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

Pull x86 mm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - Continued work to add support for 5-level paging provided by future
     Intel CPUs. In particular we switch the x86 GUP code to the generic
     implementation. (Kirill A. Shutemov)

   - Continued work to add PCID CPU support to native kernels as well.
     In this round most of the focus is on reworking/refreshing the TLB
     flush infrastructure for the upcoming PCID changes. (Andy
     Lutomirski)"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  x86/mm: Delete a big outdated comment about TLB flushing
  x86/mm: Don't reenter flush_tlb_func_common()
  x86/KASLR: Fix detection 32/64 bit bootloaders for 5-level paging
  x86/ftrace: Exclude functions in head64.c from function-tracing
  x86/mmap, ASLR: Do not treat unlimited-stack tasks as legacy mmap
  x86/mm: Remove reset_lazy_tlbstate()
  x86/ldt: Simplify the LDT switching logic
  x86/boot/64: Put __startup_64() into .head.text
  x86/mm: Add support for 5-level paging for KASLR
  x86/mm: Make kernel_physical_mapping_init() support 5-level paging
  x86/mm: Add sync_global_pgds() for configuration with 5-level paging
  x86/boot/64: Add support of additional page table level during early boot
  x86/boot/64: Rename init_level4_pgt and early_level4_pgt
  x86/boot/64: Rewrite startup_64() in C
  x86/boot/compressed: Enable 5-level paging during decompression stage
  x86/boot/efi: Define __KERNEL32_CS GDT on 64-bit configurations
  x86/boot/efi: Fix __KERNEL_CS definition of GDT entry on 64-bit configurations
  x86/boot/efi: Cleanup initialization of GDT entries
  x86/asm: Fix comment in return_from_SYSCALL_64()
  x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation
  ...

16 files changed, 273 insertions, 132 deletions

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 2f77bcefe6b4..d2ff779f347e 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -74,7 +74,7 @@ struct efi_scratch {
 	__kernel_fpu_begin();						\
 									\
 	if (efi_scratch.use_pgd) {					\
-		efi_scratch.prev_cr3 = read_cr3();			\
+		efi_scratch.prev_cr3 = __read_cr3();			\
 		write_cr3((unsigned long)efi_scratch.efi_pgt);		\
 		__flush_tlb_all();					\
 	}								\
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..ecfcb6643c9b 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;
 };
 
 /*
@@ -87,22 +87,46 @@ 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
 	clear_LDT();
 #endif
+}
+
+static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
+{
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	/*
+	 * Load the LDT if either the old or new mm had an LDT.
+	 *
+	 * An mm will never go from having an LDT to not having an LDT.  Two
+	 * mms never share an LDT, so we don't gain anything by checking to
+	 * see whether the LDT changed.  There's also no guarantee that
+	 * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL,
+	 * then prev->context.ldt will also be non-NULL.
+	 *
+	 * If we really cared, we could optimize the case where prev == next
+	 * and we're exiting lazy mode.  Most of the time, if this happens,
+	 * we don't actually need to reload LDTR, but modify_ldt() is mostly
+	 * used by legacy code and emulators where we don't need this level of
+	 * performance.
+	 *
+	 * This uses | instead of || because it generates better code.
+	 */
+	if (unlikely((unsigned long)prev->context.ldt |
+		     (unsigned long)next->context.ldt))
+		load_mm_ldt(next);
+#endif
 
 	DEBUG_LOCKS_WARN_ON(preemptible());
 }
 
 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,
@@ -220,18 +244,6 @@ static inline int vma_pkey(struct vm_area_struct *vma)
 }
 #endif
 
-static inline bool __pkru_allows_pkey(u16 pkey, bool write)
-{
-	u32 pkru = read_pkru();
-
-	if (!__pkru_allows_read(pkru, pkey))
-		return false;
-	if (write && !__pkru_allows_write(pkru, pkey))
-		return false;
-
-	return true;
-}
-
 /*
  * We only want to enforce protection keys on the current process
  * because we effectively have no access to PKRU for other
@@ -268,4 +280,23 @@ 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 a3dcf8944cb9..9ccac1926587 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -61,7 +61,7 @@ static inline void write_cr2(unsigned long x)
 	PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
 }
 
-static inline unsigned long read_cr3(void)
+static inline unsigned long __read_cr3(void)
 {
 	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
 }
@@ -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/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 50d35e3185f5..c8821bab938f 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -212,4 +212,51 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 #define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
 #define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
 
