Merge tag 'x86_mm_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm cleanups from Borislav Petkov:

 - PTRACE_GETREGS/PTRACE_PUTREGS regset selection cleanup

 - Another initial cleanup - more to follow - to the fault handling
   code.

 - Other minor cleanups and corrections.

* tag 'x86_mm_for_v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/{fault,efi}: Fix and rename efi_recover_from_page_fault()
  x86/fault: Don't run fixups for SMAP violations
  x86/fault: Don't look for extable entries for SMEP violations
  x86/fault: Rename no_context() to kernelmode_fixup_or_oops()
  x86/fault: Bypass no_context() for implicit kernel faults from usermode
  x86/fault: Split the OOPS code out from no_context()
  x86/fault: Improve kernel-executing-user-memory handling
  x86/fault: Correct a few user vs kernel checks wrt WRUSS
  x86/fault: Document the locking in the fault_signal_pending() path
  x86/fault/32: Move is_f00f_bug() to do_kern_addr_fault()
  x86/fault: Fold mm_fault_error() into do_user_addr_fault()
  x86/fault: Skip the AMD erratum #91 workaround on unaffected CPUs
  x86/fault: Fix AMD erratum #91 errata fixup for user code
  x86/Kconfig: Remove HPET_EMULATE_RTC depends on RTC
  x86/asm: Fixup TASK_SIZE_MAX comment
  x86/ptrace: Clean up PTRACE_GETREGS/PTRACE_PUTREGS regset selection
  x86/vm86/32: Remove VM86_SCREEN_BITMAP support
  x86: Remove definition of DEBUG
  x86/entry: Remove now unused do_IRQ() declaration
  x86/mm: Remove duplicate definition of _PAGE_PAT_LARGE
  ...

arch/x86/Kconfig

@@ -890,7 +890,7 @@ config HPET_TIMER
 
 config HPET_EMULATE_RTC
 	def_bool y
-	depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y)
+	depends on HPET_TIMER && (RTC_DRV_CMOS=m || RTC_DRV_CMOS=y)
 
 config APB_TIMER
 	def_bool y if X86_INTEL_MID

arch/x86/include/asm/efi.h

@@ -139,7 +139,7 @@ extern void __init efi_dump_pagetable(void);
 extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);
 extern void efi_delete_dummy_variable(void);
-extern void efi_recover_from_page_fault(unsigned long phys_addr);
+extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
 
 void efi_enter_mm(void);

arch/x86/include/asm/irq.h

@@ -40,8 +40,6 @@ extern void native_init_IRQ(void);
 
 extern void __handle_irq(struct irq_desc *desc, struct pt_regs *regs);
 
-extern __visible void do_IRQ(struct pt_regs *regs, unsigned long vector);
-
 extern void init_ISA_irqs(void);
 
 extern void __init init_IRQ(void);

arch/x86/include/asm/page_64_types.h

@@ -66,7 +66,7 @@
  * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
  * address, then that syscall will enter the kernel with a
  * non-canonical return address, and SYSRET will explode dangerously.
- * We avoid this particular problem by preventing anything executable
+ * We avoid this particular problem by preventing anything
  * from being mapped at the maximum canonical address.
  *
  * On AMD CPUs in the Ryzen family, there's a nasty bug in which the

arch/x86/include/asm/pgtable_types.h

@@ -177,8 +177,6 @@ enum page_cache_mode {
 #define __pgprot(x)		((pgprot_t) { (x) } )
 #define __pg(x)			__pgprot(x)
 
-#define _PAGE_PAT_LARGE		(_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
-
 #define PAGE_NONE	     __pg(   0|   0|   0|___A|   0|   0|   0|___G)
 #define PAGE_SHARED	     __pg(__PP|__RW|_USR|___A|__NX|   0|   0|   0)
 #define PAGE_SHARED_EXEC     __pg(__PP|__RW|_USR|___A|   0|   0|   0|   0)

arch/x86/include/asm/vm86.h

@@ -36,7 +36,6 @@ struct vm86 {
 	unsigned long saved_sp0;
 
 	unsigned long flags;
-	unsigned long screen_bitmap;
 	unsigned long cpu_type;
 	struct revectored_struct int_revectored;
 	struct revectored_struct int21_revectored;

