1 files changed, 177 insertions, 26 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 38a336e2eea1..f6f0d2dda2ea 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -56,6 +56,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 
@@ -132,9 +133,14 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                         if (unlikely(!anon_vma))
                                 goto out_enomem_free_avc;
                         allocated = anon_vma;
+                        /*
+                         * This VMA had no anon_vma yet.  This anon_vma is
+                         * the root of any anon_vma tree that might form.
+                         */
+                        anon_vma->root = anon_vma;
                 }
 
-                spin_lock(&anon_vma->lock);
+                anon_vma_lock(anon_vma);
                 /* page_table_lock to protect against threads */
                 spin_lock(&mm->page_table_lock);
                 if (likely(!vma->anon_vma)) {
@@ -142,12 +148,12 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                         avc->anon_vma = anon_vma;
                         avc->vma = vma;
                         list_add(&avc->same_vma, &vma->anon_vma_chain);
-                        list_add(&avc->same_anon_vma, &anon_vma->head);
+                        list_add_tail(&avc->same_anon_vma, &anon_vma->head);
                         allocated = NULL;
                         avc = NULL;
                 }
                 spin_unlock(&mm->page_table_lock);
-                spin_unlock(&anon_vma->lock);
+                anon_vma_unlock(anon_vma);
 
                 if (unlikely(allocated))
                         anon_vma_free(allocated);
@@ -170,9 +176,9 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
         avc->anon_vma = anon_vma;
         list_add(&avc->same_vma, &vma->anon_vma_chain);
 
-        spin_lock(&anon_vma->lock);
+        anon_vma_lock(anon_vma);
         list_add_tail(&avc->same_anon_vma, &anon_vma->head);
-        spin_unlock(&anon_vma->lock);
+        anon_vma_unlock(anon_vma);
 }
 
 /*
@@ -224,9 +230,21 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
         avc = anon_vma_chain_alloc();
         if (!avc)
                 goto out_error_free_anon_vma;
-        anon_vma_chain_link(vma, avc, anon_vma);
+
+        /*
+         * The root anon_vma's spinlock is the lock actually used when we
+         * lock any of the anon_vmas in this anon_vma tree.
+         */
+        anon_vma->root = pvma->anon_vma->root;
+        /*
+         * With KSM refcounts, an anon_vma can stay around longer than the
+         * process it belongs to.  The root anon_vma needs to be pinned
+         * until this anon_vma is freed, because the lock lives in the root.
+         */
+        get_anon_vma(anon_vma->root);
         /* Mark this anon_vma as the one where our new (COWed) pages go. */
         vma->anon_vma = anon_vma;
+        anon_vma_chain_link(vma, avc, anon_vma);
 
         return 0;
 
@@ -246,22 +264,29 @@ static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain)
         if (!anon_vma)
                 return;
 
-        spin_lock(&anon_vma->lock);
+        anon_vma_lock(anon_vma);
         list_del(&anon_vma_chain->same_anon_vma);
 
         /* We must garbage collect the anon_vma if it's empty */
         empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma);
-        spin_unlock(&anon_vma->lock);
+        anon_vma_unlock(anon_vma);
 
-        if (empty)
+        if (empty) {
+                /* We no longer need the root anon_vma */
+                if (anon_vma->root != anon_vma)
+                        drop_anon_vma(anon_vma->root);
                 anon_vma_free(anon_vma);
+        }
 }
 
 void unlink_anon_vmas(struct vm_area_struct *vma)
 {
         struct anon_vma_chain *avc, *next;
 
-        /* Unlink each anon_vma chained to the VMA. */
+        /*
+         * Unlink each anon_vma chained to the VMA.  This list is ordered
+         * from newest to oldest, ensuring the root anon_vma gets freed last.
+         */
         list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) {
                 anon_vma_unlink(avc);
                 list_del(&avc->same_vma);
@@ -291,7 +316,7 @@ void __init anon_vma_init(void)
  */
 struct anon_vma *page_lock_anon_vma(struct page *page)
 {
-        struct anon_vma *anon_vma;
+        struct anon_vma *anon_vma, *root_anon_vma;
         unsigned long anon_mapping;
 
         rcu_read_lock();
@@ -302,8 +327,21 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
                 goto out;
 
         anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-        spin_lock(&anon_vma->lock);
-        return anon_vma;
+        root_anon_vma = ACCESS_ONCE(anon_vma->root);
+        spin_lock(&root_anon_vma->lock);
+
+        /*
+         * If this page is still mapped, then its anon_vma cannot have been
+         * freed.  But if it has been unmapped, we have no security against
+         * the anon_vma structure being freed and reused (for another anon_vma:
+         * SLAB_DESTROY_BY_RCU guarantees that - so the spin_lock above cannot
+         * corrupt): with anon_vma_prepare() or anon_vma_fork() redirecting
+         * anon_vma->root before page_unlock_anon_vma() is called to unlock.
+         */
+        if (page_mapped(page))
+                return anon_vma;
+
+        spin_unlock(&root_anon_vma->lock);
 out:
         rcu_read_unlock();
         return NULL;
@@ -311,7 +349,7 @@ out:
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
-        spin_unlock(&anon_vma->lock);
+        anon_vma_unlock(anon_vma);
         rcu_read_unlock();
 }
 
@@ -326,6 +364,8 @@ vma_address(struct page *page, struct vm_area_struct *vma)
         pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
         unsigned long address;
 
+        if (unlikely(is_vm_hugetlb_page(vma)))
+                pgoff = page->index << huge_page_order(page_hstate(page));
         address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
         if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
                 /* page should be within @vma mapping range */
@@ -340,9 +380,10 @@ vma_address(struct page *page, struct vm_area_struct *vma)
  */
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
-        if (PageAnon(page))
-                ;
-        else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
+        if (PageAnon(page)) {
+                if (vma->anon_vma->root != page_anon_vma(page)->root)
+                        return -EFAULT;
+        } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
                 if (!vma->vm_file ||
                     vma->vm_file->f_mapping != page->mapping)
                         return -EFAULT;
@@ -369,6 +410,12 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
         pte_t *pte;
         spinlock_t *ptl;
 
+        if (unlikely(PageHuge(page))) {
+                pte = huge_pte_offset(mm, address);
+                ptl = &mm->page_table_lock;
+                goto check;
+        }
+
         pgd = pgd_offset(mm, address);
         if (!pgd_present(*pgd))
                 return NULL;
@@ -389,6 +436,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
         }
 
         ptl = pte_lockptr(mm, pmd);
+check:
         spin_lock(ptl);
         if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
                 *ptlp = ptl;
@@ -743,14 +791,20 @@ static void __page_set_anon_rmap(struct page *page,
          * If the page isn't exclusively mapped into this vma,
          * we must use the _oldest_ possible anon_vma for the
          * page mapping!
-         *
-         * So take the last AVC chain entry in the vma, which is
-         * the deepest ancestor, and use the anon_vma from that.
          */
         if (!exclusive) {
-                struct anon_vma_chain *avc;
-                avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
-                anon_vma = avc->anon_vma;
+                if (PageAnon(page))
+                        return;
+                anon_vma = anon_vma->root;
+        } else {
+                /*
+                 * In this case, swapped-out-but-not-discarded swap-cache
+                 * is remapped. So, no need to update page->mapping here.
+                 * We convice anon_vma poitned by page->mapping is not obsolete
+                 * because vma->anon_vma is necessary to be a family of it.
+                 */
+                if (PageAnon(page))
+                        return;
         }
 
         anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
@@ -780,6 +834,7 @@ static void __page_check_anon_rmap(struct page *page,
          * are initially only visible via the pagetables, and the pte is locked
          * over the call to page_add_new_anon_rmap.
          */
+        BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root);
         BUG_ON(page->index != linear_page_index(vma, address));
 #endif
 }
@@ -798,6 +853,17 @@ static void __page_check_anon_rmap(struct page *page,
 void page_add_anon_rmap(struct page *page,
         struct vm_area_struct *vma, unsigned long address)
 {
+        do_page_add_anon_rmap(page, vma, address, 0);
+}
+
+/*
+ * Special version of the above for do_swap_page, which often runs
+ * into pages that are exclusively owned by the current process.
+ * Everybody else should continue to use page_add_anon_rmap above.
+ */
+void do_page_add_anon_rmap(struct page *page,
+        struct vm_area_struct *vma, unsigned long address, int exclusive)
+{
         int first = atomic_inc_and_test(&page->_mapcount);
         if (first)
                 __inc_zone_page_state(page, NR_ANON_PAGES);
@@ -807,7 +873,7 @@ void page_add_anon_rmap(struct page *page,
         VM_BUG_ON(!PageLocked(page));
         VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
         if (first)
-                __page_set_anon_rmap(page, vma, address, 0);
+                __page_set_anon_rmap(page, vma, address, exclusive);
         else
                 __page_check_anon_rmap(page, vma, address);
 }
@@ -873,6 +939,12 @@ void page_remove_rmap(struct page *page)
                 page_clear_dirty(page);
                 set_page_dirty(page);
         }
+        /*
+         * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
+         * and not charged by memcg for now.
+         */
+        if (unlikely(PageHuge(page)))
+                return;
         if (PageAnon(page)) {
                 mem_cgroup_uncharge_page(page);
                 __dec_zone_page_state(page, NR_ANON_PAGES);
@@ -1368,6 +1440,42 @@ int try_to_munlock(struct page *page)
                 return try_to_unmap_file(page, TTU_MUNLOCK);
 }
 
