fuse: process direct IO asynchronously

index 19b50e7..6685cb0 100644
@@ -491,6 +491,18 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
 	req->out.args[0].size = count;
 }
 
+static void fuse_release_user_pages(struct fuse_req *req, int write)
+{
+	unsigned i;
+
+	for (i = 0; i < req->num_pages; i++) {
+		struct page *page = req->pages[i];
+		if (write)
+			set_page_dirty_lock(page);
+		put_page(page);
+	}
+}
+
 static size_t fuse_send_read(struct fuse_req *req, struct file *file,
 			     loff_t pos, size_t count, fl_owner_t owner)
 {

@@ -1035,18 +1047,6 @@ out:
 	return written ? written : err;
 }
 
-static void fuse_release_user_pages(struct fuse_req *req, int write)
-{
-	unsigned i;
-
-	for (i = 0; i < req->num_pages; i++) {
-		struct page *page = req->pages[i];
-		if (write)
-			set_page_dirty_lock(page);
-		put_page(page);
-	}
-}
-
 static inline void fuse_page_descs_length_init(struct fuse_req *req,
 		unsigned index, unsigned nr_pages)
 {

index 6685cb0..634f54a 100644
@@ -503,6 +503,100 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
 	}
 }
 
+/**
+ * In case of short read, the caller sets 'pos' to the position of
+ * actual end of fuse request in IO request. Otherwise, if bytes_requested
+ * == bytes_transferred or rw == WRITE, the caller sets 'pos' to -1.
+ *
+ * An example:
+ * User requested DIO read of 64K. It was splitted into two 32K fuse requests,
+ * both submitted asynchronously. The first of them was ACKed by userspace as
+ * fully completed (req->out.args[0].size == 32K) resulting in pos == -1. The
+ * second request was ACKed as short, e.g. only 1K was read, resulting in
+ * pos == 33K.
+ *
+ * Thus, when all fuse requests are completed, the minimal non-negative 'pos'
+ * will be equal to the length of the longest contiguous fragment of
+ * transferred data starting from the beginning of IO request.
+ */
+static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
+{
+	int left;
+
+	spin_lock(&io->lock);
+	if (err)
+		io->err = io->err ? : err;
+	else if (pos >= 0 && (io->bytes < 0 || pos < io->bytes))
+		io->bytes = pos;
+
+	left = --io->reqs;
+	spin_unlock(&io->lock);
+
+	if (!left) {
+		long res;
+
+		if (io->err)
+			res = io->err;
+		else if (io->bytes >= 0 && io->write)
+			res = -EIO;
+		else {
+			res = io->bytes < 0 ? io->size : io->bytes;
+
+			if (!is_sync_kiocb(io->iocb)) {
+				struct path *path = &io->iocb->ki_filp->f_path;
+				struct inode *inode = path->dentry->d_inode;
+				struct fuse_conn *fc = get_fuse_conn(inode);
+				struct fuse_inode *fi = get_fuse_inode(inode);
+
+				spin_lock(&fc->lock);
+				fi->attr_version = ++fc->attr_version;
+				spin_unlock(&fc->lock);
+			}
+		}
+
+		aio_complete(io->iocb, res, 0);
+		kfree(io);
+	}
+}
+
+static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req)
+{
+	struct fuse_io_priv *io = req->io;
+	ssize_t pos = -1;
+
+	fuse_release_user_pages(req, !io->write);
+
+	if (io->write) {
+		if (req->misc.write.in.size != req->misc.write.out.size)
+			pos = req->misc.write.in.offset - io->offset +
+				req->misc.write.out.size;
+	} else {
+		if (req->misc.read.in.size != req->out.args[0].size)
+			pos = req->misc.read.in.offset - io->offset +
+				req->out.args[0].size;
+	}
+
+	fuse_aio_complete(io, req->out.h.error, pos);
+}
+
+static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req,
+		size_t num_bytes, struct kiocb *iocb)
+{
+	struct fuse_io_priv *io = iocb->private;
+
+	spin_lock(&io->lock);
+	io->size += num_bytes;
+	io->reqs++;
+	spin_unlock(&io->lock);
+
+	req->io = io;
+	req->end = fuse_aio_complete_req;
+
+	fuse_request_send_background(fc, req);
+
+	return num_bytes;
+}
+
 static size_t fuse_send_read(struct fuse_req *req, struct file *file,
 			     loff_t pos, size_t count, fl_owner_t owner)
 {

index e4f70ea..618d48a 100644
@@ -219,6 +219,18 @@ enum fuse_req_state {
 	FUSE_REQ_FINISHED
 };
 