arch/x86/include/uapi/asm/vm86.h

@@ -97,7 +97,7 @@ struct revectored_struct {
 struct vm86_struct {
 	struct vm86_regs regs;
 	unsigned long flags;
-	unsigned long screen_bitmap;
+	unsigned long screen_bitmap;		/* unused, preserved by vm86() */
 	unsigned long cpu_type;
 	struct revectored_struct int_revectored;
 	struct revectored_struct int21_revectored;
@@ -106,7 +106,7 @@ struct vm86_struct {
 /*
  * flags masks
  */
-#define VM86_SCREEN_BITMAP	0x0001
+#define VM86_SCREEN_BITMAP	0x0001        /* no longer supported */
 
 struct vm86plus_info_struct {
 	unsigned long force_return_for_pic:1;

arch/x86/kernel/cpu/mtrr/cleanup.c

@@ -537,9 +537,9 @@ static void __init print_out_mtrr_range_state(void)
 		if (!size_base)
 			continue;
 
-		size_base = to_size_factor(size_base, &size_factor),
+		size_base = to_size_factor(size_base, &size_factor);
 		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
-		start_base = to_size_factor(start_base, &start_factor),
+		start_base = to_size_factor(start_base, &start_factor);
 		type = range_state[i].type;
 
 		pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n",

arch/x86/kernel/cpu/mtrr/generic.c

@@ -3,7 +3,6 @@
  * This only handles 32bit MTRR on 32bit hosts. This is strictly wrong
  * because MTRRs can span up to 40 bits (36bits on most modern x86)
  */
-#define DEBUG
 
 #include <linux/export.h>
 #include <linux/init.h>

arch/x86/kernel/cpu/mtrr/mtrr.c

@@ -31,8 +31,6 @@
     System Programming Guide; Section 9.11. (1997 edition - PPro).
 */
 
-#define DEBUG
-
 #include <linux/types.h> /* FIXME: kvm_para.h needs this */
 
 #include <linux/stop_machine.h>

arch/x86/kernel/pci-iommu_table.c

@@ -4,9 +4,6 @@
 #include <linux/string.h>
 #include <linux/kallsyms.h>
 
-
-#define DEBUG 1
-
 static struct iommu_table_entry * __init
 find_dependents_of(struct iommu_table_entry *start,
 		   struct iommu_table_entry *finish,

arch/x86/kernel/ptrace.c

@@ -704,6 +704,9 @@ void ptrace_disable(struct task_struct *child)
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 static const struct user_regset_view user_x86_32_view; /* Initialized below. */
 #endif
+#ifdef CONFIG_X86_64
+static const struct user_regset_view user_x86_64_view; /* Initialized below. */
+#endif
 
 long arch_ptrace(struct task_struct *child, long request,
 		 unsigned long addr, unsigned long data)
@@ -711,6 +714,14 @@ long arch_ptrace(struct task_struct *child, long request,
 	int ret;
 	unsigned long __user *datap = (unsigned long __user *)data;
 
+#ifdef CONFIG_X86_64
+	/* This is native 64-bit ptrace() */
+	const struct user_regset_view *regset_view = &user_x86_64_view;
+#else
+	/* This is native 32-bit ptrace() */
+	const struct user_regset_view *regset_view = &user_x86_32_view;
+#endif
+
 	switch (request) {
 	/* read the word at location addr in the USER area. */
 	case PTRACE_PEEKUSR: {
@@ -749,28 +760,28 @@ long arch_ptrace(struct task_struct *child, long request,
 
 	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
 		return copy_regset_to_user(child,
-					   task_user_regset_view(current),
+					   regset_view,
 					   REGSET_GENERAL,
 					   0, sizeof(struct user_regs_struct),
 					   datap);
 
 	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
 		return copy_regset_from_user(child,
-					     task_user_regset_view(current),
+					     regset_view,
 					     REGSET_GENERAL,
 					     0, sizeof(struct user_regs_struct),
 					     datap);
 
 	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
 		return copy_regset_to_user(child,
-					   task_user_regset_view(current),
+					   regset_view,
 					   REGSET_FP,
 					   0, sizeof(struct user_i387_struct),
 					   datap);
 
