}
-	return prefetch;
-}
 
-static void
-force_sig_info_fault(int si_signo, int si_code, unsigned long address,
-		     struct task_struct *tsk, int fault)
-{
-	unsigned lsb = 0;
-	siginfo_t info;
-
-	info.si_signo	= si_signo;
-	info.si_errno	= 0;
-	info.si_code	= si_code;
-	info.si_addr	= (void __user *)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;
-	info.si_addr_lsb = lsb;
-
-	force_sig_info(si_signo, &info, tsk);
+	pagefault_enable();
+	return prefetch;
 }
 
 DEFINE_SPINLOCK(pgd_lock);
@@ -190,6 +176,7 @@ 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;
 
@@ -202,63 +189,47 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	/*
 	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
 	 * and redundant with the set_pmd() on non-PAE. As would
-	 * set_pud.
+	 * set_p4d/set_pud.
 	 */
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
+	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_k))
-		return NULL;
 
-	if (!pmd_present(*pmd))
+	if (pmd_present(*pmd) != pmd_present(*pmd_k))
 		set_pmd(pmd, *pmd_k);
+
+	if (!pmd_present(*pmd_k))
+		return NULL;
 	else
-		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
 
 	return pmd_k;
 }
 
-void vmalloc_sync_all(void)
-{
-	unsigned long address;
-
-	if (SHARED_KERNEL_PMD)
-		return;
-
-	for (address = VMALLOC_START & PMD_MASK;
-	     address >= TASK_SIZE && address < FIXADDR_TOP;
-	     address += PMD_SIZE) {
-		struct page *page;
-
-		spin_lock(&pgd_lock);
-		list_for_each_entry(page, &pgd_list, lru) {
-			spinlock_t *pgt_lock;
-			pmd_t *ret;
-
-			/* the pgt_lock only for Xen */
-			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
-
-			spin_lock(pgt_lock);
-			ret = vmalloc_sync_one(page_address(page), address);
-			spin_unlock(pgt_lock);
-
-			if (!ret)
-				break;
-		}
-		spin_unlock(&pgd_lock);
-	}
-}
-
 /*
- * 32-bit:
- *
  *   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 __kprobes int vmalloc_fault(unsigned long address)
+static noinline int vmalloc_fault(unsigned long address)
 {
 	unsigned long pgd_paddr;
 	pmd_t *pmd_k;
@@ -268,8 +239,6 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
@@ -277,33 +246,44 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	 * Do _not_ use "current" here. We might be inside
 	 * an interrupt in the middle of a task switch..
 	 */
-	pgd_paddr = read_cr3();
+	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);
 
-/*
- * Did it hit the DOS screen memory VA from vm86 mode?
- */
-static inline void
-check_v8086_mode(struct pt_regs *regs, unsigned long address,
-		 struct task_struct *tsk)
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
-	unsigned long bit;
+	unsigned long addr;
 
-	if (!v8086_mode(regs))
-		return;
+	for (addr = start & PMD_MASK;
+	     addr >= TASK_SIZE_MAX && addr < VMALLOC_END;
+	     addr += PMD_SIZE) {
+		struct page *page;
+
+		spin_lock(&pgd_lock);
+		list_for_each_entry(page, &pgd_list, lru) {
+			spinlock_t *pgt_lock;
+
+			/* the pgt_lock only for Xen */
+			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 
-	bit = (address - 0xA0000) >> PAGE_SHIFT;
-	if (bit < 32)
-		tsk->thread.screen_bitmap |= 1 << bit;
+			spin_lock(pgt_lock);
+			vmalloc_sync_one(page_address(page), addr);
+			spin_unlock(pgt_lock);
+		}
+		spin_unlock(&pgd_lock);
+	}
 }
 
 static bool low_pfn(unsigned long pfn)
@@ -313,18 +293,26 @@ static bool low_pfn(unsigned long pfn)
 
 static void dump_pagetable(unsigned long address)
 {
-	pgd_t *base = __va(read_cr3());
+	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
-	printk("*pdpt = %016Lx ", pgd_val(*pgd));
+	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
-	pmd = pmd_offset(pud_offset(pgd, address), address);
-	printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd));
+	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
@@ -332,97 +320,17 @@ static void dump_pagetable(unsigned long address)
 	 * 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_large(*pmd))
+	if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd))
 		goto out;
 
 	pte = pte_offset_kernel(pmd, address);
-	printk("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte));
+	pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte));
 out:
-	printk("\n");
+	pr_cont("\n");
 }
 
