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>
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 98ce3ac..354cbdb 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -135,6 +135,50 @@
struct page *pages[DIO_PAGES]; /* page buffer */
};
+static void __inode_dio_wait(struct inode *inode)
+{
+ wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP);
+ DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
+
+ do {
+ prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE);
+ if (atomic_read(&inode->i_dio_count))
+ schedule();
+ } while (atomic_read(&inode->i_dio_count));
+ finish_wait(wq, &q.wait);
+}
+
+/**
+ * inode_dio_wait - wait for outstanding DIO requests to finish
+ * @inode: inode to wait for
+ *
+ * Waits for all pending direct I/O requests to finish so that we can
+ * proceed with a truncate or equivalent operation.
+ *
+ * Must be called under a lock that serializes taking new references
+ * to i_dio_count, usually by inode->i_mutex.
+ */
+void inode_dio_wait(struct inode *inode)
+{
+ if (atomic_read(&inode->i_dio_count))
+ __inode_dio_wait(inode);
+}
+EXPORT_SYMBOL_GPL(inode_dio_wait);
+
+/*
+ * inode_dio_done - signal finish of a direct I/O requests
+ * @inode: inode the direct I/O happens on
+ *
+ * This is called once we've finished processing a direct I/O request,
+ * and is used to wake up callers waiting for direct I/O to be quiesced.
+ */
+void inode_dio_done(struct inode *inode)
+{
+ if (atomic_dec_and_test(&inode->i_dio_count))
+ wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
+}
+EXPORT_SYMBOL_GPL(inode_dio_done);
+
/*
* How many pages are in the queue?
*/
@@ -254,9 +298,7 @@
}
if (dio->flags & DIO_LOCKING)
- /* lockdep: non-owner release */
- up_read_non_owner(&dio->inode->i_alloc_sem);
-
+ inode_dio_done(dio->inode);
return ret;
}
@@ -980,9 +1022,6 @@
return ret;
}
-/*
- * Releases both i_mutex and i_alloc_sem
- */
static ssize_t
direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
const struct iovec *iov, loff_t offset, unsigned long nr_segs,
@@ -1146,15 +1185,14 @@
* For writes this function is called under i_mutex and returns with
* i_mutex held, for reads, i_mutex is not held on entry, but it is
* taken and dropped again before returning.
- * For reads and writes i_alloc_sem is taken in shared mode and released
- * on I/O completion (which may happen asynchronously after returning to
- * the caller).
+ * The i_dio_count counter keeps track of the number of outstanding
+ * direct I/O requests, and truncate waits for it to reach zero.
+ * New references to i_dio_count must only be grabbed with i_mutex
+ * held.
*
* - if the flags value does NOT contain DIO_LOCKING we don't use any
* internal locking but rather rely on the filesystem to synchronize
* direct I/O reads/writes versus each other and truncate.
- * For reads and writes both i_mutex and i_alloc_sem are not held on
- * entry and are never taken.
*/
ssize_t
__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
@@ -1234,10 +1272,9 @@
}
/*
- * Will be released at I/O completion, possibly in a
- * different thread.
+ * Will be decremented at I/O completion time.
*/
- down_read_non_owner(&inode->i_alloc_sem);
+ atomic_inc(&inode->i_dio_count);
}
/*