22 files changed, 373 insertions, 447 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4ccfacc7232a..7a065d81dc43 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,7 +69,7 @@ config X86
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
-	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP
+	select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select BUILDTIME_EXTABLE_SORT
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 580b60f5ac83..d4d5e1ee8e9c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,7 @@ static int x86_pmu_event_init(struct perf_event *event)
 
 static void refresh_pce(void *ignored)
 {
-	if (current->active_mm)
-		load_mm_cr4(current->active_mm);
+	load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm));
 }
 
 static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2334,7 +2333,7 @@ static unsigned long get_segment_base(unsigned int segment)
 
 		/* IRQs are off, so this synchronizes with smp_store_release */
 		ldt = lockless_dereference(current->active_mm->context.ldt);
-		if (!ldt || idx > ldt->size)
+		if (!ldt || idx > ldt->nr_entries)
 			return 0;
 
 		desc = &ldt->entries[idx];
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 59405a248fc2..9b76cd331990 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,8 +22,8 @@ typedef struct {
 #ifdef CONFIG_SMP
 	unsigned int irq_resched_count;
 	unsigned int irq_call_count;
-	unsigned int irq_tlb_count;
 #endif
+	unsigned int irq_tlb_count;
 #ifdef CONFIG_X86_THERMAL_VECTOR
 	unsigned int irq_thermal_count;
 #endif
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index f9813b6d8b80..79b647a7ebd0 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -37,12 +37,6 @@ typedef struct {
 #endif
 } mm_context_t;
 
-#ifdef CONFIG_SMP
 void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 68b329d77b3a..5a93f6261302 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -47,7 +47,7 @@ struct ldt_struct {
 	 * allocations, but it's not worth trying to optimize.
 	 */
 	struct desc_struct *entries;
-	unsigned int size;
+	unsigned int nr_entries;
 };
 
 /*
@@ -87,7 +87,7 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 	 */
 
 	if (unlikely(ldt))
-		set_ldt(ldt->entries, ldt->size);
+		set_ldt(ldt->entries, ldt->nr_entries);
 	else
 		clear_LDT();
 #else
@@ -99,10 +99,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
-#ifdef CONFIG_SMP
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
-#endif
 }
 
 static inline int init_new_context(struct task_struct *tsk,
@@ -268,4 +266,23 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }
 
+
+/*
+ * This can be used from process context to figure out what the value of
+ * CR3 is without needing to do a (slow) read_cr3().
+ *
+ * It's intended to be used for code like KVM that sneakily changes CR3
+ * and needs to restore it.  It needs to be used very carefully.
+ */
+static inline unsigned long __get_current_cr3_fast(void)
+{
+	unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd);
+
+	/* For now, be very restrictive about when this can be called. */
+	VM_WARN_ON(in_nmi() || !in_atomic());
+
+	VM_BUG_ON(cr3 != read_cr3());
+	return cr3;
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 55fa56fe4e45..9a15739d9f4b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -312,11 +312,9 @@ static inline void __flush_tlb_single(unsigned long addr)
 }
 
 static inline void flush_tlb_others(const struct cpumask *cpumask,
-				    struct mm_struct *mm,
-				    unsigned long start,
-				    unsigned long end)
+				    const struct flush_tlb_info *info)
 {
-	PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end);
+	PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info);
 }
 
 static inline int paravirt_pgd_alloc(struct mm_struct *mm)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 7465d6fe336f..cb976bab6299 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -51,6 +51,7 @@ struct mm_struct;
 struct desc_struct;
 struct task_struct;
 struct cpumask;
+struct flush_tlb_info;
 
 /*
  * Wrapper type for pointers to code which uses the non-standard
@@ -223,9 +224,7 @@ struct pv_mmu_ops {
 	void (*flush_tlb_kernel)(void);
 	void (*flush_tlb_single)(unsigned long addr);
 	void (*flush_tlb_others)(const struct cpumask *cpus,
-				 struct mm_struct *mm,
-				 unsigned long start,
-				 unsigned long end);
+				 const struct flush_tlb_info *info);
 
