linux/io_uring/uring_cmd.c
Pavel Begunkov 6746ee4c3a io_uring/cmd: expose iowq to cmds
When an io_uring request needs blocking context we offload it to the
io_uring's thread pool called io-wq. We can get there off ->uring_cmd
by returning -EAGAIN, but there is no straightforward way of doing that
from an asynchronous callback. Add a helper that would transfer a
command to a blocking context.

Note, we do an extra hop via task_work before io_queue_iowq(), that's a
limitation of io_uring infra we have that can likely be lifted later
if that would ever become a problem.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f735f807d7c8ba50c9452c69dfe5d3e9e535037b.1726072086.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-09-11 10:44:10 -06:00

364 lines
9.5 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/io_uring/cmd.h>
#include <linux/io_uring/net.h>
#include <linux/security.h>
#include <linux/nospec.h>
#include <net/sock.h>
#include <uapi/linux/io_uring.h>
#include <asm/ioctls.h>
#include "io_uring.h"
#include "alloc_cache.h"
#include "rsrc.h"
#include "uring_cmd.h"
static struct uring_cache *io_uring_async_get(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
struct uring_cache *cache;
cache = io_alloc_cache_get(&ctx->uring_cache);
if (cache) {
req->flags |= REQ_F_ASYNC_DATA;
req->async_data = cache;
return cache;
}
if (!io_alloc_async_data(req))
return req->async_data;
return NULL;
}
static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
struct uring_cache *cache = req->async_data;
if (issue_flags & IO_URING_F_UNLOCKED)
return;
if (io_alloc_cache_put(&req->ctx->uring_cache, cache)) {
ioucmd->sqe = NULL;
req->async_data = NULL;
req->flags &= ~REQ_F_ASYNC_DATA;
}
}
bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx,
struct task_struct *task, bool cancel_all)
{
struct hlist_node *tmp;
struct io_kiocb *req;
bool ret = false;
lockdep_assert_held(&ctx->uring_lock);
hlist_for_each_entry_safe(req, tmp, &ctx->cancelable_uring_cmd,
hash_node) {
struct io_uring_cmd *cmd = io_kiocb_to_cmd(req,
struct io_uring_cmd);
struct file *file = req->file;
if (!cancel_all && req->task != task)
continue;
if (cmd->flags & IORING_URING_CMD_CANCELABLE) {
/* ->sqe isn't available if no async data */
if (!req_has_async_data(req))
cmd->sqe = NULL;
file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL |
IO_URING_F_COMPLETE_DEFER);
ret = true;
}
}
io_submit_flush_completions(ctx);
return ret;
}
static void io_uring_cmd_del_cancelable(struct io_uring_cmd *cmd,
unsigned int issue_flags)
{
struct io_kiocb *req = cmd_to_io_kiocb(cmd);
struct io_ring_ctx *ctx = req->ctx;
if (!(cmd->flags & IORING_URING_CMD_CANCELABLE))
return;
cmd->flags &= ~IORING_URING_CMD_CANCELABLE;
io_ring_submit_lock(ctx, issue_flags);
hlist_del(&req->hash_node);
io_ring_submit_unlock(ctx, issue_flags);
}
/*
* Mark this command as concelable, then io_uring_try_cancel_uring_cmd()
* will try to cancel this issued command by sending ->uring_cmd() with
* issue_flags of IO_URING_F_CANCEL.
*
* The command is guaranteed to not be done when calling ->uring_cmd()
* with IO_URING_F_CANCEL, but it is driver's responsibility to deal
* with race between io_uring canceling and normal completion.
*/
void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
unsigned int issue_flags)
{
struct io_kiocb *req = cmd_to_io_kiocb(cmd);
struct io_ring_ctx *ctx = req->ctx;
if (!(cmd->flags & IORING_URING_CMD_CANCELABLE)) {
cmd->flags |= IORING_URING_CMD_CANCELABLE;
io_ring_submit_lock(ctx, issue_flags);
hlist_add_head(&req->hash_node, &ctx->cancelable_uring_cmd);
io_ring_submit_unlock(ctx, issue_flags);
}
}
EXPORT_SYMBOL_GPL(io_uring_cmd_mark_cancelable);
static void io_uring_cmd_work(struct io_kiocb *req, struct io_tw_state *ts)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
/* task_work executor checks the deffered list completion */
ioucmd->task_work_cb(ioucmd, IO_URING_F_COMPLETE_DEFER);
}
void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
void (*task_work_cb)(struct io_uring_cmd *, unsigned),
unsigned flags)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
ioucmd->task_work_cb = task_work_cb;
req->io_task_work.func = io_uring_cmd_work;
__io_req_task_work_add(req, flags);
}
EXPORT_SYMBOL_GPL(__io_uring_cmd_do_in_task);
static inline void io_req_set_cqe32_extra(struct io_kiocb *req,
u64 extra1, u64 extra2)
{
req->big_cqe.extra1 = extra1;
req->big_cqe.extra2 = extra2;
}
/*
* Called by consumers of io_uring_cmd, if they originally returned
* -EIOCBQUEUED upon receiving the command.
