1 files changed, 61 insertions, 22 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c641edf553a9..bcdc393b6580 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)
  *
@@ -84,7 +85,7 @@
  *    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
@@ -106,7 +107,7 @@
  *
  *  (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
  */
 
 /*
@@ -118,6 +119,16 @@ 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--;
@@ -562,6 +573,17 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 }
 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
@@ -643,15 +665,32 @@ EXPORT_SYMBOL_GPL(__lock_page_killable);
 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_RETRY_NOWAIT)) {
-                        up_read(&mm->mmap_sem);
+        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);
+                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;
         }
 }
 
@@ -1528,15 +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++;
 
         /*
@@ -1550,12 +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);
 }
 
 /*
@@ -1622,6 +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);
@@ -1660,7 +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;