From: john cooper <john.cooper@redhat.com>
Date: Sat, 4 Apr 2009 16:28:58 -0400
Subject: [mm] mmu-notifier: optimized ability to admin host pages
Message-id: 49D7C30A.3050809@redhat.com
O-Subject: [RHEL5.4 PATCH] implement mmu_notifier mechanism V3, [3/5] BZ#485718
Bugzilla: 485718
RH-Acked-by: Rik van Riel <riel@redhat.com>

BZ#485718  https://bugzilla.redhat.com/show_bug.cgi?id=485718

This mechanism provides an optimized ability for KVM to
administer host pages used by a guest in shadow mmu
translations (shadow pte, shadow tlb).  These shadow
translations may be traversed asynchronously via an
mmu during guest mode execution, causing a race to
exist between this asynchronous access and (for example)
the host attempting to swap out the associated guest page.
Without such visibility into host vm operations this race
is sub-optimally addressed via guest page pinning and
map/unmap of shadow translations.

See the description of the API introduced by this patch
which annotates the definitiopn of 'struct mmu_notifier_ops'
in include/linux/mmu_notifier.h for detail.

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
new file mode 100644
index 0000000..fecf0ad
--- /dev/null
+++ b/include/linux/mmu_notifier.h
@@ -0,0 +1,279 @@
+#ifndef _LINUX_MMU_NOTIFIER_H
+#define _LINUX_MMU_NOTIFIER_H
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+
+struct mmu_notifier;
+struct mmu_notifier_ops;
+
+#ifdef CONFIG_MMU_NOTIFIER
+
+/*
+ * The mmu notifier_mm structure is allocated and installed in
+ * mm->mmu_notifier_mm inside the mm_take_all_locks() protected
+ * critical section and it's released only when mm_count reaches zero
+ * in mmdrop().
+ */
+struct mmu_notifier_mm {
+	/* all mmu notifiers registerd in this mm are queued in this list */
+	struct hlist_head list;
+	/* to serialize the list modifications and hlist_unhashed */
+	spinlock_t lock;
+};
+
+struct mmu_notifier_ops {
+	/*
+	 * Called either by mmu_notifier_unregister or when the mm is
+	 * being destroyed by exit_mmap, always before all pages are
+	 * freed. This can run concurrently with other mmu notifier
+	 * methods (the ones invoked outside the mm context) and it
+	 * should tear down all secondary mmu mappings and freeze the
+	 * secondary mmu. If this method isn't implemented you've to
+	 * be sure that nothing could possibly write to the pages
+	 * through the secondary mmu by the time the last thread with
+	 * tsk->mm == mm exits.
+	 *
+	 * As side note: the pages freed after ->release returns could
+	 * be immediately reallocated by the gart at an alias physical
+	 * address with a different cache model, so if ->release isn't
+	 * implemented because all _software_ driven memory accesses
+	 * through the secondary mmu are terminated by the time the
+	 * last thread of this mm quits, you've also to be sure that
+	 * speculative _hardware_ operations can't allocate dirty
+	 * cachelines in the cpu that could not be snooped and made
+	 * coherent with the other read and write operations happening
+	 * through the gart alias address, so leading to memory
+	 * corruption.
+	 */
+	void (*release)(struct mmu_notifier *mn,
+			struct mm_struct *mm);
+
+	/*
+	 * clear_flush_young is called after the VM is
+	 * test-and-clearing the young/accessed bitflag in the
+	 * pte. This way the VM will provide proper aging to the
+	 * accesses to the page through the secondary MMUs and not
+	 * only to the ones through the Linux pte.
+	 */
+	int (*clear_flush_young)(struct mmu_notifier *mn,
+				 struct mm_struct *mm,
+				 unsigned long address);
+
+	/*
+	 * Before this is invoked any secondary MMU is still ok to
+	 * read/write to the page previously pointed to by the Linux
+	 * pte because the page hasn't been freed yet and it won't be
+	 * freed until this returns. If required set_page_dirty has to
+	 * be called internally to this method.
+	 */
+	void (*invalidate_page)(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long address);
+
+	/*
+	 * invalidate_range_start() and invalidate_range_end() must be
+	 * paired and are called only when the mmap_sem and/or the
+	 * locks protecting the reverse maps are held. The subsystem
+	 * must guarantee that no additional references are taken to
+	 * the pages in the range established between the call to
+	 * invalidate_range_start() and the matching call to
+	 * invalidate_range_end().
+	 *
+	 * Invalidation of multiple concurrent ranges may be
+	 * optionally permitted by the driver. Either way the
+	 * establishment of sptes is forbidden in the range passed to
+	 * invalidate_range_begin/end for the whole duration of the
+	 * invalidate_range_begin/end critical section.
+	 *
+	 * invalidate_range_start() is called when all pages in the
+	 * range are still mapped and have at least a refcount of one.
+	 *
+	 * invalidate_range_end() is called when all pages in the
+	 * range have been unmapped and the pages have been freed by
+	 * the VM.
+	 *
+	 * The VM will remove the page table entries and potentially
+	 * the page between invalidate_range_start() and
+	 * invalidate_range_end(). If the page must not be freed
+	 * because of pending I/O or other circumstances then the
+	 * invalidate_range_start() callback (or the initial mapping
+	 * by the driver) must make sure that the refcount is kept
+	 * elevated.
+	 *
+	 * If the driver increases the refcount when the pages are
