| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200524192206.4093-13-axboe@kernel.dk>
Date: Sun, 24 May 2020 13:22:06 -0600
From: Jens Axboe <axboe@...nel.dk>
To: io-uring@...r.kernel.org
Cc: linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, Jens Axboe <axboe@...nel.dk>
Subject: [PATCH 12/12] io_uring: support true async buffered reads, if file provides it
If the file is flagged with FMODE_BUF_RASYNC, then we don't have to punt
the buffered read to an io-wq worker. Instead we can rely on page
unlocking callbacks to support retry based async IO. This is a lot more
efficient than doing async thread offload.
The retry is done similarly to how we handle poll based retry. From
the unlock callback, we simply queue the retry to a task_work based
handler.
Signed-off-by: Jens Axboe <axboe@...nel.dk>
---
fs/io_uring.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 112 insertions(+)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e95481c552ff..23073857239c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -498,6 +498,8 @@ struct io_async_rw {
struct iovec *iov;
ssize_t nr_segs;
ssize_t size;
+ struct wait_page_queue wpq;
+ struct callback_head task_work;
};
struct io_async_ctx {
@@ -2568,6 +2570,112 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return 0;
}
+static void io_async_buf_cancel(struct callback_head *cb)
+{
+ struct io_async_rw *rw;
+ struct io_ring_ctx *ctx;
+ struct io_kiocb *req;
+
+ rw = container_of(cb, struct io_async_rw, task_work);
+ req = rw->wpq.wait.private;
+ ctx = req->ctx;
+
+ spin_lock_irq(&ctx->completion_lock);
+ io_cqring_fill_event(req, -ECANCELED);
+ io_commit_cqring(ctx);
+ spin_unlock_irq(&ctx->completion_lock);
+
+ io_cqring_ev_posted(ctx);
+ req_set_fail_links(req);
+ io_double_put_req(req);
+}
+
+static void io_async_buf_retry(struct callback_head *cb)
+{
+ struct io_async_rw *rw;
+ struct io_ring_ctx *ctx;
+ struct io_kiocb *req;
+
+ rw = container_of(cb, struct io_async_rw, task_work);
+ req = rw->wpq.wait.private;
+ ctx = req->ctx;
+
+ __set_current_state(TASK_RUNNING);
+ mutex_lock(&ctx->uring_lock);
+ __io_queue_sqe(req, NULL);
+ mutex_unlock(&ctx->uring_lock);
+}
+
+static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
+ int sync, void *arg)
+{
+ struct wait_page_queue *wpq;
+ struct io_kiocb *req = wait->private;
+ struct io_async_rw *rw = &req->io->rw;
+ struct wait_page_key *key = arg;
+ struct task_struct *tsk;
+ int ret;
+
+ wpq = container_of(wait, struct wait_page_queue, wait);
+
+ ret = wake_page_match(wpq, key);
+ if (ret != 1)
+ return ret;
+
+ list_del_init(&wait->entry);
+
+ init_task_work(&rw->task_work, io_async_buf_retry);
+ /* submit ref gets dropped, acquire a new one */
+ refcount_inc(&req->refs);
+ tsk = req->task;
+ ret = task_work_add(tsk, &rw->task_work, true);
+ if (unlikely(ret)) {
+ /* queue just for cancelation */
+ init_task_work(&rw->task_work, io_async_buf_cancel);
+ tsk = io_wq_get_task(req->ctx->io_wq);
+ task_work_add(tsk, &rw->task_work, true);
+ }
+ wake_up_process(tsk);
+ return 1;
+}
+
+static bool io_rw_should_retry(struct io_kiocb *req)
+{
+ struct kiocb *kiocb = &req->rw.kiocb;
+ int ret;
+
+ /* never retry for NOWAIT, we just complete with -EAGAIN */
+ if (req->flags & REQ_F_NOWAIT)
+ return false;
+
+ /* already tried, or we're doing O_DIRECT */
+ if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_WAITQ))
+ return false;
+ /*
+ * just use poll if we can, and don't attempt if the fs doesn't
+ * support callback based unlocks
+ */
+ if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
+ return false;
+
+ /*
+ * If request type doesn't require req->io to defer in general,
+ * we need to allocate it here
+ */
+ if (!req->io && __io_alloc_async_ctx(req))
+ return false;
+
+ ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq,
+ io_async_buf_func, req);
+ if (!ret) {
+ get_task_struct(current);
+ req->task = current;
+ return true;
+ }
+
+ return false;
+}
+
static int io_read(struct io_kiocb *req, bool force_nonblock)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -2601,6 +2709,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
if (!ret) {
ssize_t ret2;
+retry:
if (req->file->f_op->read_iter)
ret2 = call_read_iter(req->file, kiocb, &iter);
else
@@ -2619,6 +2728,9 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
if (!(req->flags & REQ_F_NOWAIT) &&
!file_can_poll(req->file))
req->flags |= REQ_F_MUST_PUNT;
+ if (io_rw_should_retry(req))
+ goto retry;
+ kiocb->ki_flags &= ~IOCB_WAITQ;
return -EAGAIN;
}
}
--
2.26.2
Powered by blists - more mailing lists