 	/* Hooks for allocating and freeing a pagetable top-level */
 	int  (*pgd_alloc)(struct mm_struct *mm);
diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h
new file mode 100644
index 000000000000..f4a6ff352a0e
--- /dev/null
+++ b/arch/x86/include/asm/tlbbatch.h
@@ -0,0 +1,14 @@
+#ifndef _ARCH_X86_TLBBATCH_H
+#define _ARCH_X86_TLBBATCH_H
+
+#include <linux/cpumask.h>
+
+struct arch_tlbflush_unmap_batch {
+	/*
+	 * Each bit set is a CPU that potentially has a TLB entry for one of
+	 * the PFNs being flushed..
+	 */
+	struct cpumask cpumask;
+};
+
+#endif /* _ARCH_X86_TLBBATCH_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6ed9ea469b48..388c2463fde6 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -7,6 +7,7 @@
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 static inline void __invpcid(unsigned long pcid, unsigned long addr,
 			     unsigned long type)
@@ -65,10 +66,14 @@ static inline void invpcid_flush_all_nonglobals(void)
 #endif
 
 struct tlb_state {
-#ifdef CONFIG_SMP
-	struct mm_struct *active_mm;
+	/*
+	 * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts
+	 * are on.  This means that it may not match current->active_mm,
+	 * which will contain the previous user mm when we're in lazy TLB
+	 * mode even if we've already switched back to swapper_pg_dir.
+	 */
+	struct mm_struct *loaded_mm;
 	int state;
-#endif
 
 	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
@@ -220,84 +225,16 @@ static inline void __flush_tlb_one(unsigned long addr)
  *  - flush_tlb_page(vma, vmaddr) flushes one page
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- *  - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus
+ *  - flush_tlb_others(cpumask, info) flushes TLBs on other cpus
  *
  * ..but the i386 has somewhat limited tlb flushing capabilities,
  * and page-granular flushes are available only on i486 and up.
  */
-
-#ifndef CONFIG_SMP
-
-/* "_up" is for UniProcessor.
- *
- * This is a helper for other header functions.  *Not* intended to be called
- * directly.  All global TLB flushes need to either call this, or to bump the
- * vm statistics themselves.
- */
-static inline void __flush_tlb_up(void)
-{
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
-}
-
-static inline void flush_tlb_all(void)
-{
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb_all();
-}
-
-static inline void local_flush_tlb(void)
-{
-	__flush_tlb_up();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long addr)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void flush_tlb_mm_range(struct mm_struct *mm,
-	   unsigned long start, unsigned long end, unsigned long vmflag)
-{
-	if (mm == current->active_mm)
-		__flush_tlb_up();
-}
-
-static inline void native_flush_tlb_others(const struct cpumask *cpumask,
-					   struct mm_struct *mm,
-					   unsigned long start,
-					   unsigned long end)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-	flush_tlb_all();
-}
-
-#else  /* SMP */
-
-#include <asm/smp.h>
+struct flush_tlb_info {
+	struct mm_struct *mm;
+	unsigned long start;
+	unsigned long end;
+};
 
 #define local_flush_tlb() __flush_tlb()
 
@@ -307,14 +244,17 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
 
 extern void flush_tlb_all(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
+
 void native_flush_tlb_others(const struct cpumask *cpumask,
-				struct mm_struct *mm,
-				unsigned long start, unsigned long end);
+			     const struct flush_tlb_info *info);
 
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
@@ -322,14 +262,22 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 static inline void reset_lazy_tlbstate(void)
 {
 	this_cpu_write(cpu_tlbstate.state, 0);
-	this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
+	this_cpu_write(cpu_tlbstate.loaded_mm, &init_mm);
+
+	WARN_ON(read_cr3() != __pa_symbol(swapper_pg_dir));
+}
+
+static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
+					struct mm_struct *mm)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
 }
 
-#endif	/* SMP */
+extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, start, end)	\
-	native_flush_tlb_others(mask, mm, start, end)
+#define flush_tlb_others(mask, info)	\
+	native_flush_tlb_others(mask, info)
 #endif
 
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 6686820feae9..b5a32231abd8 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_UV_UV_H
 #define _ASM_X86_UV_UV_H
 
+#include <asm/tlbflush.h>
+
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 
 struct cpumask;
@@ -15,10 +17,7 @@ extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
 extern void uv_system_init(void);
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-						 struct mm_struct *mm,
-						 unsigned long start,
-						 unsigned long end,
-						 unsigned int cpu);
+						 const struct flush_tlb_info *info);
 
 #else	/* X86_UV */
 
@@ -28,8 +27,8 @@ static inline int is_uv_hubless(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
 static inline const struct cpumask *
-uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
-		    unsigned long start, unsigned long end, unsigned int cpu)
+uv_flush_tlb_others(const struct cpumask *cpumask,
+		    const struct flush_tlb_info *info)
 { return cpumask; }
 
 #endif	/* X86_UV */
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d4a15831ac58..a870910c8565 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -22,24 +22,25 @@
 #include <asm/syscalls.h>
 
 /* context.lock is held for us, so we don't need any locking. */
-static void flush_ldt(void *current_mm)
+static void flush_ldt(void *__mm)
 {
+	struct mm_struct *mm = __mm;
 	mm_context_t *pc;
 
