7 files changed, 227 insertions, 45 deletions

diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c
index 83768df27806..f1936d51b458 100644
--- a/drivers/net/cassini.c
+++ b/drivers/net/cassini.c
@@ -576,6 +576,18 @@ static void cas_spare_recover(struct cas *cp, const gfp_t flags)
         list_for_each_safe(elem, tmp, &list) {
                 cas_page_t *page = list_entry(elem, cas_page_t, list);
 
+                /*
+                 * With the lockless pagecache, cassini buffering scheme gets
+                 * slightly less accurate: we might find that a page has an
+                 * elevated reference count here, due to a speculative ref,
+                 * and skip it as in-use. Ideally we would be able to reclaim
+                 * it. However this would be such a rare case, it doesn't
+                 * matter too much as we should pick it up the next time round.
+                 *
+                 * Importantly, if we find that the page has a refcount of 1
+                 * here (our refcount), then we know it is definitely not inuse
+                 * so we can reuse it.
+                 */
                 if (page_count(page->buffer) > 1)
                         continue;
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ee1ec2c7723c..a81d81890422 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -12,6 +12,7 @@
 #include <asm/uaccess.h>
 #include <linux/gfp.h>
 #include <linux/bitops.h>
+#include <linux/hardirq.h> /* for in_interrupt() */
 
 /*
  * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
@@ -62,6 +63,98 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 #define page_cache_release(page)        put_page(page)
 void release_pages(struct page **pages, int nr, int cold);
 
+/*
+ * speculatively take a reference to a page.
+ * If the page is free (_count == 0), then _count is untouched, and 0
+ * is returned. Otherwise, _count is incremented by 1 and 1 is returned.
+ *
+ * This function must be called inside the same rcu_read_lock() section as has
+ * been used to lookup the page in the pagecache radix-tree (or page table):
+ * this allows allocators to use a synchronize_rcu() to stabilize _count.
+ *
+ * Unless an RCU grace period has passed, the count of all pages coming out
+ * of the allocator must be considered unstable. page_count may return higher
+ * than expected, and put_page must be able to do the right thing when the
+ * page has been finished with, no matter what it is subsequently allocated
+ * for (because put_page is what is used here to drop an invalid speculative
+ * reference).
+ *
+ * This is the interesting part of the lockless pagecache (and lockless
+ * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
+ * has the following pattern:
+ * 1. find page in radix tree
+ * 2. conditionally increment refcount
+ * 3. check the page is still in pagecache (if no, goto 1)
+ *
+ * Remove-side that cares about stability of _count (eg. reclaim) has the
+ * following (with tree_lock held for write):
+ * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
+ * B. remove page from pagecache
+ * C. free the page
+ *
+ * There are 2 critical interleavings that matter:
+ * - 2 runs before A: in this case, A sees elevated refcount and bails out
+ * - A runs before 2: in this case, 2 sees zero refcount and retries;
+ *   subsequently, B will complete and 1 will find no page, causing the
+ *   lookup to return NULL.
+ *
+ * It is possible that between 1 and 2, the page is removed then the exact same
+ * page is inserted into the same position in pagecache. That's OK: the
+ * old find_get_page using tree_lock could equally have run before or after
+ * such a re-insertion, depending on order that locks are granted.
+ *
+ * Lookups racing against pagecache insertion isn't a big problem: either 1
+ * will find the page or it will not. Likewise, the old find_get_page could run
+ * either before the insertion or afterwards, depending on timing.
+ */
+static inline int page_cache_get_speculative(struct page *page)
+{
+        VM_BUG_ON(in_interrupt());
+
+#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+# ifdef CONFIG_PREEMPT
+        VM_BUG_ON(!in_atomic());
+# endif
+        /*
+         * Preempt must be disabled here - we rely on rcu_read_lock doing
+         * this for us.
+         *
+         * Pagecache won't be truncated from interrupt context, so if we have
+         * found a page in the radix tree here, we have pinned its refcount by
+         * disabling preempt, and hence no need for the "speculative get" that
+         * SMP requires.
+         */
+        VM_BUG_ON(page_count(page) == 0);
+        atomic_inc(&page->_count);
+
+#else
+        if (unlikely(!get_page_unless_zero(page))) {
+                /*
+                 * Either the page has been freed, or will be freed.
+                 * In either case, retry here and the caller should
+                 * do the right thing (see comments above).
+                 */
+                return 0;
+        }
+#endif
+        VM_BUG_ON(PageTail(page));
+
+        return 1;
+}
+
+static inline int page_freeze_refs(struct page *page, int count)
+{
+        return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+}
+
+static inline void page_unfreeze_refs(struct page *page, int count)
+{
+        VM_BUG_ON(page_count(page) != 0);
+        VM_BUG_ON(count == 0);
+
+        atomic_set(&page->_count, count);
+}
+
 #ifdef CONFIG_NUMA
 extern struct page *__page_cache_alloc(gfp_t gfp);
 #else
@@ -133,7 +226,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
         return read_cache_page(mapping, index, filler, data);
 }
 
