linux/io_uring/uring_cmd.c
Linus Torvalds 4c72e2b8c4 for-6.8/io_uring-2024-01-08
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAmWcOk0QHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpq2wEACgP1Gvfb2cR65B/6tkLJ6neKnYOPVSYx9F
 4Mv6KS306vmOsE67LqynhtAe/Hgfv0NKADN+mKLLV8IdwhneLAwFxRoHl8QPO2dW
 DIxohDMLIqzY/SOUBqBHMS8b5lEr79UVh8vXjAuuYCBTcHBndi4hj0S0zkwf5YiK
 Vma6ty+TnzmOv+c6+OCgZZlwFhkxD1pQBM5iOlFRAkdt3Er/2e8FqthK0/od7Fgy
 Ii9xdxYZU9KTsM4R+IWhqZ1rj1qUdtMPSGzFRbzFt3b6NdANRZT9MUlxvSkuHPIE
 P/9anpmgu41gd2JbHuyVnw+4jdZMhhZUPUYtphmQ5n35rcFZjv1gnJalH/Nw/DTE
 78bDxxP0+35bkuq5MwHfvA3imVsGnvnFx5MlZBoqvv+VK4S3Q6E2+ARQZdiG+2Is
 8Uyjzzt0nq2waUO3H1JLkgiM9J9LFqaYQLE68u569m4NCfRSpoZva9KVmNpre2K0
 9WdGy2gfzaYAQkGud2TULzeLiEbWfvZAL0o43jYXkVPRKmnffCEphf2X6C2IDV/3
 5ZR4bandRRC6DVnE+8n1MB06AYtpJPB/w3rplON+l/V5Gnb7wRNwiUrBr/F15OOy
 OPbAnP6k56wY/JRpgzdbNqwGi8EvGWX6t3Kqjp2mczhs2as8M193FKS2xppl1TYl
 BPyTsAfbdQ==
 =5v/U
 -----END PGP SIGNATURE-----

Merge tag 'for-6.8/io_uring-2024-01-08' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "Mostly just come fixes and cleanups, but one feature as well. In
  detail:

   - Harden the check for handling IOPOLL based on return (Pavel)

   - Various minor optimizations (Pavel)

   - Drop remnants of SCM_RIGHTS fd passing support, now that it's no
     longer supported since 6.7 (me)

   - Fix for a case where bytes_done wasn't initialized properly on a
     failure condition for read/write requests (me)

   - Move the register related code to a separate file (me)

   - Add support for returning the provided ring buffer head (me)

   - Add support for adding a direct descriptor to the normal file table
     (me, Christian Brauner)

   - Fix for ensuring pending task_work for a ring with DEFER_TASKRUN is
     run even if we timeout waiting (me)"

* tag 'for-6.8/io_uring-2024-01-08' of git://git.kernel.dk/linux:
  io_uring: ensure local task_work is run on wait timeout
  io_uring/kbuf: add method for returning provided buffer ring head
  io_uring/rw: ensure io->bytes_done is always initialized
  io_uring: drop any code related to SCM_RIGHTS
  io_uring/unix: drop usage of io_uring socket
  io_uring/register: move io_uring_register(2) related code to register.c
  io_uring/openclose: add support for IORING_OP_FIXED_FD_INSTALL
  io_uring/cmd: inline io_uring_cmd_get_task
  io_uring/cmd: inline io_uring_cmd_do_in_task_lazy
  io_uring: split out cmd api into a separate header
  io_uring: optimise ltimeout for inline execution
  io_uring: don't check iopoll if request completes
2024-01-11 14:19:23 -08:00

279 lines
7.3 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/security.h>
#include <linux/nospec.h>
#include <uapi/linux/io_uring.h>
#include <asm/ioctls.h>
#include "io_uring.h"
#include "rsrc.h"
#include "uring_cmd.h"
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);
unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED;
ioucmd->task_work_cb(ioucmd, issue_flags);
}
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);
if (req->ctx->flags & IORING_SETUP_IOPOLL) {
/* order with io_iopoll_req_issued() checking ->iopoll_complete */
smp_store_release(&req->iopoll_completed, 1);
} else {
struct io_tw_state ts = {
.locked = !(issue_flags & IO_URING_F_UNLOCKED),
};
io_req_task_complete(req, &ts);
}
}
EXPORT_SYMBOL_GPL(io_uring_cmd_done);
int io_uring_cmd_prep_async(struct io_kiocb *req)
{
struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
memcpy(req->async_data, ioucmd->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->sqe = sqe;
ioucmd->cmd_op = READ_ONCE(sqe->cmd_op);
return 0;
}
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) {
if (!req_has_async_data(req)) {
if (io_alloc_async_data(req))
return -ENOMEM;
io_uring_cmd_prep_async(req);
}
return -EAGAIN;
}
if (ret != -EIOCBQUEUED) {
if (ret < 0)
req_set_fail(req);
io_req_set_res(req, ret, 0);
return ret;
}
return IOU_ISSUE_SKIP_COMPLETE;
}
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);
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