+#define gup_get_pte gup_get_pte
+/*
+ * WARNING: only to be used in the get_user_pages_fast() implementation.
+ *
+ * With get_user_pages_fast(), we walk down the pagetables without taking
+ * any locks.  For this we would like to load the pointers atomically,
+ * but that is not possible (without expensive cmpxchg8b) on PAE.  What
+ * we do have is the guarantee that a PTE will only either go from not
+ * present to present, or present to not present or both -- it will not
+ * switch to a completely different present page without a TLB flush in
+ * between; something that we are blocking by holding interrupts off.
+ *
+ * Setting ptes from not present to present goes:
+ *
+ *   ptep->pte_high = h;
+ *   smp_wmb();
+ *   ptep->pte_low = l;
+ *
+ * And present to not present goes:
+ *
+ *   ptep->pte_low = 0;
+ *   smp_wmb();
+ *   ptep->pte_high = 0;
+ *
+ * We must ensure here that the load of pte_low sees 'l' iff pte_high
+ * sees 'h'. We load pte_high *after* loading pte_low, which ensures we
+ * don't see an older value of pte_high.  *Then* we recheck pte_low,
+ * which ensures that we haven't picked up a changed pte high. We might
+ * have gotten rubbish values from pte_low and pte_high, but we are
+ * guaranteed that pte_low will not have the present bit set *unless*
+ * it is 'l'. Because get_user_pages_fast() only operates on present ptes
+ * we're safe.
+ */
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+	pte_t pte;
+
+	do {
+		pte.pte_low = ptep->pte_low;
+		smp_rmb();
+		pte.pte_high = ptep->pte_high;
+		smp_rmb();
+	} while (unlikely(pte.pte_low != ptep->pte_low));
+
+	return pte;
+}
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f5af95a0c6b8..77037b6f1caa 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -244,6 +244,11 @@ static inline int pud_devmap(pud_t pud)
 	return 0;
 }
 #endif
+
+static inline int pgd_devmap(pgd_t pgd)
+{
+	return 0;
+}
 #endif
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -917,7 +922,7 @@ extern pgd_t trampoline_pgd_entry;
 static inline void __meminit init_trampoline_default(void)
 {
 	/* Default trampoline pgd value */
-	trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)];
+	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
@@ -1185,6 +1190,54 @@ static inline u16 pte_flags_pkey(unsigned long pte_flags)
 #endif
 }
 
+static inline bool __pkru_allows_pkey(u16 pkey, bool write)
+{
+	u32 pkru = read_pkru();
+
+	if (!__pkru_allows_read(pkru, pkey))
+		return false;
+	if (write && !__pkru_allows_write(pkru, pkey))
+		return false;
+
+	return true;
+}
+
+/*
+ * 'pteval' can come from a PTE, PMD or PUD.  We only check
+ * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the
+ * same value on all 3 types.
+ */
+static inline bool __pte_access_permitted(unsigned long pteval, bool write)
+{
+	unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER;
+
+	if (write)
+		need_pte_bits |= _PAGE_RW;
+
+	if ((pteval & need_pte_bits) != need_pte_bits)
+		return 0;
+
+	return __pkru_allows_pkey(pte_flags_pkey(pteval), write);
+}
+
+#define pte_access_permitted pte_access_permitted
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+	return __pte_access_permitted(pte_val(pte), write);
+}
+
+#define pmd_access_permitted pmd_access_permitted
+static inline bool pmd_access_permitted(pmd_t pmd, bool write)
+{
+	return __pte_access_permitted(pmd_val(pmd), write);
+}
+
+#define pud_access_permitted pud_access_permitted
+static inline bool pud_access_permitted(pud_t pud, bool write)
+{
+	return __pte_access_permitted(pud_val(pud), write);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 9991224f6238..2160c1fee920 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -14,15 +14,17 @@
 #include <linux/bitops.h>
 #include <linux/threads.h>
 
+extern p4d_t level4_kernel_pgt[512];
+extern p4d_t level4_ident_pgt[512];
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
 extern pte_t level1_fixmap_pgt[512];
-extern pgd_t init_level4_pgt[];
+extern pgd_t init_top_pgt[];
 
-#define swapper_pg_dir init_level4_pgt
+#define swapper_pg_dir init_top_pgt
 
 extern void paging_init(void);
 
@@ -227,6 +229,20 @@ extern void cleanup_highmap(void);
 extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 
-#endif /* !__ASSEMBLY__ */
+#define gup_fast_permitted gup_fast_permitted
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
+		int write)
+{
+	unsigned long len, end;
+
+	len = (unsigned long)nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (end < start)
+		return false;
+	if (end >> __VIRTUAL_MASK_SHIFT)
+		return false;
+	return true;
+}
 
