Merge toomuch.toronto.redhat.com:/md0/linux-2.5

into toomuch.toronto.redhat.com:/md0/aio-2.5

fs/aio.c

@@ -176,29 +176,24 @@ static int aio_setup_ring(struct kioctx *ctx)
 /* aio_ring_event: returns a pointer to the event at the given index from
  * kmap_atomic(, km).  Release the pointer with put_aio_ring_event();
  */
-static inline struct io_event *aio_ring_event(struct aio_ring_info *info, int nr, enum km_type km)
-{
-	struct io_event *events;
 #define AIO_EVENTS_PER_PAGE	(PAGE_SIZE / sizeof(struct io_event))
 #define AIO_EVENTS_FIRST_PAGE	((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event))
-
-	if (nr < AIO_EVENTS_FIRST_PAGE) {
-		struct aio_ring *ring;
-		ring = kmap_atomic(info->ring_pages[0], km);
-		return &ring->io_events[nr];
-	}
-	nr -= AIO_EVENTS_FIRST_PAGE;
-
-	events = kmap_atomic(info->ring_pages[1 + nr / AIO_EVENTS_PER_PAGE], km);
-
-	return events + (nr % AIO_EVENTS_PER_PAGE);
-}
-
-static inline void put_aio_ring_event(struct io_event *event, enum km_type km)
-{
-	void *p = (void *)((unsigned long)event & PAGE_MASK);
-	kunmap_atomic(p, km);
-}
+#define AIO_EVENTS_OFFSET	(AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE)
+
+#define aio_ring_event(info, nr, km) ({					\
+	unsigned pos = (nr) + AIO_EVENTS_OFFSET;			\
+	struct io_event *__event;					\
+	__event = kmap_atomic(						\
+			(info)->ring_pages[pos / AIO_EVENTS_PER_PAGE], km); \
+	__event += pos % AIO_EVENTS_PER_PAGE;				\
+	__event;							\
+})
+
+#define put_aio_ring_event(event, km) do {	\
+	struct io_event *__event = (event);	\
+	(void)__event;				\
+	kunmap_atomic((void *)((unsigned long)__event & PAGE_MASK), km); \
+} while(0)
 
 /* ioctx_alloc
  *	Allocates and initializes an ioctx.  Returns an ERR_PTR if it failed.
@@ -557,7 +552,10 @@ int aio_complete(struct kiocb *iocb, long res, long res2)
 		iocb->ki_users--;
 		ret = (0 == iocb->ki_users);
 		spin_unlock_irq(&ctx->ctx_lock);
-		return 0;
+
+		/* sync iocbs put the task here for us */
+		wake_up_process(iocb->ki_user_obj);
+		return ret;
 	}
 
 	info = &ctx->ring_info;
@@ -937,6 +935,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb *user_iocb,
 
 	req->ki_user_obj = user_iocb;
 	req->ki_user_data = iocb->aio_data;
+	req->ki_pos = iocb->aio_offset;
 
 	buf = (char *)(unsigned long)iocb->aio_buf;
 
@@ -951,7 +950,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb *user_iocb,
 		ret = -EINVAL;
 		if (file->f_op->aio_read)
 			ret = file->f_op->aio_read(req, buf,
-					iocb->aio_nbytes, iocb->aio_offset);
+					iocb->aio_nbytes, req->ki_pos);
 		break;
 	case IOCB_CMD_PWRITE:
 		ret = -EBADF;
@@ -963,7 +962,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb *user_iocb,
 		ret = -EINVAL;
 		if (file->f_op->aio_write)
 			ret = file->f_op->aio_write(req, buf,
-					iocb->aio_nbytes, iocb->aio_offset);
+					iocb->aio_nbytes, req->ki_pos);
 		break;
 	case IOCB_CMD_FDSYNC:
 		ret = -EINVAL;

fs/exec.c

@@ -131,7 +131,7 @@ asmlinkage long sys_uselib(const char * library)
 		goto out;
 
 	error = -ENOEXEC;
-	if(file->f_op && file->f_op->read) {
+	if(file->f_op) {
 		struct linux_binfmt * fmt;
 
 		read_lock(&binfmt_lock);
@@ -452,19 +452,16 @@ struct file *open_exec(const char *name)
 }
 
 int kernel_read(struct file *file, unsigned long offset,
-	char * addr, unsigned long count)
+	char *addr, unsigned long count)
 {
 	mm_segment_t old_fs;
 	loff_t pos = offset;
-	int result = -ENOSYS;
+	int result;
 
-	if (!file->f_op->read)
-		goto fail;
 	old_fs = get_fs();
 	set_fs(get_ds());
-	result = file->f_op->read(file, addr, count, &pos);
+	result = vfs_read(file, addr, count, &pos);
 	set_fs(old_fs);
-fail:
 	return result;
 }
 

fs/ext2/file.c

@@ -41,6 +41,8 @@ struct file_operations ext2_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_file_read,
 	.write		= generic_file_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= generic_file_aio_write,
 	.ioctl		= ext2_ioctl,
 	.mmap		= generic_file_mmap,
 	.open		= generic_file_open,

fs/ext3/file.c

@@ -58,8 +58,9 @@ static int ext3_open_file (struct inode * inode, struct file * filp)
  */
 
 static ssize_t
-ext3_file_write(struct file *file, const char *buf, size_t count, loff_t *ppos)
+ext3_file_write(struct kiocb *iocb, const char *buf, size_t count, loff_t pos)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_dentry->d_inode;
 
