8 files changed, 149 insertions, 108 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f13e067e1467..707d0dc6da0f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -11,6 +11,8 @@
 #include <linux/writeback.h>
 #include <linux/device.h>
 
+static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
 {
 }
@@ -25,6 +27,11 @@ struct backing_dev_info default_backing_dev_info = {
 };
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
+struct backing_dev_info noop_backing_dev_info = {
+        .name           = "noop",
+};
+EXPORT_SYMBOL_GPL(noop_backing_dev_info);
+
 static struct class *bdi_class;
 
 /*
@@ -715,6 +722,33 @@ void bdi_destroy(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_destroy);
 
+/*
+ * For use from filesystems to quickly init and register a bdi associated
+ * with dirty writeback
+ */
+int bdi_setup_and_register(struct backing_dev_info *bdi, char *name,
+                           unsigned int cap)
+{
+        char tmp[32];
+        int err;
+
+        bdi->name = name;
+        bdi->capabilities = cap;
+        err = bdi_init(bdi);
+        if (err)
+                return err;
+
+        sprintf(tmp, "%.28s%s", name, "-%d");
+        err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq));
+        if (err) {
+                bdi_destroy(bdi);
+                return err;
+        }
+
+        return 0;
+}
+EXPORT_SYMBOL(bdi_setup_and_register);
+
 static wait_queue_head_t congestion_wqh[2] = {
                 __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
                 __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6034dc9e9796..4c9e6bbf3772 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -546,6 +546,7 @@ static void free_huge_page(struct page *page)
 
         mapping = (struct address_space *) page_private(page);
         set_page_private(page, 0);
+        page->mapping = NULL;
         BUG_ON(page_count(page));
         INIT_LIST_HEAD(&page->lru);
 
@@ -1038,7 +1039,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
                 page = alloc_buddy_huge_page(h, vma, addr);
                 if (!page) {
                         hugetlb_put_quota(inode->i_mapping, chg);
-                        return ERR_PTR(-VM_FAULT_OOM);
+                        return ERR_PTR(-VM_FAULT_SIGBUS);
                 }
         }
 
@@ -2447,8 +2448,10 @@ retry:
                         spin_lock(&inode->i_lock);
                         inode->i_blocks += blocks_per_huge_page(h);
                         spin_unlock(&inode->i_lock);
-                } else
+                } else {
                         lock_page(page);
+                        page->mapping = HUGETLB_POISON;
+                }
         }
 
         /*
diff --git a/mm/ksm.c b/mm/ksm.c
index 8cdfc2a1e8bf..956880f2ff49 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -365,7 +365,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
         do {
                 cond_resched();
                 page = follow_page(vma, addr, FOLL_GET);
-                if (!page)
+                if (IS_ERR_OR_NULL(page))
                         break;
                 if (PageKsm(page))
                         ret = handle_mm_fault(vma->vm_mm, vma, addr,
@@ -447,7 +447,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
                 goto out;
 
         page = follow_page(vma, addr, FOLL_GET);
-        if (!page)
+        if (IS_ERR_OR_NULL(page))
                 goto out;
         if (PageAnon(page)) {
                 flush_anon_page(vma, page, addr);
@@ -1086,7 +1086,7 @@ struct rmap_item *unstable_tree_search_insert(struct rmap_item *rmap_item,
                 cond_resched();
                 tree_rmap_item = rb_entry(*new, struct rmap_item, node);
                 tree_page = get_mergeable_page(tree_rmap_item);
-                if (!tree_page)
+                if (IS_ERR_OR_NULL(tree_page))
                         return NULL;
 
                 /*
@@ -1294,7 +1294,7 @@ next_mm:
                         if (ksm_test_exit(mm))
                                 break;
                         *page = follow_page(vma, ksm_scan.address, FOLL_GET);
-                        if (*page && PageAnon(*page)) {
+                        if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) {
                                 flush_anon_page(vma, *page, ksm_scan.address);
                                 flush_dcache_page(*page);
                                 rmap_item = get_next_rmap_item(slot,
@@ -1308,7 +1308,7 @@ next_mm:
                                 up_read(&mm->mmap_sem);
                                 return rmap_item;
                         }
-                        if (*page)
+                        if (!IS_ERR_OR_NULL(*page))
                                 put_page(*page);
                         ksm_scan.address += PAGE_SIZE;
                         cond_resched();
@@ -1367,7 +1367,7 @@ next_mm:
 static void ksm_do_scan(unsigned int scan_npages)
 {
         struct rmap_item *rmap_item;
-        struct page *page;
+        struct page *uninitialized_var(page);
 
