17 files changed, 374 insertions, 253 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 3790a66d6898..acdf06bc418b 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1194,6 +1194,10 @@ static efi_status_t setup_e820(struct boot_params *params,
 		unsigned int e820_type = 0;
 		unsigned long m = efi->efi_memmap;
 
+#ifdef CONFIG_X86_64
+		m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
 		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a94b82e8f156..69126184c609 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@ static inline void clear_LDT(void)
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 876e74e8eec7..b6b7bc3f5d26 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+	struct ldt_struct *ldt;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 166af2a8e865..23e0625a6183 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -20,6 +20,50 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
 #endif	/* !CONFIG_PARAVIRT */
 
 /*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -55,7 +99,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -77,7 +121,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 			 */
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7bc49c3b9684..e757fcbe90db 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1383,7 +1383,7 @@ void cpu_init(void)
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1426,7 +1426,7 @@ void cpu_init(void)
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6b5acd5f4a34..c832e9f54cd6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -32,6 +32,7 @@
 #include <asm/smp.h>
 #include <asm/alternative.h>
 #include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
 #include <asm/timer.h>
 #include <asm/desc.h>
 #include <asm/ldt.h>
@@ -1987,21 +1988,25 @@ static unsigned long get_segment_base(unsigned int segment)
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = raw_cpu_ptr(gdt_page.gdt);
+		desc = raw_cpu_ptr(gdt_page.gdt) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e36d9815ef56..fad5cd9d7c4b 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1459,20 +1459,77 @@ ENTRY(nmi)
 	 * a nested NMI that updated the copy interrupt stack frame, a
 	 * jump will be made to the repeat_nmi code that will handle the second
 	 * NMI.
+	 *
+	 * However, espfix prevents us from directly returning to userspace
+	 * with a single IRET instruction.  Similarly, IRET to user mode
+	 * can fault.  We therefore handle NMIs from user space like
+	 * other IST entries.
 	 */
 
 	/* Use %rdx as out temp variable throughout */
 	pushq_cfi %rdx
 	CFI_REL_OFFSET rdx, 0
 
+	testb	$3, CS-RIP+8(%rsp)
+	jz	.Lnmi_from_kernel
+
+	/*
+	 * NMI from user mode.  We need to run on the thread stack, but we
+	 * can't go through the normal entry paths: NMIs are masked, and
+	 * we don't want to enable interrupts, because then we'll end
+	 * up in an awkward situation in which IRQs are on but NMIs
+	 * are off.
+	 */
+
+	SWAPGS
+	cld
+	movq	%rsp, %rdx
+	movq	PER_CPU_VAR(kernel_stack), %rsp
+	addq	$KERNEL_STACK_OFFSET, %rsp
+	pushq	5*8(%rdx)	/* pt_regs->ss */
+	pushq	4*8(%rdx)	/* pt_regs->rsp */
+	pushq	3*8(%rdx)	/* pt_regs->flags */
+	pushq	2*8(%rdx)	/* pt_regs->cs */
+	pushq	1*8(%rdx)	/* pt_regs->rip */
+	pushq   $-1		/* pt_regs->orig_ax */
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	pushq   (%rdx)		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   %rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	pushq	%rbx		/* pt_regs->rbx */
+	pushq	%rbp		/* pt_regs->rbp */
+	pushq	%r12		/* pt_regs->r12 */
+	pushq	%r13		/* pt_regs->r13 */
+	pushq	%r14		/* pt_regs->r14 */
+	pushq	%r15		/* pt_regs->r15 */
+
 	/*
-	 * If %cs was not the kernel segment, then the NMI triggered in user
-	 * space, which means it is definitely not nested.
+	 * At this point we no longer need to worry about stack damage
+	 * due to nesting -- we're on the normal thread stack and we're
+	 * done with the NMI stack.
 	 */
-	cmpl $__KERNEL_CS, 16(%rsp)
-	jne first_nmi
+
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
 
 	/*
+	 * Return back to user mode.  We must *not* do the normal exit
+	 * work, because we don't want to enable interrupts.  Fortunately,
+	 * do_nmi doesn't modify pt_regs.
+	 */
+	SWAPGS
+
+	addq	$6*8, %rsp	/* skip bx, bp, and r12-r15 */
+	jmp	restore_args
+
+.Lnmi_from_kernel:
+	/*
 	 * Check the special variable on the stack to see if NMIs are
 	 * executing.
 	 */
@@ -1629,29 +1686,11 @@ end_repeat_nmi:
 	call save_paranoid
 	DEFAULT_FRAME 0
 
-	/*
-	 * Save off the CR2 register. If we take a page fault in the NMI then
-	 * it could corrupt the CR2 value. If the NMI preempts a page fault
-	 * handler before it was able to read the CR2 register, and then the
-	 * NMI itself takes a page fault, the page fault that was preempted
-	 * will read the information from the NMI page fault and not the
-	 * origin fault. Save it off and restore it if it changes.
-	 * Use the r12 callee-saved register.
-	 */
-	movq %cr2, %r12
-
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq %rsp,%rdi
 	movq $-1,%rsi
 	call do_nmi
 