+	 * initially mapped into an address space then either
+	 * invalidate_range_start() or invalidate_range_end() may
+	 * decrease the refcount. If the refcount is decreased on
+	 * invalidate_range_start() then the VM can free pages as page
+	 * table entries are removed.  If the refcount is only
+	 * droppped on invalidate_range_end() then the driver itself
+	 * will drop the last refcount but it must take care to flush
+	 * any secondary tlb before doing the final free on the
+	 * page. Pages will no longer be referenced by the linux
+	 * address space but may still be referenced by sptes until
+	 * the last refcount is dropped.
+	 */
+	void (*invalidate_range_start)(struct mmu_notifier *mn,
+				       struct mm_struct *mm,
+				       unsigned long start, unsigned long end);
+	void (*invalidate_range_end)(struct mmu_notifier *mn,
+				     struct mm_struct *mm,
+				     unsigned long start, unsigned long end);
+};
+
+/*
+ * The notifier chains are protected by mmap_sem and/or the reverse map
+ * semaphores. Notifier chains are only changed when all reverse maps and
+ * the mmap_sem locks are taken.
+ *
+ * Therefore notifier chains can only be traversed when either
+ *
+ * 1. mmap_sem is held.
+ * 2. One of the reverse map locks is held (i_mmap_lock or anon_vma->lock).
+ * 3. No other concurrent thread can access the list (release)
+ */
+struct mmu_notifier {
+	struct hlist_node hlist;
+	const struct mmu_notifier_ops *ops;
+};
+
+static inline int mm_has_notifiers(struct mm_struct *mm)
+{
+	return unlikely(mm->mmu_notifier_mm);
+}
+
+extern int mmu_notifier_register(struct mmu_notifier *mn,
+				 struct mm_struct *mm);
+extern int __mmu_notifier_register(struct mmu_notifier *mn,
+				   struct mm_struct *mm);
+extern void mmu_notifier_unregister(struct mmu_notifier *mn,
+				    struct mm_struct *mm);
+extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
+extern void __mmu_notifier_release(struct mm_struct *mm);
+extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					  unsigned long address);
+extern void __mmu_notifier_invalidate_page(struct mm_struct *mm,
+					  unsigned long address);
+extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end);
+extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end);
+
+static inline void mmu_notifier_release(struct mm_struct *mm)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_release(mm);
+}
+
+static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	if (mm_has_notifiers(mm))
+		return __mmu_notifier_clear_flush_young(mm, address);
+	return 0;
+}
+
+static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
+					  unsigned long address)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_page(mm, address);
+}
+
+static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_range_start(mm, start, end);
+}
+
+static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_range_end(mm, start, end);
+}
+
+static inline void mmu_notifier_mm_init(struct mm_struct *mm)
+{
+	mm->mmu_notifier_mm = NULL;
+}
+
+static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_mm_destroy(mm);
+}
+
+/*
+ * These two macros will sometime replace ptep_clear_flush.
+ * ptep_clear_flush is impleemnted as macro itself, so this also is
+ * implemented as a macro until ptep_clear_flush will converted to an
+ * inline function, to diminish the risk of compilation failure. The
+ * invalidate_page method over time can be moved outside the PT lock
+ * and these two macros can be later removed.
+ */
+#define ptep_clear_flush_notify(__vma, __address, __ptep)		\
+({									\
+	pte_t __pte;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__pte = ptep_clear_flush(___vma, ___address, __ptep);		\
+	mmu_notifier_invalidate_page(___vma->vm_mm, ___address);	\
+	__pte;								\
+})
+
+#define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
+({									\
+	int __young;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__young = ptep_clear_flush_young(___vma, ___address, __ptep);	\
+	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
+						  ___address);		\
+	__young;							\
+})
+
+#else /* CONFIG_MMU_NOTIFIER */
+
+static inline void mmu_notifier_release(struct mm_struct *mm)
+{
+}
+
+static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return 0;
+}
+
+static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
+					  unsigned long address)
+{
+}
+
+static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
+static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
+static inline void mmu_notifier_mm_init(struct mm_struct *mm)
+{
+}
+
+static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
+{
+}
+
+#define ptep_clear_flush_young_notify ptep_clear_flush_young
+#define ptep_clear_flush_notify ptep_clear_flush
+
+#endif /* CONFIG_MMU_NOTIFIER */
+
+#endif /* _LINUX_MMU_NOTIFIER_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ce00fe8..267ddcb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -67,6 +67,7 @@ struct sched_param {
 #include <linux/fs_struct.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
+#include <linux/cpumask.h>
 #include <linux/pid.h>
 #include <linux/percpu.h>
 #include <linux/topology.h>
@@ -393,6 +394,9 @@ struct mm_struct {
 	/* aio bits */
 	rwlock_t		ioctx_list_lock;
 	struct kioctx		*ioctx_list;
+#ifdef CONFIG_MMU_NOTIFIER
+	struct mmu_notifier_mm *mmu_notifier_mm;
+#endif
 };
 