         while (scan_npages--) {
                 cond_resched();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f4ede99c8b9b..8a79a6f0f029 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1601,7 +1601,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
                          * There is a small race that "from" or "to" can be
                          * freed by rmdir, so we use css_tryget().
                          */
-                        rcu_read_lock();
                         from = mc.from;
                         to = mc.to;
                         if (from && css_tryget(&from->css)) {
@@ -1622,7 +1621,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
                                         do_continue = (to == mem_over_limit);
                                 css_put(&to->css);
                         }
-                        rcu_read_unlock();
                         if (do_continue) {
                                 DEFINE_WAIT(wait);
                                 prepare_to_wait(&mc.waitq, &wait,
@@ -2429,11 +2427,11 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
         }
         unlock_page_cgroup(pc);
 
+        *ptr = mem;
         if (mem) {
-                ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
+                ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false);
                 css_put(&mem->css);
         }
-        *ptr = mem;
         return ret;
 }
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 8f4e2dfceec1..3f82720e0515 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -607,44 +607,3 @@ void user_shm_unlock(size_t size, struct user_struct *user)
         spin_unlock(&shmlock_user_lock);
         free_uid(user);
 }
-
-int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-                          size_t size)
-{
-        unsigned long lim, vm, pgsz;
-        int error = -ENOMEM;
-
-        pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-        down_write(&mm->mmap_sem);
-
-        lim = ACCESS_ONCE(rlim[RLIMIT_AS].rlim_cur) >> PAGE_SHIFT;
-        vm   = mm->total_vm + pgsz;
-        if (lim < vm)
-                goto out;
-
-        lim = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur) >> PAGE_SHIFT;
-        vm   = mm->locked_vm + pgsz;
-        if (lim < vm)
-                goto out;
-
-        mm->total_vm  += pgsz;
-        mm->locked_vm += pgsz;
-
-        error = 0;
- out:
-        up_write(&mm->mmap_sem);
-        return error;
-}
-
-void refund_locked_memory(struct mm_struct *mm, size_t size)
-{
-        unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-        down_write(&mm->mmap_sem);
-
-        mm->total_vm  -= pgsz;
-        mm->locked_vm -= pgsz;
-
-        up_write(&mm->mmap_sem);
-}
diff --git a/mm/mmap.c b/mm/mmap.c
index 75557c639ad4..456ec6f27889 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -507,11 +507,12 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
         struct address_space *mapping = NULL;
         struct prio_tree_root *root = NULL;
         struct file *file = vma->vm_file;
-        struct anon_vma *anon_vma = NULL;
         long adjust_next = 0;
         int remove_next = 0;
 
         if (next && !insert) {
+                struct vm_area_struct *exporter = NULL;
+
                 if (end >= next->vm_end) {
                         /*
                          * vma expands, overlapping all the next, and
@@ -519,7 +520,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
                          */
 again:                  remove_next = 1 + (end > next->vm_end);
                         end = next->vm_end;
-                        anon_vma = next->anon_vma;
+                        exporter = next;
                         importer = vma;
                 } else if (end > next->vm_start) {
                         /*
@@ -527,7 +528,7 @@ again:			remove_next = 1 + (end > next->vm_end);
                          * mprotect case 5 shifting the boundary up.
                          */
                         adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
-                        anon_vma = next->anon_vma;
+                        exporter = next;
                         importer = vma;
                 } else if (end < vma->vm_end) {
                         /*
@@ -536,28 +537,19 @@ again:			remove_next = 1 + (end > next->vm_end);
                          * mprotect case 4 shifting the boundary down.
                          */
                         adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
-                        anon_vma = next->anon_vma;
+                        exporter = vma;
                         importer = next;
                 }
-        }
 