-	if (current->active_mm != current_mm)
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
 		return;
 
-	pc = &current->active_mm->context;
-	set_ldt(pc->ldt->entries, pc->ldt->size);
+	pc = &mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
 }
 
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
-static struct ldt_struct *alloc_ldt_struct(unsigned int size)
+static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 {
 	struct ldt_struct *new_ldt;
 	unsigned int alloc_size;
 
-	if (size > LDT_ENTRIES)
+	if (num_entries > LDT_ENTRIES)
 		return NULL;
 
 	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
@@ -47,7 +48,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size)
 		return NULL;
 
 	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
-	alloc_size = size * LDT_ENTRY_SIZE;
+	alloc_size = num_entries * LDT_ENTRY_SIZE;
 
 	/*
 	 * Xen is very picky: it requires a page-aligned LDT that has no
@@ -65,14 +66,14 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size)
 		return NULL;
 	}
 
-	new_ldt->size = size;
+	new_ldt->nr_entries = num_entries;
 	return new_ldt;
 }
 
 /* After calling this, the LDT is immutable. */
 static void finalize_ldt_struct(struct ldt_struct *ldt)
 {
-	paravirt_alloc_ldt(ldt->entries, ldt->size);
+	paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
 }
 
 /* context.lock is held */
@@ -91,8 +92,8 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 	if (likely(!ldt))
 		return;
 
-	paravirt_free_ldt(ldt->entries, ldt->size);
-	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+	paravirt_free_ldt(ldt->entries, ldt->nr_entries);
+	if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE)
 		vfree_atomic(ldt->entries);
 	else
 		free_page((unsigned long)ldt->entries);
@@ -122,14 +123,14 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
 		goto out_unlock;
 	}
 
-	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
 	if (!new_ldt) {
 		retval = -ENOMEM;
 		goto out_unlock;
 	}
 
 	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
-	       new_ldt->size * LDT_ENTRY_SIZE);
+	       new_ldt->nr_entries * LDT_ENTRY_SIZE);
 	finalize_ldt_struct(new_ldt);
 
 	mm->context.ldt = new_ldt;
@@ -152,9 +153,9 @@ void destroy_context_ldt(struct mm_struct *mm)
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int retval;
-	unsigned long size;
 	struct mm_struct *mm = current->mm;
+	unsigned long entries_size;
+	int retval;
 
 	mutex_lock(&mm->context.lock);
 
@@ -166,18 +167,18 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
-	if (size > bytecount)
-		size = bytecount;
+	entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE;
+	if (entries_size > bytecount)
+		entries_size = bytecount;
 
-	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+	if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) {
 		retval = -EFAULT;
 		goto out_unlock;
 	}
 
-	if (size != bytecount) {
+	if (entries_size != bytecount) {
 		/* Zero-fill the rest and pretend we read bytecount bytes. */
-		if (clear_user(ptr + size, bytecount - size)) {
+		if (clear_user(ptr + entries_size, bytecount - entries_size)) {
 			retval = -EFAULT;
 			goto out_unlock;
 		}
@@ -208,7 +209,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 {
 	struct mm_struct *mm = current->mm;
 	struct ldt_struct *new_ldt, *old_ldt;
-	unsigned int oldsize, newsize;
+	unsigned int old_nr_entries, new_nr_entries;
 	struct user_desc ldt_info;
 	struct desc_struct ldt;
 	int error;
@@ -247,17 +248,18 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 
 	mutex_lock(&mm->context.lock);
 
-	old_ldt = mm->context.ldt;
-	oldsize = old_ldt ? old_ldt->size : 0;
-	newsize = max(ldt_info.entry_number + 1, oldsize);
+	old_ldt       = mm->context.ldt;
+	old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
+	new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries);
 
 	error = -ENOMEM;
-	new_ldt = alloc_ldt_struct(newsize);
+	new_ldt = alloc_ldt_struct(new_nr_entries);
 	if (!new_ldt)
 		goto out_unlock;
 
 	if (old_ldt)
-		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+		memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE);
+
 	new_ldt->entries[ldt_info.entry_number] = ldt;
 	finalize_ldt_struct(new_ldt);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b6840bf3940b..9c39ab8bcc41 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -142,7 +142,7 @@ void release_thread(struct task_struct *dead_task)
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt->entries,
-				dead_task->mm->context.ldt->size);
+				dead_task->mm->context.ldt->nr_entries);
 			BUG();
 		}
 #endif
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index f07f83b3611b..5f25cfbd952e 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -34,7 +34,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 
 		mutex_lock(&child->mm->context.lock);
 		if (unlikely(!child->mm->context.ldt ||
-			     seg >= child->mm->context.ldt->size))
+			     seg >= child->mm->context.ldt->nr_entries))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
 			desc = &child->mm->context.ldt->entries[seg];
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9b4b5d6dcd34..19cde555d73f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -48,6 +48,7 @@
 #include <asm/kexec.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/mmu_context.h>
 