 struct sighand_struct {
diff --git a/kernel/fork.c b/kernel/fork.c
index 6a953e9..f0f3640 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -26,6 +26,7 @@
 #include <linux/key.h>
 #include <linux/binfmts.h>
 #include <linux/mman.h>
+#include <linux/mmu_notifier.h>
 #include <linux/fs.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -460,6 +461,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
+		mmu_notifier_mm_init(mm);
 		return mm;
 	}
 
@@ -496,6 +498,7 @@ void fastcall __mmdrop(struct mm_struct *mm)
 	free_mm_flags(mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
+	mmu_notifier_mm_destroy(mm);
 	free_mm(mm);
 }
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 59d3216..2047f46 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -158,3 +158,6 @@ config RESOURCES_64BIT
 	default 64BIT
 	help
 	  This option allows memory and IO resources to be 64 bit.
+
+config MMU_NOTIFIER
+	bool
diff --git a/mm/Makefile b/mm/Makefile
index 9dd824c..8a8b863 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 obj-$(CONFIG_SLOB) += slob.o
+obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index a83cc14..8dc00e6 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/uio.h>
 #include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
 #include <linux/uaccess.h>
 #include <asm/tlbflush.h>
 
@@ -188,7 +189,7 @@ __xip_unmap (struct address_space * mapping,
 		if (pte) {
 			/* Nuke the page table entry. */
 			flush_cache_page(vma, address, pte_pfn(*pte));
-			pteval = ptep_clear_flush(vma, address, pte);
+			pteval = ptep_clear_flush_notify(vma, address, pte);
 			page_remove_rmap(page);
 			dec_mm_counter(mm, file_rss);
 			BUG_ON(pte_dirty(pteval));
diff --git a/mm/fremap.c b/mm/fremap.c
index 487d524..8f37a25 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -15,6 +15,7 @@
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
@@ -212,9 +213,11 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 			spin_unlock(&mapping->i_mmap_lock);
 		}
 