-        /*
-         * When changing only vma->vm_end, we don't really need anon_vma lock.
-         */
-        if (vma->anon_vma && (insert || importer || start != vma->vm_start))
-                anon_vma = vma->anon_vma;
-        if (anon_vma) {
                 /*
                  * Easily overlooked: when mprotect shifts the boundary,
                  * make sure the expanding vma has anon_vma set if the
                  * shrinking vma had, to cover any anon pages imported.
                  */
-                if (importer && !importer->anon_vma) {
-                        /* Block reverse map lookups until things are set up. */
-                        if (anon_vma_clone(importer, vma)) {
+                if (exporter && exporter->anon_vma && !importer->anon_vma) {
+                        if (anon_vma_clone(importer, exporter))
                                 return -ENOMEM;
-                        }
-                        importer->anon_vma = anon_vma;
+                        importer->anon_vma = exporter->anon_vma;
                 }
         }
 
@@ -825,6 +817,61 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 }
 
 /*
+ * Rough compatbility check to quickly see if it's even worth looking
+ * at sharing an anon_vma.
+ *
+ * They need to have the same vm_file, and the flags can only differ
+ * in things that mprotect may change.
+ *
+ * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
+ * we can merge the two vma's. For example, we refuse to merge a vma if
+ * there is a vm_ops->close() function, because that indicates that the
+ * driver is doing some kind of reference counting. But that doesn't
+ * really matter for the anon_vma sharing case.
+ */
+static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
+{
+        return a->vm_end == b->vm_start &&
+                mpol_equal(vma_policy(a), vma_policy(b)) &&
+                a->vm_file == b->vm_file &&
+                !((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
+                b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
+}
+
+/*
+ * Do some basic sanity checking to see if we can re-use the anon_vma
+ * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
+ * the same as 'old', the other will be the new one that is trying
+ * to share the anon_vma.
+ *
+ * NOTE! This runs with mm_sem held for reading, so it is possible that
+ * the anon_vma of 'old' is concurrently in the process of being set up
+ * by another page fault trying to merge _that_. But that's ok: if it
+ * is being set up, that automatically means that it will be a singleton
+ * acceptable for merging, so we can do all of this optimistically. But
+ * we do that ACCESS_ONCE() to make sure that we never re-load the pointer.
+ *
+ * IOW: that the "list_is_singular()" test on the anon_vma_chain only
+ * matters for the 'stable anon_vma' case (ie the thing we want to avoid
+ * is to return an anon_vma that is "complex" due to having gone through
+ * a fork).
+ *
+ * We also make sure that the two vma's are compatible (adjacent,
+ * and with the same memory policies). That's all stable, even with just
+ * a read lock on the mm_sem.
+ */
+static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
+{
+        if (anon_vma_compatible(a, b)) {
+                struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma);
+
+                if (anon_vma && list_is_singular(&old->anon_vma_chain))
+                        return anon_vma;
+        }
+        return NULL;
+}
+
+/*
  * find_mergeable_anon_vma is used by anon_vma_prepare, to check
  * neighbouring vmas for a suitable anon_vma, before it goes off
  * to allocate a new anon_vma.  It checks because a repetitive
@@ -834,28 +881,16 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
  */
 struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
 {
+        struct anon_vma *anon_vma;
         struct vm_area_struct *near;
-        unsigned long vm_flags;
 
         near = vma->vm_next;
         if (!near)
                 goto try_prev;
 
-        /*
-         * Since only mprotect tries to remerge vmas, match flags
-         * which might be mprotected into each other later on.
-         * Neither mlock nor madvise tries to remerge at present,
-         * so leave their flags as obstructing a merge.
-         */
-        vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
-        vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
-        if (near->anon_vma && vma->vm_end == near->vm_start &&
-                        mpol_equal(vma_policy(vma), vma_policy(near)) &&
-                        can_vma_merge_before(near, vm_flags,
-                                NULL, vma->vm_file, vma->vm_pgoff +
-                                ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT)))
-                return near->anon_vma;
+        anon_vma = reusable_anon_vma(near, vma, near);
+        if (anon_vma)
+                return anon_vma;
 try_prev:
         /*
          * It is potentially slow to have to call find_vma_prev here.
@@ -868,14 +903,9 @@ try_prev:
         if (!near)
                 goto none;
 
