1 files changed, 194 insertions, 92 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 83a45d35468..bcdc393b658 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -34,6 +34,7 @@
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
 #include <linux/mm_inline.h> /* for page_is_file_cache() */
+#include <linux/cleancache.h>
 #include "internal.h"
 
 /*
@@ -58,16 +59,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock               (truncate_pagecache)
+ *  ->i_mmap_mutex              (truncate_pagecache)
  *    ->private_lock            (__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock             (exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_lock             (truncate->unmap_mapping_range)
+ *    ->i_mmap_mutex            (truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  *      ->page_table_lock or pte_lock   (various, mainly in memory.c)
  *        ->mapping->tree_lock  (arch-dependent flush_dcache_mmap_lock)
  *
@@ -80,11 +81,11 @@
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
  *
- *  ->inode_lock
- *    ->sb_lock                 (fs/fs-writeback.c)
+ *  inode_wb_list_lock
+ *    sb_lock                   (fs/fs-writeback.c)
  *    ->mapping->tree_lock      (__sync_single_inode)
  *
- *  ->i_mmap_lock
+ *  ->i_mmap_mutex
  *    ->anon_vma.lock           (vma_adjust)
  *
  *  ->anon_vma.lock
@@ -98,24 +99,36 @@
  *    ->zone.lru_lock           (check_pte_range->isolate_lru_page)
  *    ->private_lock            (page_remove_rmap->set_page_dirty)
  *    ->tree_lock               (page_remove_rmap->set_page_dirty)
- *    ->inode_lock              (page_remove_rmap->set_page_dirty)
- *    ->inode_lock              (zap_pte_range->set_page_dirty)
+ *    inode_wb_list_lock        (page_remove_rmap->set_page_dirty)
+ *    ->inode->i_lock           (page_remove_rmap->set_page_dirty)
+ *    inode_wb_list_lock        (zap_pte_range->set_page_dirty)
+ *    ->inode->i_lock           (zap_pte_range->set_page_dirty)
  *    ->private_lock            (zap_pte_range->__set_page_dirty_buffers)
  *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
- *    ->i_mmap_lock
+ *    ->i_mmap_mutex
  */
 
 /*
- * Remove a page from the page cache and free it. Caller has to make
+ * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
  * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __remove_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page)
 {
         struct address_space *mapping = page->mapping;
 
+        /*
+         * if we're uptodate, flush out into the cleancache, otherwise
+         * invalidate any existing cleancache entries.  We can't leave
+         * stale data around in the cleancache once our page is gone
+         */
+        if (PageUptodate(page) && PageMappedToDisk(page))
+                cleancache_put_page(page);
+        else
+                cleancache_flush_page(mapping, page);
+
         radix_tree_delete(&mapping->page_tree, page->index);
         page->mapping = NULL;
         mapping->nrpages--;
@@ -137,7 +150,15 @@ void __remove_from_page_cache(struct page *page)
         }
 }
 
-void remove_from_page_cache(struct page *page)
+/**
+ * delete_from_page_cache - delete page from page cache
+ * @page: the page which the kernel is trying to remove from page cache
+ *
+ * This must be called only on pages that have been verified to be in the page
+ * cache and locked.  It will never put the page into the free list, the caller
+ * has a reference on the page.
+ */
+void delete_from_page_cache(struct page *page)
 {
         struct address_space *mapping = page->mapping;
         void (*freepage)(struct page *);
@@ -146,54 +167,25 @@ void remove_from_page_cache(struct page *page)
 
         freepage = mapping->a_ops->freepage;
         spin_lock_irq(&mapping->tree_lock);
-        __remove_from_page_cache(page);
+        __delete_from_page_cache(page);
         spin_unlock_irq(&mapping->tree_lock);
         mem_cgroup_uncharge_cache_page(page);
 
         if (freepage)
                 freepage(page);
+        page_cache_release(page);
 }
-EXPORT_SYMBOL(remove_from_page_cache);
+EXPORT_SYMBOL(delete_from_page_cache);
 
