fs: kill i_alloc_sem

i_alloc_sem is a rather special rw_semaphore.  It's the last one that may
be released by a non-owner, and it's write side is always mirrored by
real exclusion.  It's intended use it to wait for all pending direct I/O
requests to finish before starting a truncate.

Replace it with a hand-grown construct:

 - exclusion for truncates is already guaranteed by i_mutex, so it can
   simply fall way
 - the reader side is replaced by an i_dio_count member in struct inode
   that counts the number of pending direct I/O requests.  Truncate can't
   proceed as long as it's non-zero
 - when i_dio_count reaches non-zero we wake up a pending truncate using
   wake_up_bit on a new bit in i_flags
 - new references to i_dio_count can't appear while we are waiting for
   it to read zero because the direct I/O count always needs i_mutex
   (or an equivalent like XFS's i_iolock) for starting a new operation.

This scheme is much simpler, and saves the space of a spinlock_t and a
struct list_head in struct inode (typically 160 bits on a non-debug 64-bit
system).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

2 files changed, 10 insertions, 12 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ac97bca282d2..de1d3953599d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -551,9 +551,8 @@ bail:
 
 /*
  * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
- * particularly interested in the aio/dio case.  Like the core uses
- * i_alloc_sem, we use the rw_lock DLM lock to protect io on one node from
- * truncation on another.
+ * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+ * to protect io on one node from truncation on another.
  */
 static void ocfs2_dio_end_io(struct kiocb *iocb,
                              loff_t offset,
@@ -569,7 +568,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
         BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
 
         if (ocfs2_iocb_is_sem_locked(iocb)) {
-                up_read(&inode->i_alloc_sem);
+                inode_dio_done(inode);
                 ocfs2_iocb_clear_sem_locked(iocb);
         }
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 1406c37a5722..2c3a465514a2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2236,9 +2236,9 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
         ocfs2_iocb_clear_sem_locked(iocb);
 
 relock:
-        /* to match setattr's i_mutex -> i_alloc_sem -> rw_lock ordering */
+        /* to match setattr's i_mutex -> rw_lock ordering */
         if (direct_io) {
-                down_read(&inode->i_alloc_sem);
+                atomic_inc(&inode->i_dio_count);
                 have_alloc_sem = 1;
                 /* communicate with ocfs2_dio_end_io */
                 ocfs2_iocb_set_sem_locked(iocb);
@@ -2290,7 +2290,7 @@ relock:
          */
         if (direct_io && !can_do_direct) {
                 ocfs2_rw_unlock(inode, rw_level);
-                up_read(&inode->i_alloc_sem);
+                inode_dio_done(inode);
 
                 have_alloc_sem = 0;
                 rw_level = -1;
@@ -2361,8 +2361,7 @@ out_dio:
         /*
          * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
          * function pointer which is called when o_direct io completes so that
-         * it can unlock our rw lock.  (it's the clustered equivalent of
-         * i_alloc_sem; protects truncate from racing with pending ios).
+         * it can unlock our rw lock.
          * Unfortunately there are error cases which call end_io and others
          * that don't.  so we don't have to unlock the rw_lock if either an
          * async dio is going to do it in the future or an end_io after an
@@ -2379,7 +2378,7 @@ out:
 
 out_sems:
         if (have_alloc_sem) {
-                up_read(&inode->i_alloc_sem);
+                inode_dio_done(inode);
                 ocfs2_iocb_clear_sem_locked(iocb);
         }
 
@@ -2531,8 +2530,8 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
          * need locks to protect pending reads from racing with truncate.
          */
         if (filp->f_flags & O_DIRECT) {
-                down_read(&inode->i_alloc_sem);
                 have_alloc_sem = 1;
+                atomic_inc(&inode->i_dio_count);
                 ocfs2_iocb_set_sem_locked(iocb);
 
                 ret = ocfs2_rw_lock(inode, 0);
@@ -2575,7 +2574,7 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb,
 
 bail:
         if (have_alloc_sem) {
-                up_read(&inode->i_alloc_sem);
+                inode_dio_done(inode);
                 ocfs2_iocb_clear_sem_locked(iocb);
         }
         if (rw_level != -1)