path: root/io_uring/rw.c

// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/fsnotify.h>
#include <linux/poll.h>
#include <linux/nospec.h>
#include <linux/compat.h>
#include <linux/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "opdef.h"
#include "kbuf.h"
#include "rsrc.h"
#include "rw.h"

struct io_rw {
	/* NOTE: kiocb has the file as the first member, so don't do it here */
	struct kiocb			kiocb;
	u64				addr;
	u32				len;
	rwf_t				flags;
};

static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
	return req->flags & REQ_F_SUPPORT_NOWAIT;
}

#ifdef CONFIG_COMPAT
static int io_iov_compat_buffer_select_prep(struct io_rw *rw)
{
	struct compat_iovec __user *uiov;
	compat_ssize_t clen;

	uiov = u64_to_user_ptr(rw->addr);
	if (!access_ok(uiov, sizeof(*uiov)))
		return -EFAULT;
	if (__get_user(clen, &uiov->iov_len))
		return -EFAULT;
	if (clen < 0)
		return -EINVAL;

	rw->len = clen;
	return 0;
}
#endif

static int io_iov_buffer_select_prep(struct io_kiocb *req)
{
	struct iovec __user *uiov;
	struct iovec iov;
	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);

	if (rw->len != 1)
		return -EINVAL;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return io_iov_compat_buffer_select_prep(rw);
#endif

	uiov = u64_to_user_ptr(rw->addr);
	if (copy_from_user(&iov, uiov, sizeof(*uiov)))
		return -EFAULT;
	rw->len = iov.iov_len;
	return 0;
}

int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
	unsigned ioprio;
	int ret;

	rw->kiocb.ki_pos = READ_ONCE(sqe->off);
	/* used for fixed read/write too - just read unconditionally */
	req->buf_index = READ_ONCE(sqe->buf_index);

	if (req->opcode == IORING_OP_READ_FIXED ||
	    req->opcode == IORING_OP_WRITE_FIXED) {
		struct io_ring_ctx *ctx = req->ctx;
		u16 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);
	}

	ioprio = READ_ONCE(sqe->ioprio);
	if (ioprio) {
		ret = ioprio_check_cap(ioprio);
		if (ret)
			return ret;

		rw->kiocb.ki_ioprio = ioprio;
	} else {
		rw->kiocb.ki_ioprio = get_current_ioprio();
	}

	rw->addr = READ_ONCE(sqe->addr);
	rw->len = READ_ONCE(sqe->len);
	rw->flags = READ_ONCE(sqe->rw_flags);

	/* Have to do this validation here, as this is in io_read() rw->len might
	 * have chanaged due to buffer selection
	 */
	if (req->opcode == IORING_OP_READV && req->flags & REQ_F_BUFFER_SELECT) {
		ret = io_iov_buffer_select_prep(req);
		if (ret)
			return ret;
	}

	return 0;
}

void io_readv_writev_cleanup(struct io_kiocb *req)
{
	struct io_async_rw *io = req->async_data;

	kfree(io->free_iovec);
}

static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
{
	switch (ret) {
	case -EIOCBQUEUED:
		break;
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/*
		 * We can't just restart the syscall, since previously
		 * submitted sqes may already be in progress. Just fail this
		 * IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		kiocb->ki_complete(kiocb, ret);
	}
}

static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
{
	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);

	if (rw->kiocb.ki_pos != -1)
		return &rw->kiocb.ki_pos;

	if (!(req->file->f_mode & FMODE_STREAM)) {
		req->flags |= REQ_F_CUR_POS;
		rw->kiocb.ki_pos = req->file->f_pos;
		return &rw