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>

1 files changed, 9 insertions, 2 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1393742bba9b..2fe920774abf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -779,7 +779,7 @@ struct inode {
         struct timespec         i_ctime;
         blkcnt_t                i_blocks;
         unsigned short          i_bytes;
-        struct rw_semaphore     i_alloc_sem;
+        atomic_t                i_dio_count;
         const struct file_operations    *i_fop; /* former ->i_op->default_file_ops */
         struct file_lock        *i_flock;
         struct address_space    *i_mapping;
@@ -1705,6 +1705,10 @@ struct super_operations {
  *                      set during data writeback, and cleared with a wakeup
  *                      on the bit address once it is done.
  *
+ * I_REFERENCED         Marks the inode as recently references on the LRU list.
+ *
+ * I_DIO_WAKEUP         Never set.  Only used as a key for wait_on_bit().
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC            (1 << 0)
@@ -1718,6 +1722,8 @@ struct super_operations {
 #define __I_SYNC                7
 #define I_SYNC                  (1 << __I_SYNC)
 #define I_REFERENCED            (1 << 8)
+#define __I_DIO_WAKEUP          9
+#define I_DIO_WAKEUP            (1 << I_DIO_WAKEUP)
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
 
@@ -1828,7 +1834,6 @@ struct file_system_type {
         struct lock_class_key i_lock_key;
         struct lock_class_key i_mutex_key;
         struct lock_class_key i_mutex_dir_key;
-        struct lock_class_key i_alloc_sem_key;
 };
 
 extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
@@ -2404,6 +2409,8 @@ enum {
 };
 
 void dio_end_io(struct bio *bio, int error);
+void inode_dio_wait(struct inode *inode);
+void inode_dio_done(struct inode *inode);
 
 ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
         struct block_device *bdev, const struct iovec *iov, loff_t offset,