mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 09:50:04 +00:00
![Björn Töpel](/assets/img/avatar_default.png)
Another setsockopt (XDP_RX_QUEUE) is added to let the process allocate a queue, where the kernel can pass completed Rx frames from the kernel to user process. The mmapping of the queue is done using the XDP_PGOFF_RX_QUEUE offset. Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
301 lines
5.9 KiB
C
301 lines
5.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/* XDP sockets
|
|
*
|
|
* AF_XDP sockets allows a channel between XDP programs and userspace
|
|
* applications.
|
|
* Copyright(c) 2018 Intel Corporation.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* Author(s): Björn Töpel <bjorn.topel@intel.com>
|
|
* Magnus Karlsson <magnus.karlsson@intel.com>
|
|
*/
|
|
|
|
#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__
|
|
|
|
#include <linux/if_xdp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/socket.h>
|
|
#include <linux/file.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/net.h>
|
|
#include <linux/netdevice.h>
|
|
#include <net/xdp_sock.h>
|
|
#include <net/xdp.h>
|
|
|
|
#include "xsk_queue.h"
|
|
#include "xdp_umem.h"
|
|
|
|
static struct xdp_sock *xdp_sk(struct sock *sk)
|
|
{
|
|
return (struct xdp_sock *)sk;
|
|
}
|
|
|
|
static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
|
|
bool umem_queue)
|
|
{
|
|
struct xsk_queue *q;
|
|
|
|
if (entries == 0 || *queue || !is_power_of_2(entries))
|
|
return -EINVAL;
|
|
|
|
q = xskq_create(entries, umem_queue);
|
|
if (!q)
|
|
return -ENOMEM;
|
|
|
|
*queue = q;
|
|
return 0;
|
|
}
|
|
|
|
static int xsk_release(struct socket *sock)
|
|
{
|
|
struct sock *sk = sock->sk;
|
|
struct net *net;
|
|
|
|
if (!sk)
|
|
return 0;
|
|
|
|
net = sock_net(sk);
|
|
|
|
local_bh_disable();
|
|
sock_prot_inuse_add(net, sk->sk_prot, -1);
|
|
local_bh_enable();
|
|
|
|
sock_orphan(sk);
|
|
sock->sk = NULL;
|
|
|
|
sk_refcnt_debug_release(sk);
|
|
sock_put(sk);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int xsk_setsockopt(struct socket *sock, int level, int optname,
|
|
char __user *optval, unsigned int optlen)
|
|
{
|
|
struct sock *sk = sock->sk;
|
|
struct xdp_sock *xs = xdp_sk(sk);
|
|
int err;
|
|
|
|
if (level != SOL_XDP)
|
|
return -ENOPROTOOPT;
|
|
|
|
switch (optname) {
|
|
case XDP_RX_RING:
|
|
{
|
|
struct xsk_queue **q;
|
|
int entries;
|
|
|
|
if (optlen < sizeof(entries))
|
|
return -EINVAL;
|
|
if (copy_from_user(&entries, optval, sizeof(entries)))
|
|
return -EFAULT;
|
|
|
|
mutex_lock(&xs->mutex);
|
|
q = &xs->rx;
|
|
err = xsk_init_queue(entries, q, false);
|
|
mutex_unlock(&xs->mutex);
|
|
return err;
|
|
}
|
|
case XDP_UMEM_REG:
|
|
{
|
|
struct xdp_umem_reg mr;
|
|
struct xdp_umem *umem;
|
|
|
|
if (xs->umem)
|
|
return -EBUSY;
|
|
|
|
if (copy_from_user(&mr, optval, sizeof(mr)))
|
|
return -EFAULT;
|
|
|
|
mutex_lock(&xs->mutex);
|
|
err = xdp_umem_create(&umem);
|
|
|
|
err = xdp_umem_reg(umem, &mr);
|
|
if (err) {
|
|
kfree(umem);
|
|
mutex_unlock(&xs->mutex);
|
|
return err;
|
|
}
|
|
|
|
/* Make sure umem is ready before it can be seen by others */
|
|
smp_wmb();
|
|
|
|
xs->umem = umem;
|
|
mutex_unlock(&xs->mutex);
|
|
return 0;
|
|
}
|
|
case XDP_UMEM_FILL_RING:
|
|
{
|
|
struct xsk_queue **q;
|
|
int entries;
|
|
|
|
if (!xs->umem)
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(&entries, optval, sizeof(entries)))
