1 files changed, 60 insertions, 14 deletions

diff --git a/mm/truncate.c b/mm/truncate.c
index ba887bff48c5..e13f22efaad7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -19,6 +19,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/buffer_head.h>  /* grr. try_to_release_page,
                                    do_invalidatepage */
+#include <linux/cleancache.h>
 #include "internal.h"
 
 
@@ -51,6 +52,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
         zero_user_segment(page, partial, PAGE_CACHE_SIZE);
+        cleancache_flush_page(page->mapping, page);
         if (page_has_private(page))
                 do_invalidatepage(page, partial);
 }
@@ -106,9 +108,8 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
         cancel_dirty_page(page, PAGE_CACHE_SIZE);
 
         clear_page_mlock(page);
-        remove_from_page_cache(page);
         ClearPageMappedToDisk(page);
-        page_cache_release(page);       /* pagecache ref */
+        delete_from_page_cache(page);
         return 0;
 }
 
@@ -215,6 +216,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
         pgoff_t next;
         int i;
 
+        cleancache_flush_inode(mapping);
         if (mapping->nrpages == 0)
                 return;
 
@@ -225,6 +227,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
         next = start;
         while (next <= end &&
                pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+                mem_cgroup_uncharge_start();
                 for (i = 0; i < pagevec_count(&pvec); i++) {
                         struct page *page = pvec.pages[i];
                         pgoff_t page_index = page->index;
@@ -247,6 +250,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
                         unlock_page(page);
                 }
                 pagevec_release(&pvec);
+                mem_cgroup_uncharge_end();
                 cond_resched();
         }
 
@@ -290,6 +294,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
                 pagevec_release(&pvec);
                 mem_cgroup_uncharge_end();
         }
+        cleancache_flush_inode(mapping);
 }
 EXPORT_SYMBOL(truncate_inode_pages_range);
 
@@ -299,6 +304,11 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @lstart: offset from which to truncate
  *
  * Called under (and serialised by) inode->i_mutex.
+ *
+ * Note: When this function returns, there can be a page in the process of
+ * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
+ * mapping->nrpages can be non-zero when this function returns even after
+ * truncation of the whole mapping.
  */
 void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 {
@@ -320,11 +330,12 @@ EXPORT_SYMBOL(truncate_inode_pages);
  * pagetables.
  */
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
-                                       pgoff_t start, pgoff_t end)
+                pgoff_t start, pgoff_t end)
 {
         struct pagevec pvec;
         pgoff_t next = start;
-        unsigned long ret = 0;
+        unsigned long ret;
+        unsigned long count = 0;
         int i;
 
         pagevec_init(&pvec, 0);
@@ -351,9 +362,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
                         if (lock_failed)
                                 continue;
 
-                        ret += invalidate_inode_page(page);
-
+                        ret = invalidate_inode_page(page);
                         unlock_page(page);
+                        /*
+                         * Invalidation is a hint that the page is no longer
+                         * of interest and try to speed up its reclaim.
+                         */
+                        if (!ret)
+                                deactivate_page(page);
+                        count += ret;
                         if (next > end)
                                 break;
                 }
@@ -361,7 +378,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
                 mem_cgroup_uncharge_end();
                 cond_resched();
         }
-        return ret;
+        return count;
 }
 EXPORT_SYMBOL(invalidate_mapping_pages);
 
@@ -387,9 +404,13 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 
         clear_page_mlock(page);
         BUG_ON(page_has_private(page));
-        __remove_from_page_cache(page);
+        __delete_from_page_cache(page);
         spin_unlock_irq(&mapping->tree_lock);
         mem_cgroup_uncharge_cache_page(page);
+
+        if (mapping->a_ops->freepage)
+                mapping->a_ops->freepage(page);
+
         page_cache_release(page);       /* pagecache ref */
         return 1;
 failed:
@@ -428,6 +449,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
         int did_range_unmap = 0;
         int wrapped = 0;
 
+        cleancache_flush_inode(mapping);
         pagevec_init(&pvec, 0);
         next = start;
         while (next <= end && !wrapped &&
@@ -486,6 +508,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
                 mem_cgroup_uncharge_end();
                 cond_resched();
         }
+        cleancache_flush_inode(mapping);
         return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
@@ -545,13 +568,12 @@ EXPORT_SYMBOL(truncate_pagecache);
  * @inode: inode
  * @newsize: new file size
  *
- * truncate_setsize updastes i_size update and performs pagecache
- * truncation (if necessary) for a file size updates. It will be
- * typically be called from the filesystem's setattr function when
- * ATTR_SIZE is passed in.
+ * truncate_setsize updates i_size and performs pagecache truncation (if
+ * necessary) to @newsize. It will be typically be called from the filesystem's
+ * setattr function when ATTR_SIZE is passed in.
  *
- * Must be called with inode_mutex held and after all filesystem
- * specific block truncation has been performed.
+ * Must be called with inode_mutex held and before all filesystem specific
+ * block truncation has been performed.
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
@@ -586,3 +608,27 @@ int vmtruncate(struct inode *inode, loff_t offset)
         return 0;
 }
 EXPORT_SYMBOL(vmtruncate);
+
+int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+{
+        struct address_space *mapping = inode->i_mapping;
+
+        /*
+         * If the underlying filesystem is not going to provide
+         * a way to truncate a range of blocks (punch a hole) -
+         * we should return failure right now.
+         */
+        if (!inode->i_op->truncate_range)
+                return -ENOSYS;
+
+        mutex_lock(&inode->i_mutex);
+        down_write(&inode->i_alloc_sem);
+        unmap_mapping_range(mapping, offset, (end - offset), 1);
+        inode->i_op->truncate_range(inode, offset, end);
+        /* unmap again to remove racily COWed private pages */
+        unmap_mapping_range(mapping, offset, (end - offset), 1);
+        up_write(&inode->i_alloc_sem);
+        mutex_unlock(&inode->i_mutex);
+
+        return 0;
+}