 #include "trace.h"
 #include "pmu.h"
@@ -596,6 +597,7 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
+		unsigned long vmcs_host_cr3;	/* May not match real cr3 */
 		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
@@ -5012,12 +5014,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	u32 low32, high32;
 	unsigned long tmpl;
 	struct desc_ptr dt;
-	unsigned long cr0, cr4;
+	unsigned long cr0, cr3, cr4;
 
 	cr0 = read_cr0();
 	WARN_ON(cr0 & X86_CR0_TS);
 	vmcs_writel(HOST_CR0, cr0);  /* 22.2.3 */
-	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
+
+	/*
+	 * Save the most likely value for this task's CR3 in the VMCS.
+	 * We can't use __get_current_cr3_fast() because we're not atomic.
+	 */
+	cr3 = read_cr3();
+	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
+	vmx->host_state.vmcs_host_cr3 = cr3;
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
 	cr4 = cr4_read_shadow();
@@ -8820,7 +8829,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long debugctlmsr, cr4;
+	unsigned long debugctlmsr, cr3, cr4;
 
 	/* Don't enter VMX if guest state is invalid, let the exit handler
 	   start emulation until we arrive back to a valid state */
@@ -8842,6 +8851,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->host_state.vmcs_host_cr3 = cr3;
+	}
+
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 5e044d506b7a..a179254a5122 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -27,7 +27,7 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	seg >>= 3;
 	mutex_lock(&current->mm->context.lock);
-	if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+	if (current->mm->context.ldt && seg < current->mm->context.ldt->nr_entries)
 		ret = current->mm->context.ldt->entries[seg];
 	mutex_unlock(&current->mm->context.lock);
 #endif
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cbc87ea98751..88ee942cb47d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -811,10 +811,8 @@ void __init zone_sizes_init(void)
 }
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
-#ifdef CONFIG_SMP
-	.active_mm = &init_mm,
+	.loaded_mm = &init_mm,
 	.state = 0,
-#endif
 	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
 };
 EXPORT_SYMBOL_GPL(cpu_tlbstate);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6e7bedf69af7..2a5e851f2035 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -15,7 +15,7 @@
 #include <linux/debugfs.h>
 
 /*
- *	Smarter SMP flushing macros.
+ *	TLB flushing, formerly SMP-only
  *		c/o Linus Torvalds.
  *
  *	These mean you can really definitely utterly forget about
@@ -28,39 +28,28 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
-#ifdef CONFIG_SMP
-
-struct flush_tlb_info {
-	struct mm_struct *flush_mm;
-	unsigned long flush_start;
-	unsigned long flush_end;
-};
-
-/*
- * We cannot call mmdrop() because we are in interrupt context,
- * instead update mm->cpu_vm_mask.
- */
 void leave_mm(int cpu)
 {
-	struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+
+	/*
+	 * It's plausible that we're in lazy TLB mode while our mm is init_mm.
+	 * If so, our callers still expect us to flush the TLB, but there
+	 * aren't any user TLB entries in init_mm to worry about.
+	 *
+	 * This needs to happen before any other sanity checks due to
+	 * intel_idle's shenanigans.
+	 */
+	if (loaded_mm == &init_mm)
+		return;
+
 	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		BUG();
-	if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
-		cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
-		load_cr3(swapper_pg_dir);
-		/*
-		 * This gets called in the idle path where RCU
-		 * functions differently.  Tracing normally
-		 * uses RCU, so we have to call the tracepoint
-		 * specially here.
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-	}
+
+	switch_mm(NULL, &init_mm, NULL);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
-#endif /* CONFIG_SMP */
-
 void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	       struct task_struct *tsk)
 {
@@ -75,117 +64,111 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			struct task_struct *tsk)
 {
 	unsigned cpu = smp_processor_id();
+	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 
-	if (likely(prev != next)) {
-		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-			/*
-			 * If our current stack is in vmalloc space and isn't
-			 * mapped in the new pgd, we'll double-fault.  Forcibly
-			 * map it.
-			 */
-			unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
-
-			pgd_t *pgd = next->pgd + stack_pgd_index;
-
-			if (unlikely(pgd_none(*pgd)))
-				set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
-		}
+	/*
+	 * NB: The scheduler will call us with prev == next when
+	 * switching from lazy TLB mode to normal mode if active_mm
+	 * isn't changing.  When this happens, there is no guarantee
+	 * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next.
+	 *
+	 * NB: leave_mm() calls us with prev == NULL and tsk == NULL.
+	 */
 
