vfs: Implement proper O_SYNC semantics

While Linux provided an O_SYNC flag basically since day 1, it took until
Linux 2.4.0-test12pre2 to actually get it implemented for filesystems,
since that day we had generic_osync_around with only minor changes and the
great "For now, when the user asks for O_SYNC, we'll actually give
O_DSYNC" comment.  This patch intends to actually give us real O_SYNC
semantics in addition to the O_DSYNC semantics.  After Jan's O_SYNC
patches which are required before this patch it's actually surprisingly
simple, we just need to figure out when to set the datasync flag to
vfs_fsync_range and when not.

This patch renames the existing O_SYNC flag to O_DSYNC while keeping it's
numerical value to keep binary compatibility, and adds a new real O_SYNC
flag.  To guarantee backwards compatiblity it is defined as expanding to
both the O_DSYNC and the new additional binary flag (__O_SYNC) to make
sure we are backwards-compatible when compiled against the new headers.

This also means that all places that don't care about the differences can
just check O_DSYNC and get the right behaviour for O_SYNC, too - only
places that actuall care need to check __O_SYNC in addition.  Drivers and
network filesystems have been updated in a fail safe way to always do the
full sync magic if O_DSYNC is set.  The few places setting O_SYNC for
lower layers are kept that way for now to stay failsafe.

We enforce that O_DSYNC is set when __O_SYNC is set early in the open path
to make sure we always get these sane options.

Note that parisc really screwed up their headers as they already define a
O_DSYNC that has always been a no-op.  We try to repair it by using it for
the new O_DSYNC and redefinining O_SYNC to send both the traditional
O_SYNC numerical value _and_ the O_DSYNC one.

Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Grant Grundler <grundler@parisc-linux.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger@sun.com>
Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jan Kara <jack@suse.cz>

11 files changed, 29 insertions, 15 deletions

diff --git a/fs/afs/write.c b/fs/afs/write.c
index c63a3c8beb73..6be1bc31616a 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -692,8 +692,9 @@ ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov,
         }
 
         /* return error values for O_SYNC and IS_SYNC() */
-        if (IS_SYNC(&vnode->vfs_inode) || iocb->ki_filp->f_flags & O_SYNC) {
-                ret = afs_fsync(iocb->ki_filp, dentry, 1);
+        if (IS_SYNC(&vnode->vfs_inode) || iocb->ki_filp->f_flags & O_DSYNC) {
+                ret = afs_fsync(iocb->ki_filp, dentry,
+                                (iocb->ki_filp->f_flags & __O_SYNC) ? 0 : 1);
                 if (ret < 0)
                         result = ret;
         }
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 06550affbd27..77f759302e12 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -909,7 +909,7 @@ static ssize_t btrfs_file_write(struct file *file, const char __user *buf,
         unsigned long last_index;
         int will_write;
 
-        will_write = ((file->f_flags & O_SYNC) || IS_SYNC(inode) ||
+        will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
                       (file->f_flags & O_DIRECT));
 
         nrptrs = min((count + PAGE_CACHE_SIZE - 1) / PAGE_CACHE_SIZE,
@@ -1076,7 +1076,7 @@ out_nolock:
                 if (err)
                         num_written = err;
 
-                if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
+                if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
                         trans = btrfs_start_transaction(root, 1);
                         ret = btrfs_log_dentry_safe(trans, root,
                                                     file->f_dentry);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 1f42f772865a..6ccf7262d1b7 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -214,7 +214,8 @@ int cifs_posix_open(char *full_path, struct inode **pinode,
                 posix_flags |= SMB_O_EXCL;
         if (oflags & O_TRUNC)
                 posix_flags |= SMB_O_TRUNC;
-        if (oflags & O_SYNC)
+        /* be safe and imply O_SYNC for O_DSYNC */
+        if (oflags & O_DSYNC)
                 posix_flags |= SMB_O_SYNC;
         if (oflags & O_DIRECTORY)
                 posix_flags |= SMB_O_DIRECTORY;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 429337eb7afe..057e1dae12ab 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -76,8 +76,10 @@ static inline fmode_t cifs_posix_convert_flags(unsigned int flags)
            reopening a file.  They had their effect on the original open */
         if (flags & O_APPEND)
                 posix_flags |= (fmode_t)O_APPEND;
-        if (flags & O_SYNC)
-                posix_flags |= (fmode_t)O_SYNC;
+        if (flags & O_DSYNC)
+                posix_flags |= (fmode_t)O_DSYNC;
+        if (flags & __O_SYNC)
+                posix_flags |= (fmode_t)__O_SYNC;
         if (flags & O_DIRECTORY)
                 posix_flags |= (fmode_t)O_DIRECTORY;
         if (flags & O_NOFOLLOW)
diff --git a/fs/namei.c b/fs/namei.c
index d11f404667e9..b83d38f614ff 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1678,6 +1678,15 @@ struct file *do_filp_open(int dfd, const char *pathname,
         int will_write;
         int flag = open_to_namei_flags(open_flag);
 