-int add_to_page_cache(struct page *page, struct address_space *mapping,
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
                                 pgoff_t index, gfp_t gfp_mask);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
                                 pgoff_t index, gfp_t gfp_mask);
@@ -141,6 +234,22 @@ extern void remove_from_page_cache(struct page *page);
 extern void __remove_from_page_cache(struct page *page);
 
 /*
+ * Like add_to_page_cache_locked, but used to add newly allocated pages:
+ * the page is new, so we can just run SetPageLocked() against it.
+ */
+static inline int add_to_page_cache(struct page *page,
+                struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
+{
+        int error;
+
+        SetPageLocked(page);
+        error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
+        if (unlikely(error))
+                ClearPageLocked(page);
+        return error;
+}
+
+/*
  * Return byte-offset into filesystem object for page.
  */
 static inline loff_t page_offset(struct page *page)
diff --git a/mm/filemap.c b/mm/filemap.c
index 2d3ec1ffc66e..4e182a9a14c0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -442,39 +442,43 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 }
 
 /**
- * add_to_page_cache - add newly allocated pagecache pages
+ * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:       page to add
  * @mapping:    the page's address_space
  * @offset:     page index
  * @gfp_mask:   page allocation mode
  *
- * This function is used to add newly allocated pagecache pages;
- * the page is new, so we can just run SetPageLocked() against it.
- * The other page state flags were set by rmqueue().
- *
+ * This function is used to add a page to the pagecache. It must be locked.
  * This function does not add the page to the LRU.  The caller must do that.
  */
-int add_to_page_cache(struct page *page, struct address_space *mapping,
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
                 pgoff_t offset, gfp_t gfp_mask)
 {
-        int error = mem_cgroup_cache_charge(page, current->mm,
+        int error;
+
+        VM_BUG_ON(!PageLocked(page));
+
+        error = mem_cgroup_cache_charge(page, current->mm,
                                         gfp_mask & ~__GFP_HIGHMEM);
         if (error)
                 goto out;
 
         error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
         if (error == 0) {
+                page_cache_get(page);
+                page->mapping = mapping;
+                page->index = offset;
+
                 write_lock_irq(&mapping->tree_lock);
                 error = radix_tree_insert(&mapping->page_tree, offset, page);
-                if (!error) {
-                        page_cache_get(page);
-                        SetPageLocked(page);
-                        page->mapping = mapping;
-                        page->index = offset;
+                if (likely(!error)) {
                         mapping->nrpages++;
                         __inc_zone_page_state(page, NR_FILE_PAGES);
-                } else
+                } else {
+                        page->mapping = NULL;
                         mem_cgroup_uncharge_cache_page(page);
+                        page_cache_release(page);
+                }
 
                 write_unlock_irq(&mapping->tree_lock);
                 radix_tree_preload_end();
@@ -483,7 +487,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
 out:
         return error;
 }
-EXPORT_SYMBOL(add_to_page_cache);
+EXPORT_SYMBOL(add_to_page_cache_locked);
 
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
                                 pgoff_t offset, gfp_t gfp_mask)
diff --git a/mm/migrate.c b/mm/migrate.c
index d8c65a65c61d..3ca6392e82cc 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -285,7 +285,15 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 
         page = migration_entry_to_page(entry);
 