+		mmu_notifier_invalidate_range_start(mm, start, start + size);
 		err = vma->vm_ops->populate(vma, start, size,
 					    vma->vm_page_prot,
 					    pgoff, flags & MAP_NONBLOCK);
+		mmu_notifier_invalidate_range_end(mm, start, start + size);
 
 		/*
 		 * We can't clear VM_NONLINEAR because we'd have to do
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 56794fd..c38767f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/sysctl.h>
 #include <linux/highmem.h>
+#include <linux/mmu_notifier.h>
 #include <linux/nodemask.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
@@ -445,6 +446,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	BUG_ON(start & ~HPAGE_MASK);
 	BUG_ON(end & ~HPAGE_MASK);
 
+	mmu_notifier_invalidate_range_start(mm, start, end);
 	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += HPAGE_SIZE) {
 		ptep = huge_pte_offset(mm, address);
@@ -463,6 +465,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	}
 	spin_unlock(&mm->page_table_lock);
 	flush_tlb_range(vma, start, end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/mm/memory.c b/mm/memory.c
index 5233ed2..7c07d55 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -50,6 +50,7 @@
 #include <linux/delayacct.h>
 #include <linux/init.h>
 #include <linux/writeback.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -668,6 +669,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	unsigned long next;
 	unsigned long addr = src_vma->vm_start;
 	unsigned long end = src_vma->vm_end;
+	int ret;
 
 	/*
 	 * Don't copy ptes where a page fault will fill them correctly.
@@ -684,17 +686,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		return copy_hugetlb_page_range(dst_mm, src_mm,
 					       dst_vma, src_vma);
 
+	/*
+	 * We need to invalidate the secondary MMU mappings only when
+	 * there could be a permission downgrade on the ptes of the
+	 * parent mm. And a permission downgrade will only happen if
+	 * is_cow_mapping() returns true.
+	 */
+	if (is_cow_mapping(src_vma->vm_flags))
+		mmu_notifier_invalidate_range_start(src_mm, addr, end);
+
+	ret = 0;
 	dst_pgd = pgd_offset(dst_mm, addr);
 	src_pgd = pgd_offset(src_mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
-				   dst_vma, src_vma, addr, next))
-			return -ENOMEM;
+		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+				   dst_vma, src_vma, addr, next))) {
+			ret = -ENOMEM;
+			break;
+		}
 	} while (dst_pgd++, src_pgd++, addr = next, addr != end);
-	return 0;
+
+	if (is_cow_mapping(src_vma->vm_flags))
+		mmu_notifier_invalidate_range_end(src_mm,
+						src_vma->vm_start, end);
+	return ret;
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
@@ -904,7 +922,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 	unsigned long start = start_addr;
 	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
 	int fullmm = (*tlbp)->fullmm;
+	struct mm_struct *mm = vma->vm_mm;
 
+	mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
 		unsigned long end;
 
@@ -955,6 +975,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
 		}
 	}
 out:
+	mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
 	return start;	/* which is now the end (or restart) address */
 }
 
@@ -1639,10 +1660,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long end = addr + size;
+	unsigned long start = addr, end = addr + size;
 	int err;
 
 	BUG_ON(addr >= end);
+	mmu_notifier_invalidate_range_start(mm, start, end);
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
@@ -1650,6 +1672,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
+	mmu_notifier_invalidate_range_end(mm, start, end);
 	return err;
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
@@ -1941,7 +1964,7 @@ gotten:
 		 * seen in the presence of one thread doing SMC and another
 		 * thread doing COW.
 		 */
-		ptep_clear_flush(vma, address, page_table);
+		ptep_clear_flush_notify(vma, address, page_table);
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
 		lru_cache_add_active(new_page);
diff --git a/mm/mmap.c b/mm/mmap.c
index 634fa18..821587c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -25,6 +25,7 @@
 #include <linux/mount.h>
 #include <linux/mempolicy.h>
 #include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
 #include <linux/random.h>
 
