summaryrefslogtreecommitdiff
path: root/fs/io_uring.c
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2020-01-08 15:18:09 -0700
committerJens Axboe <axboe@kernel.dk>2020-01-29 15:46:09 -0700
commit3e4827b05d2ac2d377ed136a52829ec46787bf4b (patch)
treea3969e58dd0a55dde73d262cb771fef34bfa762c /fs/io_uring.c
parent39220e8d4a2aaab045ea03cc16d737e85d0817bf (diff)
io_uring: add support for epoll_ctl(2)for-5.6/io_uring-vfs-2020-01-29for-5.6/io_uring-vfs
This adds IORING_OP_EPOLL_CTL, which can perform the same work as the epoll_ctl(2) system call. Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/io_uring.c')
-rw-r--r--fs/io_uring.c71
1 files changed, 71 insertions, 0 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0d8d0e217847..c5ca84a305d3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -74,6 +74,7 @@
#include <linux/namei.h>
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
+#include <linux/eventpoll.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -423,6 +424,14 @@ struct io_madvise {
u32 advice;
};
+struct io_epoll {
+ struct file *file;
+ int epfd;
+ int op;
+ int fd;
+ struct epoll_event event;
+};
+
struct io_async_connect {
struct sockaddr_storage address;
};
@@ -536,6 +545,7 @@ struct io_kiocb {
struct io_files_update files_update;
struct io_fadvise fadvise;
struct io_madvise madvise;
+ struct io_epoll epoll;
};
struct io_async_ctx *io;
@@ -728,6 +738,10 @@ static const struct io_op_def io_op_defs[] = {
.fd_non_neg = 1,
.file_table = 1,
},
+ [IORING_OP_EPOLL_CTL] = {
+ .unbound_nonreg_file = 1,
+ .file_table = 1,
+ },
};
static void io_wq_submit_work(struct io_wq_work **workptr);
@@ -2611,6 +2625,52 @@ static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
return io_openat2(req, nxt, force_nonblock);
}
+static int io_epoll_ctl_prep(struct io_kiocb *req,
+ const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_EPOLL)
+ if (sqe->ioprio || sqe->buf_index)
+ return -EINVAL;
+
+ req->epoll.epfd = READ_ONCE(sqe->fd);
+ req->epoll.op = READ_ONCE(sqe->len);
+ req->epoll.fd = READ_ONCE(sqe->off);
+
+ if (ep_op_has_event(req->epoll.op)) {
+ struct epoll_event __user *ev;
+
+ ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
+ return -EFAULT;
+ }
+
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
+static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
+ bool force_nonblock)
+{
+#if defined(CONFIG_EPOLL)
+ struct io_epoll *ie = &req->epoll;
+ int ret;
+
+ ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_cqring_add_event(req, ret);
+ io_put_req_find_next(req, nxt);
+ return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
+}
+
static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
@@ -4075,6 +4135,9 @@ static int io_req_defer_prep(struct io_kiocb *req,
case IORING_OP_OPENAT2:
ret = io_openat2_prep(req, sqe);
break;
+ case IORING_OP_EPOLL_CTL:
+ ret = io_epoll_ctl_prep(req, sqe);
+ break;
default:
printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
req->opcode);
@@ -4303,6 +4366,14 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
ret = io_openat2(req, nxt, force_nonblock);
break;
+ case IORING_OP_EPOLL_CTL:
+ if (sqe) {
+ ret = io_epoll_ctl_prep(req, sqe);
+ if (ret)
+ break;
+ }
+ ret = io_epoll_ctl(req, nxt, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;