*/
void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2,
unsigned issue_flags)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
io_uring_cmd_del_cancelable(ioucmd, issue_flags);
if (ret < 0)
req_set_fail(req);
io_req_set_res(req, ret, 0);
if (req->ctx->flags & IORING_SETUP_CQE32)
io_req_set_cqe32_extra(req, res2, 0);
io_req_uring_cleanup(req, issue_flags);
if (req->ctx->flags & IORING_SETUP_IOPOLL) {
/* order with io_iopoll_req_issued() checking ->iopoll_complete */
smp_store_release(&req->iopoll_completed, 1);
} else if (issue_flags & IO_URING_F_COMPLETE_DEFER) {
if (WARN_ON_ONCE(issue_flags & IO_URING_F_UNLOCKED))
return;
io_req_complete_defer(req);
} else {
req->io_task_work.func = io_req_task_complete;
io_req_task_work_add(req);
}
}
EXPORT_SYMBOL_GPL(io_uring_cmd_done);
static int io_uring_cmd_prep_setup(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
struct uring_cache *cache;
cache = io_uring_async_get(req);
if (unlikely(!cache))
return -ENOMEM;
if (!(req->flags & REQ_F_FORCE_ASYNC)) {
/* defer memcpy until we need it */
ioucmd->sqe = sqe;
return 0;
}
memcpy(req->async_data, sqe, uring_sqe_size(req->ctx));
ioucmd->sqe = req->async_data;
return 0;
}
int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
if (sqe->__pad1)
return -EINVAL;
ioucmd->flags = READ_ONCE(sqe->uring_cmd_flags);
if (ioucmd->flags & ~IORING_URING_CMD_MASK)
return -EINVAL;
if (ioucmd->flags & IORING_URING_CMD_FIXED) {
struct io_ring_ctx *ctx = req->ctx;
u16 index;
req->buf_index = READ_ONCE(sqe->buf_index);
if (unlikely(req->buf_index >= ctx->nr_user_bufs))
return -EFAULT;
index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
req->imu = ctx->user_bufs[index];
io_req_set_rsrc_node(req, ctx, 0);
}
ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
return io_uring_cmd_prep_setup(req, sqe);
}
int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
struct io_ring_ctx *ctx = req->ctx;
struct file *file = req->file;
int ret;
if (!file->f_op->uring_cmd)
return -EOPNOTSUPP;
ret = security_uring_cmd(ioucmd);
if (ret)
return ret;
if (ctx->flags & IORING_SETUP_SQE128)
issue_flags |= IO_URING_F_SQE128;
if (ctx->flags & IORING_SETUP_CQE32)
issue_flags |= IO_URING_F_CQE32;
if (ctx->compat)
issue_flags |= IO_URING_F_COMPAT;
if (ctx->flags & IORING_SETUP_IOPOLL) {
if (!file->f_op->uring_cmd_iopoll)
return -EOPNOTSUPP;
issue_flags |= IO_URING_F_IOPOLL;
req->iopoll_completed = 0;
}
ret = file->f_op->uring_cmd(ioucmd, issue_flags);
if (ret == -EAGAIN) {
struct uring_cache *cache = req->async_data;
if (ioucmd->sqe != (void *) cache)
memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx));
return -EAGAIN;
} else if (ret == -EIOCBQUEUED) {
return -EIOCBQUEUED;
}
if (ret < 0)
req_set_fail(req);
io_req_uring_cleanup(req, issue_flags);
io_req_set_res(req, ret, 0);
return IOU_OK;
}
int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
struct iov_iter *iter, void *ioucmd)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
return io_import_fixed(rw, iter, req->imu, ubuf, len);
}
EXPORT_SYMBOL_GPL(io_uring_cmd_import_fixed);
void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
{
struct io_kiocb *req = cmd_to_io_kiocb(ioucmd);
io_req_queue_iowq(req);
}
static inline int io_uring_cmd_getsockopt(struct socket *sock,
struct io_uring_cmd *cmd,
unsigned int issue_flags)
{
bool compat = !!(issue_flags & IO_URING_F_COMPAT);
int optlen, optname, level, err;
void __user *optval;
level = READ_ONCE(cmd->sqe->level);
if (level != SOL_SOCKET)
return -EOPNOTSUPP;
optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
optname = READ_ONCE(cmd->sqe->optname);
optlen = READ_ONCE(cmd->sqe->optlen);
err = do_sock_getsockopt(sock, compat, level, optname,
USER_SOCKPTR(optval),
KERNEL_SOCKPTR(&optlen));
if (err)
return err;
/* On success, return optlen */
return optlen;
}
static inline int io_uring_cmd_setsockopt(struct socket *sock,
struct io_uring_cmd *cmd,
unsigned int issue_flags)
{
bool compat = !!(issue_flags & IO_URING_F_COMPAT);
int optname, optlen, level;
void __user *optval;
sockptr_t optval_s;
optval = u64_to_user_ptr(READ_ONCE(cmd->sqe->optval));
optname = READ_ONCE(cmd->sqe->optname);
optlen = READ_ONCE(cmd->sqe->optlen);
level = READ_ONCE(cmd->sqe->level);
optval_s = USER_SOCKPTR(optval);
return do_sock_setsockopt(sock, compat, level, optname, optval_s,
optlen);
}
#if defined(CONFIG_NET)
int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags)
{
struct socket *sock = cmd->file->private_data;
struct sock *sk = sock->sk;
struct proto *prot = READ_ONCE(sk->sk_prot);
int ret, arg = 0;
if (!prot || !prot->ioctl)
return -EOPNOTSUPP;
switch (cmd->sqe->cmd_op) {
case SOCKET_URING_OP_SIOCINQ:
ret = prot->ioctl(sk, SIOCINQ, &arg);
if (ret)
return ret;
return arg;
case SOCKET_URING_OP_SIOCOUTQ:
ret = prot->ioctl(sk, SIOCOUTQ, &arg);
if (ret)
return ret;
return arg;
case SOCKET_URING_OP_GETSOCKOPT:
return io_uring_cmd_getsockopt(sock, cmd, issue_flags);
case SOCKET_URING_OP_SETSOCKOPT:
return io_uring_cmd_setsockopt(sock, cmd, issue_flags);
default:
return -EOPNOTSUPP;
}
}
EXPORT_SYMBOL_GPL(io_uring_cmd_sock);
#endif