 	/*
@@ -72,13 +73,15 @@ ext3_file_write(struct file *file, const char *buf, size_t count, loff_t *ppos)
 	if (IS_SYNC(inode) || (file->f_flags & O_SYNC))
 		mark_inode_dirty(inode);
 
-	return generic_file_write(file, buf, count, ppos);
+	return generic_file_aio_write(iocb, buf, count, pos);
 }
 
 struct file_operations ext3_file_operations = {
 	.llseek		= generic_file_llseek,
-	.read		= generic_file_read,
-	.write		= ext3_file_write,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read		= generic_file_aio_read,
+	.aio_write		= ext3_file_write,
 	.readv		= generic_file_readv,
 	.writev		= generic_file_writev,
 	.ioctl		= ext3_ioctl,

fs/nfs/file.c

@@ -35,15 +35,17 @@
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
 static int  nfs_file_mmap(struct file *, struct vm_area_struct *);
-static ssize_t nfs_file_read(struct file *, char *, size_t, loff_t *);
-static ssize_t nfs_file_write(struct file *, const char *, size_t, loff_t *);
+static ssize_t nfs_file_read(struct kiocb *, char *, size_t, loff_t);
+static ssize_t nfs_file_write(struct kiocb *, const char *, size_t, loff_t);
 static int  nfs_file_flush(struct file *);
 static int  nfs_fsync(struct file *, struct dentry *dentry, int datasync);
 
 struct file_operations nfs_file_operations = {
 	.llseek		= remote_llseek,
-	.read		= nfs_file_read,
-	.write		= nfs_file_write,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read		= nfs_file_read,
+	.aio_write		= nfs_file_write,
 	.mmap		= nfs_file_mmap,
 	.open		= nfs_open,
 	.flush		= nfs_file_flush,
@@ -89,19 +91,19 @@ nfs_file_flush(struct file *file)
 }
 
 static ssize_t
-nfs_file_read(struct file * file, char * buf, size_t count, loff_t *ppos)
+nfs_file_read(struct kiocb *iocb, char * buf, size_t count, loff_t pos)
 {
-	struct dentry * dentry = file->f_dentry;
+	struct dentry * dentry = iocb->ki_filp->f_dentry;
 	struct inode * inode = dentry->d_inode;
 	ssize_t result;
 
 	dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
-		(unsigned long) count, (unsigned long) *ppos);
+		(unsigned long) count, (unsigned long) pos);
 
 	result = nfs_revalidate_inode(NFS_SERVER(inode), inode);
 	if (!result)
-		result = generic_file_read(file, buf, count, ppos);
+		result = generic_file_aio_read(iocb, buf, count, pos);
 	return result;
 }
 
@@ -206,15 +208,15 @@ struct address_space_operations nfs_file_aops = {
  * Write to a file (through the page cache).
  */
 static ssize_t
-nfs_file_write(struct file *file, const char *buf, size_t count, loff_t *ppos)
+nfs_file_write(struct kiocb *iocb, const char *buf, size_t count, loff_t pos)
 {
-	struct dentry * dentry = file->f_dentry;
+	struct dentry * dentry = iocb->ki_filp->f_dentry;
 	struct inode * inode = dentry->d_inode;
 	ssize_t result;
 
 	dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
-		inode->i_ino, (unsigned long) count, (unsigned long) *ppos);
+		inode->i_ino, (unsigned long) count, (unsigned long) pos);
 
 	result = -EBUSY;
 	if (IS_SWAPFILE(inode))
@@ -227,7 +229,7 @@ nfs_file_write(struct file *file, const char *buf, size_t count, loff_t *ppos)
 	if (!count)
 		goto out;
 
-	result = generic_file_write(file, buf, count, ppos);
+	result = generic_file_aio_write(iocb, buf, count, pos);
 out:
 	return result;
 

fs/read_write.c

@@ -176,6 +176,20 @@ asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
 }
 #endif
 