+        /*
+         * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
+         * check for O_DSYNC if the need any syncing at all we enforce it's
+         * always set instead of having to deal with possibly weird behaviour
+         * for malicious applications setting only __O_SYNC.
+         */
+        if (open_flag & __O_SYNC)
+                open_flag |= O_DSYNC;
+
         if (!acc_mode)
                 acc_mode = MAY_OPEN | ACC_MODE(flag);
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index f5fdd39e037a..6b891328f332 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -581,7 +581,7 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode)
 {
         struct nfs_open_context *ctx;
 
-        if (IS_SYNC(inode) || (filp->f_flags & O_SYNC))
+        if (IS_SYNC(inode) || (filp->f_flags & O_DSYNC))
                 return 1;
         ctx = nfs_file_open_context(filp);
         if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags))
@@ -622,7 +622,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 
         nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, count);
         result = generic_file_aio_write(iocb, iov, nr_segs, pos);
-        /* Return error values for O_SYNC and IS_SYNC() */
+        /* Return error values for O_DSYNC and IS_SYNC() */
         if (result >= 0 && nfs_need_sync_write(iocb->ki_filp, inode)) {
                 int err = nfs_do_fsync(nfs_file_open_context(iocb->ki_filp), inode);
                 if (err < 0)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c84b5cc1a943..b1ce2ea9b93b 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -774,7 +774,7 @@ int nfs_updatepage(struct file *file, struct page *page,
          */
         if (nfs_write_pageuptodate(page, inode) &&
                         inode->i_flock == NULL &&
-                        !(file->f_flags & O_SYNC)) {
+                        !(file->f_flags & O_DSYNC)) {
                 count = max(count + offset, nfs_page_length(page));
                 offset = 0;
         }
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index de059f490586..3d30a1c974a8 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2006,7 +2006,7 @@ out_dio:
         /* buffered aio wouldn't have proper lock coverage today */
         BUG_ON(ret == -EIOCBQUEUED && !(file->f_flags & O_DIRECT));
 
-        if ((file->f_flags & O_SYNC && !direct_io) || IS_SYNC(inode)) {
+        if ((file->f_flags & O_DSYNC && !direct_io) || IS_SYNC(inode)) {
                 ret = filemap_fdatawrite_range(file->f_mapping, pos,
                                                pos + count - 1);
                 if (ret < 0)
diff --git a/fs/sync.c b/fs/sync.c
index d104591b066b..b75ca68dc081 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -295,10 +295,11 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
  */
 int generic_write_sync(struct file *file, loff_t pos, loff_t count)
 {
-        if (!(file->f_flags & O_SYNC) && !IS_SYNC(file->f_mapping->host))
+        if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
                 return 0;
         return vfs_fsync_range(file, file->f_path.dentry, pos,
-                               pos + count - 1, 1);
+                               pos + count - 1,
+                               (file->f_flags & __O_SYNC) ? 0 : 1);
 }
 EXPORT_SYMBOL(generic_write_sync);
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 1009adc8d602..eaa3d480bc20 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1401,7 +1401,7 @@ static ssize_t ubifs_aio_write(struct kiocb *iocb, const struct iovec *iov,
         if (ret < 0)
                 return ret;
 
-        if (ret > 0 && (IS_SYNC(inode) || iocb->ki_filp->f_flags & O_SYNC)) {
+        if (ret > 0 && (IS_SYNC(inode) || iocb->ki_filp->f_flags & O_DSYNC)) {
                 err = ubifs_sync_wbufs_by_inode(c, inode);
                 if (err)
                         return err;
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 072050f8d346..339c52b1a434 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -811,7 +811,7 @@ write_retry:
         XFS_STATS_ADD(xs_write_bytes, ret);
 
         /* Handle various SYNC-type writes */
-        if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
+        if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
                 loff_t end = pos + ret - 1;
                 int error2;