 	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
 		return copy_regset_from_user(child,
-					     task_user_regset_view(current),
+					     regset_view,
 					     REGSET_FP,
 					     0, sizeof(struct user_i387_struct),
 					     datap);
@@ -1152,28 +1163,28 @@ static long x32_arch_ptrace(struct task_struct *child,
 
 	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
 		return copy_regset_to_user(child,
-					   task_user_regset_view(current),
+					   &user_x86_64_view,
 					   REGSET_GENERAL,
 					   0, sizeof(struct user_regs_struct),
 					   datap);
 
 	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
 		return copy_regset_from_user(child,
-					     task_user_regset_view(current),
+					     &user_x86_64_view,
 					     REGSET_GENERAL,
 					     0, sizeof(struct user_regs_struct),
 					     datap);
 
 	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
 		return copy_regset_to_user(child,
-					   task_user_regset_view(current),
+					   &user_x86_64_view,
 					   REGSET_FP,
 					   0, sizeof(struct user_i387_struct),
 					   datap);
 
 	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
 		return copy_regset_from_user(child,
-					     task_user_regset_view(current),
+					     &user_x86_64_view,
 					     REGSET_FP,
 					     0, sizeof(struct user_i387_struct),
 					     datap);
@@ -1309,6 +1320,25 @@ void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask)
 	xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask;
 }
 
+/*
+ * This is used by the core dump code to decide which regset to dump.  The
+ * core dump code writes out the resulting .e_machine and the corresponding
+ * regsets.  This is suboptimal if the task is messing around with its CS.L
+ * field, but at worst the core dump will end up missing some information.
+ *
+ * Unfortunately, it is also used by the broken PTRACE_GETREGSET and
+ * PTRACE_SETREGSET APIs.  These APIs look at the .regsets field but have
+ * no way to make sure that the e_machine they use matches the caller's
+ * expectations.  The result is that the data format returned by
+ * PTRACE_GETREGSET depends on the returned CS field (and even the offset
+ * of the returned CS field depends on its value!) and the data format
+ * accepted by PTRACE_SETREGSET is determined by the old CS value.  The
+ * upshot is that it is basically impossible to use these APIs correctly.
+ *
+ * The best way to fix it in the long run would probably be to add new
+ * improved ptrace() APIs to read and write registers reliably, possibly by
+ * allowing userspace to select the ELF e_machine variant that they expect.
+ */
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
 #ifdef CONFIG_IA32_EMULATION

arch/x86/kernel/sys_x86_64.c

@@ -90,14 +90,10 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
 		unsigned long, fd, unsigned long, off)
 {
-	long error;
-	error = -EINVAL;
 	if (off & ~PAGE_MASK)
-		goto out;
+		return -EINVAL;
 
-	error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
-out:
-	return error;
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
 }
 
 static void find_start_end(unsigned long addr, unsigned long flags,

arch/x86/kernel/vm86_32.c

@@ -134,7 +134,11 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	unsafe_put_user(regs->ds, &user->regs.ds, Efault_end);
 	unsafe_put_user(regs->fs, &user->regs.fs, Efault_end);
 	unsafe_put_user(regs->gs, &user->regs.gs, Efault_end);
-	unsafe_put_user(vm86->screen_bitmap, &user->screen_bitmap, Efault_end);
+
+	/*
+	 * Don't write screen_bitmap in case some user had a value there
+	 * and expected it to remain unchanged.
+	 */
 
 	user_access_end();
 
@@ -160,49 +164,6 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	do_exit(SIGSEGV);
 }
 
-static void mark_screen_rdonly(struct mm_struct *mm)
-{
-	struct vm_area_struct *vma;
-	spinlock_t *ptl;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	int i;
-
-	mmap_write_lock(mm);
-	pgd = pgd_offset(mm, 0xA0000);
-	if (pgd_none_or_clear_bad(pgd))
-		goto out;
-	p4d = p4d_offset(pgd, 0xA0000);
-	if (p4d_none_or_clear_bad(p4d))
-		goto out;
-	pud = pud_offset(p4d, 0xA0000);
-	if (pud_none_or_clear_bad(pud))
-		goto out;
-	pmd = pmd_offset(pud, 0xA0000);
-
-	if (pmd_trans_huge(*pmd)) {
-		vma = find_vma(mm, 0xA0000);
-		split_huge_pmd(vma, pmd, 0xA0000);
-	}
-	if (pmd_none_or_clear_bad(pmd))
-		goto out;
-	pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);
-	for (i = 0; i < 32; i++) {
-		if (pte_present(*pte))
-			set_pte(pte, pte_wrprotect(*pte));
-		pte++;
-	}
-	pte_unmap_unlock(pte, ptl);
-out:
-	mmap_write_unlock(mm);
-	flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false);
-}
-
-
-
 static int do_vm86_irq_handling(int subfunction, int irqnumber);
 static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus);
 