+/** The request IO state (for asynchronous processing) */
+struct fuse_io_priv {
+	spinlock_t lock;
+	unsigned reqs;
+	ssize_t bytes;
+	size_t size;
+	__u64 offset;
+	bool write;
+	int err;
+	struct kiocb *iocb;
+};
+
 /**
  * A request to the client
  */

@@ -323,6 +335,9 @@ struct fuse_req {
 	/** Inode used in the request or NULL */
 	struct inode *inode;
 
+	/** AIO control block */
+	struct fuse_io_priv *io;
+
 	/** Link on fi->writepages */
 	struct list_head writepages_entry;
 

index 65ce10a..beb99e9 100644
@@ -93,7 +93,7 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count,
 	loff_t pos = 0;
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
 
-	return fuse_direct_io(file, &iov, 1, count, &pos, 0);
+	return fuse_direct_io(file, &iov, 1, count, &pos, 0, NULL);
 }
 
 static ssize_t cuse_write(struct file *file, const char __user *buf,

@@ -106,7 +106,7 @@ static ssize_t cuse_write(struct file *file, const char __user *buf,
 	 * No locking or generic_write_checks(), the server is
 	 * responsible for locking and sanity checks.
 	 */
-	return fuse_direct_io(file, &iov, 1, count, &pos, 1);
+	return fuse_direct_io(file, &iov, 1, count, &pos, 1, NULL);
 }
 
 static int cuse_open(struct inode *inode, struct file *file)

164 lines not on this page · raw message

index 618d48a..173c959 100644
@@ -828,7 +828,7 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 		 bool isdir);
 ssize_t fuse_direct_io(struct file *file, const struct iovec *iov,
 		       unsigned long nr_segs, size_t count, loff_t *ppos,
-		       int write);
+		       int write, struct kiocb *async);
 long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
 		   unsigned int flags);
 long fuse_ioctl_common(struct file *file, unsigned int cmd,

index c585158..ef6d3de 100644
@@ -2348,14 +2348,54 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	ssize_t ret = 0;
 	struct file *file = NULL;
 	loff_t pos = 0;
+	struct inode *inode;
+	loff_t i_size;
+	size_t count = iov_length(iov, nr_segs);
+	struct kiocb *async_cb = NULL;
 
 	file = iocb->ki_filp;
 	pos = offset;
+	inode = file->f_mapping->host;
+	i_size = i_size_read(inode);
+
+	/* cannot write beyond eof asynchronously */
+	if (is_sync_kiocb(iocb) || (offset + count <= i_size) || rw != WRITE) {
+		struct fuse_io_priv *io;
+
+		io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
+		if (!io)
+			return -ENOMEM;
+
+		spin_lock_init(&io->lock);
+		io->reqs = 1;
+		io->bytes = -1;
+		io->size = 0;
+		io->offset = offset;
+		io->write = (rw == WRITE);
+		io->err = 0;
+		io->iocb = iocb;
+		iocb->private = io;
+
+		async_cb = iocb;
+	}
 
 	if (rw == WRITE)
-		ret = __fuse_direct_write(file, iov, nr_segs, &pos, NULL);
+		ret = __fuse_direct_write(file, iov, nr_segs, &pos, async_cb);
 	else
-		ret = __fuse_direct_read(file, iov, nr_segs, &pos, NULL);
+		ret = __fuse_direct_read(file, iov, nr_segs, &pos, async_cb);
+
+	if (async_cb) {
+		fuse_aio_complete(async_cb->private, ret == count ? 0 : -EIO,
+				  -1);
+
+		if (!is_sync_kiocb(iocb))
+			return -EIOCBQUEUED;
+
+		ret = wait_on_sync_kiocb(iocb);
+
+		if (rw == WRITE && ret > 0)
+			fuse_write_update_size(inode, pos);
+	}
 
 	return ret;
 }

index ef6d3de..3e0fdb7 100644
@@ -2341,6 +2341,53 @@ int fuse_notify_poll_wakeup(struct fuse_conn *fc,
 	return 0;
 }
 