 #include <asm/uaccess.h>
@@ -2085,6 +2086,7 @@ void exit_mmap(struct mm_struct *mm)
 #ifdef arch_exit_mmap
 	arch_exit_mmap(mm);
 #endif
+	mmu_notifier_release(mm);
 
 	lru_add_drain();
 	flush_cache_mm(mm);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
new file mode 100644
index 0000000..599576f
--- /dev/null
+++ b/mm/mmu_notifier.c
@@ -0,0 +1,277 @@
+/*
+ *  linux/mm/mmu_notifier.c
+ *
+ *  Copyright (C) 2008  Qumranet, Inc.
+ *  Copyright (C) 2008  SGI
+ *             Christoph Lameter <clameter@sgi.com>
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+
+#include <linux/list.h>
+#include <linux/mmu_notifier.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+
+/*
+ * This function can't run concurrently against mmu_notifier_register
+ * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
+ * runs with mm_users == 0. Other tasks may still invoke mmu notifiers
+ * in parallel despite there being no task using this mm any more,
+ * through the vmas outside of the exit_mmap context, such as with
+ * vmtruncate. This serializes against mmu_notifier_unregister with
+ * the mmu_notifier_mm->lock in addition to RCU and it serializes
+ * against the other mmu notifiers with RCU. struct mmu_notifier_mm
+ * can't go away from under us as exit_mmap holds an mm_count pin
+ * itself.
+ */
+void __mmu_notifier_release(struct mm_struct *mm)
+{
+	struct mmu_notifier *mn;
+
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
+		mn = hlist_entry(mm->mmu_notifier_mm->list.first,
+				 struct mmu_notifier,
+				 hlist);
+		/*
+		 * We arrived before mmu_notifier_unregister so
+		 * mmu_notifier_unregister will do nothing other than
+		 * to wait ->release to finish and
+		 * mmu_notifier_unregister to return.
+		 */
+		hlist_del_init_rcu(&mn->hlist);
+		/*
+		 * RCU here will block mmu_notifier_unregister until
+		 * ->release returns.
+		 */
+		rcu_read_lock();
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+		/*
+		 * if ->release runs before mmu_notifier_unregister it
+		 * must be handled as it's the only way for the driver
+		 * to flush all existing sptes and stop the driver
+		 * from establishing any more sptes before all the
+		 * pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+		rcu_read_unlock();
+		spin_lock(&mm->mmu_notifier_mm->lock);
+	}
+	spin_unlock(&mm->mmu_notifier_mm->lock);
+
+	/*
+	 * synchronize_rcu here prevents mmu_notifier_release to
+	 * return to exit_mmap (which would proceed freeing all pages
+	 * in the mm) until the ->release method returns, if it was
+	 * invoked by mmu_notifier_unregister.
+	 *
+	 * The mmu_notifier_mm can't go away from under us because one
+	 * mm_count is hold by exit_mmap.
+	 */
+	synchronize_rcu();
+}
+
+/*
+ * If no young bitflag is supported by the hardware, ->clear_flush_young can
+ * unmap the address and return 1 or 0 depending if the mapping previously
+ * existed or not.
+ */
+int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					unsigned long address)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+	int young = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->clear_flush_young)
+			young |= mn->ops->clear_flush_young(mn, mm, address);
+	}
+	rcu_read_unlock();
+
+	return young;
+}
+
+void __mmu_notifier_invalidate_page(struct mm_struct *mm,
+					  unsigned long address)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_page)
+			mn->ops->invalidate_page(mn, mm, address);
+	}
+	rcu_read_unlock();
+}
+
+void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range_start)
+			mn->ops->invalidate_range_start(mn, mm, start, end);
+	}
+	rcu_read_unlock();
+}
+
+void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range_end)
+			mn->ops->invalidate_range_end(mn, mm, start, end);
+	}
+	rcu_read_unlock();
+}
+
+static int do_mmu_notifier_register(struct mmu_notifier *mn,
+				    struct mm_struct *mm,
+				    int take_mmap_sem)
+{
+	struct mmu_notifier_mm *mmu_notifier_mm;
+	int ret;
+
+	BUG_ON(atomic_read(&mm->mm_users) <= 0);
+
+	ret = -ENOMEM;
+	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
+	if (unlikely(!mmu_notifier_mm))
+		goto out;
+
+	if (take_mmap_sem)
+		down_write(&mm->mmap_sem);