+#endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 39fb618e2211..79aa2f98398d 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -8,4 +8,40 @@
 #else
 #define X86_VM_MASK	0 /* No VM86 support */
 #endif
+
+/*
+ * CR3's layout varies depending on several things.
+ *
+ * If CR4.PCIDE is set (64-bit only), then CR3[11:0] is the address space ID.
+ * If PAE is enabled, then CR3[11:5] is part of the PDPT address
+ * (i.e. it's 32-byte aligned, not page-aligned) and CR3[4:0] is ignored.
+ * Otherwise (non-PAE, non-PCID), CR3[3] is PWT, CR3[4] is PCD, and
+ * CR3[2:0] and CR3[11:5] are ignored.
+ *
+ * In all cases, Linux puts zeros in the low ignored bits and in PWT and PCD.
+ *
+ * CR3[63] is always read as zero.  If CR4.PCIDE is set, then CR3[63] may be
+ * written as 1 to prevent the write to CR3 from flushing the TLB.
+ *
+ * On systems with SME, one bit (in a variable position!) is stolen to indicate
+ * that the top-level paging structure is encrypted.
+ *
+ * All of the remaining bits indicate the physical address of the top-level
+ * paging structure.
+ *
+ * CR3_ADDR_MASK is the mask used by read_cr3_pa().
+ */
+#ifdef CONFIG_X86_64
+/* Mask off the address space ID bits. */
+#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull
+#define CR3_PCID_MASK 0xFFFull
+#else
+/*
+ * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
+ * a tiny bit of code size by setting all the bits.
+ */
+#define CR3_ADDR_MASK 0xFFFFFFFFull
+#define CR3_PCID_MASK 0ull
+#endif
+
 #endif /* _ASM_X86_PROCESSOR_FLAGS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a28b671f1549..2e1696294af5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -231,6 +231,14 @@ native_cpuid_reg(ebx)
 native_cpuid_reg(ecx)
 native_cpuid_reg(edx)
 
+/*
+ * Friendlier CR3 helpers.
+ */
+static inline unsigned long read_cr3_pa(void)
+{
+	return __read_cr3() & CR3_ADDR_MASK;
+}
+
 static inline void load_cr3(pgd_t *pgdir)
 {
 	write_cr3(__pa(pgdir));
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 12af3e35edfa..9efaabf5b54b 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -39,7 +39,7 @@ static inline void native_write_cr2(unsigned long val)
 	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
 }
 
-static inline unsigned long native_read_cr3(void)
+static inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
 	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
@@ -159,9 +159,13 @@ static inline void write_cr2(unsigned long x)
 	native_write_cr2(x);
 }
 
-static inline unsigned long read_cr3(void)
+/*
+ * Careful!  CR3 contains more than just an address.  You probably want
+ * read_cr3_pa() instead.
+ */
+static inline unsigned long __read_cr3(void)
 {
-	return native_read_cr3();
+	return __native_read_cr3();
 }
 
 static inline void write_cr3(unsigned long x)
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..50ea3482e1d1 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
@@ -151,7 +156,7 @@ static inline void __native_flush_tlb(void)
 	 * back:
 	 */
 	preempt_disable();
-	native_write_cr3(native_read_cr3());
+	native_write_cr3(__native_read_cr3());
 	preempt_enable();
 }
 
@@ -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()
 
@@ -307,29 +244,32 @@ 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
 
-static inline void reset_lazy_tlbstate(void)
+static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
+					struct mm_struct *mm)
 {
-	this_cpu_write(cpu_tlbstate.state, 0);
-	this_cpu_write(cpu_tlbstate.active_mm, &init_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/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 567de50a4c2a..185f3d10c194 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -104,6 +104,8 @@
 #define X86_CR4_OSFXSR		_BITUL(X86_CR4_OSFXSR_BIT)
 #define X86_CR4_OSXMMEXCPT_BIT	10 /* enable unmasked SSE exceptions */
 #define X86_CR4_OSXMMEXCPT	_BITUL(X86_CR4_OSXMMEXCPT_BIT)
+#define X86_CR4_LA57_BIT	12 /* enable 5-level page tables */
+#define X86_CR4_LA57		_BITUL(X86_CR4_LA57_BIT)
 #define X86_CR4_VMXE_BIT	13 /* enable VMX virtualization */
 #define X86_CR4_VMXE		_BITUL(X86_CR4_VMXE_BIT)
 #define X86_CR4_SMXE_BIT	14 /* enable safer mode (TXT) */