 #else /* CONFIG_X86_64: */
 
-void vmalloc_sync_all(void)
-{
-	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
-}
-
-/*
- * 64-bit:
- *
- *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
- */
-static noinline __kprobes int vmalloc_fault(unsigned long address)
-{
-	pgd_t *pgd, *pgd_ref;
-	pud_t *pud, *pud_ref;
-	pmd_t *pmd, *pmd_ref;
-	pte_t *pte, *pte_ref;
-
-	/* Make sure we are in vmalloc area: */
-	if (!(address >= VMALLOC_START && address < VMALLOC_END))
-		return -1;
-
-	WARN_ON_ONCE(in_nmi());
-
-	/*
-	 * Copy kernel mappings over when needed. This can also
-	 * happen within a race in page table update. In the later
-	 * case just flush:
-	 */
-	pgd = pgd_offset(current->active_mm, address);
-	pgd_ref = pgd_offset_k(address);
-	if (pgd_none(*pgd_ref))
-		return -1;
-
-	if (pgd_none(*pgd)) {
-		set_pgd(pgd, *pgd_ref);
-		arch_flush_lazy_mmu_mode();
-	} else {
-		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-	}
-
-	/*
-	 * Below here mismatches are bugs because these lower tables
-	 * are shared:
-	 */
-
-	pud = pud_offset(pgd, address);
-	pud_ref = pud_offset(pgd_ref, address);
-	if (pud_none(*pud_ref))
-		return -1;
-
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
-		BUG();
-
-	pmd = pmd_offset(pud, address);
-	pmd_ref = pmd_offset(pud_ref, address);
-	if (pmd_none(*pmd_ref))
-		return -1;
-
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
-		BUG();
-
-	pte_ref = pte_offset_kernel(pmd_ref, address);
-	if (!pte_present(*pte_ref))
-		return -1;
-
-	pte = pte_offset_kernel(pmd, address);
-
-	/*
-	 * Don't use pte_page here, because the mappings can point
-	 * outside mem_map, and the NUMA hash lookup cannot handle
-	 * that:
-	 */
-	if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
-		BUG();
-
-	return 0;
-}
-
 #ifdef CONFIG_CPU_SUP_AMD
 static const char errata93_warning[] =
 KERN_ERR 
@@ -432,26 +340,18 @@ KERN_ERR
 "******* Disabling USB legacy in the BIOS may also help.\n";
 #endif
 
-/*
- * No vm86 mode in 64-bit mode:
- */
-static inline void
-check_v8086_mode(struct pt_regs *regs, unsigned long address,
-		 struct task_struct *tsk)
-{
-}
-
 static int bad_address(void *p)
 {
 	unsigned long dummy;
 
-	return probe_kernel_address((unsigned long *)p, dummy);
+	return get_kernel_nofault(dummy, (unsigned long *)p);
 }
 
 static void dump_pagetable(unsigned long address)
 {
-	pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK);
+	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;
@@ -459,37 +359,45 @@ static void dump_pagetable(unsigned long address)
 	if (bad_address(pgd))
 		goto bad;
 
-	printk("PGD %lx ", pgd_val(*pgd));
+	pr_info("PGD %lx ", pgd_val(*pgd));
 
 	if (!pgd_present(*pgd))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	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;
 
-	printk("PUD %lx ", pud_val(*pud));
-	if (!pud_present(*pud) || pud_large(*pud))
+	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;
 
