io_uring: add support for futex wake and wait

Add support for FUTEX_WAKE/WAIT primitives.

IORING_OP_FUTEX_WAKE is mix of FUTEX_WAKE and FUTEX_WAKE_BITSET, as
it does support passing in a bitset.

Similary, IORING_OP_FUTEX_WAIT is a mix of FUTEX_WAIT and
FUTEX_WAIT_BITSET.

For both of them, they are using the futex2 interface.

FUTEX_WAKE is straight forward, as those can always be done directly from
the io_uring submission without needing async handling. For FUTEX_WAIT,
things are a bit more complicated. If the futex isn't ready, then we
rely on a callback via futex_queue->wake() when someone wakes up the
futex. From that calback, we queue up task_work with the original task,
which will post a CQE and wake it, if necessary.

Cancelations are supported, both from the application point-of-view,
but also to be able to cancel pending waits if the ring exits before
all events have occurred. The return value of futex_unqueue() is used
to gate who wins the potential race between cancelation and futex
wakeups. Whomever gets a 'ret == 1' return from that claims ownership
of the io_uring futex request.

This is just the barebones wait/wake support. PI or REQUEUE support is
not added at this point, unclear if we might look into that later.

Likewise, explicit timeouts are not supported either. It is expected
that users that need timeouts would do so via the usual io_uring
mechanism to do that using linked timeouts.

The SQE format is as follows:

`addr`		Address of futex
`fd`		futex2(2) FUTEX2_* flags
`futex_flags`	io_uring specific command flags. None valid now.
`addr2`		Value of futex
`addr3`		Mask to wake/wait

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 235 insertions, 0 deletions

