netfs: Implement unbuffered/DIO read support

Implement support for unbuffered and DIO reads in the netfs library,
utilising the existing read helper code to do block splitting and
individual queuing.  The code also handles extraction of the destination
buffer from the supplied iterator, allowing async unbuffered reads to take
place.

The read will be split up according to the rsize setting and, if supplied,
the ->clamp_length() method.  Note that the next subrequest will be issued
as soon as issue_op returns, without waiting for previous ones to finish.
The network filesystem needs to pause or handle queuing them if it doesn't
want to fire them all at the server simultaneously.

Once all the subrequests have finished, the state will be assessed and the
amount of data to be indicated as having being obtained will be
determined.  As the subrequests may finish in any order, if an intermediate
subrequest is short, any further subrequests may be copied into the buffer
and then abandoned.

In the future, this will also take care of doing an unbuffered read from
encrypted content, with the decryption being done by the library.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org

1 files changed, 75 insertions, 8 deletions

diff --git a/fs/netfs/io.c b/fs/netfs/io.c
index 774aef6ea4cb..c972415c8aad 100644
--- a/fs/netfs/io.c
+++ b/fs/netfs/io.c
@@ -78,7 +78,9 @@ static void netfs_read_from_server(struct netfs_io_request *rreq,
 				   struct netfs_io_subrequest *subreq)
 {
 	netfs_stat(&netfs_n_rh_download);
-	if (iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
+
+	if (rreq->origin != NETFS_DIO_READ &&
+	    iov_iter_count(&subreq->io_iter) != subreq->len - subreq->transferred)
 		pr_warn("R=%08x[%u] ITER PRE-MISMATCH %zx != %zx-%zx %lx\n",
 			rreq->debug_id, subreq->debug_index,
 			iov_iter_count(&subreq->io_iter), subreq->len,
@@ -342,6 +344,43 @@ static void netfs_rreq_is_still_valid(struct netfs_io_request *rreq)
 }
 
 /*
+ * Determine how much we can admit to having read from a DIO read.
+ */
+static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
+{
+	struct netfs_io_subrequest *subreq;
+	unsigned int i;
+	size_t transferred = 0;
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
+		if (subreq->error || subreq->transferred == 0)
+			break;
+		transferred += subreq->transferred;
+		if (subreq->transferred < subreq->len)
+			break;
+	}
+
+	for (i = 0; i < rreq->direct_bv_count; i++)
+		flush_dcache_page(rreq->direct_bv[i].bv_page);
+
+	rreq->transferred = transferred;
+	task_io_account_read(transferred);
+
+	if (rreq->iocb) {
+		rreq->iocb->ki_pos += transferred;
+		if (rreq->iocb->ki_complete)
+			rreq->iocb->ki_complete(
+				rreq->iocb, rreq->error ? rreq->error : transferred);
+	}
+	if (rreq->netfs_ops->done)
+		rreq->netfs_ops->done(rreq);
+	inode_dio_end(rreq->inode);
+}
+
+/*
  * Assess the state of a read request and decide what to do next.
  *
  * Note that we could be in an ordinary kernel thread, on a workqueue or in
@@ -361,7 +400,10 @@ again:
 		return;
 	}
 
-	netfs_rreq_unlock_folios(rreq);
+	if (rreq->origin != NETFS_DIO_READ)
+		netfs_rreq_unlock_folios(rreq);
+	else
+		netfs_rreq_assess_dio(rreq);
 
 	trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip);
 	clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
@@ -526,14 +568,16 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 			struct netfs_io_subrequest *subreq,
 			struct iov_iter *io_iter)
 {
-	enum netfs_io_source source;
+	enum netfs_io_source source = NETFS_DOWNLOAD_FROM_SERVER;
 	size_t lsize;
 
 	_enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size);
 
-	source = netfs_cache_prepare_read(subreq, rreq->i_size);
-	if (source == NETFS_INVALID_READ)
-		goto out;
+	if (rreq->origin != NETFS_DIO_READ) {
+		source = netfs_cache_prepare_read(subreq, rreq->i_size);
+		if (source == NETFS_INVALID_READ)
+			goto out;
+	}
 
 	if (source == NETFS_DOWNLOAD_FROM_SERVER) {
 		/* Call out to the netfs to let it shrink the request to fit
@@ -544,6 +588,8 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq,
 		 */
 		if (subreq->len > rreq->i_size - subreq->start)
 			subreq->len = rreq->i_size - subreq->start;
+		if (rreq->rsize && subreq->len > rreq->rsize)
+			subreq->len = rreq->rsize;
 
 		if (rreq->netfs_ops->clamp_length &&
 		    !rreq->netfs_ops->clamp_length(subreq)) {
@@ -662,6 +708,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		return -EIO;
 	}
 
+	if (rreq->origin == NETFS_DIO_READ)
+		inode_dio_begin(rreq->inode);
+
+	// TODO: Use bounce buffer if requested
 	rreq->io_iter = rreq->iter;
 
 	INIT_WORK(&rreq->work, netfs_rreq_work);
@@ -673,11 +723,25 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 	atomic_set(&rreq->nr_outstanding, 1);
 	io_iter = rreq->io_iter;
 	do {
+		_debug("submit %llx + %zx >= %llx",
+		       rreq->start, rreq->submitted, rreq->i_size);
+		if (rreq->origin == NETFS_DIO_READ &&
+		    rreq->start + rreq->submitted >= rreq->i_size)
+			break;
 		if (!netfs_rreq_submit_slice(rreq, &io_iter, &debug_index))
 			break;
+		if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) &&
+		    test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags))
+			break;
 
 	} while (rreq->submitted < rreq->len);
 
+	if (!rreq->submitted) {
+		netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit);
+		ret = 0;
+		goto out;
+	}
+
 	if (sync) {
 		/* Keep nr_outstanding incremented so that the ref always
 		 * belongs to us, and the service code isn't punted off to a
@@ -694,7 +758,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 			    TASK_UNINTERRUPTIBLE);
 
 		ret = rreq->error;
-		if (ret == 0 && rreq->submitted < rreq->len) {
+		if (ret == 0 && rreq->submitted < rreq->len &&
+		    rreq->origin != NETFS_DIO_READ) {
 			trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
 			ret = -EIO;
 		}
@@ -702,7 +767,9 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
 		/* If we decrement nr_outstanding to 0, the ref belongs to us. */
 		if (atomic_dec_and_test(&rreq->nr_outstanding))
 			netfs_rreq_assess(rreq, false);
-		ret = 0;
+		ret = -EIOCBQUEUED;
 	}
+
+out:
 	return ret;
 }