-	printk("PMD %lx ", pmd_val(*pmd));
-	if (!pmd_present(*pmd) || pmd_large(*pmd))
+	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;
 
-	printk("PTE %lx", pte_val(*pte));
+	pr_cont("PTE %lx", pte_val(*pte));
 out:
-	printk("\n");
+	pr_cont("\n");
 	return;
 bad:
-	printk("BAD\n");
+	pr_info("BAD\n");
 }
 
 #endif /* CONFIG_X86_64 */
@@ -515,6 +423,9 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 	    || boot_cpu_data.x86 != 0xf)
 		return 0;
 
+	if (user_mode(regs))
+		return 0;
+
 	if (address != regs->ip)
 		return 0;
 
@@ -549,56 +460,131 @@ static int is_errata100(struct pt_regs *regs, unsigned long address)
 	return 0;
 }
 
-static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
+/* 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
-	unsigned long nr;
-
-	/*
-	 * Pentium F0 0F C7 C8 bug workaround:
-	 */
-	if (boot_cpu_has_bug(X86_BUG_F00F)) {
-		nr = (address - idt_descr.address) >> 3;
-
-		if (nr == 6) {
-			do_invalid_op(regs, 0);
-			return 1;
-		}
+	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 const char nx_warning[] = KERN_CRIT
-"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
+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)
+show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
 	if (!oops_may_print())
 		return;
 
-	if (error_code & PF_INSTR) {
+	if (error_code & X86_PF_INSTR) {
 		unsigned int level;
-
-		pte_t *pte = lookup_address(address, &level);
-
-		if (pte && pte_present(*pte) && !pte_exec(*pte))
-			printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
+		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()));
 	}
 
-	printk(KERN_ALERT "BUG: unable to handle kernel ");
-	if (address < PAGE_SIZE)
-		printk(KERN_CONT "NULL pointer dereference");
+	if (address < PAGE_SIZE && !user_mode(regs))
+		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
+			(void *)address);
 	else
-		printk(KERN_CONT "paging request");
+		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;
 
-	printk(KERN_CONT " at %p\n", (void *) address);
-	printk(KERN_ALERT "IP:");
-	printk_address(regs->ip, 1);
+		/*
+		 * 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
@@ -617,55 +603,97 @@ pgtable_bad(struct pt_regs *regs, unsigned long error_code,
 	       tsk->comm, address);
 	dump_pagetable(address);
 
-	tsk->thread.cr2		= address;
-	tsk->thread.trap_nr	= X86_TRAP_PF;
-	tsk->thread.error_code	= error_code;
-
 	if (__die("Bad pagetable", regs, error_code))
 		sig = 0;
 
 	oops_end(flags, regs, sig);
 }
 
-static noinline void
-no_context(struct pt_regs *regs, unsigned long error_code,
-	   unsigned long address, int signal, int si_code)
+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;
-	unsigned long *stackend;
+
+	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;
 
-	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs)) {
-		if (current_thread_info()->sig_on_uaccess_error && signal) {
-			tsk->thread.trap_nr = X86_TRAP_PF;
-			tsk->thread.error_code = error_code | PF_USER;
-			tsk->thread.cr2 = address;
-
-			/* XXX: hwpoison faults will set the wrong code. */
-			force_sig_info_fault(signal, si_code, address, tsk, 0);
-		}
-		return;
+	if (user_mode(regs)) {
+		/*
+		 * Implicit kernel access from user mode?  Skip the stack
+		 * overflow and EFI special cases.
+		 */
+		goto oops;
 	}
 
+#ifdef CONFIG_VMAP_STACK
 	/*
-	 * 32-bit:
-	 *
-	 *   Valid to do another page fault here, because if this fault
-	 *   had been triggered by is_prefetch fixup_exception would have
-	 *   handled it.
-	 *
-	 * 64-bit:
-	 *
-	 *   Hall of shame of CPU/BIOS bugs.
+	 * 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_prefetch(regs, error_code, address))
-		return;
+	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
 