@@ -282,6 +243,15 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 			offsetof(struct vm86_struct, int_revectored)))
 		return -EFAULT;
 
+
+	/* VM86_SCREEN_BITMAP had numerous bugs and appears to have no users. */
+	if (v.flags & VM86_SCREEN_BITMAP) {
+		char comm[TASK_COMM_LEN];
+
+		pr_info_once("vm86: '%s' uses VM86_SCREEN_BITMAP, which is no longer supported\n", get_task_comm(comm, current));
+		return -EINVAL;
+	}
+
 	memset(&vm86regs, 0, sizeof(vm86regs));
 
 	vm86regs.pt.bx = v.regs.ebx;
@@ -302,7 +272,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	vm86regs.gs = v.regs.gs;
 
 	vm86->flags = v.flags;
-	vm86->screen_bitmap = v.screen_bitmap;
 	vm86->cpu_type = v.cpu_type;
 
 	if (copy_from_user(&vm86->int_revectored,
@@ -370,9 +339,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	update_task_stack(tsk);
 	preempt_enable();
 
-	if (vm86->flags & VM86_SCREEN_BITMAP)
-		mark_screen_rdonly(tsk->mm);
-
 	memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs));
 	return regs->ax;
 }

arch/x86/mm/fault.c

@@ -16,7 +16,7 @@
 #include <linux/prefetch.h>		/* prefetchw			*/
 #include <linux/context_tracking.h>	/* exception_enter(), ...	*/
 #include <linux/uaccess.h>		/* faulthandler_disabled()	*/
-#include <linux/efi.h>			/* efi_recover_from_page_fault()*/
+#include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
 #include <linux/mm_types.h>
 
 #include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
@@ -25,7 +25,7 @@
 #include <asm/vsyscall.h>		/* emulate_vsyscall		*/
 #include <asm/vm86.h>			/* struct vm86			*/
 #include <asm/mmu_context.h>		/* vma_pkey()			*/
-#include <asm/efi.h>			/* efi_recover_from_page_fault()*/
+#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, ...		*/
@@ -54,7 +54,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
  * 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:
  *
@@ -83,11 +83,7 @@ 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
@@ -110,6 +106,15 @@ 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)
 {
@@ -117,6 +122,10 @@ 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:
@@ -127,20 +136,31 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
 	instr = (void *)convert_ip_to_linear(current, regs);
 	max_instr = instr + 15;
 
-	if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE_MAX)
-		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 (get_kernel_nofault(opcode, instr))
-			break;
+		if (user_mode(regs)) {
+			if (get_user(opcode, instr))
+				break;
+		} else {
+			if (get_kernel_nofault(opcode, instr))
+				break;
+		}
 
 		instr++;
 
 		if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
 			break;
 	}
+
+	pagefault_enable();
 	return prefetch;
 }
 
@@ -262,25 +282,6 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 	}
 }
 
-/*
- * 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)
-{
-#ifdef CONFIG_VM86
-	unsigned long bit;
-
-	if (!v8086_mode(regs) || !tsk->thread.vm86)
-		return;
-
-	bit = (address - 0xA0000) >> PAGE_SHIFT;
-	if (bit < 32)
-		tsk->thread.vm86->screen_bitmap |= 1 << bit;
-#endif
-}
-
 static bool low_pfn(unsigned long pfn)
 {
 	return pfn < max_low_pfn;
@@ -335,15 +336,6 @@ 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;
@@ -427,6 +419,9 @@ 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;
 