+static void fuse_do_truncate(struct file *file)
+{
+	struct fuse_file *ff = file->private_data;
+	struct inode *inode = file->f_mapping->host;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_req *req;
+	struct fuse_setattr_in inarg;
+	struct fuse_attr_out outarg;
+	int err;
+
+	req = fuse_get_req_nopages(fc);
+	if (IS_ERR(req)) {
+		printk(KERN_WARNING "failed to allocate req for truncate "
+		       "(%ld)\n", PTR_ERR(req));
+		return;
+	}
+
+	memset(&inarg, 0, sizeof(inarg));
+	memset(&outarg, 0, sizeof(outarg));
+
+	inarg.valid |= FATTR_SIZE;
+	inarg.size = i_size_read(inode);
+
+	inarg.valid |= FATTR_FH;
+	inarg.fh = ff->fh;
+
+	req->in.h.opcode = FUSE_SETATTR;
+	req->in.h.nodeid = get_node_id(inode);
+	req->in.numargs = 1;
+	req->in.args[0].size = sizeof(inarg);
+	req->in.args[0].value = &inarg;
+	req->out.numargs = 1;
+	if (fc->minor < 9)
+		req->out.args[0].size = FUSE_COMPAT_ATTR_OUT_SIZE;
+	else
+		req->out.args[0].size = sizeof(outarg);
+	req->out.args[0].value = &outarg;
+
+	fuse_request_send(fc, req);
+	err = req->out.h.error;
+	fuse_put_request(fc, req);
+
+	if (err)
+		printk(KERN_WARNING "failed to truncate to %lld with error "
+		       "%d\n", i_size_read(inode), err);
+}
+
 static ssize_t
 fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 			loff_t offset, unsigned long nr_segs)

@@ -2393,8 +2440,12 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 
 		ret = wait_on_sync_kiocb(iocb);
 
-		if (rw == WRITE && ret > 0)
-			fuse_write_update_size(inode, pos);
+		if (rw == WRITE) {
+			if (ret > 0)
+				fuse_write_update_size(inode, pos);
+			else if (ret < 0 && offset + count > i_size)
+				fuse_do_truncate(file);
+		}
 	}
 
 	return ret;

index 3e0fdb7..d2094e1 100644
@@ -1324,7 +1324,7 @@ EXPORT_SYMBOL_GPL(fuse_direct_io);
 
 static ssize_t __fuse_direct_read(struct file *file, const struct iovec *iov,
 				  unsigned long nr_segs, loff_t *ppos,
-				  struct kiocb *async)
+				  struct kiocb *async, size_t count)
 {
 	ssize_t res;
 	struct inode *inode = file->f_path.dentry->d_inode;

@@ -1332,8 +1332,7 @@ static ssize_t __fuse_direct_read(struct file *file, const struct iovec *iov,
 	if (is_bad_inode(inode))
 		return -EIO;
 
-	res = fuse_direct_io(file, iov, nr_segs, iov_length(iov, nr_segs),
-			     ppos, 0, async);
+	res = fuse_direct_io(file, iov, nr_segs, count, ppos, 0, async);
 
 	fuse_invalidate_attr(inode);
 

@@ -1344,7 +1343,7 @@ static ssize_t fuse_direct_read(struct file *file, char __user *buf,
 				     size_t count, loff_t *ppos)
 {
 	struct iovec iov = { .iov_base = buf, .iov_len = count };
-	return __fuse_direct_read(file, &iov, 1, ppos, NULL);
+	return __fuse_direct_read(file, &iov, 1, ppos, NULL, count);
 }
 
 static ssize_t __fuse_direct_write(struct file *file, const struct iovec *iov,

@@ -2405,8 +2404,15 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	inode = file->f_mapping->host;
 	i_size = i_size_read(inode);
 
+	/* optimization for short read */
+	if (rw != WRITE && offset + count > i_size) {
+		if (offset >= i_size)
+			return 0;
+		count = i_size - offset;
+	}
+
 	/* cannot write beyond eof asynchronously */
-	if (is_sync_kiocb(iocb) || (offset + count <= i_size) || rw != WRITE) {
+	if (is_sync_kiocb(iocb) || (offset + count <= i_size)) {
 		struct fuse_io_priv *io;
 
 		io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);

@@ -2429,7 +2435,8 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 	if (rw == WRITE)
 		ret = __fuse_direct_write(file, iov, nr_segs, &pos, async_cb);
 	else
-		ret = __fuse_direct_read(file, iov, nr_segs, &pos, async_cb);
+		ret = __fuse_direct_read(file, iov, nr_segs, &pos, async_cb,
+					 count);
 
 	if (async_cb) {
 		fuse_aio_complete(async_cb->private, ret == count ? 0 : -EIO,