-	if (is_errata93(regs, address))
+	/*
+	 * 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);
+
+	/* Only not-present faults should be handled by KFENCE. */
+	if (!(error_code & X86_PF_PROT) &&
+	    kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs))
 		return;
 
+oops:
 	/*
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice:
@@ -674,14 +702,9 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	show_fault_oops(regs, error_code, address);
 
-	stackend = end_of_stack(tsk);
-	if (tsk != &init_task && *stackend != STACK_END_MAGIC)
+	if (task_stack_end_corrupted(current))
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
-	tsk->thread.cr2		= address;
-	tsk->thread.trap_nr	= X86_TRAP_PF;
-	tsk->thread.error_code	= error_code;
-
 	sig = SIGKILL;
 	if (__die("Oops", regs, error_code))
 		sig = 0;
@@ -692,6 +715,27 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	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:
@@ -700,126 +744,175 @@ 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 %p sp %p error %lx",
-		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
-		tsk->comm, task_pid_nr(tsk), address,
+	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, int si_code)
+		       unsigned long address, u32 pkey, int si_code)
 {
 	struct task_struct *tsk = current;
 
-	/* User mode accesses just cause a SIGSEGV */
-	if (error_code & PF_USER) {
-		/*
-		 * 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 (!user_mode(regs)) {
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGSEGV, si_code, pkey);
+		return;
+	}
 
-		if (is_errata100(regs, address))
-			return;
+	if (!(error_code & X86_PF_USER)) {
+		/* Implicit user access to kernel memory -- just oops */
+		page_fault_oops(regs, error_code, address);
+		return;
+	}
 
-#ifdef CONFIG_X86_64
-		/*
-		 * Instruction fetch faults in the vsyscall page might need
-		 * emulation.
-		 */
-		if (unlikely((error_code & PF_INSTR) &&
-			     ((address & ~0xfff) == VSYSCALL_START))) {
-			if (emulate_vsyscall(regs, address))
-				return;
-		}
-#endif
-		/* Kernel addresses are always protection faults: */
-		if (address >= TASK_SIZE)
-			error_code |= PF_PROT;
+	/*
+	 * User mode accesses just cause a SIGSEGV.
+	 * It's possible to have interrupts off here:
+	 */
+	local_irq_enable();
 
-		if (likely(show_unhandled_signals))
-			show_signal_msg(regs, error_code, address, tsk);
+	/*
+	 * Valid to do another page fault here because this one came
+	 * from user space:
+	 */
+	if (is_prefetch(regs, error_code, address))
+		return;
 
-		tsk->thread.cr2		= address;
-		tsk->thread.error_code	= error_code;
-		tsk->thread.trap_nr	= X86_TRAP_PF;
+	if (is_errata100(regs, address))
+		return;
 
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);
+	sanitize_error_code(address, &error_code);
 
+	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
 		return;
-	}
 
-	if (is_f00f_bug(regs, 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);
 
-	no_context(regs, error_code, address, SIGSEGV, si_code);
+	local_irq_disable();
 }
 
 static noinline void
 bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 		     unsigned long address)
 {
-	__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
+	__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, int si_code)
+	   unsigned long address, struct mm_struct *mm,
+	   struct vm_area_struct *vma, u32 pkey, int si_code)
 {
-	struct mm_struct *mm = current->mm;
-
 	/*
 	 * Something tried to access memory that isn't in our memory map..
 	 * Fix it, but check if it's kernel or user first..
 	 */
-	up_read(&mm->mmap_sem);
+	if (mm)
+		mmap_read_unlock(mm);
+	else
+		vma_end_read(vma);
 
-	__bad_area_nosemaphore(regs, error_code, address, si_code);
+	__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
 }
 