-static int sync_page(void *word)
+static int sleep_on_page(void *word)
 {
-        struct address_space *mapping;
-        struct page *page;
-
-        page = container_of((unsigned long *)word, struct page, flags);
-
-        /*
-         * page_mapping() is being called without PG_locked held.
-         * Some knowledge of the state and use of the page is used to
-         * reduce the requirements down to a memory barrier.
-         * The danger here is of a stale page_mapping() return value
-         * indicating a struct address_space different from the one it's
-         * associated with when it is associated with one.
-         * After smp_mb(), it's either the correct page_mapping() for
-         * the page, or an old page_mapping() and the page's own
-         * page_mapping() has gone NULL.
-         * The ->sync_page() address_space operation must tolerate
-         * page_mapping() going NULL. By an amazing coincidence,
-         * this comes about because none of the users of the page
-         * in the ->sync_page() methods make essential use of the
-         * page_mapping(), merely passing the page down to the backing
-         * device's unplug functions when it's non-NULL, which in turn
-         * ignore it for all cases but swap, where only page_private(page) is
-         * of interest. When page_mapping() does go NULL, the entire
-         * call stack gracefully ignores the page and returns.
-         * -- wli
-         */
-        smp_mb();
-        mapping = page_mapping(page);
-        if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
-                mapping->a_ops->sync_page(page);
         io_schedule();
         return 0;
 }
 
-static int sync_page_killable(void *word)
+static int sleep_on_page_killable(void *word)
 {
-        sync_page(word);
+        sleep_on_page(word);
         return fatal_signal_pending(current) ? -EINTR : 0;
 }
 
@@ -387,6 +379,76 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 EXPORT_SYMBOL(filemap_write_and_wait_range);
 
 /**
+ * replace_page_cache_page - replace a pagecache page with a new one
+ * @old:        page to be replaced
+ * @new:        page to replace with
+ * @gfp_mask:   allocation mode
+ *
+ * This function replaces a page in the pagecache with a new one.  On
+ * success it acquires the pagecache reference for the new page and
+ * drops it for the old page.  Both the old and new pages must be
+ * locked.  This function does not add the new page to the LRU, the
+ * caller must do that.
+ *
+ * The remove + add is atomic.  The only way this function can fail is
+ * memory allocation failure.
+ */
+int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
+{
+        int error;
+        struct mem_cgroup *memcg = NULL;
+
+        VM_BUG_ON(!PageLocked(old));
+        VM_BUG_ON(!PageLocked(new));
+        VM_BUG_ON(new->mapping);
+
+        /*
+         * This is not page migration, but prepare_migration and
+         * end_migration does enough work for charge replacement.
+         *
+         * In the longer term we probably want a specialized function
+         * for moving the charge from old to new in a more efficient
+         * manner.
+         */
+        error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
+        if (error)
+                return error;
+
+        error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+        if (!error) {
+                struct address_space *mapping = old->mapping;
+                void (*freepage)(struct page *);
+
+                pgoff_t offset = old->index;
+                freepage = mapping->a_ops->freepage;
+
+                page_cache_get(new);
+                new->mapping = mapping;
+                new->index = offset;
+
+                spin_lock_irq(&mapping->tree_lock);
+                __delete_from_page_cache(old);
+                error = radix_tree_insert(&mapping->page_tree, offset, new);
+                BUG_ON(error);
+                mapping->nrpages++;
+                __inc_zone_page_state(new, NR_FILE_PAGES);
+                if (PageSwapBacked(new))
+                        __inc_zone_page_state(new, NR_SHMEM);
+                spin_unlock_irq(&mapping->tree_lock);
+                radix_tree_preload_end();
+                if (freepage)
+                        freepage(old);
+                page_cache_release(old);
+                mem_cgroup_end_migration(memcg, old, new, true);
+        } else {
+                mem_cgroup_end_migration(memcg, old, new, false);
+        }
+
+        return error;
+}
+EXPORT_SYMBOL_GPL(replace_page_cache_page);
+
+/**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:       page to add
  * @mapping:    the page's address_space
@@ -479,12 +541,6 @@ struct page *__page_cache_alloc(gfp_t gfp)
 EXPORT_SYMBOL(__page_cache_alloc);
 #endif
 