@@ -462,10 +457,12 @@ static int is_errata100(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 address)
+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) && idt_is_f00f_address(address)) {
+	if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) &&
+	    idt_is_f00f_address(address)) {
 		handle_invalid_op(regs);
 		return 1;
 	}
@@ -630,53 +627,20 @@ static void set_signal_archinfo(unsigned long address,
 }
 
 static noinline void
-no_context(struct pt_regs *regs, unsigned long error_code,
-	   unsigned long address, int signal, int si_code)
+page_fault_oops(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
-	struct task_struct *tsk = current;
 	unsigned long flags;
 	int sig;
 
 	if (user_mode(regs)) {
 		/*
-		 * This is an implicit supervisor-mode access from user
-		 * mode.  Bypass all the kernel-mode recovery code and just
-		 * OOPS.
+		 * Implicit kernel access from user mode?  Skip the stack
+		 * overflow and EFI special cases.
 		 */
 		goto oops;
 	}
 
-	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
-		/*
-		 * Any interrupt that takes a fault gets the fixup. This makes
-		 * the below recursive fault logic only apply to a faults from
-		 * task context.
-		 */
-		if (in_interrupt())
-			return;
-
-		/*
-		 * Per the above we're !in_interrupt(), aka. task context.
-		 *
-		 * In this case we need to make sure we're not recursively
-		 * faulting through the emulate_vsyscall() logic.
-		 */
-		if (current->thread.sig_on_uaccess_err && signal) {
-			sanitize_error_code(address, &error_code);
-
-			set_signal_archinfo(address, error_code);
-
-			/* XXX: hwpoison faults will set the wrong code. */
-			force_sig_fault(signal, si_code, (void __user *)address);
-		}
-
-		/*
-		 * Barring that, we can do the fixup and be happy.
-		 */
-		return;
-	}
-
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Stack overflow?  During boot, we can fault near the initial
@@ -684,8 +648,8 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	 * that we're in vmalloc space to avoid this.
 	 */
 	if (is_vmalloc_addr((void *)address) &&
-	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
-	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
+	    (((unsigned long)current->stack - 1 - address < PAGE_SIZE) ||
+	     address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) {
 		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
 		/*
 		 * We're likely to be running with very little stack space
@@ -709,28 +673,12 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 #endif
 
 	/*
-	 * 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.
-	 */
-	if (is_prefetch(regs, error_code, address))
-		return;
-
-	if (is_errata93(regs, address))
-		return;
-
-	/*
-	 * Buggy firmware could access regions which might page fault, try to
-	 * recover from such faults.
+	 * 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_recover_from_page_fault(address);
+		efi_crash_gracefully_on_page_fault(address);
 
 oops:
 	/*
@@ -741,7 +689,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	show_fault_oops(regs, error_code, address);
 
-	if (task_stack_end_corrupted(tsk))
+	if (task_stack_end_corrupted(current))
 		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
 
 	sig = SIGKILL;
@@ -754,6 +702,53 @@ 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)
+{
+	WARN_ON_ONCE(user_mode(regs));
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
+		/*
+		 * Any interrupt that takes a fault gets the fixup. This makes
+		 * the below recursive fault logic only apply to a faults from
+		 * task context.
+		 */
+		if (in_interrupt())
+			return;
+
+		/*
+		 * Per the above we're !in_interrupt(), aka. task context.
+		 *
+		 * In this case we need to make sure we're not recursively
+		 * faulting through the emulate_vsyscall() logic.
+		 */
+		if (current->thread.sig_on_uaccess_err && signal) {
+			sanitize_error_code(address, &error_code);
+
+			set_signal_archinfo(address, error_code);
+
+			/* XXX: hwpoison faults will set the wrong code. */
+			force_sig_fault(signal, si_code, (void __user *)address);
+		}
+
+		/*
+		 * Barring that, we can do the fixup and be happy.
+		 */
+		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:
@@ -796,47 +791,49 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 {
 	struct task_struct *tsk = current;
 
-	/* User mode accesses just cause a SIGSEGV */
-	if (user_mode(regs) && (error_code & X86_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, pkey, si_code);
+		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;
+	}
 
-		sanitize_error_code(address, &error_code);
+	/*
+	 * User mode accesses just cause a SIGSEGV.
+	 * It's possible to have interrupts off here:
+	 */
+	local_irq_enable();
 
-		if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
-			return;
+	/*
+	 * Valid to do another page fault here because this one came
+	 * from user space:
+	 */
+	if (is_prefetch(regs, error_code, address))
+		return;
 
-		if (likely(show_unhandled_signals))
-			show_signal_msg(regs, error_code, address, tsk);
+	if (is_errata100(regs, address))
+		return;
 