|
|
return -EFAULT;
|
|
|
|
mutex_lock(&xs->mutex);
|
|
q = &xs->umem->fq;
|
|
err = xsk_init_queue(entries, q, true);
|
|
mutex_unlock(&xs->mutex);
|
|
return err;
|
|
}
|
|
default:
|
|
break;
|
|
}
|
|
|
|
return -ENOPROTOOPT;
|
|
}
|
|
|
|
static int xsk_mmap(struct file *file, struct socket *sock,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
|
|
unsigned long size = vma->vm_end - vma->vm_start;
|
|
struct xdp_sock *xs = xdp_sk(sock->sk);
|
|
struct xsk_queue *q = NULL;
|
|
unsigned long pfn;
|
|
struct page *qpg;
|
|
|
|
if (offset == XDP_PGOFF_RX_RING) {
|
|
q = xs->rx;
|
|
} else {
|
|
if (!xs->umem)
|
|
return -EINVAL;
|
|
|
|
if (offset == XDP_UMEM_PGOFF_FILL_RING)
|
|
q = xs->umem->fq;
|
|
else
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (!q)
|
|
return -EINVAL;
|
|
|
|
qpg = virt_to_head_page(q->ring);
|
|
if (size > (PAGE_SIZE << compound_order(qpg)))
|
|
return -EINVAL;
|
|
|
|
pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
|
|
return remap_pfn_range(vma, vma->vm_start, pfn,
|
|
size, vma->vm_page_prot);
|
|
}
|
|
|
|
static struct proto xsk_proto = {
|
|
.name = "XDP",
|
|
.owner = THIS_MODULE,
|
|
.obj_size = sizeof(struct xdp_sock),
|
|
};
|
|
|
|
static const struct proto_ops xsk_proto_ops = {
|
|
.family = PF_XDP,
|
|
.owner = THIS_MODULE,
|
|
.release = xsk_release,
|
|
.bind = sock_no_bind,
|
|
.connect = sock_no_connect,
|
|
.socketpair = sock_no_socketpair,
|
|
.accept = sock_no_accept,
|
|
.getname = sock_no_getname,
|
|
.poll = sock_no_poll,
|
|
.ioctl = sock_no_ioctl,
|
|
.listen = sock_no_listen,
|
|
.shutdown = sock_no_shutdown,
|
|
.setsockopt = xsk_setsockopt,
|
|
.getsockopt = sock_no_getsockopt,
|
|
.sendmsg = sock_no_sendmsg,
|
|
.recvmsg = sock_no_recvmsg,
|
|
.mmap = xsk_mmap,
|
|
.sendpage = sock_no_sendpage,
|
|
};
|
|
|
|
static void xsk_destruct(struct sock *sk)
|
|
{
|
|
struct xdp_sock *xs = xdp_sk(sk);
|
|
|
|
if (!sock_flag(sk, SOCK_DEAD))
|
|
return;
|
|
|
|
xskq_destroy(xs->rx);
|
|
xdp_put_umem(xs->umem);
|
|
|
|
sk_refcnt_debug_dec(sk);
|
|
}
|
|
|
|
static int xsk_create(struct net *net, struct socket *sock, int protocol,
|
|
int kern)
|
|
{
|
|
struct sock *sk;
|
|
struct xdp_sock *xs;
|
|
|
|
if (!ns_capable(net->user_ns, CAP_NET_RAW))
|
|
return -EPERM;
|
|
if (sock->type != SOCK_RAW)
|
|
return -ESOCKTNOSUPPORT;
|
|
|
|
if (protocol)
|
|
return -EPROTONOSUPPORT;
|
|
|
|
sock->state = SS_UNCONNECTED;
|
|
|
|
sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern);
|
|
if (!sk)
|
|
return -ENOBUFS;
|
|
|
|
sock->ops = &xsk_proto_ops;
|
|
|
|
sock_init_data(sock, sk);
|
|
|
|
sk->sk_family = PF_XDP;
|
|
|
|
sk->sk_destruct = xsk_destruct;
|
|
sk_refcnt_debug_inc(sk);
|
|
|
|
xs = xdp_sk(sk);
|
|
mutex_init(&xs->mutex);
|
|
|
|
local_bh_disable();
|
|
sock_prot_inuse_add(net, &xsk_proto, 1);
|
|
local_bh_enable();
|
|
|
|
return 0;
|
|
}
|
|
|
|
static const struct net_proto_family xsk_family_ops = {
|
|
.family = PF_XDP,
|
|
.create = xsk_create,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static int __init xsk_init(void)
|
|
{
|
|
int err;
|
|
|
|
err = proto_register(&xsk_proto, 0 /* no slab */);
|
|
if (err)
|
|
goto out;
|
|
|
|
err = sock_register(&xsk_family_ops);
|
|
if (err)
|
|
goto out_proto;
|
|
|
|
return 0;
|
|
|
|
out_proto:
|
|
proto_unregister(&xsk_proto);
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
fs_initcall(xsk_init);
|