[GFS2] Put back O_DIRECT support
This patch adds back O_DIRECT support with various caveats
attached:
1. Journaled data can be read via O_DIRECT since its now the
same on disk format as normal data files.
2. Journaled data writes with O_DIRECT will be failed sliently
back to normal writes (should we really do this I wonder or
should we return an error instead?)
3. Stuffed files will be failed back to normal buffered I/O
4. All the usual corner cases (write beyond current end of file,
write to an unallocated block) will also revert to normal buffered I/O.
The I/O path is slightly odd as reads arrive at the page cache layer
with the lock for the file already held, but writes arrive unlocked.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index b14357e..74706f3 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -14,6 +14,7 @@
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/mpage.h>
+#include <linux/fs.h>
#include <asm/semaphore.h>
#include "gfs2.h"
@@ -555,30 +556,73 @@
return ret;
}
-static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+static ssize_t gfs2_direct_IO_write(struct kiocb *iocb, const struct iovec *iov,
+ loff_t offset, unsigned long nr_segs)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file->f_mapping->host;
+ struct gfs2_inode *ip = get_v2ip(inode);
+ struct gfs2_holder gh;
+ int rv;
+
+ /*
+ * Shared lock, even though its write, since we do no allocation
+ * on this path. All we need change is atime.
+ */
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, GL_ATIME, &gh);
+ rv = gfs2_glock_nq_m_atime(1, &gh);
+ if (rv)
+ goto out;
+
+ /*
+ * Should we return an error here? I can't see that O_DIRECT for
+ * a journaled file makes any sense. For now we'll silently fall
+ * back to buffered I/O, likewise we do the same for stuffed
+ * files since they are (a) small and (b) unaligned.
+ */
+ if (gfs2_is_jdata(ip))
+ goto out;
+
+ if (gfs2_is_stuffed(ip))
+ goto out;
+
+ rv = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+ iov, offset, nr_segs, get_blocks_noalloc,
+ NULL, DIO_OWN_LOCKING);
+out:
+ gfs2_glock_dq_m(1, &gh);
+ gfs2_holder_uninit(&gh);
+
+ return rv;
+}
+
+/**
+ * gfs2_direct_IO
+ *
+ * This is called with a shared lock already held for the read path.
+ * Currently, no locks are held when the write path is called.
+ */
+static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
+ const struct iovec *iov, loff_t offset,
+ unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct gfs2_inode *ip = get_v2ip(inode);
struct gfs2_sbd *sdp = ip->i_sbd;
- get_blocks_t *gb = get_blocks;
atomic_inc(&sdp->sd_ops_address);
- if (gfs2_is_jdata(ip))
+ if (rw == WRITE)
+ return gfs2_direct_IO_write(iocb, iov, offset, nr_segs);
+
+ if (gfs2_assert_warn(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)) ||
+ gfs2_assert_warn(sdp, !gfs2_is_stuffed(ip)))
return -EINVAL;
- if (rw == WRITE) {
- return -EOPNOTSUPP; /* for now */
- } else {
- if (gfs2_assert_warn(sdp, gfs2_glock_is_locked_by_me(ip->i_gl)) ||
- gfs2_assert_warn(sdp, !gfs2_is_stuffed(ip)))
- return -EINVAL;
- }
-
- return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
- offset, nr_segs, gb, NULL);
+ return __blockdev_direct_IO(READ, iocb, inode, inode->i_sb->s_bdev, iov,
+ offset, nr_segs, get_blocks, NULL,
+ DIO_OWN_LOCKING);
}
struct address_space_operations gfs2_file_aops = {
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 56820b3..bcde7a0 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -176,16 +176,16 @@
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
- count += iv->iov_len;
- if (unlikely((ssize_t)(count|iv->iov_len) < 0))
- return -EINVAL;
- if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
- continue;
- if (seg == 0)
- return -EFAULT;
- nr_segs = seg;
- count -= iv->iov_len; /* This segment is no good */
- break;
+ count += iv->iov_len;
+ if (unlikely((ssize_t)(count|iv->iov_len) < 0))
+ return -EINVAL;
+ if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
+ continue;
+ if (seg == 0)
+ return -EFAULT;
+ nr_segs = seg;
+ count -= iv->iov_len; /* This segment is no good */
+ break;
}
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
@@ -204,10 +204,14 @@
retval = gfs2_glock_nq_m_atime(1, &gh);
if (retval)
goto out;
-
+ if (gfs2_is_stuffed(ip)) {
+ gfs2_glock_dq_m(1, &gh);
+ gfs2_holder_uninit(&gh);
+ goto fallback_to_normal;
+ }
size = i_size_read(inode);
if (pos < size) {
- retval = gfs2_direct_IO_read(iocb, iov, pos, nr_segs);
+ retval = gfs2_direct_IO_read(iocb, iov, pos, nr_segs);
if (retval > 0 && !is_sync_kiocb(iocb))
retval = -EIOCBQUEUED;
if (retval > 0)
@@ -219,6 +223,7 @@
goto out;
}
+fallback_to_normal:
retval = 0;
if (count) {
for (seg = 0; seg < nr_segs; seg++) {