diff --git a/io_uring/futex.c b/io_uring/futex.c
new file mode 100644
index 000000000000..eb4406ac46fb
--- /dev/null
+++ b/io_uring/futex.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "../kernel/futex/futex.h"
+#include "io_uring.h"
+#include "rsrc.h"
+#include "futex.h"
+
+struct io_futex {
+	struct file	*file;
+	u32 __user	*uaddr;
+	unsigned long	futex_val;
+	unsigned long	futex_mask;
+	u32		futex_flags;
+};
+
+struct io_futex_data {
+	union {
+		struct futex_q		q;
+		struct io_cache_entry	cache;
+	};
+	struct io_kiocb	*req;
+};
+
+void io_futex_cache_init(struct io_ring_ctx *ctx)
+{
+	io_alloc_cache_init(&ctx->futex_cache, IO_NODE_ALLOC_CACHE_MAX,
+				sizeof(struct io_futex_data));
+}
+
+static void io_futex_cache_entry_free(struct io_cache_entry *entry)
+{
+	kfree(container_of(entry, struct io_futex_data, cache));
+}
+
+void io_futex_cache_free(struct io_ring_ctx *ctx)
+{
+	io_alloc_cache_free(&ctx->futex_cache, io_futex_cache_entry_free);
+}
+
+static void io_futex_complete(struct io_kiocb *req, struct io_tw_state *ts)
+{
+	struct io_futex_data *ifd = req->async_data;
+	struct io_ring_ctx *ctx = req->ctx;
+
+	io_tw_lock(ctx, ts);
+	if (!io_alloc_cache_put(&ctx->futex_cache, &ifd->cache))
+		kfree(ifd);
+	req->async_data = NULL;
+	hlist_del_init(&req->hash_node);
+	io_req_task_complete(req, ts);
+}
+
+static bool __io_futex_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req)
+{
+	struct io_futex_data *ifd = req->async_data;
+
+	/* futex wake already done or in progress */
+	if (!futex_unqueue(&ifd->q))
+		return false;
+
+	hlist_del_init(&req->hash_node);
+	io_req_set_res(req, -ECANCELED, 0);
+	req->io_task_work.func = io_futex_complete;
+	io_req_task_work_add(req);
+	return true;
+}
+
+int io_futex_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		    unsigned int issue_flags)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	int nr = 0;
+
+	if (cd->flags & (IORING_ASYNC_CANCEL_FD|IORING_ASYNC_CANCEL_FD_FIXED))
+		return -ENOENT;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) {
+		if (req->cqe.user_data != cd->data &&
+		    !(cd->flags & IORING_ASYNC_CANCEL_ANY))
+			continue;
+		if (__io_futex_cancel(ctx, req))
+			nr++;
+		if (!(cd->flags & IORING_ASYNC_CANCEL_ALL))
+			break;
+	}
+	io_ring_submit_unlock(ctx, issue_flags);
+
+	if (nr)
+		return nr;
+
+	return -ENOENT;
+}
+
+bool io_futex_remove_all(struct io_ring_ctx *ctx, struct task_struct *task,
+			 bool cancel_all)
+{
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	bool found = false;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	hlist_for_each_entry_safe(req, tmp, &ctx->futex_list, hash_node) {
+		if (!io_match_task_safe(req, task, cancel_all))
+			continue;
+		__io_futex_cancel(ctx, req);
+		found = true;
+	}
+
+	return found;
+}
+
+int io_futex_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	u32 flags;
+
+	if (unlikely(sqe->len || sqe->futex_flags || sqe->buf_index ||
+		     sqe->file_index))
+		return -EINVAL;
+
+	iof->uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	iof->futex_val = READ_ONCE(sqe->addr2);
+	iof->futex_mask = READ_ONCE(sqe->addr3);
+	flags = READ_ONCE(sqe->fd);
+
+	if (flags & ~FUTEX2_VALID_MASK)
+		return -EINVAL;
+
+	iof->futex_flags = futex2_to_flags(flags);
+	if (!futex_flags_valid(iof->futex_flags))
+		return -EINVAL;
+
+	if (!futex_validate_input(iof->futex_flags, iof->futex_val) ||
+	    !futex_validate_input(iof->futex_flags, iof->futex_mask))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void io_futex_wake_fn(struct wake_q_head *wake_q, struct futex_q *q)
+{
+	struct io_futex_data *ifd = container_of(q, struct io_futex_data, q);
+	struct io_kiocb *req = ifd->req;
+
+	if (unlikely(!__futex_wake_mark(q)))
+		return;
+
+	io_req_set_res(req, 0, 0);
+	req->io_task_work.func = io_futex_complete;
+	io_req_task_work_add(req);
+}
+
+static struct io_futex_data *io_alloc_ifd(struct io_ring_ctx *ctx)
+{
+	struct io_cache_entry *entry;
+
+	entry = io_alloc_cache_get(&ctx->futex_cache);
+	if (entry)
+		return container_of(entry, struct io_futex_data, cache);
+
+	return kmalloc(sizeof(struct io_futex_data), GFP_NOWAIT);
+}
+
+int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_futex_data *ifd = NULL;
+	struct futex_hash_bucket *hb;
+	int ret;
+
+	if (!iof->futex_mask) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	io_ring_submit_lock(ctx, issue_flags);
+	ifd = io_alloc_ifd(ctx);
+	if (!ifd) {
+		ret = -ENOMEM;
+		goto done_unlock;
+	}
+
+	req->async_data = ifd;
+	ifd->q = futex_q_init;
+	ifd->q.bitset = iof->futex_mask;
+	ifd->q.wake = io_futex_wake_fn;
+	ifd->req = req;
+
+	ret = futex_wait_setup(iof->uaddr, iof->futex_val, iof->futex_flags,
+			       &ifd->q, &hb);
+	if (!ret) {
+		hlist_add_head(&req->hash_node, &ctx->futex_list);
+		io_ring_submit_unlock(ctx, issue_flags);
+
+		futex_queue(&ifd->q, hb);
+		return IOU_ISSUE_SKIP_COMPLETE;
+	}
+
+done_unlock:
+	io_ring_submit_unlock(ctx, issue_flags);
+done:
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	kfree(ifd);
+	return IOU_OK;
+}
+
+int io_futex_wake(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_futex *iof = io_kiocb_to_cmd(req, struct io_futex);
+	int ret;
+
+	/*
+	 * Strict flags - ensure that waking 0 futexes yields a 0 result.
+	 * See commit 43adf8449510 ("futex: FLAGS_STRICT") for details.
+	 */
+	ret = futex_wake(iof->uaddr, FLAGS_STRICT | iof->futex_flags,
+			 iof->futex_val, iof->futex_mask);
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+	return IOU_OK;
+}