-#ifdef CONFIG_SMP
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
+	this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 
-		cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (real_prev == next) {
+		/*
+		 * There's nothing to do: we always keep the per-mm control
+		 * regs in sync with cpu_tlbstate.loaded_mm.  Just
+		 * sanity-check mm_cpumask.
+		 */
+		if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next))))
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+		return;
+	}
 
+	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
 		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
+		 * If our current stack is in vmalloc space and isn't
+		 * mapped in the new pgd, we'll double-fault.  Forcibly
+		 * map it.
 		 */
-		load_cr3(next->pgd);
+		unsigned int stack_pgd_index = pgd_index(current_stack_pointer());
 
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+		pgd_t *pgd = next->pgd + stack_pgd_index;
 
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		if (unlikely(pgd_none(*pgd)))
+			set_pgd(pgd, init_mm.pgd[stack_pgd_index]);
+	}
 
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
 
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		/*
-		 * Load the LDT, if the LDT is different.
-		 *
-		 * It's possible that prev->context.ldt doesn't match
-		 * the LDT register.  This can happen if leave_mm(prev)
-		 * was called and then modify_ldt changed
-		 * prev->context.ldt but suppressed an IPI to this CPU.
-		 * In this case, prev->context.ldt != NULL, because we
-		 * never set context.ldt to NULL while the mm still
-		 * exists.  That means that next->context.ldt !=
-		 * prev->context.ldt, because mms never share an LDT.
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-#endif
-	}
-#ifdef CONFIG_SMP
-	  else {
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * On established mms, the mm_cpumask is only changed
-			 * from irq context, from ptep_clear_flush() while in
-			 * lazy tlb mode, and here. Irqs are blocked during
-			 * schedule, protecting us from simultaneous changes.
-			 */
-			cpumask_set_cpu(cpu, mm_cpumask(next));
+	WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
 
-			/*
-			 * We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_mm_cr4(next);
-			load_mm_ldt(next);
-		}
-	}
+	/*
+	 * Re-load page tables.
+	 *
+	 * This logic has an ordering constraint:
+	 *
+	 *  CPU 0: Write to a PTE for 'next'
+	 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
+	 *  CPU 1: set bit 1 in next's mm_cpumask
+	 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
+	 *
+	 * We need to prevent an outcome in which CPU 1 observes
+	 * the new PTE value and CPU 0 observes bit 1 clear in
+	 * mm_cpumask.  (If that occurs, then the IPI will never
+	 * be sent, and CPU 0's TLB will contain a stale entry.)
+	 *
+	 * The bad outcome can occur if either CPU's load is
+	 * reordered before that CPU's store, so both CPUs must
+	 * execute full barriers to prevent this from happening.
+	 *
+	 * Thus, switch_mm needs a full barrier between the
+	 * store to mm_cpumask and any operation that could load
+	 * from next->pgd.  TLB fills are special and can happen
+	 * due to instruction fetches or for no reason at all,
+	 * and neither LOCK nor MFENCE orders them.
+	 * Fortunately, load_cr3() is serializing and gives the
+	 * ordering guarantee we need.
+	 */
+	load_cr3(next->pgd);
+
+	/*
+	 * This gets called via leave_mm() in the idle path where RCU
+	 * functions differently.  Tracing normally uses RCU, so we have to
+	 * call the tracepoint specially here.
+	 */
+	trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+
+	/* Stop flush ipis for the previous mm */
+	WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
+		     real_prev != &init_mm);
+	cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+
+	/* Load per-mm CR4 state */
+	load_mm_cr4(next);
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	/*
+	 * Load the LDT, if the LDT is different.
+	 *
+	 * It's possible that prev->context.ldt doesn't match
+	 * the LDT register.  This can happen if leave_mm(prev)
+	 * was called and then modify_ldt changed
+	 * prev->context.ldt but suppressed an IPI to this CPU.
+	 * In this case, prev->context.ldt != NULL, because we
+	 * never set context.ldt to NULL while the mm still
+	 * exists.  That means that next->context.ldt !=
+	 * prev->context.ldt, because mms never share an LDT.
+	 */
+	if (unlikely(real_prev->context.ldt != next->context.ldt))
+		load_mm_ldt(next);
 #endif
 }
 
-#ifdef CONFIG_SMP
-
 /*
  * The flush IPI assumes that a thread switch happens in this order:
  * [cpu0: the cpu that switches]
@@ -222,69 +205,75 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
  * write/read ordering problems.
  */
 