-	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq %cr2, %rcx
-	cmpq %rcx, %r12
-	je 1f
-	movq %r12, %cr2
-1:
-	
 	testl %ebx,%ebx				/* swapgs needed? */
 	jnz nmi_restore
 nmi_swapgs:
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d759cc..2bcc0525f1c1 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
-
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	struct ldt_struct *new_ldt;
+	int alloc_size;
+
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
-
-	if (!newldt)
-		return -ENOMEM;
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
+	}
 
-	paravirt_alloc_ldt(newldt, mincount);
+	new_ldt->size = size;
+	return new_ldt;
+}
 
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
-	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
+{
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
+
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
 
-	if (err < 0)
-		return err;
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@ static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index c3e985d1751c..5c5ec7d28d9b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -408,15 +408,15 @@ static void default_do_nmi(struct pt_regs *regs)
 NOKPROBE_SYMBOL(default_do_nmi);
 
 /*
- * NMIs can hit breakpoints which will cause it to lose its
- * NMI context with the CPU when the breakpoint does an iret.
- */
-#ifdef CONFIG_X86_32
-/*
- * For i386, NMIs use the same stack as the kernel, and we can
- * add a workaround to the iret problem in C (preventing nested
- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
- * can be in:
+ * NMIs can hit breakpoints which will cause it to lose its NMI context
+ * with the CPU when the breakpoint or page fault does an IRET.
+ *
+ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
+ * NMI processing.  On x86_64, the asm glue protects us from nested NMIs
+ * if the outer NMI came from kernel mode, but we can still nest if the
+ * outer NMI came from user mode.
+ *
+ * To handle these nested NMIs, we have three states:
  *
  *  1) not running
  *  2) executing
@@ -430,15 +430,14 @@ NOKPROBE_SYMBOL(default_do_nmi);
  * (Note, the latch is binary, thus multiple NMIs triggering,
  *  when one is running, are ignored. Only one NMI is restarted.)
  *
- * If an NMI hits a breakpoint that executes an iret, another
- * NMI can preempt it. We do not want to allow this new NMI
- * to run, but we want to execute it when the first one finishes.
- * We set the state to "latched", and the exit of the first NMI will
- * perform a dec_return, if the result is zero (NOT_RUNNING), then
- * it will simply exit the NMI handler. If not, the dec_return
- * would have set the state to NMI_EXECUTING (what we want it to
- * be when we are running). In this case, we simply jump back
- * to rerun the NMI handler again, and restart the 'latched' NMI.
+ * If an NMI executes an iret, another NMI can preempt it. We do not
+ * want to allow this new NMI to run, but we want to execute it when the
+ * first one finishes.  We set the state to "latched", and the exit of
+ * the first NMI will perform a dec_return, if the result is zero
+ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
+ * dec_return would have set the state to NMI_EXECUTING (what we want it
+ * to be when we are running). In this case, we simply jump back to
+ * rerun the NMI handler again, and restart the 'latched' NMI.
  *
  * No trap (breakpoint or page fault) should be hit before nmi_restart,
  * thus there is no race between the first check of state for NOT_RUNNING
@@ -461,49 +460,36 @@ enum nmi_states {
 static DEFINE_PER_CPU(enum nmi_states, nmi_state);
 static DEFINE_PER_CPU(unsigned long, nmi_cr2);
 
-#define nmi_nesting_preprocess(regs)					\
-	do {								\
-		if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {	\
-			this_cpu_write(nmi_state, NMI_LATCHED);		\
-			return;						\
-		}							\
-		this_cpu_write(nmi_state, NMI_EXECUTING);		\
-		this_cpu_write(nmi_cr2, read_cr2());			\
-	} while (0);							\
-	nmi_restart:
-
-#define nmi_nesting_postprocess()					\
-	do {								\
-		if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))	\
-			write_cr2(this_cpu_read(nmi_cr2));		\
-		if (this_cpu_dec_return(nmi_state))			\
-			goto nmi_restart;				\
-	} while (0)
-#else /* x86_64 */
+#ifdef CONFIG_X86_64
 /*
- * In x86_64 things are a bit more difficult. This has the same problem
- * where an NMI hitting a breakpoint that calls iret will remove the
- * NMI context, allowing a nested NMI to enter. What makes this more
- * difficult is that both NMIs and breakpoints have their own stack.
- * When a new NMI or breakpoint is executed, the stack is set to a fixed
- * point. If an NMI is nested, it will have its stack set at that same
- * fixed address that the first NMI had, and will start corrupting the
- * stack. This is handled in entry_64.S, but the same problem exists with
- * the breakpoint stack.
+ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint.  Without
+ * some care, the inner breakpoint will clobber the outer breakpoint's
+ * stack.
  *
- * If a breakpoint is being processed, and the debug stack is being used,
- * if an NMI comes in and also hits a breakpoint, the stack pointer
- * will be set to the same fixed address as the breakpoint that was
- * interrupted, causing that stack to be corrupted. To handle this case,
- * check if the stack that was interrupted is the debug stack, and if
- * so, change the IDT so that new breakpoints will use the current stack
- * and not switch to the fixed address. On return of the NMI, switch back
- * to the original IDT.
+ * If a breakpoint is being processed, and the debug stack is being
+ * used, if an NMI comes in and also hits a breakpoint, the stack
+ * pointer will be set to the same fixed address as the breakpoint that
+ * was interrupted, causing that stack to be corrupted. To handle this
+ * case, check if the stack that was interrupted is the debug stack, and
+ * if so, change the IDT so that new breakpoints will use the current
+ * stack and not switch to the fixed address. On return of the NMI,
+ * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+#endif
 