-static noinline void
-bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+static inline bool bad_area_access_from_pkeys(unsigned long error_code,
+		struct vm_area_struct *vma)
 {
-	__bad_area(regs, error_code, address, SEGV_MAPERR);
+	/* 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)
+		      unsigned long address, struct mm_struct *mm,
+		      struct vm_area_struct *vma)
 {
-	__bad_area(regs, error_code, address, SEGV_ACCERR);
+	/*
+	 * 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,
-	  unsigned int fault)
+	  vm_fault_t fault)
 {
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
-	int code = BUS_ADRERR;
-
-	up_read(&mm->mmap_sem);
-
 	/* Kernel mode? Handle exceptions or die: */
-	if (!(error_code & PF_USER)) {
-		no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
+	if (!user_mode(regs)) {
+		kernelmode_fixup_or_oops(regs, error_code, address,
+					 SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY);
 		return;
 	}
 
@@ -827,72 +920,38 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	if (is_prefetch(regs, error_code, address))
 		return;
 
-	tsk->thread.cr2		= address;
-	tsk->thread.error_code	= error_code;
-	tsk->thread.trap_nr	= X86_TRAP_PF;
+	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)) {
-		printk(KERN_ERR
+		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);
-		code = BUS_MCEERR_AR;
+		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_info_fault(SIGBUS, code, address, tsk, fault);
+	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
 }
 
-static noinline int
-mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, unsigned int fault)
+static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
 {
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if (fatal_signal_pending(current)) {
-		if (!(fault & VM_FAULT_RETRY))
-			up_read(&current->mm->mmap_sem);
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address, 0, 0);
-		return 1;
-	}
-	if (!(fault & VM_FAULT_ERROR))
+	if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
 		return 0;
 
-	if (fault & VM_FAULT_OOM) {
-		/* Kernel mode? Handle exceptions or die: */
-		if (!(error_code & PF_USER)) {
-			up_read(&current->mm->mmap_sem);
-			no_context(regs, error_code, address,
-				   SIGSEGV, SEGV_MAPERR);
-			return 1;
-		}
-
-		up_read(&current->mm->mmap_sem);
-
-		/*
-		 * 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
-			BUG();
-	}
-	return 1;
-}
-
-static int spurious_fault_check(unsigned long error_code, pte_t *pte)
-{
-	if ((error_code & PF_WRITE) && !pte_write(*pte))
-		return 0;
-
-	if ((error_code & PF_INSTR) && !pte_exec(*pte))
+	if ((error_code & X86_PF_INSTR) && !pte_exec(*pte))
 		return 0;
 
 	return 1;
@@ -907,45 +966,71 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
  * 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 __kprobes int
-spurious_fault(unsigned long error_code, unsigned long address)
+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;
 
-	/* Reserved-bit violation or user access to kernel space? */
-	if (error_code & (PF_USER | PF_RSVD))
+	/*
+	 * 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;
 
-	pud = pud_offset(pgd, address);
+	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_large(*pud))
-		return spurious_fault_check(error_code, (pte_t *) pud);
+	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_large(*pmd))
-		return spurious_fault_check(error_code, (pte_t *) pmd);
+	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_fault_check(error_code, pte);
+	ret = spurious_kernel_fault_check(error_code, pte);
 	if (!ret)
 		return 0;
 
@@ -953,87 +1038,114 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	 * Make sure we have permissions in PMD.
 	 * If not, then there's a bug in the page tables:
 	 */
-	ret = spurious_fault_check(error_code, (pte_t *) pmd);
+	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)
 {
-	if (error_code & PF_WRITE) {
+	/* 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 & PF_PROT))
+	if (unlikely(error_code & X86_PF_PROT))
 		return 1;
 
 	/* read, not present: */
-	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+	if (unlikely(!vma_is_accessible(vma)))
 		return 1;
 
 	return 0;
 }
 
-static int fault_in_kernel_space(unsigned long address)
-{
-	return address >= TASK_SIZE_MAX;
-}
-
-static inline bool smap_violation(int error_code, struct pt_regs *regs)
+bool fault_in_kernel_space(unsigned long address)
 {
-	if (error_code & PF_USER)
-		return false;
-
-	if (!user_mode_vm(regs) && (regs->flags & X86_EFLAGS_AC))
+	/*
+	 * 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 true;
+	return address >= TASK_SIZE_MAX;
 }
 
