mmu_notifier: Allow to manage CPU external TLBs

index deca874..1bac99c 100644
@@ -235,6 +235,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 		__mmu_notifier_invalidate_range_end(mm, start, end);
 }
 
+static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 	mm->mmu_notifier_mm = NULL;

@@ -326,6 +331,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 {
 }
 
+static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 }

index 1bac99c..f760e95 100644
@@ -273,6 +273,32 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__young;							\
 })
 
+#define	ptep_clear_flush_notify(__vma, __address, __ptep)		\
+({									\
+	unsigned long ___addr = __address & PAGE_MASK;			\
+	struct mm_struct *___mm = (__vma)->vm_mm;			\
+	pte_t ___pte;							\
+									\
+	___pte = ptep_clear_flush(__vma, __address, __ptep);		\
+	mmu_notifier_invalidate_range(___mm, ___addr,			\
+					___addr + PAGE_SIZE);		\
+									\
+	___pte;								\
+})
+
+#define pmdp_clear_flush_notify(__vma, __haddr, __pmd)			\
+({									\
+	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
+	struct mm_struct *___mm = (__vma)->vm_mm;			\
+	pmd_t ___pmd;							\
+									\
+	___pmd = pmdp_clear_flush(__vma, __haddr, __pmd);		\
+	mmu_notifier_invalidate_range(___mm, ___haddr,			\
+				      ___haddr + HPAGE_PMD_SIZE);	\
+									\
+	___pmd;								\
+})
+
 /*
  * set_pte_at_notify() sets the pte _after_ running the notifier.
  * This is safe to start by updating the secondary MMUs, because the primary MMU

@@ -346,6 +372,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
+#define	ptep_clear_flush_notify ptep_clear_flush
+#define pmdp_clear_flush_notify pmdp_clear_flush
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */

index 6f3254e..642262d 100644
@@ -186,7 +186,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	}
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
-	ptep_clear_flush(vma, addr, ptep);
+	ptep_clear_flush_notify(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
 	page_remove_rmap(page);

index 72b8fa3..9129013 100644
@@ -37,7 +37,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (pte_present(pte)) {
 		flush_cache_page(vma, addr, pte_pfn(pte));
-		pte = ptep_clear_flush(vma, addr, ptep);
+		pte = ptep_clear_flush_notify(vma, addr, ptep);
 		page = vm_normal_page(vma, addr, pte);
 		if (page) {
 			if (pte_dirty(pte))

index 33514d8..b322c97 100644
@@ -1031,7 +1031,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		goto out_free_pages;
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
-	pmdp_clear_flush(vma, haddr, pmd);
+	pmdp_clear_flush_notify(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);

@@ -1168,7 +1168,7 @@ alloc:
 		pmd_t entry;
 		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		pmdp_clear_flush(vma, haddr, pmd);
+		pmdp_clear_flush_notify(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);

@@ -1499,7 +1499,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		pmd_t entry;
 		ret = 1;
 		if (!prot_numa) {
-			entry = pmdp_get_and_clear(mm, addr, pmd);
+			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
 			if (pmd_numa(entry))
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);

@@ -1631,6 +1631,7 @@ static int __split_huge_page_splitting(struct page *page,
 		 * serialize against split_huge_page*.
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
+
 		ret = 1;
 		spin_unlock(ptl);
 	}

@@ -2793,7 +2794,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	pmd_t _pmd;
 	int i;
 
-	pmdp_clear_flush(vma, haddr, pmd);
+	pmdp_clear_flush_notify(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);

index 9221c02..603851d 100644
@@ -2602,8 +2602,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			}
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else {
-			if (cow)
+			if (cow) {
 				huge_ptep_set_wrprotect(src, addr, src_pte);
+				mmu_notifier_invalidate_range(src, mmun_start,
+								   mmun_end);
+			}
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);

@@ -2911,6 +2914,7 @@ retry_avoidcopy:
 
 		/* Break COW */
 		huge_ptep_clear_flush(vma, address, ptep);
+		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
 		page_remove_rmap(old_page);

@@ -3385,6 +3389,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	 * and that page table be reused and filled with junk.
 	 */
 	flush_tlb_range(vma, start, end);
+	mmu_notifier_invalidate_range(mm, start, end);
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 

index 346ddc9..a73df3b 100644
@@ -892,7 +892,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 		 * this assure us that no O_DIRECT can happen after the check
 		 * or in the middle of the check.
 		 */
-		entry = ptep_clear_flush(vma, addr, ptep);
+		entry = ptep_clear_flush_notify(vma, addr, ptep);
 		/*
 		 * Check that no O_DIRECT or similar I/O is in progress on the
 		 * page