-        get_page(page);
+        /*
+         * Once radix-tree replacement of page migration started, page_count
+         * *must* be zero. And, we don't want to call wait_on_page_locked()
+         * against a page without get_page().
+         * So, we use get_page_unless_zero(), here. Even failed, page fault
+         * will occur again.
+         */
+        if (!get_page_unless_zero(page))
+                goto out;
         pte_unmap_unlock(ptep, ptl);
         wait_on_page_locked(page);
         put_page(page);
@@ -305,6 +313,7 @@ out:
 static int migrate_page_move_mapping(struct address_space *mapping,
                 struct page *newpage, struct page *page)
 {
+        int expected_count;
         void **pslot;
 
         if (!mapping) {
@@ -319,12 +328,18 @@ static int migrate_page_move_mapping(struct address_space *mapping,
         pslot = radix_tree_lookup_slot(&mapping->page_tree,
                                         page_index(page));
 
-        if (page_count(page) != 2 + !!PagePrivate(page) ||
+        expected_count = 2 + !!PagePrivate(page);
+        if (page_count(page) != expected_count ||
                         (struct page *)radix_tree_deref_slot(pslot) != page) {
                 write_unlock_irq(&mapping->tree_lock);
                 return -EAGAIN;
         }
 
+        if (!page_freeze_refs(page, expected_count)) {
+                write_unlock_irq(&mapping->tree_lock);
+                return -EAGAIN;
+        }
+
         /*
          * Now we know that no one else is looking at the page.
          */
@@ -338,6 +353,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 
         radix_tree_replace_slot(pslot, newpage);
 
+        page_unfreeze_refs(page, expected_count);
         /*
          * Drop cache reference from old page.
          * We know this isn't the last reference.
diff --git a/mm/shmem.c b/mm/shmem.c
index f92fea94d037..1089092aecaf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -936,7 +936,7 @@ found:
         spin_lock(&info->lock);
         ptr = shmem_swp_entry(info, idx, NULL);
         if (ptr && ptr->val == entry.val) {
-                error = add_to_page_cache(page, inode->i_mapping,
+                error = add_to_page_cache_locked(page, inode->i_mapping,
                                                 idx, GFP_NOWAIT);
                 /* does mem_cgroup_uncharge_cache_page on error */
         } else  /* we must compensate for our precharge above */
@@ -1301,8 +1301,8 @@ repeat:
                         SetPageUptodate(filepage);
                         set_page_dirty(filepage);
                         swap_free(swap);
-                } else if (!(error = add_to_page_cache(
-                                swappage, mapping, idx, GFP_NOWAIT))) {
+                } else if (!(error = add_to_page_cache_locked(swappage, mapping,
+                                        idx, GFP_NOWAIT))) {
                         info->flags |= SHMEM_PAGEIN;
                         shmem_swp_set(info, entry, 0);
                         shmem_swp_unmap(entry);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index d8aadaf2a0ba..3e3381d6c7ee 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -64,7 +64,7 @@ void show_swap_cache_info(void)
 }
 
 /*
- * add_to_swap_cache resembles add_to_page_cache on swapper_space,
+ * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
  * but sets SwapCache flag and private instead of mapping and index.
  */
 int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
@@ -76,19 +76,26 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
         BUG_ON(PagePrivate(page));
         error = radix_tree_preload(gfp_mask);
         if (!error) {
+                page_cache_get(page);
+                SetPageSwapCache(page);
+                set_page_private(page, entry.val);
+
                 write_lock_irq(&swapper_space.tree_lock);
                 error = radix_tree_insert(&swapper_space.page_tree,
                                                 entry.val, page);
-                if (!error) {
-                        page_cache_get(page);
-                        SetPageSwapCache(page);
-                        set_page_private(page, entry.val);
+                if (likely(!error)) {
                         total_swapcache_pages++;
                         __inc_zone_page_state(page, NR_FILE_PAGES);
                         INC_CACHE_INFO(add_total);
                 }
                 write_unlock_irq(&swapper_space.tree_lock);
                 radix_tree_preload_end();
+
+                if (unlikely(error)) {
+                        set_page_private(page, 0UL);
+                        ClearPageSwapCache(page);
+                        page_cache_release(page);
+                }
         }
         return error;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 26672c6cd3ce..0075eac1cd04 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -391,12 +391,10 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 }
 
