path: root/io_uring/register.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Code related to the io_uring_register() syscall
 *
 * Copyright (C) 2023 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/refcount.h>
#include <linux/bits.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/compat.h>
#include <linux/io_uring.h>
#include <linux/io_uring_types.h>

#include "io_uring.h"
#include "opdef.h"
#include "tctx.h"
#include "rsrc.h"
#include "sqpoll.h"
#include "register.h"
#include "cancel.h"
#include "kbuf.h"
#include "napi.h"
#include "eventfd.h"
#include "msg_ring.h"
#include "memmap.h"
#include "zcrx.h"

#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
				 IORING_REGISTER_LAST + IORING_OP_LAST)

static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
			   unsigned nr_args)
{
	struct io_uring_probe *p;
	size_t size;
	int i, ret;

	if (nr_args > IORING_OP_LAST)
		nr_args = IORING_OP_LAST;

	size = struct_size(p, ops, nr_args);
	p = kzalloc(size, GFP_KERNEL);
	if (!p)
		return -ENOMEM;

	ret = -EFAULT;
	if (copy_from_user(p, arg, size))
		goto out;
	ret = -EINVAL;
	if (memchr_inv(p, 0, size))
		goto out;

	p->last_op = IORING_OP_LAST - 1;

	for (i = 0; i < nr_args; i++) {
		p->ops[i].op = i;
		if (io_uring_op_supported(i))
			p->ops[i].flags = IO_URING_OP_SUPPORTED;
	}
	p->ops_len = i;

	ret = 0;
	if (copy_to_user(arg, p, size))
		ret = -EFAULT;
out:
	kfree(p);
	return ret;
}

int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
{
	const struct cred *creds;

	creds = xa_erase(&ctx->personalities, id);
	if (creds) {
		put_cred(creds);
		return 0;
	}

	return -EINVAL;
}


static int io_register_personality(struct io_ring_ctx *ctx)
{
	const struct cred *creds;
	u32 id;
	int ret;

	creds = get_current_cred();

	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
	if (ret < 0) {
		put_cred(creds);
		return ret;
	}
	return id;
}

static __cold int io_parse_restrictions(void __user *arg, unsigned int nr_args,
					struct io_restriction *restrictions)
{
	struct io_uring_restriction *res;
	size_t size;
	int i, ret;

	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
		return -EINVAL;

	size = array_size(nr_args, sizeof(*res));
	if (size == SIZE_MAX)
		return -EOVERFLOW;

	res = memdup_user(arg, size);
	if (IS_ERR(res))
		return PTR_ERR(res);

	ret = -EINVAL;

	for (i = 0; i < nr_args; i++) {
		switch (res[i].opcode) {
		case IORING_RESTRICTION_REGISTER_OP:
			if (res[i].register_op >= IORING_REGISTER_LAST)
				goto err;
			__set_bit(res[i].register_op, restrictions->register_op);
			break;
		case IORING_RESTRICTION_SQE_OP:
			if (res[i].sqe_op >= IORING_OP_LAST)
				goto err;
			__set_bit(res[i].sqe_op, restrictions->sqe_op);
			break;
		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
			restrictions->sqe_flags_allowed = res[i].sqe_flags;
			break;
		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
			restrictions->sqe_flags_required = res[i].sqe_flags;
			break;
		default:
			goto err;
		}
	}

	ret = 0;

err:
	kfree(res);
	return ret;
}

static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
					   void __user *arg, unsigned int nr_args)
{
	int ret;

	/* Restrictions allowed only if rings started disabled */
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	/* We allow only a single restrictions registration */
	if (ctx->restrictions.registered)
		return -EBUSY;

	ret = io_parse_restrictions(arg, nr_args, &ctx->restrictions);
	/* Reset all restrictions if an error happened */
	if (ret != 0)
		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
	else
		ctx->restrictions.registered = true;
	return ret;
}

static int io_register_enable_rings(struct io_ring_ctx *ctx)
{
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) {
		WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
		/*
		 * Lazy activation attempts would fail if it was polled before
		 * submitter_task is set.
		 */
		if (wq_has_sleeper(&ctx->poll_wq))
			io_activate_pollwq(ctx);
	}

	if (ctx->restrictions.registered)
		ctx->restricted = 1;

	ctx->flags &= ~IORING_SETUP_R_DISABLED;
	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
		wake_up(&ctx->sq_data->wait);
	return 0;
}

static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx,
					 cpumask_var_t new_mask)
{
	int ret;

	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
		ret = io_wq_cpu_affinity(current->io_uring,<