-        vm_flags = vma->vm_flags & ~(VM_READ|VM_WRITE|VM_EXEC);
-        vm_flags |= near->vm_flags & (VM_READ|VM_WRITE|VM_EXEC);
-
-        if (near->anon_vma && near->vm_end == vma->vm_start &&
-                        mpol_equal(vma_policy(near), vma_policy(vma)) &&
-                        can_vma_merge_after(near, vm_flags,
-                                NULL, vma->vm_file, vma->vm_pgoff))
-                return near->anon_vma;
+        anon_vma = reusable_anon_vma(near, near, vma);
+        if (anon_vma)
+                return anon_vma;
 none:
         /*
          * There's no absolute need to look only at touching neighbours:
@@ -1947,7 +1977,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
                 return 0;
 
         /* Clean everything up if vma_adjust failed. */
-        new->vm_ops->close(new);
+        if (new->vm_ops && new->vm_ops->close)
+                new->vm_ops->close(new);
         if (new->vm_file) {
                 if (vma->vm_flags & VM_EXECUTABLE)
                         removed_exe_file_vma(mm);
diff --git a/mm/rmap.c b/mm/rmap.c
index eaa7a09eb72e..0feeef860a8f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -133,8 +133,8 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                                 goto out_enomem_free_avc;
                         allocated = anon_vma;
                 }
-                spin_lock(&anon_vma->lock);
 
+                spin_lock(&anon_vma->lock);
                 /* page_table_lock to protect against threads */
                 spin_lock(&mm->page_table_lock);
                 if (likely(!vma->anon_vma)) {
@@ -144,14 +144,15 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                         list_add(&avc->same_vma, &vma->anon_vma_chain);
                         list_add(&avc->same_anon_vma, &anon_vma->head);
                         allocated = NULL;
+                        avc = NULL;
                 }
                 spin_unlock(&mm->page_table_lock);
-
                 spin_unlock(&anon_vma->lock);
-                if (unlikely(allocated)) {
+
+                if (unlikely(allocated))
                         anon_vma_free(allocated);
+                if (unlikely(avc))
                         anon_vma_chain_free(avc);
-                }
         }
         return 0;
 
@@ -182,7 +183,7 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src)
 {
         struct anon_vma_chain *avc, *pavc;
 
-        list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
+        list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
                 avc = anon_vma_chain_alloc();
                 if (!avc)
                         goto enomem_failure;
@@ -335,14 +336,13 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 
 /*
  * At what user virtual address is page expected in vma?
- * checking that the page matches the vma.
+ * Caller should check the page is actually part of the vma.
  */
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
-        if (PageAnon(page)) {
-                if (vma->anon_vma != page_anon_vma(page))
-                        return -EFAULT;
-        } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
+        if (PageAnon(page))
+                ;
+        else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
                 if (!vma->vm_file ||
                     vma->vm_file->f_mapping != page->mapping)
                         return -EFAULT;
@@ -730,13 +730,29 @@ void page_move_anon_rmap(struct page *page,
  * @page:       the page to add the mapping to
  * @vma:        the vm area in which the mapping is added
  * @address:    the user virtual address mapped
+ * @exclusive:  the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
-        struct vm_area_struct *vma, unsigned long address)
+        struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
         struct anon_vma *anon_vma = vma->anon_vma;
 
         BUG_ON(!anon_vma);
+
+        /*
+         * 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;
+        }
+
         anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
         page->mapping = (struct address_space *) anon_vma;
         page->index = linear_page_index(vma, address);
@@ -791,7 +807,7 @@ 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);
+                __page_set_anon_rmap(page, vma, address, 0);
         else
                 __page_check_anon_rmap(page, vma, address);
 }
@@ -813,7 +829,7 @@ void page_add_new_anon_rmap(struct page *page,
         SetPageSwapBacked(page);
         atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
         __inc_zone_page_state(page, NR_ANON_PAGES);
-        __page_set_anon_rmap(page, vma, address);
+        __page_set_anon_rmap(page, vma, address, 1);
         if (page_evictable(page, vma))
                 lru_cache_add_lru(page, LRU_ACTIVE_ANON);
         else
diff --git a/mm/slub.c b/mm/slub.c
index 7d6c8b1ccf63..d2a54fe71ea2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2153,7 +2153,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
         int local_node;
 
         if (slab_state >= UP && (s < kmalloc_caches ||
-                        s > kmalloc_caches + KMALLOC_CACHES))
+                        s >= kmalloc_caches + KMALLOC_CACHES))
                 local_node = page_to_nid(virt_to_page(s));
         else
                 local_node = 0;