1 files changed, 62 insertions, 120 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index ccea3b665c12..ef169f37156d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -39,11 +39,10 @@
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
-#include <linux/buffer_head.h> /* for generic_osync_inode */
+#include <linux/buffer_head.h> /* for try_to_free_buffers */
 
 #include <asm/mman.h>
 
-
 /*
  * Shared mappings implemented 30.11.1994. It's not fully working yet,
  * though.
@@ -59,7 +58,7 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock               (vmtruncate)
+ *  ->i_mmap_lock               (truncate_pagecache)
  *    ->private_lock            (__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock             (exclusive_swap_page, others)
  *        ->mapping->tree_lock
@@ -105,6 +104,10 @@
  *
  *  ->task->proc_lock
  *    ->dcache_lock             (proc_pid_lookup)
+ *
+ *  (code doesn't rely on that order, so you could switch it around)
+ *  ->tasklist_lock             (memory_failure, collect_procs_ao)
+ *    ->i_mmap_lock
  */
 
 /*
@@ -120,6 +123,8 @@ void __remove_from_page_cache(struct page *page)
         page->mapping = NULL;
         mapping->nrpages--;
         __dec_zone_page_state(page, NR_FILE_PAGES);
+        if (PageSwapBacked(page))
+                __dec_zone_page_state(page, NR_SHMEM);
         BUG_ON(page_mapped(page));
 
         /*
@@ -307,68 +312,24 @@ int wait_on_page_writeback_range(struct address_space *mapping,
 }
 
 /**
- * sync_page_range - write and wait on all pages in the passed range
- * @inode:      target inode
- * @mapping:    target address_space
- * @pos:        beginning offset in pages to write
- * @count:      number of bytes to write
- *
- * Write and wait upon all the pages in the passed range.  This is a "data
- * integrity" operation.  It waits upon in-flight writeout before starting and
- * waiting upon new writeout.  If there was an IO error, return it.
+ * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range
+ * @mapping: address space structure to wait for
+ * @start:      offset in bytes where the range starts
+ * @end:        offset in bytes where the range ends (inclusive)
  *
- * We need to re-take i_mutex during the generic_osync_inode list walk because
- * it is otherwise livelockable.
- */
-int sync_page_range(struct inode *inode, struct address_space *mapping,
-                        loff_t pos, loff_t count)
-{
-        pgoff_t start = pos >> PAGE_CACHE_SHIFT;
-        pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
-        int ret;
-
-        if (!mapping_cap_writeback_dirty(mapping) || !count)
-                return 0;
-        ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
-        if (ret == 0) {
-                mutex_lock(&inode->i_mutex);
-                ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
-                mutex_unlock(&inode->i_mutex);
-        }
-        if (ret == 0)
-                ret = wait_on_page_writeback_range(mapping, start, end);
-        return ret;
-}
-EXPORT_SYMBOL(sync_page_range);
-
-/**
- * sync_page_range_nolock - write & wait on all pages in the passed range without locking
- * @inode:      target inode
- * @mapping:    target address_space
- * @pos:        beginning offset in pages to write
- * @count:      number of bytes to write
+ * Walk the list of under-writeback pages of the given address space
+ * in the given range and wait for all of them.
  *
- * 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.
+ * This is just a simple wrapper so that callers don't have to convert offsets
+ * to page indexes themselves
  */
-int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
-                           loff_t pos, loff_t count)
+int filemap_fdatawait_range(struct address_space *mapping, loff_t start,
+                            loff_t end)
 {
-        pgoff_t start = pos >> PAGE_CACHE_SHIFT;
-        pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
-        int ret;
-
-        if (!mapping_cap_writeback_dirty(mapping) || !count)
-                return 0;
-        ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
-        if (ret == 0)
-                ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
-        if (ret == 0)
-                ret = wait_on_page_writeback_range(mapping, start, end);
-        return ret;
+        return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT,
+                                            end >> PAGE_CACHE_SHIFT);
 }
-EXPORT_SYMBOL(sync_page_range_nolock);
+EXPORT_SYMBOL(filemap_fdatawait_range);
 
 /**
  * filemap_fdatawait - wait for all under-writeback pages to complete
@@ -476,6 +437,8 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
                 if (likely(!error)) {
                         mapping->nrpages++;
                         __inc_zone_page_state(page, NR_FILE_PAGES);
+                        if (PageSwapBacked(page))
+                                __inc_zone_page_state(page, NR_SHMEM);
                         spin_unlock_irq(&mapping->tree_lock);
                 } else {
                         page->mapping = NULL;
@@ -1648,7 +1611,7 @@ page_not_uptodate:
 }
 EXPORT_SYMBOL(filemap_fault);
 