-/*
- * TLB flush funcation:
- * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
- * 2) Leave the mm if we are in the lazy tlb mode.
- */
-static void flush_tlb_func(void *info)
+static void flush_tlb_func_common(const struct flush_tlb_info *f,
+				  bool local, enum tlb_flush_reason reason)
 {
-	struct flush_tlb_info *f = info;
+	if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) {
+		leave_mm(smp_processor_id());
+		return;
+	}
+
+	if (f->end == TLB_FLUSH_ALL) {
+		local_flush_tlb();
+		if (local)
+			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
+		trace_tlb_flush(reason, TLB_FLUSH_ALL);
+	} else {
+		unsigned long addr;
+		unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT;
+		addr = f->start;
+		while (addr < f->end) {
+			__flush_tlb_single(addr);
+			addr += PAGE_SIZE;
+		}
+		if (local)
+			count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages);
+		trace_tlb_flush(reason, nr_pages);
+	}
+}
+
+static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason)
+{
+	const struct flush_tlb_info *f = info;
+
+	flush_tlb_func_common(f, true, reason);
+}
+
+static void flush_tlb_func_remote(void *info)
+{
+	const struct flush_tlb_info *f = info;
 
 	inc_irq_stat(irq_tlb_count);
 
-	if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+	if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm))
 		return;
 
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
-	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
-		if (f->flush_end == TLB_FLUSH_ALL) {
-			local_flush_tlb();
-			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL);
-		} else {
-			unsigned long addr;
-			unsigned long nr_pages =
-				(f->flush_end - f->flush_start) / PAGE_SIZE;
-			addr = f->flush_start;
-			while (addr < f->flush_end) {
-				__flush_tlb_single(addr);
-				addr += PAGE_SIZE;
-			}
-			trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages);
-		}
-	} else
-		leave_mm(smp_processor_id());
-
+	flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
-				 struct mm_struct *mm, unsigned long start,
-				 unsigned long end)
+			     const struct flush_tlb_info *info)
 {
-	struct flush_tlb_info info;
-
-	info.flush_mm = mm;
-	info.flush_start = start;
-	info.flush_end = end;
-
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	if (end == TLB_FLUSH_ALL)
+	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
 	else
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI,
-				(end - start) >> PAGE_SHIFT);
+				(info->end - info->start) >> PAGE_SHIFT);
 
 	if (is_uv_system()) {
 		unsigned int cpu;
 
 		cpu = smp_processor_id();
-		cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu);
+		cpumask = uv_flush_tlb_others(cpumask, info);
 		if (cpumask)
-			smp_call_function_many(cpumask, flush_tlb_func,
-								&info, 1);
+			smp_call_function_many(cpumask, flush_tlb_func_remote,
+					       (void *)info, 1);
 		return;
 	}
-	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
+	smp_call_function_many(cpumask, flush_tlb_func_remote,
+			       (void *)info, 1);
 }
 
 /*
@@ -302,85 +291,36 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag)
 {
-	unsigned long addr;
-	/* do a global flush by default */
-	unsigned long base_pages_to_flush = TLB_FLUSH_ALL;
+	int cpu;
 
-	preempt_disable();
+	struct flush_tlb_info info = {
+		.mm = mm,
+	};
 
-	if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB))
-		base_pages_to_flush = (end - start) >> PAGE_SHIFT;
-	if (base_pages_to_flush > tlb_single_page_flush_ceiling)
-		base_pages_to_flush = TLB_FLUSH_ALL;
+	cpu = get_cpu();
 
-	if (current->active_mm != mm) {
-		/* Synchronize with switch_mm. */
-		smp_mb();
+	/* Synchronize with switch_mm. */
+	smp_mb();
 
-		goto out;
-	}
-
-	if (!current->mm) {
-		leave_mm(smp_processor_id());
-
-		/* Synchronize with switch_mm. */
-		smp_mb();
-
-		goto out;
-	}
-
-	/*
-	 * Both branches below are implicit full barriers (MOV to CR or
-	 * INVLPG) that synchronize with switch_mm.
-	 */
-	if (base_pages_to_flush == TLB_FLUSH_ALL) {
-		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-		local_flush_tlb();
+	/* Should we flush just the requested range? */
+	if ((end != TLB_FLUSH_ALL) &&
+	    !(vmflag & VM_HUGETLB) &&
+	    ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) {
+		info.start = start;
+		info.end = end;
 	} else {
-		/* flush range by one by one 'invlpg' */
-		for (addr = start; addr < end;	addr += PAGE_SIZE) {
-			count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-			__flush_tlb_single(addr);
-		}
-	}
-	trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush);
-out:
-	if (base_pages_to_flush == TLB_FLUSH_ALL) {
-		start = 0UL;
-		end = TLB_FLUSH_ALL;
-	}
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, end);
-	preempt_enable();
-}
-
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
-	struct mm_struct *mm = vma->vm_mm;
-
-	preempt_disable();
-
-	if (current->active_mm == mm) {
-		if (current->mm) {
-			/*
-			 * Implicit full barrier (INVLPG) that synchronizes
-			 * with switch_mm.
-			 */
-			__flush_tlb_one(start);
-		} else {
-			leave_mm(smp_processor_id());
-
-			/* Synchronize with switch_mm. */
-			smp_mb();
-		}
+		info.start = 0UL;
+		info.end = TLB_FLUSH_ALL;
 	}
 