+ssize_t do_sync_read(struct file *filp, char *buf, size_t len, loff_t *ppos)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	ret = filp->f_op->aio_read(&kiocb, buf, len, kiocb.ki_pos);
+	if (-EIOCBQUEUED == ret)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
 ssize_t vfs_read(struct file *file, char *buf, size_t count, loff_t *pos)
 {
 	struct inode *inode = file->f_dentry->d_inode;
@@ -183,14 +197,17 @@ ssize_t vfs_read(struct file *file, char *buf, size_t count, loff_t *pos)
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
-	if (!file->f_op || !file->f_op->read)
+	if (!file->f_op || (!file->f_op->read && !file->f_op->aio_read))
 		return -EINVAL;
 
 	ret = locks_verify_area(FLOCK_VERIFY_READ, inode, file, *pos, count);
 	if (!ret) {
 		ret = security_ops->file_permission (file, MAY_READ);
 		if (!ret) {
-			ret = file->f_op->read(file, buf, count, pos);
+			if (file->f_op->read)
+				ret = file->f_op->read(file, buf, count, pos);
+			else
+				ret = do_sync_read(file, buf, count, pos);
 			if (ret > 0)
 				dnotify_parent(file->f_dentry, DN_ACCESS);
 		}
@@ -199,6 +216,20 @@ ssize_t vfs_read(struct file *file, char *buf, size_t count, loff_t *pos)
 	return ret;
 }
 
+ssize_t do_sync_write(struct file *filp, const char *buf, size_t len, loff_t *ppos)
+{
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	kiocb.ki_pos = *ppos;
+	ret = filp->f_op->aio_write(&kiocb, buf, len, kiocb.ki_pos);
+	if (-EIOCBQUEUED == ret)
+		ret = wait_on_sync_kiocb(&kiocb);
+	*ppos = kiocb.ki_pos;
+	return ret;
+}
+
 ssize_t vfs_write(struct file *file, const char *buf, size_t count, loff_t *pos)
 {
 	struct inode *inode = file->f_dentry->d_inode;
@@ -206,14 +237,17 @@ ssize_t vfs_write(struct file *file, const char *buf, size_t count, loff_t *pos)
 
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
-	if (!file->f_op || !file->f_op->write)
+	if (!file->f_op || (!file->f_op->write && !file->f_op->aio_write))
 		return -EINVAL;
 
 	ret = locks_verify_area(FLOCK_VERIFY_WRITE, inode, file, *pos, count);
 	if (!ret) {
 		ret = security_ops->file_permission (file, MAY_WRITE);
 		if (!ret) {
-			ret = file->f_op->write(file, buf, count, pos);
+			if (file->f_op->write)
+				ret = file->f_op->write(file, buf, count, pos);
+			else
+				ret = do_sync_write(file, buf, count, pos);
 			if (ret > 0)
 				dnotify_parent(file->f_dentry, DN_MODIFY);
 		}

include/linux/aio.h

@@ -37,6 +37,7 @@ struct kiocb {
 	void			*ki_data;	/* for use by the the file */
 	void			*ki_user_obj;	/* pointer to userland's iocb */
 	__u64			ki_user_data;	/* user's data for completion */
+	loff_t			ki_pos;
 
 	long			private[KIOCB_PRIVATE_SIZE/sizeof(long)];
 };

include/linux/fs.h

@@ -751,7 +751,7 @@ struct file_operations {
 	ssize_t (*read) (struct file *, char *, size_t, loff_t *);
 	ssize_t (*aio_read) (struct kiocb *, char *, size_t, loff_t);
 	ssize_t (*write) (struct file *, const char *, size_t, loff_t *);
-	ssize_t (*aio_write) (struct kiocb *, char *, size_t, loff_t);
+	ssize_t (*aio_write) (struct kiocb *, const char *, size_t, loff_t);
 	int (*readdir) (struct file *, void *, filldir_t);
 	unsigned int (*poll) (struct file *, struct poll_table_struct *);
 	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
@@ -1243,6 +1243,10 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 extern ssize_t generic_file_read(struct file *, char *, size_t, loff_t *);
 extern ssize_t generic_file_write(struct file *, const char *, size_t, loff_t *);
+extern ssize_t generic_file_aio_read(struct kiocb *, char *, size_t, loff_t);
+extern ssize_t generic_file_aio_write(struct kiocb *, const char *, size_t, loff_t);
+extern ssize_t do_sync_read(struct file *filp, char *buf, size_t len, loff_t *ppos);
+extern ssize_t do_sync_write(struct file *filp, const char *buf, size_t len, loff_t *ppos);
 ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov,
 				unsigned long nr_segs, loff_t *ppos);
 extern ssize_t generic_file_sendfile(struct file *, struct file *, loff_t *, size_t);

mm/filemap.c

@@ -1206,11 +1206,12 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 }
 
 ssize_t
-generic_file_aio_read(struct kiocb *iocb, char *buf, size_t count, loff_t *ppos)
+generic_file_aio_read(struct kiocb *iocb, char *buf, size_t count, loff_t pos)
 {
 	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
 
-	return __generic_file_aio_read(iocb, &local_iov, 1, ppos);
+	BUG_ON(iocb->ki_pos != pos);
+	return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
 }
 
 ssize_t
@@ -1966,6 +1967,12 @@ generic_file_write_nolock(struct file *file, const struct iovec *iov,
 	return err;
 }
 
+ssize_t generic_file_aio_write(struct kiocb *iocb, const char *buf,
+			       size_t count, loff_t pos)
+{
+	return generic_file_write(iocb->ki_filp, buf, count, &iocb->ki_pos);
+}
+
 ssize_t generic_file_write(struct file *file, const char *buf,
 			   size_t count, loff_t *ppos)
 {