@@ -960,7 +960,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	page_add_anon_rmap(kpage, vma, addr);
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
-	ptep_clear_flush(vma, addr, ptep);
+	ptep_clear_flush_notify(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
 	page_remove_rmap(page);

index 7e8d820..36daa2d 100644
@@ -236,6 +236,7 @@ static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	tlb->need_flush = 0;
 	tlb_flush(tlb);
+	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
 #endif

@@ -2232,7 +2233,7 @@ 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);
 		page_add_new_anon_rmap(new_page, vma, address);
 		/*
 		 * We call the notify macro here because, when using secondary

index be6dbf9..d3fb8d0 100644
@@ -1875,7 +1875,7 @@ fail_putback:
 	 */
 	flush_cache_range(vma, mmun_start, mmun_end);
 	page_add_anon_rmap(new_page, vma, mmun_start);
-	pmdp_clear_flush(vma, mmun_start, pmd);
+	pmdp_clear_flush_notify(vma, mmun_start, pmd);
 	set_pmd_at(mm, mmun_start, pmd, entry);
 	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);

@@ -1883,6 +1883,7 @@ fail_putback:
 	if (page_count(page) != 2) {
 		set_pmd_at(mm, mmun_start, pmd, orig_entry);
 		flush_tlb_range(vma, mmun_start, mmun_end);
+		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		update_mmu_cache_pmd(vma, address, &entry);
 		page_remove_rmap(new_page);
 		goto fail_putback;

index 22a4a76..8a0d02d 100644
@@ -1380,7 +1380,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 
 		/* 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)) {

index f760e95..596ea08 100644
@@ -95,11 +95,11 @@ struct mmu_notifier_ops {
 	/*
 	 * 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().
+	 * locks protecting the reverse maps are held. If the subsystem
+	 * can't guarantee that no additional references are taken to
+	 * the pages in the range, it has to implement the
+	 * invalidate_range() notifier to remove any references taken
+	 * after invalidate_range_start().
 	 *
 	 * Invalidation of multiple concurrent ranges may be
 	 * optionally permitted by the driver. Either way the

@@ -141,6 +141,29 @@ struct mmu_notifier_ops {
 	void (*invalidate_range_end)(struct mmu_notifier *mn,
 				     struct mm_struct *mm,
 				     unsigned long start, unsigned long end);
+
+	/*
+	 * invalidate_range() is either called between
+	 * invalidate_range_start() and invalidate_range_end() when the
+	 * VM has to free pages that where unmapped, but before the
+	 * pages are actually freed, or outside of _start()/_end() when
+	 * page-table pages are about to be freed.
+	 *
+	 * If invalidate_range() is used to manage a non-CPU TLB with
+	 * shared page-tables, it not necessary to implement the
+	 * invalidate_range_start()/end() notifiers, as
+	 * invalidate_range() alread catches the points in time when an
+	 * external TLB range needs to be flushed.
+	 *
+	 * The invalidate_range() function is called under the ptl
+	 * spin-lock and not allowed to sleep.
+	 *
+	 * Note that this function might be called with just a sub-range
+	 * of what was passed to invalidate_range_start()/end(), if
+	 * called between those functions.
+	 */
+	void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm,
+				 unsigned long start, unsigned long end);
 };
 
 /*

@@ -184,6 +207,8 @@ 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);
+extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end);
 
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {

@@ -238,6 +263,8 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_range(mm, start, end);
 }
 
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)

index 41cefdf..e8ecbed 100644
@@ -173,6 +173,16 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		/*
+		 * Call invalidate_range here too to avoid the need for the
+		 * subsystem of having to register an invalidate_range_end
+		 * call-back when there is invalidate_range already. Usually a
+		 * subsystem registers either invalidate_range_start()/end() or
+		 * invalidate_range(), so this will be no additional overhead
+		 * (besides the pointer check).
+		 */
+		if (mn->ops->invalidate_range)
+			mn->ops->invalidate_range(mn, mm, start, end);
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}

@@ -180,6 +190,21 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
 
+void __mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range)
+			mn->ops->invalidate_range(mn, mm, start, end);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range);
+
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
 				    struct mm_struct *mm,
 				    int take_mmap_sem)