Merge branch 'master' into upstream

[pandora-kernel.git] / mm / filemap.c

diff --git a/mm/filemap.c b/mm/filemap.c
index 7b84dc8..d1060b8 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -327,7 +327,7 @@ EXPORT_SYMBOL(sync_page_range);
  * @pos:       beginning offset in pages to write
  * @count:     number of bytes to write
  *
- * Note: Holding i_mutex across sync_page_range_nolock is not a good idea
+ * Note: Holding i_mutex across sync_page_range_nolock() is not a good idea
  * as it forces O_SYNC writers to different parts of the same file
  * to be serialised right until io completion.
  */
@@ -605,26 +605,6 @@ struct page * find_get_page(struct address_space *mapping, unsigned long offset)
 }
 EXPORT_SYMBOL(find_get_page);
 
-/**
- * find_trylock_page - find and lock a page
- * @mapping: the address_space to search
- * @offset: the page index
- *
- * Same as find_get_page(), but trylock it instead of incrementing the count.
- */
-struct page *find_trylock_page(struct address_space *mapping, unsigned long offset)
-{
-       struct page *page;
-
-       read_lock_irq(&mapping->tree_lock);
-       page = radix_tree_lookup(&mapping->page_tree, offset);
-       if (page && TestSetPageLocked(page))
-               page = NULL;
-       read_unlock_irq(&mapping->tree_lock);
-       return page;
-}
-EXPORT_SYMBOL(find_trylock_page);
-
 /**
  * find_lock_page - locate, pin and lock a pagecache page
  * @mapping: the address_space to search
@@ -804,7 +784,7 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
  * @mapping: target address_space
  * @index: the page index
  *
- * Same as grab_cache_page, but do not wait if the page is unavailable.
+ * Same as grab_cache_page(), but do not wait if the page is unavailable.
  * This is intended for speculative data generators, where the data can
  * be regenerated if the page couldn't be grabbed.  This routine should
  * be safe to call while holding the lock for another page.
@@ -1181,8 +1161,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
                if (pos < size) {
                        retval = generic_file_direct_IO(READ, iocb,
                                                iov, pos, nr_segs);
-                       if (retval > 0 && !is_sync_kiocb(iocb))
-                               retval = -EIOCBQUEUED;
                        if (retval > 0)
                                *ppos = pos + retval;
                }
@@ -1445,7 +1423,6 @@ no_cached_page:
         * effect.
         */
        error = page_cache_read(file, pgoff);
-       grab_swap_token();
 
        /*
         * The page we want has now been added to the page cache.
@@ -1893,6 +1870,7 @@ int should_remove_suid(struct dentry *dentry)
 
        return 0;
 }
+EXPORT_SYMBOL(should_remove_suid);
 
 int __remove_suid(struct dentry *dentry, int kill)
 {
@@ -2047,15 +2025,14 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
         * Sync the fs metadata but not the minor inode changes and
         * of course not the data as we did direct DMA for the IO.
         * i_mutex is held, which protects generic_osync_inode() from
-        * livelocking.
+        * livelocking.  AIO O_DIRECT ops attempt to sync metadata here.
         */
-       if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+       if ((written >= 0 || written == -EIOCBQUEUED) &&
+           ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
                int err = generic_osync_inode(inode, mapping, OSYNC_METADATA);
                if (err < 0)
                        written = err;
        }
-       if (written == count && !is_sync_kiocb(iocb))
-               written = -EIOCBQUEUED;
        return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);
@@ -2102,21 +2079,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
                /* Limit the size of the copy to the caller's write size */
                bytes = min(bytes, count);
 
-               /*
-                * Limit the size of the copy to that of the current segment,
-                * because fault_in_pages_readable() doesn't know how to walk
-                * segments.
-                */
-               bytes = min(bytes, cur_iov->iov_len - iov_base);
-
-               /*
-                * Bring in the user page that we will copy from _first_.
-                * Otherwise there's a nasty deadlock on copying from the
-                * same page as we're writing to, without it being marked
-                * up-to-date.
+               /* We only need to worry about prefaulting when writes are from
+                * user-space.  NFSd uses vfs_writev with several non-aligned
+                * segments in the vector, and limiting to one segment a time is
+                * a noticeable performance for re-write
                 */
-               fault_in_pages_readable(buf, bytes);
+               if (!segment_eq(get_fs(), KERNEL_DS)) {
+                       /*
+                        * Limit the size of the copy to that of the current
+                        * segment, because fault_in_pages_readable() doesn't
+                        * know how to walk segments.
+                        */
+                       bytes = min(bytes, cur_iov->iov_len - iov_base);
 
+                       /*
+                        * Bring in the user page that we will copy from
+                        * _first_.  Otherwise there's a nasty deadlock on
+                        * copying from the same page as we're writing to,
+                        * without it being marked up-to-date.
+                        */
+                       fault_in_pages_readable(buf, bytes);
+               }
                page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec);
                if (!page) {
                        status = -ENOMEM;
@@ -2269,7 +2252,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
        if (count == 0)
                goto out;
 
-       err = remove_suid(file->f_dentry);
+       err = remove_suid(file->f_path.dentry);
        if (err)
                goto out;