+	ret = mm_take_all_locks(mm);
+	if (unlikely(ret))
+		goto out_cleanup;
+
+	if (!mm_has_notifiers(mm)) {
+		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
+		spin_lock_init(&mmu_notifier_mm->lock);
+		mm->mmu_notifier_mm = mmu_notifier_mm;
+		mmu_notifier_mm = NULL;
+	}
+	atomic_inc(&mm->mm_count);
+
+	/*
+	 * Serialize the update against mmu_notifier_unregister. A
+	 * side note: mmu_notifier_release can't run concurrently with
+	 * us because we hold the mm_users pin (either implicitly as
+	 * current->mm or explicitly with get_task_mm() or similar).
+	 * We can't race against any other mmu notifier method either
+	 * thanks to mm_take_all_locks().
+	 */
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
+	spin_unlock(&mm->mmu_notifier_mm->lock);
+
+	mm_drop_all_locks(mm);
+out_cleanup:
+	if (take_mmap_sem)
+		up_write(&mm->mmap_sem);
+	/* kfree() does nothing if mmu_notifier_mm is NULL */
+	kfree(mmu_notifier_mm);
+out:
+	BUG_ON(atomic_read(&mm->mm_users) <= 0);
+	return ret;
+}
+
+/*
+ * Must not hold mmap_sem nor any other VM related lock when calling
+ * this registration function. Must also ensure mm_users can't go down
+ * to zero while this runs to avoid races with mmu_notifier_release,
+ * so mm has to be current->mm or the mm should be pinned safely such
+ * as with get_task_mm(). If the mm is not current->mm, the mm_users
+ * pin should be released by calling mmput after mmu_notifier_register
+ * returns. mmu_notifier_unregister must be always called to
+ * unregister the notifier. mm_count is automatically pinned to allow
+ * mmu_notifier_unregister to safely run at any time later, before or
+ * after exit_mmap. ->release will always be called before exit_mmap
+ * frees the pages.
+ */
+int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	return do_mmu_notifier_register(mn, mm, 1);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_register);
+
+/*
+ * Same as mmu_notifier_register but here the caller must hold the
+ * mmap_sem in write mode.
+ */
+int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	return do_mmu_notifier_register(mn, mm, 0);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_register);
+
+/* this is called after the last mmu_notifier_unregister() returned */
+void __mmu_notifier_mm_destroy(struct mm_struct *mm)
+{
+	BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list));
+	kfree(mm->mmu_notifier_mm);
+	mm->mmu_notifier_mm = LIST_POISON1; /* debug */
+}
+
+/*
+ * This releases the mm_count pin automatically and frees the mm
+ * structure if it was the last user of it. It serializes against
+ * running mmu notifiers with RCU and against mmu_notifier_unregister
+ * with the unregister lock + RCU. All sptes must be dropped before
+ * calling mmu_notifier_unregister. ->release or any other notifier
+ * method may be invoked concurrently with mmu_notifier_unregister,
+ * and only after mmu_notifier_unregister returned we're guaranteed
+ * that ->release or any other method can't run anymore.
+ */
+void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	BUG_ON(atomic_read(&mm->mm_count) <= 0);
+
+	spin_lock(&mm->mmu_notifier_mm->lock);
+	if (!hlist_unhashed(&mn->hlist)) {
+		hlist_del_rcu(&mn->hlist);
+
+		/*
+		 * RCU here will force exit_mmap to wait ->release to finish
+		 * before freeing the pages.
+		 */
+		rcu_read_lock();
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+		/*
+		 * exit_mmap will block in mmu_notifier_release to
+		 * guarantee ->release is called before freeing the
+		 * pages.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+		rcu_read_unlock();
+	} else
+		spin_unlock(&mm->mmu_notifier_mm->lock);
+
+	/*
+	 * Wait any running method to finish, of course including
+	 * ->release if it was run by mmu_notifier_relase instead of us.
+	 */
+	synchronize_rcu();
+
+	BUG_ON(atomic_read(&mm->mm_count) <= 0);
+
+	mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 6751990..629d6e8 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -21,6 +21,7 @@
 #include <linux/syscalls.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -204,10 +205,12 @@ success:
 		dirty_accountable = 1;
 	}
 