-		set_signal_archinfo(address, error_code);
+	sanitize_error_code(address, &error_code);
 
-		if (si_code == SEGV_PKUERR)
-			force_sig_pkuerr((void __user *)address, pkey);
+	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
+		return;
 
-		force_sig_fault(SIGSEGV, si_code, (void __user *)address);
+	if (likely(show_unhandled_signals))
+		show_signal_msg(regs, error_code, address, tsk);
 
-		local_irq_disable();
+	set_signal_archinfo(address, error_code);
 
-		return;
-	}
+	if (si_code == SEGV_PKUERR)
+		force_sig_pkuerr((void __user *)address, pkey);
 
-	if (is_f00f_bug(regs, address))
-		return;
+	force_sig_fault(SIGSEGV, si_code, (void __user *)address);
 
-	no_context(regs, error_code, address, SIGSEGV, si_code);
+	local_irq_disable();
 }
 
 static noinline void
@@ -926,8 +923,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	  vm_fault_t fault)
 {
 	/* Kernel mode? Handle exceptions or die: */
-	if (!(error_code & X86_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);
 		return;
 	}
 
@@ -961,40 +958,6 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
 }
 
-static noinline void
-mm_fault_error(struct pt_regs *regs, unsigned long error_code,
-	       unsigned long address, vm_fault_t fault)
-{
-	if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) {
-		no_context(regs, error_code, address, 0, 0);
-		return;
-	}
-
-	if (fault & VM_FAULT_OOM) {
-		/* Kernel mode? Handle exceptions or die: */
-		if (!(error_code & X86_PF_USER)) {
-			no_context(regs, error_code, address,
-				   SIGSEGV, SEGV_MAPERR);
-			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();
-	}
-}
-
 static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
 {
 	if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
@@ -1209,6 +1172,9 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 	}
 #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;
@@ -1229,10 +1195,17 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 }
 NOKPROBE_SYMBOL(do_kern_addr_fault);
 
-/* Handle faults in the user portion of the address space */
+/*
+ * 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 hw_error_code,
+			unsigned long error_code,
 			unsigned long address)
 {
 	struct vm_area_struct *vma;
@@ -1244,6 +1217,21 @@ void do_user_addr_fault(struct pt_regs *regs,
 	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 (unlikely(kprobe_page_fault(regs, X86_TRAP_PF)))
 		return;
@@ -1252,8 +1240,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * Reserved bits are never expected to be set on
 	 * entries in the user portion of the page tables.
 	 */
-	if (unlikely(hw_error_code & X86_PF_RSVD))
-		pgtable_bad(regs, hw_error_code, address);
+	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
@@ -1263,10 +1251,13 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * enforcement appears to be consistent with the USER bit.
 	 */
 	if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) &&
-		     !(hw_error_code & X86_PF_USER) &&
-		     !(regs->flags & X86_EFLAGS_AC)))
-	{
-		bad_area_nosemaphore(regs, hw_error_code, address);
+		     !(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;
 	}
 
@@ -1275,7 +1266,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * in a region with pagefaults disabled then we must not take the fault
 	 */
 	if (unlikely(faulthandler_disabled() || !mm)) {
-		bad_area_nosemaphore(regs, hw_error_code, address);
+		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
@@ -1296,9 +1287,9 @@ void do_user_addr_fault(struct pt_regs *regs,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
-	if (hw_error_code & X86_PF_WRITE)
+	if (error_code & X86_PF_WRITE)
 		flags |= FAULT_FLAG_WRITE;
-	if (hw_error_code & X86_PF_INSTR)
+	if (error_code & X86_PF_INSTR)
 		flags |= FAULT_FLAG_INSTRUCTION;
 
