[PATCH] add -o flush for fat

Fat is commonly used on removable media.  Mounting with -o flush tells the
FS to write things to disk as quickly as possible.  It is like -o sync, but
much faster (and not as safe).

Signed-off-by: Chris Mason <mason@suse.com>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 70 insertions, 2 deletions

diff --git a/fs/fat/file.c b/fs/fat/file.c
index 1ee25232e6af..d50fc47169c1 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -13,6 +13,7 @@
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
+#include <linux/blkdev.h>
 
 int fat_generic_ioctl(struct inode *inode, struct file *filp,
                       unsigned int cmd, unsigned long arg)
@@ -112,6 +113,16 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
         }
 }
 
+static int fat_file_release(struct inode *inode, struct file *filp)
+{
+        if ((filp->f_mode & FMODE_WRITE) &&
+             MSDOS_SB(inode->i_sb)->options.flush) {
+                fat_flush_inodes(inode->i_sb, inode, NULL);
+                blk_congestion_wait(WRITE, HZ/10);
+        }
+        return 0;
+}
+
 const struct file_operations fat_file_operations = {
         .llseek         = generic_file_llseek,
         .read           = do_sync_read,
@@ -121,6 +132,7 @@ const struct file_operations fat_file_operations = {
         .aio_read       = generic_file_aio_read,
         .aio_write      = generic_file_aio_write,
         .mmap           = generic_file_mmap,
+        .release        = fat_file_release,
         .ioctl          = fat_generic_ioctl,
         .fsync          = file_fsync,
         .sendfile       = generic_file_sendfile,
@@ -289,6 +301,7 @@ void fat_truncate(struct inode *inode)
         lock_kernel();
         fat_free(inode, nr_clusters);
         unlock_kernel();
+        fat_flush_inodes(inode->i_sb, inode, NULL);
 }
 
 struct inode_operations fat_file_inode_operations = {
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index ab96ae823753..045738032a83 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -24,6 +24,7 @@
 #include <linux/vfs.h>
 #include <linux/parser.h>
 #include <linux/uio.h>
+#include <linux/writeback.h>
 #include <asm/unaligned.h>
 
 #ifndef CONFIG_FAT_DEFAULT_IOCHARSET
@@ -853,7 +854,7 @@ enum {
         Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
         Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
         Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
-        Opt_obsolate, Opt_err,
+        Opt_obsolate, Opt_flush, Opt_err,
 };
 
 static match_table_t fat_tokens = {
@@ -885,7 +886,8 @@ static match_table_t fat_tokens = {
         {Opt_obsolate, "cvf_format=%20s"},
         {Opt_obsolate, "cvf_options=%100s"},
         {Opt_obsolate, "posix"},
-        {Opt_err, NULL}
+        {Opt_flush, "flush"},
+        {Opt_err, NULL},
 };
 static match_table_t msdos_tokens = {
         {Opt_nodots, "nodots"},
@@ -1026,6 +1028,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
                                 return 0;
                         opts->codepage = option;
                         break;
+                case Opt_flush:
+                        opts->flush = 1;
+                        break;
 
                 /* msdos specific */
                 case Opt_dots:
@@ -1425,6 +1430,56 @@ out_fail:
 
 EXPORT_SYMBOL_GPL(fat_fill_super);
 
+/*
+ * helper function for fat_flush_inodes.  This writes both the inode
+ * and the file data blocks, waiting for in flight data blocks before
+ * the start of the call.  It does not wait for any io started
+ * during the call
+ */
+static int writeback_inode(struct inode *inode)
+{
+
+        int ret;
+        struct address_space *mapping = inode->i_mapping;
+        struct writeback_control wbc = {
+               .sync_mode = WB_SYNC_NONE,
+              .nr_to_write = 0,
+        };
+        /* if we used WB_SYNC_ALL, sync_inode waits for the io for the
+        * inode to finish.  So WB_SYNC_NONE is sent down to sync_inode
+        * and filemap_fdatawrite is used for the data blocks
+        */
+        ret = sync_inode(inode, &wbc);
+        if (!ret)
+               ret = filemap_fdatawrite(mapping);
+        return ret;
+}
+
+/*
+ * write data and metadata corresponding to i1 and i2.  The io is
+ * started but we do not wait for any of it to finish.
+ *
+ * filemap_flush is used for the block device, so if there is a dirty
+ * page for a block already in flight, we will not wait and start the
+ * io over again
+ */
+int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2)
+{
+        int ret = 0;
+        if (!MSDOS_SB(sb)->options.flush)
+                return 0;
+        if (i1)
+                ret = writeback_inode(i1);
+        if (!ret && i2)
+                ret = writeback_inode(i2);
+        if (!ret && sb) {
+                struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+                ret = filemap_flush(mapping);
+        }
+        return ret;
+}
+EXPORT_SYMBOL_GPL(fat_flush_inodes);
+
 static int __init init_fat_fs(void)
 {
         int err;