-struct vm_operations_struct generic_file_vm_ops = {
+const struct vm_operations_struct generic_file_vm_ops = {
         .fault          = filemap_fault,
 };
 
@@ -2167,20 +2130,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
                 }
                 *ppos = end;
         }
-
-        /*
-         * 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.  AIO O_DIRECT ops attempt to sync metadata here.
-         */
 out:
-        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;
-        }
         return written;
 }
 EXPORT_SYMBOL(generic_file_direct_write);
@@ -2312,8 +2262,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 {
         struct file *file = iocb->ki_filp;
         struct address_space *mapping = file->f_mapping;
-        const struct address_space_operations *a_ops = mapping->a_ops;
-        struct inode *inode = mapping->host;
         ssize_t status;
         struct iov_iter i;
 
@@ -2323,16 +2271,6 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
         if (likely(status >= 0)) {
                 written += status;
                 *ppos = pos + status;
-
-                /*
-                 * For now, when the user asks for O_SYNC, we'll actually give
-                 * O_DSYNC
-                 */
-                if (unlikely((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-                        if (!a_ops->writepage || !is_sync_kiocb(iocb))
-                                status = generic_osync_inode(inode, mapping,
-                                                OSYNC_METADATA|OSYNC_DATA);
-                }
         }
         
         /*
@@ -2348,9 +2286,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 }
 EXPORT_SYMBOL(generic_file_buffered_write);
 
-static ssize_t
-__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov,
-                                unsigned long nr_segs, loff_t *ppos)
+/**
+ * __generic_file_aio_write - write data to a file
+ * @iocb:       IO state structure (file, offset, etc.)
+ * @iov:        vector with data to write
+ * @nr_segs:    number of segments in the vector
+ * @ppos:       position where to write
+ *
+ * This function does all the work needed for actually writing data to a
+ * file. It does all basic checks, removes SUID from the file, updates
+ * modification times and calls proper subroutines depending on whether we
+ * do direct IO or a standard buffered write.
+ *
+ * It expects i_mutex to be grabbed unless we work on a block device or similar
+ * object which does not need locking at all.
+ *
+ * This function does *not* take care of syncing data in case of O_SYNC write.
+ * A caller has to handle it. This is mainly due to the fact that we want to
+ * avoid syncing under i_mutex.
+ */
+ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
+                                 unsigned long nr_segs, loff_t *ppos)
 {
         struct file *file = iocb->ki_filp;
         struct address_space * mapping = file->f_mapping;
@@ -2447,51 +2403,37 @@ out:
         current->backing_dev_info = NULL;
         return written ? written : err;
 }
+EXPORT_SYMBOL(__generic_file_aio_write);
 
-ssize_t generic_file_aio_write_nolock(struct kiocb *iocb,
-                const struct iovec *iov, unsigned long nr_segs, loff_t pos)
-{
-        struct file *file = iocb->ki_filp;
-        struct address_space *mapping = file->f_mapping;
-        struct inode *inode = mapping->host;
-        ssize_t ret;
-
-        BUG_ON(iocb->ki_pos != pos);
-
-        ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
-                        &iocb->ki_pos);
-
-        if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
-                ssize_t err;
-
-                err = sync_page_range_nolock(inode, mapping, pos, ret);
-                if (err < 0)
-                        ret = err;
-        }
-        return ret;
-}
-EXPORT_SYMBOL(generic_file_aio_write_nolock);
-
+/**
+ * generic_file_aio_write - write data to a file
+ * @iocb:       IO state structure
+ * @iov:        vector with data to write
+ * @nr_segs:    number of segments in the vector
+ * @pos:        position in file where to write
+ *
+ * This is a wrapper around __generic_file_aio_write() to be used by most
+ * filesystems. It takes care of syncing the file in case of O_SYNC file
+ * and acquires i_mutex as needed.
+ */
 ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
                 unsigned long nr_segs, loff_t pos)
 {
         struct file *file = iocb->ki_filp;
-        struct address_space *mapping = file->f_mapping;
-        struct inode *inode = mapping->host;
+        struct inode *inode = file->f_mapping->host;
         ssize_t ret;
 
         BUG_ON(iocb->ki_pos != pos);
 
         mutex_lock(&inode->i_mutex);
-        ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs,
-                        &iocb->ki_pos);
+        ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
         mutex_unlock(&inode->i_mutex);
 
-        if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) {
+        if (ret > 0 || ret == -EIOCBQUEUED) {
                 ssize_t err;
 
-                err = sync_page_range(inode, mapping, pos, ret);
-                if (err < 0)
+                err = generic_write_sync(file, pos, ret);
+                if (err < 0 && ret > 0)
                         ret = err;
         }
         return ret;