 /*
- * This routine handles page faults.  It determines the address,
- * and the problem, and then passes it off to one of the appropriate
- * routines.
+ * 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 __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void
+do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
+		   unsigned long address)
 {
-	struct vm_area_struct *vma;
-	struct task_struct *tsk;
-	unsigned long address;
-	struct mm_struct *mm;
-	int fault;
-	int write = error_code & PF_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
-					(write ? FAULT_FLAG_WRITE : 0);
-
-	tsk = current;
-	mm = tsk->mm;
-
-	/* Get the faulting address: */
-	address = read_cr2();
-
 	/*
-	 * Detect and handle instructions that would cause a page fault for
-	 * both a tracked kernel page and a userspace page.
+	 * 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.
 	 */
-	if (kmemcheck_active(regs))
-		kmemcheck_hide(regs);
-	prefetchw(&mm->mmap_sem);
-
-	if (unlikely(kmmio_fault(regs, address)))
-		return;
+	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
 
+#ifdef CONFIG_X86_32
 	/*
-	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 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
@@ -1041,132 +1153,212 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	 * only copy the information from the master page table,
 	 * nothing more.
 	 *
-	 * This verifies that the fault happens in kernel space
-	 * (error_code & 4) == 0, and that the fault was not a
-	 * protection error (error_code & 9) == 0.
+	 * 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 (unlikely(fault_in_kernel_space(address))) {
-		if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) {
-			if (vmalloc_fault(address) >= 0)
-				return;
+	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
+		if (vmalloc_fault(address) >= 0)
+			return;
+	}
+#endif
 
-			if (kmemcheck_fault(regs, address, error_code))
-				return;
-		}
+	if (is_f00f_bug(regs, hw_error_code, address))
+		return;
 
-		/* Can handle a stale RO->RW TLB: */
-		if (spurious_fault(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 (notify_page_fault(regs))
-			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)) {
 		/*
-		 * Don't take the mm semaphore here. If we fixup a prefetch
-		 * fault we could otherwise deadlock:
+		 * 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.
 		 */
-		bad_area_nosemaphore(regs, error_code, address);
+		if (is_errata93(regs, address))
+			return;
 
+		page_fault_oops(regs, error_code, address);
 		return;
 	}
 
 	/* kprobes don't want to hook the spurious faults: */
-	if (unlikely(notify_page_fault(regs)))
+	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
+
 	/*
-	 * It's safe to allow irq's after cr2 has been saved and the
-	 * vmalloc fault has been handled.
-	 *
-	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet:
+	 * Reserved bits are never expected to be set on
+	 * entries in the user portion of the page tables.
 	 */
-	if (user_mode_vm(regs)) {
-		local_irq_enable();
-		error_code |= PF_USER;
-	} else {
-		if (regs->flags & X86_EFLAGS_IF)
-			local_irq_enable();
-	}
-
-	if (unlikely(error_code & PF_RSVD))
+	if (unlikely(error_code & X86_PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	if (static_cpu_has(X86_FEATURE_SMAP)) {
-		if (unlikely(smap_violation(error_code, regs))) {
-			bad_area_nosemaphore(regs, error_code, address);
-			return;
-		}
+	/*
+	 * 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;
 	}
 