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
-	preempt_enable();
+	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm))
+		flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
+	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), &info);
+	put_cpu();
 }
 
+
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -401,7 +341,7 @@ static void do_kernel_range_flush(void *info)
 	unsigned long addr;
 
 	/* flush range by one by one 'invlpg' */
-	for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
+	for (addr = f->start; addr < f->end; addr += PAGE_SIZE)
 		__flush_tlb_single(addr);
 }
 
@@ -410,16 +350,35 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 
 	/* Balance as user space task's flush, a bit conservative */
 	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) {
+	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
 	} else {
 		struct flush_tlb_info info;
-		info.flush_start = start;
-		info.flush_end = end;
+		info.start = start;
+		info.end = end;
 		on_each_cpu(do_kernel_range_flush, &info, 1);
 	}
 }
 
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	struct flush_tlb_info info = {
+		.mm = NULL,
+		.start = 0UL,
+		.end = TLB_FLUSH_ALL,
+	};
+
+	int cpu = get_cpu();
+
+	if (cpumask_test_cpu(cpu, &batch->cpumask))
+		flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN);
+	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
+		flush_tlb_others(&batch->cpumask, &info);
+	cpumask_clear(&batch->cpumask);
+
+	put_cpu();
+}
+
 static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
 			     size_t count, loff_t *ppos)
 {
@@ -465,5 +424,3 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
-
-#endif /* CONFIG_SMP */
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 42e65fee5673..5a22d77ffc2a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1121,11 +1121,9 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-						struct mm_struct *mm,
-						unsigned long start,
-						unsigned long end,
-						unsigned int cpu)
+					  const struct flush_tlb_info *info)
 {
+	unsigned int cpu = smp_processor_id();
 	int locals = 0, remotes = 0, hubs = 0;
 	struct bau_desc *bau_desc;
 	struct cpumask *flush_mask;
@@ -1179,8 +1177,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
-	if (!end || (end - start) <= PAGE_SIZE)
-		address = start;
+	if (!info->end || (info->end - info->start) <= PAGE_SIZE)
+		address = info->start;
 	else
 		address = TLB_FLUSH_ALL;
 
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1f386d7fdf70..21beb37114b7 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -975,37 +975,32 @@ static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 	spin_unlock(&mm->page_table_lock);
 }
 
-
-#ifdef CONFIG_SMP
-/* Another cpu may still have their %cr3 pointing at the pagetable, so
-   we need to repoint it somewhere else before we can unpin it. */
-static void drop_other_mm_ref(void *info)
+static void drop_mm_ref_this_cpu(void *info)
 {
 	struct mm_struct *mm = info;
-	struct mm_struct *active_mm;
-
-	active_mm = this_cpu_read(cpu_tlbstate.active_mm);
 
-	if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK)
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm)
 		leave_mm(smp_processor_id());
 
-	/* If this cpu still has a stale cr3 reference, then make sure
-	   it has been flushed. */
+	/*
+	 * If this cpu still has a stale cr3 reference, then make sure
+	 * it has been flushed.
+	 */
 	if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd))
-		load_cr3(swapper_pg_dir);
+		xen_mc_flush();
 }
 
+#ifdef CONFIG_SMP
+/*
+ * Another cpu may still have their %cr3 pointing at the pagetable, so
+ * we need to repoint it somewhere else before we can unpin it.
+ */
 static void xen_drop_mm_ref(struct mm_struct *mm)
 {
 	cpumask_var_t mask;
 	unsigned cpu;
 
-	if (current->active_mm == mm) {
-		if (current->mm == mm)
-			load_cr3(swapper_pg_dir);
-		else
-			leave_mm(smp_processor_id());
-	}
+	drop_mm_ref_this_cpu(mm);
 