+	mmu_notifier_invalidate_range_start(mm, start, end);
 	if (is_vm_hugetlb_page(vma))
 		hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
 	else
 		change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
+	mmu_notifier_invalidate_range_end(mm, start, end);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;
diff --git a/mm/mremap.c b/mm/mremap.c
index 1771e78..459890e 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -74,7 +75,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
 	spinlock_t *old_ptl, *new_ptl;
+	unsigned long old_start;
 
+	old_start = old_addr;
+	mmu_notifier_invalidate_range_start(vma->vm_mm,
+					    old_start, old_end);
 	if (vma->vm_file) {
 		/*
 		 * Subtle point from Rajesh Venkatasubramanian: before
@@ -115,6 +120,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
+	mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 
 #define LATENCY_LIMIT	(64 * PAGE_SIZE)
diff --git a/mm/rmap.c b/mm/rmap.c
index 887c3df..0673a13 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -53,6 +53,7 @@
 #include <linux/rmap.h>
 #include <linux/rcupdate.h>
 #include <linux/module.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 
@@ -306,7 +307,7 @@ static int page_referenced_one(struct page *page,
 	if (!pte)
 		goto out;
 
-	if (ptep_clear_flush_young(vma, address, pte))
+	if (ptep_clear_flush_young_notify(vma, address, pte))
 		referenced++;
 
 	/* Pretend the page is referenced if the task has the
@@ -454,7 +455,7 @@ static int page_mkclean_one(struct page *page, struct vm_area_struct *vma)
 		pte_t entry;
 
 		flush_cache_page(vma, address, pte_pfn(*pte));
-		entry = ptep_clear_flush(vma, address, pte);
+		entry = ptep_clear_flush_notify(vma, address, pte);
 		entry = pte_wrprotect(entry);
 		entry = pte_mkclean(entry);
 		set_pte_at(mm, address, pte, entry);
@@ -636,14 +637,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 * skipped over this mm) then we should reactivate it.
 	 */
 	if (!migration && ((vma->vm_flags & VM_LOCKED) ||
-			(ptep_clear_flush_young(vma, address, pte)))) {
+			(ptep_clear_flush_young_notify(vma, address, pte)))) {
 		ret = SWAP_FAIL;
 		goto out_unmap;
 	}
 
 	/* Nuke the page table entry. */
 	flush_cache_page(vma, address, page_to_pfn(page));
-	pteval = ptep_clear_flush(vma, address, pte);
+	pteval = ptep_clear_flush_notify(vma, address, pte);
 
 	/* Move the dirty bit to the physical page now the pte is gone. */
 	if (pte_dirty(pteval))
@@ -768,12 +769,12 @@ static void try_to_unmap_cluster(unsigned long cursor,
 		page = vm_normal_page(vma, address, *pte);
 		BUG_ON(!page || PageAnon(page));
 
-		if (ptep_clear_flush_young(vma, address, pte))
+		if (ptep_clear_flush_young_notify(vma, address, pte))
 			continue;
 
 		/* Nuke the page table entry. */
 		flush_cache_page(vma, address, pte_pfn(*pte));
-		pteval = ptep_clear_flush(vma, address, pte);
+		pteval = ptep_clear_flush_notify(vma, address, pte);
 
 		/* If nonlinear, store the file page offset in the pte. */
 		if (page->index != linear_page_index(vma, address))