-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+dotraplinkage notrace __kprobes void
+do_nmi(struct pt_regs *regs, long error_code)
 {
+	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
+		this_cpu_write(nmi_state, NMI_LATCHED);
+		return;
+	}
+	this_cpu_write(nmi_state, NMI_EXECUTING);
+	this_cpu_write(nmi_cr2, read_cr2());
+nmi_restart:
+
+#ifdef CONFIG_X86_64
 	/*
 	 * If we interrupted a breakpoint, it is possible that
 	 * the nmi handler will have breakpoints too. We need to
@@ -514,22 +500,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
 		debug_stack_set_zero();
 		this_cpu_write(update_debug_stack, 1);
 	}
-}
-
-static inline void nmi_nesting_postprocess(void)
-{
-	if (unlikely(this_cpu_read(update_debug_stack))) {
-		debug_stack_reset();
-		this_cpu_write(update_debug_stack, 0);
-	}
-}
 #endif
 
-dotraplinkage notrace void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_nesting_preprocess(regs);
-
 	nmi_enter();
 
 	inc_irq_stat(__nmi_count);
@@ -539,8 +511,17 @@ do_nmi(struct pt_regs *regs, long error_code)
 
 	nmi_exit();
 
-	/* On i386, may loop back to preprocess */
-	nmi_nesting_postprocess();
+#ifdef CONFIG_X86_64
+	if (unlikely(this_cpu_read(update_debug_stack))) {
+		debug_stack_reset();
+		this_cpu_write(update_debug_stack, 0);
+	}
+#endif
+
+	if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+		write_cr2(this_cpu_read(nmi_cr2));
+	if (this_cpu_dec_return(nmi_state))
+		goto nmi_restart;
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 67fcc43577d2..63a4b5092203 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -122,11 +122,11 @@ void __show_regs(struct pt_regs *regs, int all)
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
 	}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d0c0d0..0ccb53a9fcd9 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -27,13 +28,14 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 		struct desc_struct *desc;
 		unsigned long base;
 
-		seg &= ~7UL;
+		seg >>= 3;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     seg >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 6a11845fd8b9..72051730caf1 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -165,7 +165,7 @@ static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
 
 static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.apic->pending_events;
+	return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events;
 }
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 3e32ed5648a0..a13a38830e76 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -23,6 +23,7 @@
 #include <asm/debugreg.h>
 #include <asm/fpu-internal.h> /* pcntxt_mask */
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -154,7 +155,7 @@ static void fix_processor_context(void)
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 }
 
 /**
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index e88fda867a33..484145368a24 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -8,7 +8,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select XEN_HAVE_PVMMU
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_TSC
+	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
@@ -17,7 +17,7 @@ config XEN
 config XEN_DOM0
 	def_bool y
 	depends on XEN && PCI_XEN && SWIOTLB_XEN
-	depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI
+	depends on X86_IO_APIC && ACPI && PCI
 
 config XEN_PVHVM
 	def_bool y
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 7322755f337a..4b6e29ac0968 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,13 +13,13 @@ CFLAGS_mmu.o			:= $(nostackp)
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o
+			p2m.o apic.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-obj-$(CONFIG_XEN_DOM0)		+= apic.o vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 7d67146c3f87..d8d81d1aa1d5 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -481,6 +481,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -490,6 +491,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -501,6 +528,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -508,6 +537,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
@@ -1732,6 +1772,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #ifdef CONFIG_X86_32
 	i386_start_kernel();
 #else
+	cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
 	x86_64_start_reservations((char *)__pa_symbol(&boot_params));
 #endif
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 28c7e0be56e4..566004cc8a5b 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -94,17 +94,15 @@ struct dom0_vga_console_info;
 
 #ifdef CONFIG_XEN_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
-void __init xen_init_apic(void);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 				       size_t size)
 {
 }
-static inline void __init xen_init_apic(void)
-{
-}
 #endif
 
+void __init xen_init_apic(void);
+
 #ifdef CONFIG_XEN_EFI
 extern void xen_efi_init(void);
 #else