-static int __sleep_on_page_lock(void *word)
-{
-        io_schedule();
-        return 0;
-}
-
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
@@ -512,11 +568,22 @@ void wait_on_page_bit(struct page *page, int bit_nr)
         DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
 
         if (test_bit(bit_nr, &page->flags))
-                __wait_on_bit(page_waitqueue(page), &wait, sync_page,
+                __wait_on_bit(page_waitqueue(page), &wait, sleep_on_page,
                                                         TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(wait_on_page_bit);
 
+int wait_on_page_bit_killable(struct page *page, int bit_nr)
+{
+        DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+
+        if (!test_bit(bit_nr, &page->flags))
+                return 0;
+
+        return __wait_on_bit(page_waitqueue(page), &wait,
+                             sleep_on_page_killable, TASK_KILLABLE);
+}
+
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
  * @page: Page defining the wait queue of interest
@@ -576,17 +643,12 @@ EXPORT_SYMBOL(end_page_writeback);
 /**
  * __lock_page - get a lock on the page, assuming we need to sleep to get it
  * @page: the page to lock
- *
- * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
- * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
- * chances are that on the second loop, the block layer's plug list is empty,
- * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
  */
 void __lock_page(struct page *page)
 {
         DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
-        __wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+        __wait_on_bit_lock(page_waitqueue(page), &wait, sleep_on_page,
                                                         TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(__lock_page);
@@ -596,34 +658,39 @@ int __lock_page_killable(struct page *page)
         DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
 
         return __wait_on_bit_lock(page_waitqueue(page), &wait,
-                                        sync_page_killable, TASK_KILLABLE);
+                                        sleep_on_page_killable, TASK_KILLABLE);
 }
 EXPORT_SYMBOL_GPL(__lock_page_killable);
 
-/**
- * __lock_page_nosync - get a lock on the page, without calling sync_page()
- * @page: the page to lock
- *
- * Variant of lock_page that does not require the caller to hold a reference
- * on the page's mapping.
- */
-void __lock_page_nosync(struct page *page)
-{
-        DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
-        __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
-                                                        TASK_UNINTERRUPTIBLE);
-}
-
 int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
                          unsigned int flags)
 {
-        if (!(flags & FAULT_FLAG_ALLOW_RETRY)) {
-                __lock_page(page);
-                return 1;
-        } else {
+        if (flags & FAULT_FLAG_ALLOW_RETRY) {
+                /*
+                 * CAUTION! In this case, mmap_sem is not released
+                 * even though return 0.
+                 */
+                if (flags & FAULT_FLAG_RETRY_NOWAIT)
+                        return 0;
+
                 up_read(&mm->mmap_sem);
-                wait_on_page_locked(page);
+                if (flags & FAULT_FLAG_KILLABLE)
+                        wait_on_page_locked_killable(page);
+                else
+                        wait_on_page_locked(page);
                 return 0;
+        } else {
+                if (flags & FAULT_FLAG_KILLABLE) {
+                        int ret;
+
+                        ret = __lock_page_killable(page);
+                        if (ret) {
+                                up_read(&mm->mmap_sem);
+                                return 0;
+                        }
+                } else
+                        __lock_page(page);
+                return 1;
         }
 }
 
@@ -782,9 +849,13 @@ repeat:
                 page = radix_tree_deref_slot((void **)pages[i]);
                 if (unlikely(!page))
                         continue;
+
+                /*
+                 * This can only trigger when the entry at index 0 moves out
+                 * of or back to the root: none yet gotten, safe to restart.
+                 */
                 if (radix_tree_deref_retry(page)) {
-                        if (ret)
-                                start = pages[ret-1]->index;
+                        WARN_ON(start | i);
                         goto restart;
                 }
 
@@ -800,6 +871,13 @@ repeat:
                 pages[ret] = page;
                 ret++;
         }
+
+        /*
+         * If all entries were removed before we could secure them,
+         * try again, because callers stop trying once 0 is returned.
+         */
+        if (unlikely(!ret && nr_found))
+                goto restart;
         rcu_read_unlock();
         return ret;
 }
@@ -834,6 +912,11 @@ repeat:
                 page = radix_tree_deref_slot((void **)pages[i]);
                 if (unlikely(!page))
                         continue;
+
+                /*
+                 * This can only trigger when the entry at index 0 moves out
+                 * of or back to the root: none yet gotten, safe to restart.
+                 */
                 if (radix_tree_deref_retry(page))
                         goto restart;
 