 /*
- * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
- * someone else has a ref on the page, abort and return 0.  If it was
- * successfully detached, return 1.  Assumes the caller has a single ref on
- * this page.
+ * Same as remove_mapping, but if the page is removed from the mapping, it
+ * gets returned with a refcount of 0.
  */
-int remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page)
 {
         BUG_ON(!PageLocked(page));
         BUG_ON(mapping != page_mapping(page));
@@ -427,24 +425,24 @@ int remove_mapping(struct address_space *mapping, struct page *page)
          * Note that if SetPageDirty is always performed via set_page_dirty,
          * and thus under tree_lock, then this ordering is not required.
          */
-        if (unlikely(page_count(page) != 2))
+        if (!page_freeze_refs(page, 2))
                 goto cannot_free;
-        smp_rmb();
-        if (unlikely(PageDirty(page)))
+        /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
+        if (unlikely(PageDirty(page))) {
+                page_unfreeze_refs(page, 2);
                 goto cannot_free;
+        }
 
         if (PageSwapCache(page)) {
                 swp_entry_t swap = { .val = page_private(page) };
                 __delete_from_swap_cache(page);
                 write_unlock_irq(&mapping->tree_lock);
                 swap_free(swap);
-                __put_page(page);       /* The pagecache ref */
-                return 1;
+        } else {
+                __remove_from_page_cache(page);
+                write_unlock_irq(&mapping->tree_lock);
         }
 
-        __remove_from_page_cache(page);
-        write_unlock_irq(&mapping->tree_lock);
-        __put_page(page);
         return 1;
 
 cannot_free:
@@ -453,6 +451,26 @@ cannot_free:
 }
 
 /*
+ * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
+ * someone else has a ref on the page, abort and return 0.  If it was
+ * successfully detached, return 1.  Assumes the caller has a single ref on
+ * this page.
+ */
+int remove_mapping(struct address_space *mapping, struct page *page)
+{
+        if (__remove_mapping(mapping, page)) {
+                /*
+                 * Unfreezing the refcount with 1 rather than 2 effectively
+                 * drops the pagecache ref for us without requiring another
+                 * atomic operation.
+                 */
+                page_unfreeze_refs(page, 1);
+                return 1;
+        }
+        return 0;
+}
+
+/*
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
@@ -598,18 +616,34 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                 if (PagePrivate(page)) {
                         if (!try_to_release_page(page, sc->gfp_mask))
                                 goto activate_locked;
-                        if (!mapping && page_count(page) == 1)
-                                goto free_it;
+                        if (!mapping && page_count(page) == 1) {
+                                unlock_page(page);
+                                if (put_page_testzero(page))
+                                        goto free_it;
+                                else {
+                                        /*
+                                         * rare race with speculative reference.
+                                         * the speculative reference will free
+                                         * this page shortly, so we may
+                                         * increment nr_reclaimed here (and
+                                         * leave it off the LRU).
+                                         */
+                                        nr_reclaimed++;
+                                        continue;
+                                }
+                        }
                 }
 
-                if (!mapping || !remove_mapping(mapping, page))
+                if (!mapping || !__remove_mapping(mapping, page))
                         goto keep_locked;
 
-free_it:
                 unlock_page(page);
+free_it:
                 nr_reclaimed++;
-                if (!pagevec_add(&freed_pvec, page))
-                        __pagevec_release_nonlru(&freed_pvec);
+                if (!pagevec_add(&freed_pvec, page)) {
+                        __pagevec_free(&freed_pvec);
+                        pagevec_reinit(&freed_pvec);
+                }
                 continue;
 
 activate_locked:
@@ -623,7 +657,7 @@ keep:
         }
         list_splice(&ret_pages, page_list);
         if (pagevec_count(&freed_pvec))
-                __pagevec_release_nonlru(&freed_pvec);
+                __pagevec_free(&freed_pvec);
         count_vm_events(PGACTIVATE, pgactivate);
         return nr_reclaimed;
 }