-	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
 	/*
 	 * If we're in an interrupt, have no user context or are running
-	 * in an atomic region then we must not take the fault:
+	 * in a region with pagefaults disabled then we must not take the fault
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	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
 	/*
-	 * When running in the kernel we expect faults to occur only to
-	 * addresses in user space.  All other faults represent errors in
-	 * the kernel and should generate an OOPS.  Unfortunately, in the
-	 * case of an erroneous fault occurring in a code path which already
-	 * holds mmap_sem we will deadlock attempting to validate the fault
-	 * against the address space.  Luckily the kernel only validly
-	 * references user space from well defined areas of code, which are
-	 * listed in the exceptions table.
+	 * 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.
 	 *
-	 * As the vast majority of faults will be valid we will only perform
-	 * the source reference check when there is a possibility of a
-	 * deadlock. Attempt to lock the address space, if we cannot we then
-	 * validate the source. If this is invalid we can skip the address
-	 * space check, thus avoiding the deadlock:
+	 * 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 (unlikely(!down_read_trylock(&mm->mmap_sem))) {
-		if ((error_code & PF_USER) == 0 &&
-		    !search_exception_tables(regs->ip)) {
-			bad_area_nosemaphore(regs, error_code, address);
+	if (is_vsyscall_vaddr(address)) {
+		if (emulate_vsyscall(error_code, regs, address))
 			return;
-		}
-retry:
-		down_read(&mm->mmap_sem);
-	} else {
-		/*
-		 * The above down_read_trylock() might have succeeded in
-		 * which case we'll have missed the might_sleep() from
-		 * down_read():
-		 */
-		might_sleep();
 	}
+#endif
 
-	vma = find_vma(mm, address);
-	if (unlikely(!vma)) {
-		bad_area(regs, error_code, address);
+	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;
 	}
-	if (likely(vma->vm_start <= address))
-		goto good_area;
-	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
-		bad_area(regs, error_code, address);
-		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;
 	}
-	if (error_code & PF_USER) {
-		/*
-		 * Accessing the stack below %sp is always a bug.
-		 * The large cushion allows instructions like enter
-		 * and pusha to work. ("enter $65535, $31" pushes
-		 * 32 pointers and then decrements %sp by 65535.)
-		 */
-		if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
-			bad_area(regs, error_code, address);
-			return;
-		}
+	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;
 	}
-	if (unlikely(expand_stack(vma, address))) {
-		bad_area(regs, error_code, address);
+lock_mmap:
+
+retry:
+	vma = lock_mm_and_find_vma(mm, address, regs);
+	if (unlikely(!vma)) {
+		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
@@ -1174,59 +1366,171 @@ retry:
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
 	 */
-good_area:
 	if (unlikely(access_error(error_code, vma))) {
-		bad_area_access_error(regs, error_code, address);
+		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:
+	 * 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(mm, vma, address, flags);
+	fault = handle_mm_fault(vma, address, flags, regs);
 
-	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
-		if (mm_fault_error(regs, error_code, address, fault))
-			return;
+	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;
+
 	/*
-	 * Major/minor page fault accounting is only done on the
-	 * initial attempt. If we go through a retry, it is extremely
-	 * likely that the page will be found in page cache at that point.
+	 * 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 (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_MAJOR) {
-			tsk->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-				      regs, address);
-		} else {
-			tsk->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-				      regs, address);
-		}
-		if (fault & VM_FAULT_RETRY) {
-			/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
-			 * of starvation. */
-			flags &= ~FAULT_FLAG_ALLOW_RETRY;
-			flags |= FAULT_FLAG_TRIED;
-			goto retry;
+	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);
+}
 
-	check_v8086_mode(regs, address, tsk);
+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;
 
-	up_read(&mm->mmap_sem);
+	/* 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);
+		/*
+		 * User address page fault handling might have reenabled
+		 * interrupts. Fixing up all potential exit points of
+		 * do_user_addr_fault() and its leaf functions is just not
+		 * doable w/o creating an unholy mess or turning the code
+		 * upside down.
+		 */
+		local_irq_disable();
+	}
 }
 
-dotraplinkage void __kprobes
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
-	enum ctx_state prev_state;
+	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();
 
-	prev_state = exception_enter();
-	__do_page_fault(regs, error_code);
-	exception_exit(prev_state);
+	irqentry_exit(regs, state);
 }