@@ -894,6 +977,11 @@ repeat:
                 page = radix_tree_deref_slot((void **)pages[i]);
                 if (unlikely(!page))
                         continue;
+
+                /*
+                 * This can only trigger when the entry at index 0 moves out
+                 * of or back to the root: none yet gotten, safe to restart.
+                 */
                 if (radix_tree_deref_retry(page))
                         goto restart;
 
@@ -909,6 +997,13 @@ repeat:
                 pages[ret] = page;
                 ret++;
         }
+
+        /*
+         * If all entries were removed before we could secure them,
+         * try again, because callers stop trying once 0 is returned.
+         */
+        if (unlikely(!ret && nr_found))
+                goto restart;
         rcu_read_unlock();
 
         if (ret)
@@ -1298,12 +1393,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
         unsigned long seg = 0;
         size_t count;
         loff_t *ppos = &iocb->ki_pos;
+        struct blk_plug plug;
 
         count = 0;
         retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
         if (retval)
                 return retval;
 
+        blk_start_plug(&plug);
+
         /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
         if (filp->f_flags & O_DIRECT) {
                 loff_t size;
@@ -1376,6 +1474,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
                         break;
         }
 out:
+        blk_finish_plug(&plug);
         return retval;
 }
 EXPORT_SYMBOL(generic_file_aio_read);
@@ -1468,15 +1567,17 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
         /* If we don't want any read-ahead, don't bother */
         if (VM_RandomReadHint(vma))
                 return;
+        if (!ra->ra_pages)
+                return;
 
-        if (VM_SequentialReadHint(vma) ||
-                        offset - 1 == (ra->prev_pos >> PAGE_CACHE_SHIFT)) {
+        if (VM_SequentialReadHint(vma)) {
                 page_cache_sync_readahead(mapping, ra, file, offset,
                                           ra->ra_pages);
                 return;
         }
 
-        if (ra->mmap_miss < INT_MAX)
+        /* Avoid banging the cache line if not needed */
+        if (ra->mmap_miss < MMAP_LOTSAMISS * 10)
                 ra->mmap_miss++;
 
         /*
@@ -1490,12 +1591,10 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma,
          * mmap read-around
          */
         ra_pages = max_sane_readahead(ra->ra_pages);
-        if (ra_pages) {
-                ra->start = max_t(long, 0, offset - ra_pages/2);
-                ra->size = ra_pages;
-                ra->async_size = 0;
-                ra_submit(ra, mapping, file);
-        }
+        ra->start = max_t(long, 0, offset - ra_pages / 2);
+        ra->size = ra_pages;
+        ra->async_size = ra_pages / 4;
+        ra_submit(ra, mapping, file);
 }
 
 /*
@@ -1562,6 +1661,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
                 /* No page in the page cache at all */
                 do_sync_mmap_readahead(vma, ra, file, offset);
                 count_vm_event(PGMAJFAULT);
+                mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
                 ret = VM_FAULT_MAJOR;
 retry_find:
                 page = find_get_page(mapping, offset);
@@ -1600,7 +1700,6 @@ retry_find:
                 return VM_FAULT_SIGBUS;
         }
 
-        ra->prev_pos = (loff_t)offset << PAGE_CACHE_SHIFT;
         vmf->page = page;
         return ret | VM_FAULT_LOCKED;
 
@@ -2487,11 +2586,13 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 {
         struct file *file = iocb->ki_filp;
         struct inode *inode = file->f_mapping->host;
+        struct blk_plug plug;
         ssize_t ret;
 
         BUG_ON(iocb->ki_pos != pos);
 
         mutex_lock(&inode->i_mutex);
+        blk_start_plug(&plug);
         ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
         mutex_unlock(&inode->i_mutex);
 
@@ -2502,6 +2603,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
                 if (err < 0 && ret > 0)
                         ret = err;
         }
+        blk_finish_plug(&plug);
         return ret;
 }
 EXPORT_SYMBOL(generic_file_aio_write);