 	/* Get the "official" set of cpus referring to our pagetable. */
 	if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) {
@@ -1013,31 +1008,31 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
 			if (!cpumask_test_cpu(cpu, mm_cpumask(mm))
 			    && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd))
 				continue;
-			smp_call_function_single(cpu, drop_other_mm_ref, mm, 1);
+			smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1);
 		}
 		return;
 	}
 	cpumask_copy(mask, mm_cpumask(mm));
 
-	/* It's possible that a vcpu may have a stale reference to our
-	   cr3, because its in lazy mode, and it hasn't yet flushed
-	   its set of pending hypercalls yet.  In this case, we can
-	   look at its actual current cr3 value, and force it to flush
-	   if needed. */
+	/*
+	 * It's possible that a vcpu may have a stale reference to our
+	 * cr3, because its in lazy mode, and it hasn't yet flushed
+	 * its set of pending hypercalls yet.  In this case, we can
+	 * look at its actual current cr3 value, and force it to flush
+	 * if needed.
+	 */
 	for_each_online_cpu(cpu) {
 		if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
 			cpumask_set_cpu(cpu, mask);
 	}
 
-	if (!cpumask_empty(mask))
-		smp_call_function_many(mask, drop_other_mm_ref, mm, 1);
+	smp_call_function_many(mask, drop_mm_ref_this_cpu, mm, 1);
 	free_cpumask_var(mask);
 }
 #else
 static void xen_drop_mm_ref(struct mm_struct *mm)
 {
-	if (current->active_mm == mm)
-		load_cr3(swapper_pg_dir);
+	drop_mm_ref_this_cpu(mm);
 }
 #endif
 
@@ -1366,8 +1361,7 @@ static void xen_flush_tlb_single(unsigned long addr)
 }
 
 static void xen_flush_tlb_others(const struct cpumask *cpus,
-				 struct mm_struct *mm, unsigned long start,
-				 unsigned long end)
+				 const struct flush_tlb_info *info)
 {
 	struct {
 		struct mmuext_op op;
@@ -1379,7 +1373,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	} *args;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
+	trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
@@ -1393,9 +1387,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
 	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+	if (info->end != TLB_FLUSH_ALL &&
+	    (info->end - info->start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
-		args->op.arg1.linear_addr = start;
+		args->op.arg1.linear_addr = info->start;
 	}
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 136dfdf63ba1..fc412fbd80bd 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -14,6 +14,10 @@
 
 #include <asm/page.h>
 
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+#include <asm/tlbbatch.h>
+#endif
+
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
@@ -67,12 +71,15 @@ struct page_frag {
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	/*
-	 * Each bit set is a CPU that potentially has a TLB entry for one of
-	 * the PFNs being flushed. See set_tlb_ubc_flush_pending().
+	 * The arch code makes the following promise: generic code can modify a
+	 * PTE, then call arch_tlbbatch_add_mm() (which internally provides all
+	 * needed barriers), then call arch_tlbbatch_flush(), and the entries
+	 * will be flushed on all CPUs by the time that arch_tlbbatch_flush()
+	 * returns.
 	 */
-	struct cpumask cpumask;
+	struct arch_tlbflush_unmap_batch arch;
 
-	/* True if any bit in cpumask is set */
+	/* True if a flush is needed. */
 	bool flush_required;
 
 	/*
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index d84ae90ccd5c..be3ab2d13adf 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -93,10 +93,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #endif
 #endif
 #ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
 		NR_TLB_REMOTE_FLUSH,	/* cpu tried to flush others' tlbs */
 		NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */
-#endif /* CONFIG_SMP */
 		NR_TLB_LOCAL_FLUSH_ALL,
 		NR_TLB_LOCAL_FLUSH_ONE,
 #endif /* CONFIG_DEBUG_TLBFLUSH */
diff --git a/mm/rmap.c b/mm/rmap.c
index d405f0e0ee96..130c238fe384 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -579,25 +579,13 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma)
 void try_to_unmap_flush(void)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
-	int cpu;
 
 	if (!tlb_ubc->flush_required)
 		return;
 
-	cpu = get_cpu();
-
-	if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) {
-		count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-		local_flush_tlb();
-		trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL);
-	}
-
-	if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL);
-	cpumask_clear(&tlb_ubc->cpumask);
+	arch_tlbbatch_flush(&tlb_ubc->arch);
 	tlb_ubc->flush_required = false;
 	tlb_ubc->writable = false;
-	put_cpu();
 }
 
 /* Flush iff there are potentially writable TLB entries that can race with IO */
@@ -613,7 +601,7 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
 {
 	struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc;
 
-	cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm));
+	arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
 	tlb_ubc->flush_required = true;
 
 	/*