 #ifdef CONFIG_X86_64
@@ -1314,7 +1305,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * to consider the PF_PK bit.
 	 */
 	if (is_vsyscall_vaddr(address)) {
-		if (emulate_vsyscall(hw_error_code, regs, address))
+		if (emulate_vsyscall(error_code, regs, address))
 			return;
 	}
 #endif
@@ -1337,7 +1328,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 			 * Fault from code in kernel from
 			 * which we do not expect faults.
 			 */
-			bad_area_nosemaphore(regs, hw_error_code, address);
+			bad_area_nosemaphore(regs, error_code, address);
 			return;
 		}
 retry:
@@ -1353,17 +1344,17 @@ void do_user_addr_fault(struct pt_regs *regs,
 
 	vma = find_vma(mm, address);
 	if (unlikely(!vma)) {
-		bad_area(regs, hw_error_code, address);
+		bad_area(regs, error_code, address);
 		return;
 	}
 	if (likely(vma->vm_start <= address))
 		goto good_area;
 	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
-		bad_area(regs, hw_error_code, address);
+		bad_area(regs, error_code, address);
 		return;
 	}
 	if (unlikely(expand_stack(vma, address))) {
-		bad_area(regs, hw_error_code, address);
+		bad_area(regs, error_code, address);
 		return;
 	}
 
@@ -1372,8 +1363,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * we can handle it..
 	 */
 good_area:
-	if (unlikely(access_error(hw_error_code, vma))) {
-		bad_area_access_error(regs, hw_error_code, address, vma);
+	if (unlikely(access_error(error_code, vma))) {
+		bad_area_access_error(regs, error_code, address, vma);
 		return;
 	}
 
@@ -1392,11 +1383,14 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 */
 	fault = handle_mm_fault(vma, address, flags, regs);
 
-	/* Quick path to respond to signals */
 	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))
-			no_context(regs, hw_error_code, address, SIGBUS,
-				   BUS_ADRERR);
+			kernelmode_fixup_or_oops(regs, error_code, address,
+						 SIGBUS, BUS_ADRERR);
 		return;
 	}
 
@@ -1412,12 +1406,37 @@ void do_user_addr_fault(struct pt_regs *regs,
 	}
 
 	mmap_read_unlock(mm);
-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, hw_error_code, address, fault);
+	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);
 		return;
 	}
 
-	check_v8086_mode(regs, address, tsk);
+	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);
+			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);
 

arch/x86/mm/init.c

@@ -157,16 +157,25 @@ __ref void *alloc_low_pages(unsigned int num)
 }
 
 /*
- * By default need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS.
- * With KASLR memory randomization, depending on the machine e820 memory
- * and the PUD alignment. We may need twice more pages when KASLR memory
+ * 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.
  */
+
+#ifndef CONFIG_X86_5LEVEL
+#define INIT_PGD_PAGE_TABLES    3
+#else
+#define INIT_PGD_PAGE_TABLES    4
+#endif
+
 #ifndef CONFIG_RANDOMIZE_MEMORY
-#define INIT_PGD_PAGE_COUNT      6
+#define INIT_PGD_PAGE_COUNT      (2 * INIT_PGD_PAGE_TABLES)
 #else
-#define INIT_PGD_PAGE_COUNT      12
+#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)

arch/x86/mm/mmio-mod.c

@@ -10,8 +10,6 @@
 
 #define pr_fmt(fmt) "mmiotrace: " fmt
 
-#define DEBUG 1
-
 #include <linux/moduleparam.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>

arch/x86/platform/efi/quirks.c

@@ -687,15 +687,25 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
  * @return: Returns, if the page fault is not handled. This function
  * will never return if the page fault is handled successfully.
  */
-void efi_recover_from_page_fault(unsigned long phys_addr)
+void efi_crash_gracefully_on_page_fault(unsigned long phys_addr)
 {
 	if (!IS_ENABLED(CONFIG_X86_64))
 		return;
 
+	/*
+	 * If we get an interrupt/NMI while processing an EFI runtime service
+	 * then this is a regular OOPS, not an EFI failure.
+	 */
+	if (in_interrupt())
+		return;
+
 	/*
 	 * Make sure that an efi runtime service caused the page fault.
+	 * READ_ONCE() because we might be OOPSing in a different thread,
+	 * and we don't want to trip KTSAN while trying to OOPS.
 	 */
-	if (efi_rts_work.efi_rts_id == EFI_NONE)
+	if (READ_ONCE(efi_rts_work.efi_rts_id) == EFI_NONE ||
+	    current_work() != &efi_rts_work.work)
 		return;
 
 	/*
@@ -747,6 +757,4 @@ void efi_recover_from_page_fault(unsigned long phys_addr)
 		set_current_state(TASK_IDLE);
 		schedule();
 	}
-
-	return;
 }