+#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
+/*
+ * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root
+ * if necessary.  Be careful to do all the tests under the lock.  Once
+ * we know we are the last user, nobody else can get a reference and we
+ * can do the freeing without the lock.
+ */
+void drop_anon_vma(struct anon_vma *anon_vma)
+{
+        BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0);
+        if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
+                struct anon_vma *root = anon_vma->root;
+                int empty = list_empty(&anon_vma->head);
+                int last_root_user = 0;
+                int root_empty = 0;
+
+                /*
+                 * The refcount on a non-root anon_vma got dropped.  Drop
+                 * the refcount on the root and check if we need to free it.
+                 */
+                if (empty && anon_vma != root) {
+                        BUG_ON(atomic_read(&root->external_refcount) <= 0);
+                        last_root_user = atomic_dec_and_test(&root->external_refcount);
+                        root_empty = list_empty(&root->head);
+                }
+                anon_vma_unlock(anon_vma);
+
+                if (empty) {
+                        anon_vma_free(anon_vma);
+                        if (root_empty && last_root_user)
+                                anon_vma_free(root);
+                }
+        }
+}
+#endif
+
 #ifdef CONFIG_MIGRATION
 /*
  * rmap_walk() and its helpers rmap_walk_anon() and rmap_walk_file():
@@ -1389,7 +1497,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
         anon_vma = page_anon_vma(page);
         if (!anon_vma)
                 return ret;
-        spin_lock(&anon_vma->lock);
+        anon_vma_lock(anon_vma);
         list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
                 struct vm_area_struct *vma = avc->vma;
                 unsigned long address = vma_address(page, vma);
@@ -1399,7 +1507,7 @@ static int rmap_walk_anon(struct page *page, int (*rmap_one)(struct page *,
                 if (ret != SWAP_AGAIN)
                         break;
         }
-        spin_unlock(&anon_vma->lock);
+        anon_vma_unlock(anon_vma);
         return ret;
 }
 
@@ -1445,3 +1553,46 @@ int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
                 return rmap_walk_file(page, rmap_one, arg);
 }
 #endif /* CONFIG_MIGRATION */
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * The following three functions are for anonymous (private mapped) hugepages.
+ * Unlike common anonymous pages, anonymous hugepages have no accounting code
+ * and no lru code, because we handle hugepages differently from common pages.
+ */
+static void __hugepage_set_anon_rmap(struct page *page,
+        struct vm_area_struct *vma, unsigned long address, int exclusive)
+{
+        struct anon_vma *anon_vma = vma->anon_vma;
+        BUG_ON(!anon_vma);
+        if (!exclusive) {
+                struct anon_vma_chain *avc;
+                avc = list_entry(vma->anon_vma_chain.prev,
+                                 struct anon_vma_chain, same_vma);
+                anon_vma = avc->anon_vma;
+        }
+        anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+        page->mapping = (struct address_space *) anon_vma;
+        page->index = linear_page_index(vma, address);
+}
+
+void hugepage_add_anon_rmap(struct page *page,
+                            struct vm_area_struct *vma, unsigned long address)
+{
+        struct anon_vma *anon_vma = vma->anon_vma;
+        int first;
+        BUG_ON(!anon_vma);
+        BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+        first = atomic_inc_and_test(&page->_mapcount);
+        if (first)
+                __hugepage_set_anon_rmap(page, vma, address, 0);
+}
+
+void hugepage_add_new_anon_rmap(struct page *page,
+                        struct vm_area_struct *vma, unsigned long address)
+{
+        BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+        atomic_set(&page->_mapcount, 0);
+        __hugepage_set_anon_rmap(page, vma, address, 1);
+}
+#endif /* CONFIG_HUGETLB_PAGE */